Saved in:
Bibliographic Details
Main Authors: Krapu, Christopher, Borsuk, Mark, Calder, Ryan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.01395
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909060049141760
author Krapu, Christopher
Borsuk, Mark
Calder, Ryan
author_facet Krapu, Christopher
Borsuk, Mark
Calder, Ryan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_01395
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep autoregressive modeling for land use land cover
Krapu, Christopher
Borsuk, Mark
Calder, Ryan
Computer Vision and Pattern Recognition
Machine Learning
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.
title Deep autoregressive modeling for land use land cover
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.01395