Comparing analytical protocols for identifying causes of population changes

The cost of data aggregation: spatiotemporal compression obscures causal attribution in biodiversity monitoring | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (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];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results The cost of data aggregation: spatiotemporal compression obscures causal attribution in biodiversity monitoring View ORCID Profile Katarzyna Malinowska , View ORCID Profile Michal Wawrzynowicz , View ORCID Profile Katarzyna Markowska , View ORCID Profile Tomasz Chodkiewicz , View ORCID Profile Simon Butler , View ORCID Profile Lechoslaw Kuczynski doi: https://doi.org/10.1101/2025.05.17.654658 Katarzyna Malinowska 1 Adam Mickiewicz University, Uniwersytetu Poznanskiego 6, 61-614 Poznan Poland; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Katarzyna Malinowska For correspondence: katarzyna.malinowska{at}amu.edu.pl Michal Wawrzynowicz 1 Adam Mickiewicz University, Uniwersytetu Poznanskiego 6, 61-614 Poznan Poland; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Michal Wawrzynowicz Katarzyna Markowska 1 Adam Mickiewicz University, Uniwersytetu Poznanskiego 6, 61-614 Poznan Poland; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Katarzyna Markowska Tomasz Chodkiewicz 2 Museum & Institute of Zoology PAS, Twarda 51/55, 00-818 Warszawa, Poland; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Tomasz Chodkiewicz Simon Butler 3 University of East Anglia, Norwich Research Park, Norwich, Norfolk, NR4 7TJ, United Kingdom Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Simon Butler Lechoslaw Kuczynski 1 Adam Mickiewicz University, Uniwersytetu Poznanskiego 6, 61-614 Poznan Poland; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Lechoslaw Kuczynski Abstract Info/History Metrics Supplementary material Data/Code Preview PDF Abstract Conservation decision-making requires accurate identification of causes of population changes. Ecologists often rely on analytical protocols that aggregate high-dimensional monitoring data. We hypothesise that compressing data - either spatially, as in conventional time series (TS) analysis, or temporally, as in static species distribution models (SDMs) - destroys covariance structures and obscures the identification of causal drivers. To quantify this "aggregation cost", we conducted a rigorous simulation experiment using virtual species to establish a known "ground truth" of population drivers. We then employed a virtual ecologist approach to mimic a 20-year large-scale bird monitoring scheme, and generate realistic spatiotemporal datasets to evaluate the analytical pipelines. We benchmarked the causal attribution accuracy of aggregated TS and SDM protocols against a full-resolution spatiotemporal (FRST) framework, which retains native data dimensions and integrates mechanistic spatiotemporal covariance structures. Our simulations revealed that spatial compression severely compromises causal inference: unpenalised TS models failed to detect any true underlying drivers (accuracy = 0.50, sensitivity = 0.00). Temporal compression (SDMs) performer moderately better (accuracy = 0.68), while the FRST model achieved superior accuracy (0.88), sensitivity (0.84), and specificity (0.93). Furthermore, we identified a variable selection paradox: double penalty shrinkage marginally improved underpowered TS models, although it degraded the specificity of SDM and FRST frameworks by forcing spurious, correlated variables to absorb residual variance. Our findings demonstrate that protocols that involve data aggregation reduce the informational value of large-scale monitoring datasets. Full-resolution, mechanistically informed frameworks are essential for reliable causal attribution and robust biodiversity monitoring. Competing Interest Statement The authors have declared no competing interest. Footnotes In the new version of the manuscript, we reformulate the main aim of the study to focus explicitly on the consequences of spatiotemporal data aggregation for causal attribution. We revise and rename the Process-Oriented Model (POM), replacing it with the Full-Resolution Spatio-Temporal framework (FRST). The FRST model is now defined as a control benchmark that quantifies the extent of information loss introduced by spatial or temporal data aggregation, rather than being an inherently superior modelling strategy. We also strengthen the role of the virtual ecologist framework, presenting it as a central methodological strength of our study that allows us to evaluate causal attribution under known ground truth. The manuscript title has been revised to better reflect this focus on the costs of data aggregation and their implications for causal inference in biodiversity monitoring. In addition, we strengthen the interpretation of the results by explicitly highlighting that both TS and SDM approaches exhibit elevated Type I error rates. Overall, the article is reframed as a critical assessment of standard data aggregation protocols, demonstrating that compressing data either spatially or temporally leads to substantial information loss in ecological modelling. https://github.com/popecol/Causes Funder Information Declared National Science Center, https://ror.org/03ha2q922 , 2018/29/B/NZ8/00066 Poznan Supercomputing and Networking Center, https://ror.org/025cj6e44 , pl0090-01 Copyright The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY 4.0 International license . View the discussion thread. Back to top Previous Next Posted May 18, 2026. Download PDF Supplementary Material Data/Code Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following The cost of data aggregation: spatiotemporal compression obscures causal attribution in biodiversity monitoring Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share The cost of data aggregation: spatiotemporal compression obscures causal attribution in biodiversity monitoring Katarzyna Malinowska , Michal Wawrzynowicz , Katarzyna Markowska , Tomasz Chodkiewicz , Simon Butler , Lechoslaw Kuczynski bioRxiv 2025.05.17.654658; doi: https://doi.org/10.1101/2025.05.17.654658 Share This Article: Copy Citation Tools The cost of data aggregation: spatiotemporal compression obscures causal attribution in biodiversity monitoring Katarzyna Malinowska , Michal Wawrzynowicz , Katarzyna Markowska , Tomasz Chodkiewicz , Simon Butler , Lechoslaw Kuczynski bioRxiv 2025.05.17.654658; doi: https://doi.org/10.1101/2025.05.17.654658 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Ecology Subject Areas All Articles Animal Behavior and Cognition (7618) Biochemistry (17637) Bioengineering (13864) Bioinformatics (41853) Biophysics (21403) Cancer Biology (18540) Cell Biology (25429) Clinical Trials (138) Developmental Biology (13356) Ecology (19862) Epidemiology (2067) Evolutionary Biology (24287) Genetics (15585) Genomics (22464) Immunology (17701) Microbiology (40300) Molecular Biology (17142) Neuroscience (88440) Paleontology (666) Pathology (2825) Pharmacology and Toxicology (4814) Physiology (7633) Plant Biology (15107) Scientific Communication and Education (2042) Synthetic Biology (4285) Systems Biology (9809) Zoology (2268)