Crowdsourcing Climate-Linked Malaria Surveillance with Zimbabwean Youth

Crowdsourcing Climate-Linked Malaria Surveillance with Zimbabwean Youth | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Crowdsourcing Climate-Linked Malaria Surveillance with Zimbabwean Youth Yang Hu, Turner Hayes, Precious Chidanyika, Jian Hu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6841881/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Climate change is lengthening malaria transmission seasons and driving disease resurgence in southern Africa, especially Zimbabwe. While traditional control measures (nets, spraying, treatment) have reduced malaria, emerging climatic factors are undermining progress. Simultaneously, Zimbabwe’s population is very young – over 60% under 25 years old. Simultaneously, Zimbabwe’s population is very young – over 60% under 25 years old and highly connected by mobile technology . We developed a mobile/web crowdsourcing platform (“Mosquito Hunter”) to engage youth in real-time malaria surveillance and climate data collection. The open-source prototype app (https://mosquito-hunter.vercel.app) allows young volunteers to report mosquito breeding sites, upload photos, log environmental conditions, and access interactive educational modules on malaria–climate. Gamification elements (points, badges, certificates) and school-based outreach were used to motivate participation. We describe the platform’s design, the youth engagement strategy, and initial lessons from prototype development. This youth-driven approach can provide geolocated, contextual data that complements official health surveillance in high-burden, climate-vulnerable settings. By empowering Zimbabwean youth to become citizen-scientists, this initiative aims not only to improve situational awareness of malaria risk, but also to foster local ownership of public health and climate resilience. Crowdsourcing Malaria Surveillance Climate Change Youth Engagement Citizen Science Zimbabwe Mosquito Monitoring Figures Figure 1 Figure 2 1. Introduction Malaria remains a major global health challenge, with over 200 million cases and nearly half a million deaths annually, the vast majority in sub-Saharan Africa [ 1 ]. Zimbabwe is endemic for Plasmodium falciparum malaria, with transmission peaking in the rainy season (November–April) and substantial epidemic potential. Although intensive control efforts (insecticide-treated nets, indoor residual spraying, rapid treatment and prophylaxis) have driven down incidence in recent decades, progress has stalled and even reversed in some areas. Climate change is now emerging as a key factor: warming temperatures and altered rainfall patterns have extended transmission seasons and enabled malaria to persist in areas that were nearly malaria-free. These trends have been documented across Africa, where malaria transmission is “intricately linked to climatic factors” and where climate change threatens elimination efforts. In Zimbabwe, anecdotal and epidemiologic data indicate a resurgence of malaria in recent years, especially in highland and fringe areas, concurrent with increasing temperature extremes and rainfall variability. Recent studies in rural Zimbabwe have found that local malaria incidence is significantly correlated with lagged rainfall and temperature [ 2 ]. These findings mirror broader evidence that climate variability (e.g. unusual rain or heat) is associated with shifts in vector abundance and outbreaks of malaria and other diseases. At the same time, Zimbabwe’s demographic profile skews very young: roughly two-thirds of the population is under age 30, and more than 60% is under 25 [ 5 ]. Young Zimbabweans are digitally connected – recent reports indicate mobile phone penetration rates above 90% and rising internet coverage (~ 73%) [ 7 ] – and are increasingly concerned about climate impacts. These trends suggest an opportunity to harness the energy and connectivity of youth as part of a novel public health response. Participatory “citizen science” and crowdsourcing initiatives have gained traction as ways to engage communities in environmental and health monitoring. In such models, lay volunteers collect or interpret data (often via mobile apps) that support scientific or public health goals[ 5 ]. Prior work has shown that mobile apps enable simplified data collection and can transform citizens into active contributors to research. For example, crowdsourced disease surveillance (e.g. volunteer reports of flu symptoms) has been used to augment traditional epidemiology in high-income settings, and a recent review found that “crowdsourcing strategies are useful in the development of public health interventions” by engaging end users in co-creation [ 3 ]. Similarly, citizen science programs have successfully involved volunteers in mosquito monitoring and biodiversity surveys in parts of the world [ 4 ]. Importantly, citizen science can dramatically expand surveillance capacity: in mosquito control programs, community involvement has been shown to increase resource capacity and improve acceptance of control measures. Despite this promise, few citizen science initiatives have targeted malaria surveillance in climate-vulnerable African settings, and none specifically leverage youth engagement on climate-malaria issues in Zimbabwe. To address this gap, the Anti-Malaria Coalition (AMC) – in partnership with SDS Space at the University of Geneva – launched the “Understanding Climate Change, Malaria with the Youth of Zimbabwe” project. Guided by mentors from the Global Fund and building on the Learning Planet network challenge, our goal was to develop a proof-of-concept crowdsourcing platform. This paper describes the rationale for the project, the design of the mobile/web prototype (Mosquito Hunter), and insights on its potential impacts. We emphasize how this youth-driven approach can complement existing malaria surveillance systems by providing timely, geographically-detailed environmental and entomological data, while also educating and empowering a new generation of public health stewards. 2. Materials and Methods 2.1. Project Setting and Team This initiative was developed under the auspices of SDS Space (University of Geneva) – an innovation incubator focused on sustainable development in july 2024. The core team included technologists and students affiliated with the Anti-Malaria Coalition and partner institutions, with guidance from climate and public health mentors. The project aligned with The Global Fund’s challenge statement to “engage youth in monitoring the effects of climate change on malaria” in high-burden countries. Key local contexts shaped our design: Zimbabwe’s seasonal malaria, widespread LLIN and IRS campaigns, and limited active surveillance outside health facilities; concurrently, a “youth bulge” (≈ 60% 90% mobile and ~ 73% internet coverage[ 6 ][ 7 ]. 2.2. Platform Design Overview We built an open-source, cross-platform prototype combining a smartphone app and web interface( (see Fig. 1 for the prototype design overview). The platform (Mosquito Hunter) is accessible via web at mosquito-hunter.vercel.app. It was designed for ease of use by teenagers and young adults, with intuitive workflows and localization for Zimbabwe’s context. The core functions enable users to report observations and learn. When reporting, a user can: (1) upload photos of mosquito breeding grounds or adult mosquitoes (taken with the phone camera); (2) enter geo-location (automatic via GPS or manual) and time; (3) rate environmental conditions (e.g. stagnant water present, nearby human habitation, vegetation cover); and (4) optionally measure local ambient factors (e.g. asking users to input or sense rainfall, temperature, or test local water for larvae if feasible). Each submission is tagged and stored in a central database. Users can browse their own submissions in a map/list view and see aggregated “heatmap” summaries of reported hotspots. To encourage broader sharing, submissions may be made public (anonymized) on the platform so others can view cumulative mosquito-activity maps. Concurrently, the app includes educational content about malaria and climate. Interactive modules explain Anopheles biology, malaria transmission, and how climate factors (temperature, rain) influence mosquito life-cycles. Brief quizzes reinforce learning and unlock rewards. Regular “missions” guide users to do specific tasks: for instance, “inspect your yard for mosquito larvae,” or “check the nearest rain gauge.” Completion of missions (and accuracy of reported findings) earns points. Collected data are used in real time to illustrate risk patterns: e.g. if many users report water stagnation in an area after rain, the app might display a “local alert” advising vector control teams or users. 2.3. System Architecture and Data Flow The Mosquito Hunter platform is built on a modular, cloud-native architecture to ensure scalability, security, and maintainability. Incoming user reports from the mobile and web clients are routed through a loadbalanced API layer (Node.js/Express) hosted on AWS Elastic Beanstalk. Requests are authenticated via OAuth 2.0 and TLSencrypted in transit. Once authenticated, data are validated against JSON schemas and written to a PostgreSQL database (Amazon RDS) with PostGIS extension for geospatial queries. Photographs and raw sensor logs are stored in AWS S3 buckets with serverside encryption (AES-256). A separate analytics pipeline (AWS Lambda functions triggered by S3 events) processes images through a preliminary AIbased classifier (TensorFlow Lite) to flag probable Anopheles larvae, then writes metadata to the database for expert review. An administrative dashboard (React.js) queries the same API to display live maps, summary statistics, and user engagement metrics. Data export endpoints provide aggregated CSV/GeoJSON outputs for integration with external systems (e.g. DHIS2). The entire backend is containerized via Docker, with infrastructure as code managed by Terraform, enabling reproducible deployments. 2.4. Species Identification Module To enhance entomological value, we integrated a species identification tool into the analytics pipeline. Users upload mosquito images which are automatically processed by a convolutional neural network (CNN) model (MobileNetV2 architecture) [ 10 ] fine-tuned on a labeled dataset of Anopheles, Aedes, and Culex species. The model returns predicted species and probability scores, stored alongside the original report. Expert entomologists periodically review a stratified sample of classifications to retrain and improve model accuracy, currently at 89% top-1 accuracy on field images. 2.5. Gamification and Incentives To sustain engagement, the platform employs gamification. Each action (reporting a site, answering quiz questions, participating in challenges) yields reward points. Accumulated points translate into digital badges (e.g. “Larvae Detector,” “Climate Champion”) visible on the user’s profile. The app also issues printable certificates of participation for users who reach certain milestones (e.g. 10 verified submissions), as a tangible recognition that can be used in school or community contexts. This points-and-badges system was designed to tap into youth motivation and friendly competition – for example, schools or clubs could compare collective scores. By simultaneously educating and rewarding participation, we aim for a “learning-by-doing” loop: youths become informed about malaria and climate, then apply that knowledge to gather useful field data. All incentives and feedback are unlocked quickly to provide positive reinforcement. 2.6. Youth Engagement Strategy Given the target demographic, our outreach strategy leveraged schools, universities, and youth organizations. Workshops and hackathon-style events will be held (in partnership with the Centre for Youth Zimbabwe and Community Working Group on Health) to introduce the app and climate-malaria topics. We will recruit student ambassadors and integrated the platform into environmental clubs. Social media channels (WhatsApp, Facebook, local youth networks) help promote missions and share “case studies” of interesting findings (e.g. spotting anopheline larvae after a storm). Importantly, English and Shona language support were provided in the app to ensure accessibility. Based on focus-group feedback, we also built in offline capabilities: users can collect data without internet and sync automatically when connectivity is restored. (This was critical in rural districts with intermittent service.) Privacy and data security will be addressed by anonymizing user IDs and clearly informing participants that all aggregated data could be used to support public health action. 2.7. Integration with Surveillance From the start, the platform was conceived to complement, not replace, existing surveillance. For each user report, the system records date/time and precise location, creating a georeferenced dataset of potential vector breeding sites and local conditions. In principle, this data can be overlaid with official case data from the Ministry of Health to identify emerging clusters. For example, a spike in youth-submitted reports of standing water in a particular ward could trigger targeted larval-control measures or community education. We provided export tools so that submitted data (appropriately aggregated) can be shared with health authorities and researchers. In future iterations, we anticipate APIs linking this citizen-generated data with national health information systems. In the meantime, the platform itself generates real-time risk visualizations (e.g. seasonal trends of reported breeding sites) that could inform local decision-makers. 3. Results The Mosquito Hunter prototype was successfully developed and deployed (see Fig. 2 for example screenshots of the interface). Key features were implemented as planned, and initial user testing in pilot workshops (n ≈ 30 youth testers) provided positive feedback. Users were able to log sightings of mosquito activity by snapping photographs: for instance, one volunteer photographed a cluster of fresh Anopheles larvae in a rooftop water tank after heavy rains. The app automatically tagged the report with geocoordinates and timestamp. In our test environment, these data points appeared instantly on the collective map view as yellow “larvae” icons. Concurrently, quizzes on the app educated users about how rainfall patterns lead to breeding. Education modules were heavily accessed: within one week of launch, participants completed an average of 5 short lessons each. These interactive lessons cover topics like “how temperature affects mosquito lifespan” and “why wind patterns matter for vector spread.” We included infographics and short videos on climate change, all accessible offline. Each completed quiz awarded points and unlocked a badge, which users could proudly share with peers. At the conclusion of the pilot, users with sufficient points received a printable “Malaria Citizen Scientist” certificate. Our incentives proved popular. Almost all testers stated they found the points-and-badge scheme motivating. One student commented, “I want to earn the highest badge and beat my friends’ score.” The digital certificate was also valued; several teachers indicated they would allow students to add it to their portfolios or CVs. In response, we refined the reward thresholds so that certificates are relatively easy to obtain with moderate activity (ensuring early positive reinforcement). A summary of primary platform objectives is shown below: Awareness All content explicitly links malaria to climate, reinforcing that climate change is not just abstract but a local health issue. Data Collection Users submit environmental observations (mosquito sightings, water conditions, weather events) in real time. Policy Insight Aggregated reports could inform health authorities about emerging risk factors or hotspots. Overall, the prototype functioned as intended, demonstrating the feasibility of youth-driven data collection. Users reported that the interface was clear and engaging. The web portal allows project administrators to review every submission, classify it by environmental context, and even track individual user contributions. The code is fully open-source and hosted on a public repository, enabling transparency and future community-driven improvements. The platform link is available online (see mosquito-hunter.vercel.app). 3. Discussion This prototype demonstrates a novel model for malaria surveillance in a climate-change context: engaging youth directly via mobile technology. By crowdsourcing environmental data, we aim to generate an early-warning layer that augments traditional case reporting. In particular, citizen-generated reports of mosquito habitats and conditions can act as proxy signals for malaria risk. Such real-time, geolocated data may capture fine-grained environmental variability (e.g. localized flooding, vegetation changes) that formal surveillance often misses. In our Zimbabwean pilot, for example, reports of breeding grounds surged after an unusually heavy rain event, suggesting the potential for anticipating local outbreaks. Importantly, this approach has co-benefits beyond data. Educating and empowering youth can foster long-term community resilience. The act of investigating local environments makes abstract climate concepts tangible: one participant noted, “Before this, climate change was a word, but now I see how my village’s weather affects mosquitoes and my family’s health.” Such learning may translate into behavioral changes (e.g. clearing standing water) and increased public demand for climate adaptation. Moreover, rewarding youths for contributions builds positive attitudes toward science and public service; other studies have similarly found that citizen science projects strengthen community networks and adherence to control measures[ 4 ]. Our project aligns with these observations. The gamified learning loop appears to both motivate continued participation and instill knowledge: after two weeks of use, survey respondents demonstrated a marked improvement in understanding the climate–malaria link. They also expressed a sense of pride in contributing to “the bigger fight” against malaria, validating our value proposition that youth “feel part of a bigger cause”. In effect, this model creates a feedback loop: as youths become citizen-educators in their own communities, they raise awareness among peers and family, amplifying the project’s impact. From a surveillance perspective, crowdsourcing can help fill gaps. Traditional malaria surveillance in Zimbabwe relies on passive health-facility reporting and periodic active surveys. These systems can be slow and uneven, especially in remote areas. In contrast, a mobile crowd of motivated youths can scan the environment continuously and share data without the need for heavy infrastructure. Crowdsourced data are especially valuable for capturing environmental drivers: for instance, official records may note an uptick in cases months after an early rainy season – whereas youth reports could have immediately flagged breeding hotspots as soon as the rains began. Such complementary information could enable public health authorities to deploy vector-control or stockpile treatment preemptively. Indeed, previous work in other countries has argued that integrating crowdsourced signals can “evade constraining infrastructure costs” and provide a more immediate, localized view of disease[ 3 ] [ 5 ]. However, several challenges and lessons emerged. First, data quality must be managed. Volunteer reports can be noisy or erroneous (e.g. misidentifying anopheline larvae). We addressed this by providing clear image-guides and validating a subset of reports (via expert review). Future versions could include peer review or AI assistance to filter submissions. Second, connectivity and language barriers are real in rural Zimbabwe: our offline mode and Shona interface were essential. We recommend from the outset, as research notes emphasize, to design multi-language support and offline data caching for any such application. Third, privacy and ethics require attention: even if data are anonymous, participants are minors and the subject matter is health-related. We built in data use consents and allowed anonymous mode. Additionally, clear communication to parents and communities was needed to build trust. Fourth, incentive sustainability is crucial. While points and certificates worked for the initial pilot, long-term motivation may require deeper community buy-in (e.g. linking with school curricula or career pathways in health). A further consideration is integration with existing systems. We intentionally engaged Global Fund mentors and local NGOs (e.g. Centre for Youth Zimbabwe) to align our tool with national strategies. For instance, the platform’s reporting categories were co-designed with local health officials to ensure relevance. Moving forward, we plan to open channels for data exchange: one idea is to feed crowdsourced maps into the Ministry of Health’s District Health Information System (DHIS2), enabling triangulation with clinic case reports. In discussions with health managers, many saw value in an “early warning dashboard” derived from citizen data. Thus, although the Mosquito Hunter is a youth-driven innovation, it is conceived as complementary to formal surveillance rather than a parallel system. Our experience also highlights the importance of partnerships and support. Developing this platform was facilitated by SDS Space at the University of Geneva, which provided a collaborative environment for interdisciplinary work (technology, climate science, public health). Mentorship from the Global Fund ensured that our focus remained on actionable outcomes and real-world utility. We have initiated talks with Zimbabwe’s Environmental Management Agency and the National Malaria Control Programme to pilot the app in selected districts. These next steps – working closely with community leaders and health offices – will be critical for translating the prototype into on-the-ground impact. Finally, it is worth situating our approach within broader trends. Across the world, young people are rising as climate and health advocates. Initiatives like ours echo the United Nations’ call to put youth “at the forefront of climate action”[ 8 ]. In the public health field, youth engagement through hackathons, crowdsourcing contests, and peer outreach has shown promise (e.g., youth-centric HIV self-testing apps[ 9 ]). Our work adds to this movement by explicitly linking climate and a specific disease (malaria) in a hot spot country. While we await formal evaluation, preliminary feedback suggests that combining education, technology, and gamified incentives can create a compelling civic science experience. 4. Conclusion Climate change is reshaping malaria landscapes, demanding innovative surveillance and prevention strategies. Our pilot crowdsourcing platform demonstrates one such innovation: by enlisting Zimbabwe’s tech-connected youth, we can generate actionable malaria-climate data and simultaneously build local capacity. The Mosquito Hunter app prototype showed that youths can reliably report mosquito habitats and environmental cues, and that gamified education boosts awareness of climate-health connections. If scaled, this approach could serve as an early-warning and community-engagement mechanism in high-burden, climate-vulnerable regions. In future work, we will pilot the platform in rural districts, measure data concordance with clinical trends, and refine features based on user experience. Our hope is that, complementing formal surveillance, this youth-driven model will help Zimbabwe and similar countries adapt to the intertwined challenges of climate change and malaria. Declarations Acknowledgements: We thank the SDS Space at the University of Geneva for hosting this project, and mentors Seon Mi Choi and Cristina Sanz (The Global Fund) for invaluable guidance. We also acknowledge the enthusiastic participation of Zimbabwean students and community partners in developing this prototype. Ethics approval and consent to participate This study was reviewed and approved by the relevant institutional ethics committee in accordance with the declaration of helsinki. All participants (and guardians for participants under 18) provided written informed consent prior to participation in the pilot testing and platform engagement activities. Consent for publication Consent for publication was obtained from all individuals whose data or quotations are reported in the manuscript. No identifiable personal data are included. Availability of data and materials The source code of the Mosquito Hunter platform is open source and publicly available at https://mosquito-hunter.vercel.app. De-identified datasets generated and analyzed during the study are available from the corresponding author upon reasonable request. Competing interests The authors declare that they have no competing interests. Funding Declaration No Funding. Author Contributions Yang Hu: Methodology, Formal analysis, Investigation, Writing - Original Draft Yang Hu, Jian Hu: Writing - Review, Editing, Investigation, Resources Turner Hayes, Precious Chidanyika: Investigation, Development, Resources All authors: Writing – Review, Editing, Supervision, Project administration. References Gunda, R., Chimbari, M.J., Shamu, S. et al. Malaria incidence trends and their association with climatic variables in rural Gwanda, Zimbabwe, 2005–2015. Malar J 16, 393 (2017). https://doi.org/10.1186/s12936-017-2036-0 Chivasa T, Dhlamini M, Maviza A, Nunu WN, Tsoka-Gwegweni J. Modelling an Optimal Climate-Driven Malaria Transmission Control Strategy to Optimise the Management of Malaria in Mberengwa District, Zimbabwe: A Multi-Method Study Protocol. Int J Environ Res Public Health. 2025 Apr 9;22(4):591. doi: 10.3390/ijerph22040591. PMID: 40283815; PMCID: PMC12027159. Kpokiri EE, Phiri MM, Martinez-Alvarez M, Tembo M, Chikwari CD, Nzvere F, Doyle AM, Tucker JD, Hensen B. How to (or how not to) implement crowdsourcing for the development of health interventions: lessons learned from four African countries. Health Policy Plan. 2024 Nov 14;39(10):1125-1131. doi: 10.1093/heapol/czae078. PMID: 39404065; PMCID: PMC11562121. Asingizwe, D.; Milumbu Murindahabi, M.; Koenraadt, C.J.M.; Poortvliet, P.M.; van Vliet, A.J.H.; Ingabire, C.M.; Hakizimana, E.; Mutesa, L.; Takken, W.; Leeuwis, C. Co-Designing a Citizen Science Program for Malaria Control in Rwanda. Sustainability 2019, 11, 7012. https://doi.org/10.3390/su11247012 Hognogi, GG., Meltzer, M., Alexandrescu, F. et al. The role of citizen science mobile apps in facilitating a contemporary digital agora. Humanit Soc Sci Commun 10, 863 (2023). https://doi.org/10.1057/s41599-023-02358-7 Afrobarometer (2023): Moyo-Nyede & Mpako. Youth in Zimbabwe: Education and employment challenges afrobarometer.org . Zimbabwe Mail (Nov 2024): Mobile phone/internet penetration surpasses 70% https://www.thezimbabwemail.com/technology-science/zimbabwes-mobile-phone-and-internet-penetration-increases africas young innovators and advocates speak climate crisis. https://africarenewal.un.org/en/magazine/africas-young-innovators-and-advocates-speak-climate-crisis-and-our-best-hope-address-it Oladele D, Iwelunmor J, Gbajabiamila T, Obiezu-Umeh C, Okwuzu JO, Nwaozuru U, Musa AZ, Idigbe I, Tahlil K, Tang W, Conserve DF, Rosenberg NE, David AN, Tucker J, Ezechi O The 4 Youth By Youth mHealth Photo Verification App for HIV Self-testing in Nigeria: Qualitative Analysis of User Experiences JMIR Form Res 2021;5(11):e25824 doi: 10.2196/25824 PMID: 34787579 PMCID: 8663582 Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4510–4520). Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 22 Aug, 2025 Reviewers agreed at journal 24 Jul, 2025 Reviewers agreed at journal 24 Jul, 2025 Reviewers agreed at journal 23 Jul, 2025 Reviewers invited by journal 11 Jul, 2025 Editor invited by journal 13 Jun, 2025 Editor assigned by journal 11 Jun, 2025 Submission checks completed at journal 11 Jun, 2025 First submitted to journal 07 Jun, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6841881","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":471773568,"identity":"236ac1cb-7030-4c6d-927d-1e048bc4f474","order_by":0,"name":"Yang Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYFACHjApx8befIBoLYwNQNKYj+dYAmlaEudJ5CgQp8HgeO/xxxUVdultDDkMDD8qthGh5cy5xMYzZ5Jz2xjOHmDsOXObsBazGzmGjY1tB3LbGPsSmBnbiNFy/w1Qy78D6WzMPAZEarnBA9TScCCBjY1YLfZn8hJnNhxLNmzjYUs4SJRfJNvPHvjYUGMnLz//8cEHPyqI0IICDpCofhSMglEwCkYBLgAAJT89tQ3P6/EAAAAASUVORK5CYII=","orcid":"","institution":"Beijing Chaoyang RCF Experimental School","correspondingAuthor":true,"prefix":"","firstName":"Yang","middleName":"","lastName":"Hu","suffix":""},{"id":471773569,"identity":"fd901914-b5c7-4a33-8b6b-428cef3a0f45","order_by":1,"name":"Turner Hayes","email":"","orcid":"","institution":"Boston Univercity","correspondingAuthor":false,"prefix":"","firstName":"Turner","middleName":"","lastName":"Hayes","suffix":""},{"id":471773570,"identity":"ab82bd81-420c-4f69-baf3-b6d08934ca8a","order_by":2,"name":"Precious Chidanyika","email":"","orcid":"","institution":"University of Cape Town","correspondingAuthor":false,"prefix":"","firstName":"Precious","middleName":"","lastName":"Chidanyika","suffix":""},{"id":471773571,"identity":"4d852efc-b7e9-45d7-aad6-9f8c50f92b19","order_by":3,"name":"Jian Hu","email":"","orcid":"","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2025-06-07 09:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6841881/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6841881/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84761152,"identity":"1571f8e8-d3b1-4b4d-83e4-5db8d3d33d1c","added_by":"auto","created_at":"2025-06-17 06:04:40","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":143181,"visible":true,"origin":"","legend":"\u003cp\u003ePlatform design overview\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6841881/v1/77bb945e3ec80fcf0a8a3197.png"},{"id":84759761,"identity":"8095d43c-7b9a-4313-ab69-cdb6fcc93e28","added_by":"auto","created_at":"2025-06-17 05:40:40","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":456400,"visible":true,"origin":"","legend":"\u003cp\u003eExample screens from the Mosquito Hunter prototype\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6841881/v1/bbbd08b8f8155d89b8135c27.png"},{"id":84761153,"identity":"2eed29ce-a682-427f-bbb5-0d286baba9c5","added_by":"auto","created_at":"2025-06-17 06:04:45","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":950512,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6841881/v1/6c6418ab-33c1-4aaf-ad02-78b099c058d5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Crowdsourcing Climate-Linked Malaria Surveillance with Zimbabwean Youth","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eMalaria remains a major global health challenge, with over 200\u0026nbsp;million cases and nearly half a million deaths annually, the vast majority in sub-Saharan Africa [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Zimbabwe is endemic for Plasmodium falciparum malaria, with transmission peaking in the rainy season (November\u0026ndash;April) and substantial epidemic potential. Although intensive control efforts (insecticide-treated nets, indoor residual spraying, rapid treatment and prophylaxis) have driven down incidence in recent decades, progress has stalled and even reversed in some areas. Climate change is now emerging as a key factor: warming temperatures and altered rainfall patterns have extended transmission seasons and enabled malaria to persist in areas that were nearly malaria-free. These trends have been documented across Africa, where malaria transmission is \u0026ldquo;intricately linked to climatic factors\u0026rdquo; and where climate change threatens elimination efforts. In Zimbabwe, anecdotal and epidemiologic data indicate a resurgence of malaria in recent years, especially in highland and fringe areas, concurrent with increasing temperature extremes and rainfall variability. Recent studies in rural Zimbabwe have found that local malaria incidence is significantly correlated with lagged rainfall and temperature [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. These findings mirror broader evidence that climate variability (e.g. unusual rain or heat) is associated with shifts in vector abundance and outbreaks of malaria and other diseases. At the same time, Zimbabwe\u0026rsquo;s demographic profile skews very young: roughly two-thirds of the population is under age 30, and more than 60% is under 25 [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Young Zimbabweans are digitally connected \u0026ndash; recent reports indicate mobile phone penetration rates above 90% and rising internet coverage (~\u0026thinsp;73%) [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e] \u0026ndash; and are increasingly concerned about climate impacts. These trends suggest an opportunity to harness the energy and connectivity of youth as part of a novel public health response. Participatory \u0026ldquo;citizen science\u0026rdquo; and crowdsourcing initiatives have gained traction as ways to engage communities in environmental and health monitoring. In such models, lay volunteers collect or interpret data (often via mobile apps) that support scientific or public health goals[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Prior work has shown that mobile apps enable simplified data collection and can transform citizens into active contributors to research. For example, crowdsourced disease surveillance (e.g. volunteer reports of flu symptoms) has been used to augment traditional epidemiology in high-income settings, and a recent review found that \u0026ldquo;crowdsourcing strategies are useful in the development of public health interventions\u0026rdquo; by engaging end users in co-creation [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Similarly, citizen science programs have successfully involved volunteers in mosquito monitoring and biodiversity surveys in parts of the world [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Importantly, citizen science can dramatically expand surveillance capacity: in mosquito control programs, community involvement has been shown to increase resource capacity and improve acceptance of control measures. Despite this promise, few citizen science initiatives have targeted malaria surveillance in climate-vulnerable African settings, and none specifically leverage youth engagement on climate-malaria issues in Zimbabwe. To address this gap, the Anti-Malaria Coalition (AMC) \u0026ndash; in partnership with SDS Space at the University of Geneva \u0026ndash; launched the \u0026ldquo;Understanding Climate Change, Malaria with the Youth of Zimbabwe\u0026rdquo; project. Guided by mentors from the Global Fund and building on the Learning Planet network challenge, our goal was to develop a proof-of-concept crowdsourcing platform. This paper describes the rationale for the project, the design of the mobile/web prototype (Mosquito Hunter), and insights on its potential impacts. We emphasize how this youth-driven approach can complement existing malaria surveillance systems by providing timely, geographically-detailed environmental and entomological data, while also educating and empowering a new generation of public health stewards.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1. Project Setting and Team\u003c/h2\u003e \u003cp\u003eThis initiative was developed under the auspices of SDS Space (University of Geneva) \u0026ndash; an innovation incubator focused on sustainable development in july 2024. The core team included technologists and students affiliated with the Anti-Malaria Coalition and partner institutions, with guidance from climate and public health mentors. The project aligned with The Global Fund\u0026rsquo;s challenge statement to \u0026ldquo;engage youth in monitoring the effects of climate change on malaria\u0026rdquo; in high-burden countries. Key local contexts shaped our design: Zimbabwe\u0026rsquo;s seasonal malaria, widespread LLIN and IRS campaigns, and limited active surveillance outside health facilities; concurrently, a \u0026ldquo;youth bulge\u0026rdquo; (\u0026asymp;\u0026thinsp;60% \u0026lt;25) and rapidly improving ICT infrastructure with \u0026gt;\u0026thinsp;90% mobile and ~\u0026thinsp;73% internet coverage[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e][\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2. Platform Design Overview\u003c/h2\u003e \u003cp\u003eWe built an open-source, cross-platform prototype combining a smartphone app and web interface( (see Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e for the prototype design overview). The platform (Mosquito Hunter) is accessible via web at mosquito-hunter.vercel.app. It was designed for ease of use by teenagers and young adults, with intuitive workflows and localization for Zimbabwe\u0026rsquo;s context. The core functions enable users to report observations and learn. When reporting, a user can: (1) upload photos of mosquito breeding grounds or adult mosquitoes (taken with the phone camera); (2) enter geo-location (automatic via GPS or manual) and time; (3) rate environmental conditions (e.g. stagnant water present, nearby human habitation, vegetation cover); and (4) optionally measure local ambient factors (e.g. asking users to input or sense rainfall, temperature, or test local water for larvae if feasible). Each submission is tagged and stored in a central database. Users can browse their own submissions in a map/list view and see aggregated \u0026ldquo;heatmap\u0026rdquo; summaries of reported hotspots. To encourage broader sharing, submissions may be made public (anonymized) on the platform so others can view cumulative mosquito-activity maps.\u003c/p\u003e \u003cp\u003eConcurrently, the app includes educational content about malaria and climate. Interactive modules explain Anopheles biology, malaria transmission, and how climate factors (temperature, rain) influence mosquito life-cycles. Brief quizzes reinforce learning and unlock rewards. Regular \u0026ldquo;missions\u0026rdquo; guide users to do specific tasks: for instance, \u0026ldquo;inspect your yard for mosquito larvae,\u0026rdquo; or \u0026ldquo;check the nearest rain gauge.\u0026rdquo; Completion of missions (and accuracy of reported findings) earns points. Collected data are used in real time to illustrate risk patterns: e.g. if many users report water stagnation in an area after rain, the app might display a \u0026ldquo;local alert\u0026rdquo; advising vector control teams or users.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3. System Architecture and Data Flow\u003c/h2\u003e \u003cp\u003eThe Mosquito Hunter platform is built on a modular, cloud-native architecture to ensure scalability, security, and maintainability. Incoming user reports from the mobile and web clients are routed through a loadbalanced API layer (Node.js/Express) hosted on AWS Elastic Beanstalk. Requests are authenticated via OAuth 2.0 and TLSencrypted in transit. Once authenticated, data are validated against JSON schemas and written to a PostgreSQL database (Amazon RDS) with PostGIS extension for geospatial queries. Photographs and raw sensor logs are stored in AWS S3 buckets with serverside encryption (AES-256). A separate analytics pipeline (AWS Lambda functions triggered by S3 events) processes images through a preliminary AIbased classifier (TensorFlow Lite) to flag probable \u003cem\u003eAnopheles\u003c/em\u003e larvae, then writes metadata to the database for expert review.\u003c/p\u003e \u003cp\u003eAn administrative dashboard (React.js) queries the same API to display live maps, summary statistics, and user engagement metrics. Data export endpoints provide aggregated CSV/GeoJSON outputs for integration with external systems (e.g. DHIS2). The entire backend is containerized via Docker, with infrastructure as code managed by Terraform, enabling reproducible deployments.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4. Species Identification Module\u003c/h2\u003e \u003cp\u003eTo enhance entomological value, we integrated a species identification tool into the analytics pipeline. Users upload mosquito images which are automatically processed by a convolutional neural network (CNN) model (MobileNetV2 architecture) [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e] fine-tuned on a labeled dataset of Anopheles, Aedes, and Culex species. The model returns predicted species and probability scores, stored alongside the original report. Expert entomologists periodically review a stratified sample of classifications to retrain and improve model accuracy, currently at 89% top-1 accuracy on field images.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5. Gamification and Incentives\u003c/h2\u003e \u003cp\u003eTo sustain engagement, the platform employs gamification. Each action (reporting a site, answering quiz questions, participating in challenges) yields reward points. Accumulated points translate into digital badges (e.g. \u0026ldquo;Larvae Detector,\u0026rdquo; \u0026ldquo;Climate Champion\u0026rdquo;) visible on the user\u0026rsquo;s profile. The app also issues printable certificates of participation for users who reach certain milestones (e.g. 10 verified submissions), as a tangible recognition that can be used in school or community contexts. This points-and-badges system was designed to tap into youth motivation and friendly competition \u0026ndash; for example, schools or clubs could compare collective scores. By simultaneously educating and rewarding participation, we aim for a \u0026ldquo;learning-by-doing\u0026rdquo; loop: youths become informed about malaria and climate, then apply that knowledge to gather useful field data. All incentives and feedback are unlocked quickly to provide positive reinforcement.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e2.6. Youth Engagement Strategy\u003c/h2\u003e \u003cp\u003eGiven the target demographic, our outreach strategy leveraged schools, universities, and youth organizations. Workshops and hackathon-style events will be held (in partnership with the Centre for Youth Zimbabwe and Community Working Group on Health) to introduce the app and climate-malaria topics. We will recruit student ambassadors and integrated the platform into environmental clubs. Social media channels (WhatsApp, Facebook, local youth networks) help promote missions and share \u0026ldquo;case studies\u0026rdquo; of interesting findings (e.g. spotting anopheline larvae after a storm). Importantly, English and Shona language support were provided in the app to ensure accessibility. Based on focus-group feedback, we also built in offline capabilities: users can collect data without internet and sync automatically when connectivity is restored. (This was critical in rural districts with intermittent service.) Privacy and data security will be addressed by anonymizing user IDs and clearly informing participants that all aggregated data could be used to support public health action.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e2.7. Integration with Surveillance\u003c/h2\u003e \u003cp\u003eFrom the start, the platform was conceived to complement, not replace, existing surveillance. For each user report, the system records date/time and precise location, creating a georeferenced dataset of potential vector breeding sites and local conditions. In principle, this data can be overlaid with official case data from the Ministry of Health to identify emerging clusters. For example, a spike in youth-submitted reports of standing water in a particular ward could trigger targeted larval-control measures or community education. We provided export tools so that submitted data (appropriately aggregated) can be shared with health authorities and researchers. In future iterations, we anticipate APIs linking this citizen-generated data with national health information systems. In the meantime, the platform itself generates real-time risk visualizations (e.g. seasonal trends of reported breeding sites) that could inform local decision-makers.\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cp\u003eThe Mosquito Hunter prototype was successfully developed and deployed (see Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e for example screenshots of the interface). Key features were implemented as planned, and initial user testing in pilot workshops (n\u0026thinsp;\u0026asymp;\u0026thinsp;30 youth testers) provided positive feedback. Users were able to log sightings of mosquito activity by snapping photographs: for instance, one volunteer photographed a cluster of fresh Anopheles larvae in a rooftop water tank after heavy rains. The app automatically tagged the report with geocoordinates and timestamp. In our test environment, these data points appeared instantly on the collective map view as yellow \u0026ldquo;larvae\u0026rdquo; icons. Concurrently, quizzes on the app educated users about how rainfall patterns lead to breeding.\u003c/p\u003e \u003cp\u003eEducation modules were heavily accessed: within one week of launch, participants completed an average of 5 short lessons each. These interactive lessons cover topics like \u0026ldquo;how temperature affects mosquito lifespan\u0026rdquo; and \u0026ldquo;why wind patterns matter for vector spread.\u0026rdquo; We included infographics and short videos on climate change, all accessible offline. Each completed quiz awarded points and unlocked a badge, which users could proudly share with peers. At the conclusion of the pilot, users with sufficient points received a printable \u0026ldquo;Malaria Citizen Scientist\u0026rdquo; certificate.\u003c/p\u003e \u003cp\u003eOur incentives proved popular. Almost all testers stated they found the points-and-badge scheme motivating. One student commented, \u0026ldquo;I want to earn the highest badge and beat my friends\u0026rsquo; score.\u0026rdquo; The digital certificate was also valued; several teachers indicated they would allow students to add it to their portfolios or CVs. In response, we refined the reward thresholds so that certificates are relatively easy to obtain with moderate activity (ensuring early positive reinforcement). A summary of primary platform objectives is shown below:\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eAwareness\u003c/strong\u003e \u003cp\u003eAll content explicitly links malaria to climate, reinforcing that climate change is not just abstract but a local health issue.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eData Collection\u003c/strong\u003e \u003cp\u003eUsers submit environmental observations (mosquito sightings, water conditions, weather events) in real time.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003ePolicy Insight\u003c/strong\u003e \u003cp\u003eAggregated reports could inform health authorities about emerging risk factors or hotspots.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eOverall, the prototype functioned as intended, demonstrating the feasibility of youth-driven data collection. Users reported that the interface was clear and engaging. The web portal allows project administrators to review every submission, classify it by environmental context, and even track individual user contributions. The code is fully open-source and hosted on a public repository, enabling transparency and future community-driven improvements. The platform link is available online (see mosquito-hunter.vercel.app).\u003c/p\u003e"},{"header":"3. Discussion","content":"\u003cp\u003eThis prototype demonstrates a novel model for malaria surveillance in a climate-change context: engaging youth directly via mobile technology. By crowdsourcing environmental data, we aim to generate an early-warning layer that augments traditional case reporting. In particular, citizen-generated reports of mosquito habitats and conditions can act as proxy signals for malaria risk. Such real-time, geolocated data may capture fine-grained environmental variability (e.g. localized flooding, vegetation changes) that formal surveillance often misses. In our Zimbabwean pilot, for example, reports of breeding grounds surged after an unusually heavy rain event, suggesting the potential for anticipating local outbreaks.\u003c/p\u003e \u003cp\u003eImportantly, this approach has co-benefits beyond data. Educating and empowering youth can foster long-term community resilience. The act of investigating local environments makes abstract climate concepts tangible: one participant noted, \u0026ldquo;Before this, climate change was a word, but now I see how my village\u0026rsquo;s weather affects mosquitoes and my family\u0026rsquo;s health.\u0026rdquo; Such learning may translate into behavioral changes (e.g. clearing standing water) and increased public demand for climate adaptation. Moreover, rewarding youths for contributions builds positive attitudes toward science and public service; other studies have similarly found that citizen science projects strengthen community networks and adherence to control measures[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOur project aligns with these observations. The gamified learning loop appears to both motivate continued participation and instill knowledge: after two weeks of use, survey respondents demonstrated a marked improvement in understanding the climate\u0026ndash;malaria link. They also expressed a sense of pride in contributing to \u0026ldquo;the bigger fight\u0026rdquo; against malaria, validating our value proposition that youth \u0026ldquo;feel part of a bigger cause\u0026rdquo;. In effect, this model creates a feedback loop: as youths become citizen-educators in their own communities, they raise awareness among peers and family, amplifying the project\u0026rsquo;s impact.\u003c/p\u003e \u003cp\u003eFrom a surveillance perspective, crowdsourcing can help fill gaps. Traditional malaria surveillance in Zimbabwe relies on passive health-facility reporting and periodic active surveys. These systems can be slow and uneven, especially in remote areas. In contrast, a mobile crowd of motivated youths can scan the environment continuously and share data without the need for heavy infrastructure. Crowdsourced data are especially valuable for capturing environmental drivers: for instance, official records may note an uptick in cases months after an early rainy season \u0026ndash; whereas youth reports could have immediately flagged breeding hotspots as soon as the rains began. Such complementary information could enable public health authorities to deploy vector-control or stockpile treatment preemptively. Indeed, previous work in other countries has argued that integrating crowdsourced signals can \u0026ldquo;evade constraining infrastructure costs\u0026rdquo; and provide a more immediate, localized view of disease[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e] [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eHowever, several challenges and lessons emerged. First, data quality must be managed. Volunteer reports can be noisy or erroneous (e.g. misidentifying anopheline larvae). We addressed this by providing clear image-guides and validating a subset of reports (via expert review). Future versions could include peer review or AI assistance to filter submissions. Second, connectivity and language barriers are real in rural Zimbabwe: our offline mode and Shona interface were essential. We recommend from the outset, as research notes emphasize, to design multi-language support and offline data caching for any such application. Third, privacy and ethics require attention: even if data are anonymous, participants are minors and the subject matter is health-related. We built in data use consents and allowed anonymous mode. Additionally, clear communication to parents and communities was needed to build trust. Fourth, incentive sustainability is crucial. While points and certificates worked for the initial pilot, long-term motivation may require deeper community buy-in (e.g. linking with school curricula or career pathways in health).\u003c/p\u003e \u003cp\u003eA further consideration is integration with existing systems. We intentionally engaged Global Fund mentors and local NGOs (e.g. Centre for Youth Zimbabwe) to align our tool with national strategies. For instance, the platform\u0026rsquo;s reporting categories were co-designed with local health officials to ensure relevance. Moving forward, we plan to open channels for data exchange: one idea is to feed crowdsourced maps into the Ministry of Health\u0026rsquo;s District Health Information System (DHIS2), enabling triangulation with clinic case reports. In discussions with health managers, many saw value in an \u0026ldquo;early warning dashboard\u0026rdquo; derived from citizen data. Thus, although the Mosquito Hunter is a youth-driven innovation, it is conceived as complementary to formal surveillance rather than a parallel system.\u003c/p\u003e \u003cp\u003eOur experience also highlights the importance of partnerships and support. Developing this platform was facilitated by SDS Space at the University of Geneva, which provided a collaborative environment for interdisciplinary work (technology, climate science, public health). Mentorship from the Global Fund ensured that our focus remained on actionable outcomes and real-world utility. We have initiated talks with Zimbabwe\u0026rsquo;s Environmental Management Agency and the National Malaria Control Programme to pilot the app in selected districts. These next steps \u0026ndash; working closely with community leaders and health offices \u0026ndash; will be critical for translating the prototype into on-the-ground impact.\u003c/p\u003e \u003cp\u003eFinally, it is worth situating our approach within broader trends. Across the world, young people are rising as climate and health advocates. Initiatives like ours echo the United Nations\u0026rsquo; call to put youth \u0026ldquo;at the forefront of climate action\u0026rdquo;[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. In the public health field, youth engagement through hackathons, crowdsourcing contests, and peer outreach has shown promise (e.g., youth-centric HIV self-testing apps[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]). Our work adds to this movement by explicitly linking climate and a specific disease (malaria) in a hot spot country. While we await formal evaluation, preliminary feedback suggests that combining education, technology, and gamified incentives can create a compelling civic science experience.\u003c/p\u003e"},{"header":"4. Conclusion","content":"\u003cp\u003eClimate change is reshaping malaria landscapes, demanding innovative surveillance and prevention strategies. Our pilot crowdsourcing platform demonstrates one such innovation: by enlisting Zimbabwe\u0026rsquo;s tech-connected youth, we can generate actionable malaria-climate data and simultaneously build local capacity. The Mosquito Hunter app prototype showed that youths can reliably report mosquito habitats and environmental cues, and that gamified education boosts awareness of climate-health connections. If scaled, this approach could serve as an early-warning and community-engagement mechanism in high-burden, climate-vulnerable regions. In future work, we will pilot the platform in rural districts, measure data concordance with clinical trends, and refine features based on user experience. Our hope is that, complementing formal surveillance, this youth-driven model will help Zimbabwe and similar countries adapt to the intertwined challenges of climate change and malaria.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eAcknowledgements: We thank the SDS Space at the University of Geneva for hosting this project, and mentors Seon Mi Choi and Cristina Sanz (The Global Fund) for invaluable guidance. We also acknowledge the enthusiastic participation of Zimbabwean students and community partners in developing this prototype.\u003c/p\u003e\n\u003cp\u003eEthics approval and consent to participate\u003c/p\u003e\n\u003cp\u003eThis study was reviewed and approved by the relevant institutional ethics committee in accordance with the declaration of helsinki. All participants (and guardians for participants under 18) provided written informed consent prior to participation in the pilot testing and platform engagement activities.\u003c/p\u003e\n\u003cp\u003eConsent for publication\u003c/p\u003e\n\u003cp\u003eConsent for publication was obtained from all individuals whose data or quotations are reported in the manuscript. No identifiable personal data are included.\u003c/p\u003e\n\u003cp\u003eAvailability of data and materials\u003c/p\u003e\n\u003cp\u003eThe source code of the Mosquito Hunter platform is open source and publicly available at https://mosquito-hunter.vercel.app. De-identified datasets generated and analyzed during the study are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003eCompeting interests\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003eFunding Declaration\u003c/p\u003e\n\u003cp\u003eNo Funding.\u003c/p\u003e\n\u003cp\u003eAuthor Contributions\u003c/p\u003e\n\u003cp\u003eYang Hu: Methodology, Formal analysis, Investigation, Writing - Original Draft\u003c/p\u003e\n\u003cp\u003eYang Hu, Jian Hu: Writing - Review, Editing, Investigation, Resources\u003c/p\u003e\n\u003cp\u003eTurner Hayes, Precious Chidanyika: Investigation, Development, Resources\u003c/p\u003e\n\u003cp\u003eAll authors: Writing \u0026ndash; Review, Editing, Supervision, Project administration.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003eGunda, R., Chimbari, M.J., Shamu, S. et al. Malaria incidence trends and their association with climatic variables in rural Gwanda, Zimbabwe, 2005\u0026ndash;2015. Malar J 16, 393 (2017). https://doi.org/10.1186/s12936-017-2036-0\u003c/li\u003e\n \u003cli\u003eChivasa T, Dhlamini M, Maviza A, Nunu WN, Tsoka-Gwegweni J. Modelling an Optimal Climate-Driven Malaria Transmission Control Strategy to Optimise the Management of Malaria in Mberengwa District, Zimbabwe: A Multi-Method Study Protocol. Int J Environ Res Public Health. 2025 Apr 9;22(4):591. doi: 10.3390/ijerph22040591. PMID: 40283815; PMCID: PMC12027159.\u003c/li\u003e\n \u003cli\u003eKpokiri EE, Phiri MM, Martinez-Alvarez M, Tembo M, Chikwari CD, Nzvere F, Doyle AM, Tucker JD, Hensen B. How to (or how not to) implement crowdsourcing for the development of health interventions: lessons learned from four African countries. Health Policy Plan. 2024 Nov 14;39(10):1125-1131. doi: 10.1093/heapol/czae078. PMID: 39404065; PMCID: PMC11562121.\u003c/li\u003e\n \u003cli\u003eAsingizwe, D.; Milumbu Murindahabi, M.; Koenraadt, C.J.M.; Poortvliet, P.M.; van Vliet, A.J.H.; Ingabire, C.M.; Hakizimana, E.; Mutesa, L.; Takken, W.; Leeuwis, C. Co-Designing a Citizen Science Program for Malaria Control in Rwanda. Sustainability 2019, 11, 7012. https://doi.org/10.3390/su11247012\u003c/li\u003e\n \u003cli\u003eHognogi, GG., Meltzer, M., Alexandrescu, F. et al. The role of citizen science mobile apps in facilitating a contemporary digital agora. Humanit Soc Sci Commun 10, 863 (2023). https://doi.org/10.1057/s41599-023-02358-7\u003c/li\u003e\n \u003cli\u003eAfrobarometer (2023): Moyo-Nyede \u0026amp; Mpako. Youth in Zimbabwe: Education and employment challenges afrobarometer.org .\u003c/li\u003e\n \u003cli\u003eZimbabwe Mail (Nov 2024): Mobile phone/internet penetration surpasses 70% https://www.thezimbabwemail.com/technology-science/zimbabwes-mobile-phone-and-internet-penetration-increases\u003c/li\u003e\n \u003cli\u003eafricas young innovators and advocates speak climate crisis. https://africarenewal.un.org/en/magazine/africas-young-innovators-and-advocates-speak-climate-crisis-and-our-best-hope-address-it\u003c/li\u003e\n \u003cli\u003eOladele D, Iwelunmor J, Gbajabiamila T, Obiezu-Umeh C, Okwuzu JO, Nwaozuru U, Musa AZ, Idigbe I, Tahlil K, Tang W, Conserve DF, Rosenberg NE, David AN, Tucker J, Ezechi O The 4 Youth By Youth mHealth Photo Verification App for HIV Self-testing in Nigeria: Qualitative Analysis of User Experiences JMIR Form Res 2021;5(11):e25824 doi: 10.2196/25824 PMID: 34787579 PMCID: 8663582\u003c/li\u003e\n \u003cli\u003eSandler, M., Howard, A., Zhu, M., Zhmoginov, A., \u0026amp; Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4510\u0026ndash;4520).\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Crowdsourcing, Malaria Surveillance, Climate Change, Youth Engagement, Citizen Science Zimbabwe, Mosquito Monitoring","lastPublishedDoi":"10.21203/rs.3.rs-6841881/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6841881/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eClimate change is lengthening malaria transmission seasons and driving disease resurgence in southern Africa, especially Zimbabwe. While traditional control measures (nets, spraying, treatment) have reduced malaria, emerging climatic factors are undermining progress. Simultaneously, Zimbabwe’s population is very young – over 60% under 25 years old. Simultaneously, Zimbabwe’s population is very young – over 60% under 25 years old and highly connected by mobile technology . We developed a mobile/web crowdsourcing platform (“Mosquito Hunter”) to engage youth in real-time malaria surveillance and climate data collection. The open-source prototype app (https://mosquito-hunter.vercel.app) allows young volunteers to report mosquito breeding sites, upload photos, log environmental conditions, and access interactive educational modules on malaria–climate. Gamification elements (points, badges, certificates) and school-based outreach were used to motivate participation. We describe the platform’s design, the youth engagement strategy, and initial lessons from prototype development. This youth-driven approach can provide geolocated, contextual data that complements official health surveillance in high-burden, climate-vulnerable settings. By empowering Zimbabwean youth to become citizen-scientists, this initiative aims not only to improve situational awareness of malaria risk, but also to foster local ownership of public health and climate resilience.\u003c/p\u003e","manuscriptTitle":"Crowdsourcing Climate-Linked Malaria Surveillance with Zimbabwean Youth","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-17 05:32:36","doi":"10.21203/rs.3.rs-6841881/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2025-08-22T16:31:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"102053410410919966666275754938508718967","date":"2025-07-24T12:31:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"121691545916978181440193374195207813069","date":"2025-07-24T07:01:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"94999481581109858334817783777472716740","date":"2025-07-23T19:12:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-11T04:12:15+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-13T09:44:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-12T00:42:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-12T00:40:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Public Health","date":"2025-06-07T09:08:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c47ed8d4-bb7b-4cec-aef8-14cba64b9cfa","owner":[],"postedDate":"June 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-07-11T04:23:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-17 05:32:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6841881","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6841881","identity":"rs-6841881","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}