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.

土地利用 / 土地覆盖（LULC）建模是一项具有挑战性的任务，由于地理特征之间的长程依赖性和与地形、生态和人类发展相关的明显空间模式。我们发现土地利用空间模式建模与计算机视觉中的图像修复任务之间存在密切联系，并对一种修改后的 PixelCNN 架构进行了研究，其参数约为 1900 万个，用于 LULC 建模。与基准空间统计模型相比，我们发现前者能够捕捉到更丰富的空间相关模式，如道路和水体，但无法产生校准的预测分布，表明需要进行额外的调整。我们发现在补丁计数和邻接等重要的生态相关土地利用统计方面存在预测下离散性的证据，可以通过操作采样变异性在一定程度上改善。