mlsanityData to 14 Oct 2026

Lossy Neural Compression for Geospatial Analytics: A Review

arXiv 2503.01505 ↗First posted 3 Mar 2025eess.SP cs.AI cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Over the past decades, there has been an explosion in the amount of available Earth Observation (EO) data. The unprecedented coverage of the Earth's surface and atmosphere by satellite imagery has resulted in large volumes of data that must be transmitted to ground stations, stored in data centers, and distributed to end users. Modern Earth System Models (ESMs) face similar challenges, operating at high spatial and temporal resolutions, producing petabytes of data per simulated day. Data compression has gained relevance over the past decade, with neural compression (NC) emerging from deep learning and information theory, making EO data and ESM outputs ideal candidates due to their abundance of unlabeled data. In this review, we outline recent developments in NC applied to geospatial data. We introduce the fundamental concepts of NC including seminal works in its traditional applications to image and video compression domains with focus on lossy compression. We discuss the unique characteristics of EO and ESM data, contrasting them with "natural images", and explain the additional challenges and opportunities they present. Moreover, we review current applications of NC across various EO modalities and explore the limited efforts in ESM compression to date. The advent of self-supervised learning (SSL) and foundation models (FM) has advanced methods to efficiently distill representations from vast unlabeled data. We connect these developments to NC for EO, highlighting the similarities between the two fields and elaborate on the potential of transferring compressed feature representations for machine--to--machine communication. Based on insights drawn from this review, we devise future directions relevant to applications in EO and ESM.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 94 of its 283 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

94 of 283 references.

References · 94

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  10. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  11. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  12. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
38 more
  1. 2014Conditional Generative Adversarial Netscited by 2,162
  2. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2016Least Squares Generative Adversarial Networkscited by 1,001
  7. 2018Variational image compression with a scale hyperpriorcited by 935
  8. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  9. 2016End-to-end Optimized Image Compressioncited by 696
  10. 2022High Fidelity Neural Audio Compressioncited by 687
  11. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
  12. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  13. 2017Generative Adversarial Networks: An Overviewcited by 590
  14. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  15. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 408
  16. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  17. 2017Lossy Image Compression with Compressive Autoencoderscited by 294
  18. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  19. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 264
  20. 2021NeRV: Neural Representations for Videoscited by 256
  21. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 236
  22. 2019BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understandingcited by 234
  23. 2021COIN: COmpression with Implicit Neural representationscited by 233
  24. 2023Language Modeling Is Compressioncited by 225
  25. 2023SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagerycited by 205
  26. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 175
  27. 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 173
  28. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 170
  29. 2021Implicit Neural Representations for Image Compressioncited by 162
  30. 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 152
  31. 2022Advancing Plain Vision Transformer Towards Remote Sensing Foundation Modelcited by 149
  32. 2023Foundation Models for Generalist Geospatial Artificial Intelligencecited by 149
  33. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  34. 2020Nonlinear Transform Codingcited by 136
  35. 2018Conditional Probability Models for Deep Image Compressioncited by 133
  36. 2024Neural Video Compression with Feature Modulationcited by 123
  37. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 107
  38. 2022A high-resolution canopy height model of the Earthcited by 91

50 most cited of 94 All 94 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025TerraMind: Large-Scale Generative Multimodality for Earth Observationcited by 104
  2. 2025NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observationcited by 7
  3. 2026Earth Embeddings as Products: Taxonomy, Ecosystem, and Standardized Accesscited by 5
  4. 2025FPGA-Enabled Machine Learning Applications in Earth Observation: A Systematic Reviewcited by 2
  5. 2026Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Datacited by 2
  6. 2025Adjustable Spatio-Spectral Hyperspectral Image Compression Networkcited by 1
  7. 2026Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Modelscited by 1
  8. 2025TerraCodec: Compressing Optical Earth Observation Datacited by 0
  9. 2026HyVIC: A Metric-Driven Spatio-Spectral Hyperspectral Image Compression Architecture Based on Variational Autoencoderscited by 0
  10. 2026Earth Embeddingscited by 0