Advances in Machine Learning and Image Analysis for GeoAI provides state-of-the-art machine learning and signal processing techniques for a comprehensive collection of geospatial sensors and sensing platforms. The book covers supervised, semi-supervised and unsupervised geospatial image analysis, sensor fusion across modalities, image super-resolution, transfer learning across sensors and time-points, and spectral unmixing, among other topics. The chapters in these thematic areas cover a variety of algorithmic frameworks such as variants of convolutional neural networks, graph convolutional networks, multi-stream networks, Bayesian networks, generative adversarial networks, vision transformers, and more. It also covers emerging topics such as self-supervised learning, visual question answering etc.
This book provides graduate students, researchers, and practitioners in the area of signal processing and geospatial image analysis with the latest techniques to implement deep learning strategies in their GeoAI research.
]]>