Deep autoregressive modeling for land use land cover
This is an incremental improvement for geographic and ecological researchers, addressing spatial pattern modeling with computational methods.
The authors tackled land use/land cover modeling by adapting a PixelCNN architecture for image inpainting, finding it captures richer spatial patterns like roads and water bodies compared to a benchmark model, but it produces an uncalibrated predictive distribution with underdispersion in ecological statistics.
Land use / land cover (LULC) modeling is a challenging task due to long-range dependencies between geographic features and distinct spatial patterns related to topography, ecology, and human development. We identify a close connection between modeling of spatial patterns of land use and the task of image inpainting from computer vision and conduct a study of a modified PixelCNN architecture with approximately 19 million parameters for modeling LULC. In comparison with a benchmark spatial statistical model, we find that the former is capable of capturing much richer spatial correlation patterns such as roads and water bodies but does not produce a calibrated predictive distribution, suggesting the need for additional tuning. We find evidence of predictive underdispersion with regard to important ecologically-relevant land use statistics such as patch count and adjacency which can be ameliorated to some extent by manipulating sampling variability.