GeoAI for Earth Observation Imagery

Dalton Lunga is a group leader for GeoAI and a senior R&D staff scientist at ORNL. He is also an Associate Editor for Geoscience and Remote Sensing Letters. He is an interdisciplinary scientist with expertise in artificial intelligence, computer vision, high-performance computing and remote sensing. Dalton leads multidisciplinary teams and projects focused on developing novel methods at the intersection of AI, computer vision, and geography toward the built and physical environment mapping using earth observation data. His research is impacting the generation of accurate population estimates and information about urban growth and decline, informing disaster response, identifying at-risk areas to support national security application challenges. Prior to ORNL, Dalton was a Team Lead and Senior Research Scientist at the Council for Scientific and Industrial Research, South Africa where he established and led a Data Science for Decision Impact team. He received his Ph.D in Electrical and Computer Engineering from Purdue University, West Lafayette.Ronny Hänsch is a scientist at the Microwave and Radar Institute of the German Aerospace Center (DLR) where he leads the Machine Learning Team in the Signal Processing Group of the SAR Technology Department. His research interest is computer vision and machine learning with a focus on remote sensing (in particular SAR processing and analysis). He was chair of the GRSS Image Analysis and Data Fusion (IADF) technical committee 2021-23, and serves as co-chair of the ISPRS working group on Image Orientation and Sensor Fusion, as editor in chief of the Geoscience and Remote Sensing Letters. associate editor the ISPRS Journal of Photogrammetry and Remote Sensing, and organizer of the CVPR Workshop EarthVision (2017-2024) and the IGARSS Tutorial on Machine Learning in Remote Sensing (2017-2024). He has extensive experience in organizing remote sensing community competitions (e.g. SpaceNet and the GRSS Data Fusion Contest).

• Part I – Image PreprocessingChapter 1. Earth observation and GeoAI through the years: six decades of progress in image analysisChapter 2. Radiometric correctionChapter 3. RectificationChapter 4. Georeferencing of remote sensing imageryChapter 5. Image registrationChapter 6. Mosaicking remote sensing data: techniques, challenges, and innovations [LUNGAD_FM_Q | PDF]Part II – Image EnhancementChapter 7. PansharpeningChapter 8. Superresolution of satellite imageryChapter 9. Earth observation image denoising [LUNGAD_FM_Q | PDF]Part III – Image AnalysisChapter 10. Semantic segmentation of Earth observation dataChapter 11. Synthesis of Earth observation imageryChapter 12. Geospatial data visualization with PythonChapter 13. Multimodal data fusion for semantic mapping and change detectionChapter 14. Self-supervised learning for Earth observation foundation modelsChapter 15. Object detection in remote sensingChapter 16. A tour of visual question answering for remote sensing [LUNGAD_FM_Q | PDF]Part IV – ComputingChapter 17. Geospatial machine learning librariesChapter 18. High-performance computing for geospatial intelligenceChapter 19. Cloud infrastructure for Earth observation imagery