A Convolutional Autoencoder-Based Method for Vector Curve Data Compression

(1) Background: Curve data compression plays a critical role in efficient storage, transmission, and multi-scale visualization of spatial vector data, especially for complex geographic boundaries. Achieving high compression efficiency while preserving geometric fidelity remains a challenging task. (2) Methods: This study proposes a vector curve compression framework based on a convolutional autoencoder. Curve data are segmented and resampled to standardize network input, after which coordinate-difference sequences are encoded into low-dimensional latent vectors through convolutional layers and reconstructed via a symmetric decoder. (3) Results: Experiments conducted on global island boundary datasets demonstrate that the proposed method achieves effective compression with stable reconstruction accuracy. The compression rate can be flexibly adjusted by network parameters. Compared with Fourier series-based methods and fully connected autoencoders, the proposed model shows improved reconstruction performance at relatively high compression ratios. A convolution kernel size of 1 × 7 and a segment length of 25 km are found to yield optimal results. (4) Conclusions: The proposed method enables efficient vector curve compression and reliable coastline reconstruction, and is particularly suitable for small- and medium-scale cartographic applications up to a map scale of 1:250K.