Papers
Topics
Authors
Recent
Search
2000 character limit reached

Deep autoregressive modeling for land use land cover

Published 2 Jan 2024 in cs.CV and cs.LG | (2401.01395v1)

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. “Large-Scale Auto-Regressive Modeling Of Street Networks” arXiv, 2022 arXiv:2209.00281 [cs]
  2. Andrew Brock, Jeff Donahue and Karen Simonyan “Large Scale GAN Training for High Fidelity Natural Image Synthesis” In arXiv:1809.11096 [cs, stat], 2018 arXiv:1809.11096 [cs, stat]
  3. “Dynamic World, Near Real-Time Global 10 m Land Use Land Cover Mapping” In Scientific Data 9.1, 2022, pp. 251 DOI: 10.1038/s41597-022-01307-4
  4. Toby N Carlson and S Traci Arthur “The Impact of Land Use — Land Cover Changes Due to Urbanization on Surface Microclimate and Hydrology: A Satellite Perspective” In Global and Planetary Change 25.1, 2000, pp. 49–65 DOI: 10.1016/S0921-8181(00)00021-7
  5. “Generative Pretraining From Pixels” In Proceedings of the 37th International Conference on Machine Learning PMLR, 2020, pp. 1691–1703
  6. “Neural Ordinary Differential Equations” In arXiv:1806.07366 [cs, stat], 2018 arXiv:1806.07366 [cs, stat]
  7. Ting Chen, Ruixiang Zhang and Geoffrey Hinton “Analog Bits: Generating Discrete Data Using Diffusion Models with Self-Conditioning” In ICLR arXiv, 2023 arXiv:2208.04202 [cs]
  8. Jeffrey De Fauw, Sander Dieleman and Karen Simonyan “Hierarchical Autoregressive Image Models with Auxiliary Decoders” arXiv, 2019 arXiv:1903.04933 [cs, stat]
  9. Clayton V. Deutsch “A Sequential Indicator Simulation Program for Categorical Variables with Point and Block Data: BlockSIS” In Computers & Geosciences 32.10, 2006, pp. 1669–1681 DOI: 10.1016/j.cageo.2006.03.005
  10. Debangan Dey, Abhirup Datta and Sudipto Banerjee “Graphical Gaussian Process Models for Highly Multivariate Spatial Data” In Biometrika 109.4, 2022, pp. 993–1014 DOI: 10.1093/biomet/asab061
  11. “Hybrid Monte Carlo” In Physics Letters B 195.2, 1987
  12. “Probabilistic Semantic Inpainting with Pixel Constrained CNNs” In arXiv:1810.03728 [cs, stat], 2019 arXiv:1810.03728 [cs, stat]
  13. “Generating Realistic Geology Conditioned on Physical Measurements with Generative Adversarial Networks” In arXiv:1802.03065 [physics, stat], 2018 arXiv:1802.03065 [physics, stat]
  14. Stephen E. Fick and Robert J. Hijmans “WorldClim 2: New 1-Km Spatial Resolution Climate Surfaces for Global Land Areas” In International Journal of Climatology 37.12, 2017, pp. 4302–4315 DOI: 10.1002/joc.5086
  15. Jing Gao and Brian C. O’Neill “Data-Driven Spatial Modeling of Global Long-Term Urban Land Development: The SELECT Model” In Environmental Modelling & Software 119, 2019, pp. 458–471 DOI: 10.1016/j.envsoft.2019.06.015
  16. David García-Álvarez and Sabina Florina Nanu “Land Use Cover Datasets: A Review” In Land Use Cover Datasets and Validation Tools: Validation Practices with QGIS Cham: Springer International Publishing, 2022, pp. 47–66 DOI: 10.1007/978-3-030-90998-7˙4
  17. A.E. Gelfand “Proper Multivariate Conditional Autoregressive Models for Spatial Data Analysis” In Biostatistics 4.1, 2003, pp. 11–15 DOI: 10.1093/biostatistics/4.1.11
  18. Andrew Gelman and Donald B. Rubin “Inference from Iterative Simulation Using Multiple Sequences” In Statistical Science 7.4, 1992
  19. “Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images” In IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-6.6, 1984, pp. 721–741 DOI: 10.1109/TPAMI.1984.4767596
  20. “Finer Resolution Observation and Monitoring of Global Land Cover: First Mapping Results with Landsat TM and ETM+ Data” In International Journal of Remote Sensing 34.7 Taylor & Francis, 2013, pp. 2607–2654 DOI: 10.1080/01431161.2012.748992
  21. “Diffusion Models as Plug-and-Play Priors” arXiv, 2023 arXiv:2206.09012 [cs]
  22. “On Calibration of Modern Neural Networks” arXiv, 2017 arXiv:1706.04599 [cs]
  23. “Stochastic Variational Inference” In Journal of Machine Learning Research, 2013
  24. “Hole-Filled SRTM for the Globe : Version 4 : Data Grid”, 2008
  25. “Overall Methodology Design for the United States National Land Cover Database 2016 Products” In Remote Sensing 11.24 Multidisciplinary Digital Publishing Institute, 2019, pp. 2971 DOI: 10.3390/rs11242971
  26. K.E. Kaiser, A.N. Flores and C.R. Vernon “Janus: A Python Package for Agent-Based Modeling of Land Use and Land Cover Change” In Journal of Open Research Software 8.1, 2020, pp. 15 DOI: 10.5334/jors.306
  27. “Adam: A Method for Stochastic Optimization” In arXiv preprint arXiv:1412.6980, 2014 arXiv:1412.6980
  28. Matt J. Kusner and José Miguel Hernández-Lobato “GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution” In NIPS Workshop on Adversarial Training arXiv, 2016 DOI: 10.48550/arXiv.1611.04051
  29. John D. Landis “Imagining Land Use Futures: Applying the California Urban Futures Model” In Journal of the American Planning Association 61.4 Routledge, 1995, pp. 438–457 DOI: 10.1080/01944369508975656
  30. “FAO Global Land Cover (GLC-SHARE) Beta-Release 1.0 Database”, 2014
  31. “Projected Land-Use Change Impacts on Ecosystem Services in the United States” In Proceedings of the National Academy of Sciences 111.20 Proceedings of the National Academy of Sciences, 2014, pp. 7492–7497 DOI: 10.1073/pnas.1405557111
  32. Daniel Lewandowski, Dorota Kurowicka and Harry Joe “Generating Random Correlation Matrices Based on Vines and Extended Onion Method” In Journal of Multivariate Analysis 100.9, 2009, pp. 1989–2001 DOI: 10.1016/j.jmva.2009.04.008
  33. “Generative Autoregressive Ensembles for Satellite Imagery Manipulation Detection” In IEEE International Workshop on Information Forensics and Security (WIFS) arXiv, 2020 arXiv:2010.03758 [cs]
  34. “Linking Land-Use and Land-Cover Transitions to Their Ecological Impact in the Amazon” In Proceedings of the National Academy of Sciences 119.27 Proceedings of the National Academy of Sciences, 2022, pp. e2202310119 DOI: 10.1073/pnas.2202310119
  35. Aaron Oord, Nal Kalchbrenner and Koray Kavukcuoglu “Pixel Recurrent Neural Networks” arXiv, 2016 DOI: 10.48550/arXiv.1601.06759
  36. “Agent-Based Models of Land-Use and Land-Cover Change”, 2001
  37. “Using Neural Networks and GIS to Forecast Land Use Changes: A Land Transformation Model” In Computers, Environment and Urban Systems 26.6, 2002, pp. 553–575 DOI: 10.1016/S0198-9715(01)00015-1
  38. Ali Razavi, Aaron van den Oord and Oriol Vinyals “Generating Diverse High-Fidelity Images with VQ-VAE-2” In Advances in Neural Information Processing Systems 32 Curran Associates, Inc., 2019
  39. “Spatially Explicit Simulation of Land Use/Land Cover Changes: Current Coverage and Future Prospects” In Earth-Science Reviews 190, 2019, pp. 398–415 DOI: 10.1016/j.earscirev.2019.01.001
  40. “Resolving Label Uncertainty with Implicit Posterior Models” In Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence PMLR, 2022, pp. 1707–1717
  41. “High-Resolution Image Synthesis with Latent Diffusion Models” arXiv, 2022 arXiv:2112.10752 [cs]
  42. “PIXELCNN++: IMPROVING THE PIXELCNN WITH DISCRETIZED LOGISTIC MIXTURE LIKELIHOOD AND OTHER MODIFICATIONS” In International Conference on Learning Representations, 2017
  43. John Salvatier, Thomas V. Wiecki and Christopher Fonnesbeck “Probabilistic Programming in Python Using PyMC3” In PeerJ Computer Science 2, 2016, pp. e55 DOI: 10.7717/peerj-cs.55
  44. “Remote Sensing as the Foundation for High-Resolution United States Landscape Projections – The Land Change Monitoring, Assessment, and Projection (LCMAP) Initiative” In Environmental Modelling & Software 120, 2019, pp. 104495 DOI: 10.1016/j.envsoft.2019.104495
  45. “Spatially Explicit Modeling of 1992–2100 Land Cover and Forest Stand Age for the Conterminous United States” In Ecological Applications 24.5, 2014, pp. 1015–1036 DOI: 10.1890/13-1245.1
  46. “Discrete Flows: Invertible Generative Models of Discrete Data” In Advances in Neural Information Processing Systems 32 Curran Associates, Inc., 2019
  47. “NVAE: A Deep Hierarchical Variational Autoencoder” arXiv, 2021 arXiv:2007.03898 [cs, stat]
  48. Aaron van den Oord, Nal Kalchbrenner and Koray Kavukcoglu “Pixel Recurrent Neural Networks” In Proceedings of the 33rd International Conference on Machine Learning, 2016
  49. “WaveNet: A Generative Model for Raw Audio” In arXiv:1609.03499 [cs], 2016 arXiv:1609.03499 [cs]
  50. “Completion of the 1990s National Land Cover Data Set for the Conterminous United States from Landsat Thematic Mapper Data and Ancillary Data Sources” In Photogrammetric Engineering and Remote Sensing 67.6, 2001
  51. “High-Resolution Integrated Modelling of the Spatial Dynamics of Urban and Regional Systems” In Computers, Environment and Urban Systems 24.5, 2000, pp. 383–400 DOI: 10.1016/S0198-9715(00)00012-0
  52. “Thematic Accuracy Assessment of the NLCD 2019 Land Cover for the Conterminous United States” In GIScience & Remote Sensing 60.1, 2023, pp. 2181143 DOI: 10.1080/15481603.2023.2181143
  53. “Hex2vec: Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags” In Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery Beijing China: ACM, 2021, pp. 61–71 DOI: 10.1145/3486635.3491076
  54. “Developing a Long Short-Term Memory (LSTM) Based Model for Predicting Water Table Depth in Agricultural Areas” In Journal of Hydrology 561, 2018, pp. 918–929 DOI: 10.1016/j.jhydrol.2018.04.065
  55. Chuanxia Zheng, Tat-Jen Cham and Jianfei Cai “Pluralistic Image Completion” In arXiv:1903.04227 [cs], 2019 arXiv:1903.04227 [cs]

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up