The EarthRISE Applied Artificial Intelligence and Deep Learning Book is the product of more than seven years of community-driven knowledge sharing within the Geo-AI Working Group. It puts the WG's Knowledge Sharing pillar into practice: a curated set of applied deep learning use cases, each pairing conceptual background with executable notebooks, written for geospatial practitioners who are new to deep learning.
Think of it as a "choose your own adventure": start at data preparation, or jump straight to the chapter that matches your domain.
Open the book Source Cite (DOI)
Editors: Tim Mayer (NASA EarthRISE · UAH), Biplov Bhandari (Earth Resources Technology), David Saah (University of San Francisco · Spatial Informatics Group). First edition, June 2026. CC BY 4.0.
Chapters¶
| # | Part | Chapters |
|---|---|---|
| 1 | Introduction | |
| 2 | Data Preparation | coming soon |
| 3 | Semantic Segmentation | Rice mapping in Bhutan with U-Net · Selective logging detection (VHR) · Clay deforestation segmentation |
| 4 | Object Detection | coming soon |
| 5 | Time Series | Soybean yield prediction |
| 6 | Ecological Processes Simulation | Active fire detection with Bayesian neural networks |
| 7 | Transfer Learning | coming soon |
| 8 | Fusion | coming soon |
| 9 | Downscaling | coming soon |
| 10 | Future of DL & Foundation Models | Evaluating foundation models trained with EO data |
| 11 | Ethics and AI | coming soon |
| 12 | Conclusions | coming soon |
Cite: Mayer, T., Bhandari, B., & Saah, D. (2026). EarthRISE Applied Artificial Intelligence and Deep Learning Book. Zenodo. doi:10.5281/zenodo.20547797
Want to contribute a chapter? Open an issue on the book repo.
