GeoAI Methodological Foundations: Deep Neural Networks and Knowledge Graphs

The chapter provides an overview of the methodological foundations of GeoAI, with a focus on the use of deep learning and knowledge graphs. It covers a range of key concepts and architectures related to convolutional neural networks, recurrent neural networks, transformers, graph neural networks, generative adversarial networks, reinforcement learning, and knowledge graphs. The goal of this chapter is to highlight the importance and ways of incorporating spatial thinking and principles into the development of spatially explicit AI models and geospatial knowledge graphs.