# Deep autoregressive modeling for land use land cover

arXiv: https://arxiv.org/abs/2401.01395 · HTML: https://mlsanity.com/paper/2401.01395/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 2 Jan 2024.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [Diffusion models as plug-and-play priors](https://mlsanity.com/paper/2206.09012/) (2022)
- [Pluralistic Image Completion](https://mlsanity.com/paper/1903.04227/) (2019)
- [Discrete Flows: Invertible Generative Models of Discrete Data](https://mlsanity.com/paper/1905.10347/) (2019)
- [GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution](https://mlsanity.com/paper/1611.04051/) (2016)
- [Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags](https://mlsanity.com/paper/2111.00970/) (2021)
- [Hierarchical Autoregressive Image Models with Auxiliary Decoders](https://mlsanity.com/paper/1903.04933/) (2019)
- [Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks](https://mlsanity.com/paper/1802.03065/) (2018)
- [Resolving label uncertainty with implicit posterior models](https://mlsanity.com/paper/2202.14000/) (2022)
- [Graphical Gaussian Process Models for Highly Multivariate Spatial Data](https://mlsanity.com/paper/2009.04837/) (2020)
- [Generative Autoregressive Ensembles for Satellite Imagery Manipulation Detection](https://mlsanity.com/paper/2010.03758/) (2020)
- [Probabilistic Semantic Inpainting with Pixel Constrained CNNs](https://mlsanity.com/paper/1810.03728/) (2018)
- [Large-Scale Auto-Regressive Modeling Of Street Networks](https://mlsanity.com/paper/2209.00281/) (2022)

## Abstract (arXiv)

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.