mlsanityData to 14 Oct 2026

LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data

arXiv 2505.09803 ↗First posted 14 May 2025stat.ML cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

In many applications, we wish to fit a parametric statistical model to a small ensemble of spatially distributed random variables ('fields'). However, parameter inference using maximum likelihood estimation (MLE) is computationally prohibitive, especially for large, non-stationary fields. Thus, many recent works train neural networks to estimate parameters given spatial fields as input, sidestepping MLE completely. In this work we focus on a popular class of parametric, spatially autoregressive (SAR) models. We make a simple yet impactful observation; because the SAR parameters can be arranged on a regular grid, both inputs (spatial fields) and outputs (model parameters) can be viewed as images. Using this insight, we demonstrate that image-to-image (I2I) networks enable faster and more accurate parameter estimation for a class of non-stationary SAR models with unprecedented complexity.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 50 of its 94 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

50 of 94 references.

References · 50

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  7. 2022A ConvNet for the 2020scited by 3,579
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  9. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  10. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  11. 2018Group Normalizationcited by 1,524
  12. 2017Deep Setscited by 1,421
38 more
  1. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  2. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  3. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  4. 2018Image Transformercited by 772
  5. 2020A Survey on Visual Transformercited by 654
  6. 2019The frontier of simulation-based inferencecited by 502
  7. 2023ClimaX: A foundation model for weather and climatecited by 337
  8. 2023Neural General Circulation Models for Weather and Climatecited by 239
  9. 2021Learning to Optimize: A Primer and A Benchmarkcited by 208
  10. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
  11. 2022Forecasting Global Weather with Graph Neural Networkscited by 168
  12. 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 110
  13. 2023DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecastingcited by 109
  14. 2022HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutionscited by 103
  15. 2023ACE: A fast, skillful learned global atmospheric model for climate predictioncited by 56
  16. 2017A Case Study Competition Among Methods for Analyzing Large Spatial Datacited by 44
  17. 2024ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Predictioncited by 43
  18. 2024Neural Methods for Amortized Inferencecited by 39
  19. 2023Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Wordscited by 34
  20. 2022Likelihood-Free Parameter Estimation with Neural Bayes Estimatorscited by 32
  21. 2021Neural Networks for Parameter Estimation in Intractable Modelscited by 29
  22. 2022InstaFormer: Instance-Aware Image-to-Image Translation with Transformercited by 28
  23. 2023SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Modelscited by 28
  24. 2020Fast covariance parameter estimation of spatial Gaussian process models using neural networkscited by 25
  25. 2023ClimateSet: A Large-Scale Climate Model Dataset for Machine Learningcited by 25
  26. 2015A multi-resolution approximation for massive spatial datasetscited by 20
  27. 2021The SPDE approach for Gaussian and non-Gaussian fields: 10 years and still runningcited by 15
  28. 2023Neural Bayes Estimators for Irregular Spatial Data using Graph Neural Networkscited by 13
  29. 2024The impact of internal variability on benchmarking deep learning climate emulatorscited by 11
  30. 2023Neural Likelihood Surfaces for Spatial Processes with Computationally Intensive or Intractable Likelihoodscited by 10
  31. 2023DiffESM: Conditional Emulation of Earth System Models with Diffusion Modelscited by 9
  32. 2023Fast parameter estimation of Generalized Extreme Value distribution using Neural Networkscited by 7
  33. 2024CoDiCast: Conditional Diffusion Model for Global Weather Prediction with Uncertainty Quantificationcited by 6
  34. 2020Modeling spatial data using local likelihood estimation and a Mat'ern to SAR translationcited by 3
  35. 2017Modeling and emulation of nonstationary Gaussian fieldscited by 2
  36. 2021Modelling Big, Heterogeneous, Non-Gaussian Spatial and Spatio-Temporal Data using FRKcited by 1
  37. 2024Learning non-Gaussian spatial distributions via Bayesian transport maps with parametric shrinkagecited by 1
  38. 2025Modeling Spatial Extremes using Non-Gaussian Spatial Autoregressive Models via Convolutional Neural Networkscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Gaussian Process Decorrelation for Spatiotemporal Deep Learning-Based Snow Water Equivalent Predictioncited by 0