Deep Learning for Earth Observation Using Satellite Imagery: A Comprehensive Review

Year : 2026 | Volume : 15 | Issue : 02 | Page :
By

Asmita Chavan,

Bhakti Gavali,

Aditi Gavali,

Jyoti Ghadage,

Vaibhav Godase,

  1. Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Maharashtra, India
  2. Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Maharashtra, India
  3. Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Maharashtra, India
  4. Student, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Maharashtra, India
  5. Assistant Professor, Department of Electronics and Telecommunication Engineering, SKN Sinhgad College of Engineering, Maharashtra, India

Abstract

Earth observation (EO) satellites provide continuous, large-scale information about the Earth’s land, oceans, atmosphere, vegetation, infrastructure, and environmental conditions. The rapid growth of multispectral, hyperspectral, synthetic aperture radar (SAR), thermal, and high- resolution satellite missions has generated large volumes of heterogeneous spatial and temporal data. Conventional image-processing and machine-learning techniques often require manually designed features and may have difficulty representing the complex spatial, spectral, temporal, and multimodal characteristics of satellite observations. Deep learning (DL) has therefore become an important computational paradigm for automated Earth observation. This review presents a comprehensive analysis of deep-learning methods for satellite-image understanding, covering convolutional neural networks (CNNs), recurrent networks, encoder- decoder architectures, generative models, attention mechanisms, Vision Transformers, hybrid CNN-Transformer networks, self-supervised learning, and emerging remote-sensing foundation models. The review examines their applications in land-use/land-cover classification, semantic segmentation, object detection, change detection, flood mapping, agricultural monitoring, forest monitoring, urban analysis, disaster assessment, and environmental observation. Major public datasets including EuroSAT, BigEarthNet, SpaceNet, Sen1Floods11, fMoW, and related multimodal benchmarks are discussed. Particular attention is given to the effects of spatial and spectral resolution, multimodal fusion, temporal information, domain shift, limited labels, class imbalance, cloud contamination, computational cost, explainability, and geographic generalization. Recent developments in self-supervised learning and remote-sensing foundation models indicate a transition from task-specific models toward reusable representations that can support multiple EO applications. However, challenges remain in multimodal alignment, temporal reasoning, uncertainty quantification, physical consistency, computational efficiency, and reliable deployment. The review concludes by identifying research directions involving multimodal foundation models, physics-guided learning, edge/on-board inference, continual learning, explainable AI, and geographically robust Earth observation systems.

Keywords: Earth observation, satellite imagery, deep learning, remote sensing, CNN, Vision Transformer

[This article belongs to Research & Reviews : Journal of Space Science & Technology ]

How to cite this article: Asmita Chavan, Bhakti Gavali, Aditi Gavali, Jyoti Ghadage, Vaibhav Godase. Deep Learning for Earth Observation Using Satellite Imagery: A Comprehensive Review. Research & Reviews : Journal of Space Science & Technology. 2026; 15(02):-.
How to cite this URL: Asmita Chavan, Bhakti Gavali, Aditi Gavali, Jyoti Ghadage, Vaibhav Godase. Deep Learning for Earth Observation Using Satellite Imagery: A Comprehensive Review. Research & Reviews : Journal of Space Science & Technology. 2026; 15(02):-. Available from: https://journals.stmjournals.com/rrjosst/article=2026/view=257566

References

  1.  Zhu XX, Tuia D, Mou L, Xia GS, Zhang L, Xu F, Fraundorfer F. Deep learning in remote sensing: A comprehensive review and list of resources. IEEE geoscience and remote sensing magazine. 2017 Dec 31;5(4):8-36.
  2.  Godase V, Godase J. Diet prediction and feature importance of gut microbiome using machine learning. Evolution in Electrical and Electronic Engineering. 2024 Nov 6;5(2):214-9.
  3.  Jamadade VK, Ghodke MG, Katakdhond SS, Godase V. A comprehensive review on scalable Arduino radar platform for real-time object detection and mapping. Journal of Microprocessor and Microcontroller Research. 2025 May;2(2):1-2.
  4.  Godase V. A comprehensive study of revolutionizing EV charging with solar-powered wireless solutions. Advance Research in Power Electronics and Devices e-ISSN. 2025 Apr 18:3048-7145.
  5.  Godase V. Advanced Neural Network Models for Optimal Energy Management in Microgrids with Integrated Electric Vehicles. InProceedings of the International Conference on Trends in Material Science and Inventive Materials (ICTMIM-2025) DVD Part Number: CFP250J1-DVD 2025 Apr 18.
  6.  Dange R, Attar E, Ghodake P, Godase V. Smart agriculture automation using ESP8266 NodeMCU. J. Electron. Comput. Netw. Appl. Math,(35). 2023 Jul:1-9.
  7. Paheding S, Saleem A, Siddiqui MF, Rawashdeh N, Essa A, Reyes AA. Advancing horizons in remote sensing: a comprehensive survey of deep learning models and applications in image classification and beyond. Neural Computing and Applications. 2024 Sep;36(27):16727-67.
  8.  Persello C, Wegner JD, Hänsch R, Tuia D, Ghamisi P, Koeva M, Camps-Valls G. Deep learning and earth observation to support the sustainable development goals: Current approaches, open challenges, and future opportunities. IEEE Geoscience and Remote Sensing Magazine. 2022 Jan 14;10(2):172-200.
  9.  Miller L, Pelletier C, Webb GI. Deep learning for satellite image time-series analysis: A review. IEEE Geoscience and Remote Sensing Magazine. 2024 May 13;12(3):81-124.
  10.  Hoeser T, Bachofer F, Kuenzer C. Object detection and image segmentation with deep learning on Earth observation data: A review—Part II: Applications. Remote Sensing. 2020 Sep 18;12(18):3053.
  11.  Hoeser T, Kuenzer C. Object detection and image segmentation with deep learning on earth observation data: A review-part i: Evolution and recent trends. Remote Sensing. 2020 May 22;12(10):1667.
  12.  Jenisha C, KV AD, Kalirajan S. Recent Innovation of Deep Learning Approches in Satellite Imagery: A Comprehensive Review. In2024 International Conference on Sustainable Communication Networks and Application (ICSCNA) 2024 Dec 11 (pp. 1213-1220). IEEE.
  13.  Hussein D, Yousef MA, Abdel-Hak HA, Mostafa YG. Satellite image enhancement using deep learning and GIS integration: A comprehensive review. Rudarsko-geološko-naftni zbornik. 2025 Jul 3;40(3):95-118.
  14. Adegun AA, Viriri S, Tapamo JR. Review of deep learning methods for remote sensing satellite images classification: experimental survey and comparative analysis. Journal of Big Data. 2023 Jun 2;10(1):93.
  15. Zhao Q, Yu L. Advancing sustainable development goals through earth observation satellite data: Current insights and future directions. Journal of Remote Sensing. 2025 Jan 23;5:0403.
  16.  Mutawa AM, Alshaibani A, Almatar LA. A comprehensive review of dust storm detection and prediction techniques: Leveraging satellite data, ground observations, and machine learning. IEEE Access. 2025 Feb 11;13:39694-710.
Regular Issue Subscription Original Research
Volume 15
Issue 02
Received 21/09/2026
Accepted 22/09/2026
Published 24/09/2026
Publication Time 3 Days

Login

My IP

PlumX Metrics

Support