| Course ID: | GEOG 4592/6592. 3 hours. |
| Course Title: | Advanced Geospatial Artificial Intelligence |
Course
Description: | Advanced artificial intelligence (AI), machine learning (ML), and deep learning models and their applications on geospatial problems. Topics include deep learning fundamentals, convolution neural networks, recurrent neural networks, graph neural networks, and other deep learning models. |
| Oasis Title: | Advanced Geo AI |
| Undergraduate Prerequisite: | GEOG 4591/6591 or permission of department |
| Graduate Prerequisite: | GEOG 4591/6591 or permission of department |
Semester Course
Offered: | Offered spring semester every year. |
| Grading System: | A-F (Traditional) |
|
| Course Objectives: | 1) Students will develop an integrated understanding of various deep learning models and their suitability when applying them to different geospatial data.
2) Students will gain practical experiences by developing various deep-learning models for different geospatial problems and spatial data formats.
3) Students will be able to design and implement appropriate deep learning models for real-world geospatial problems and analyze the results. |
| Topical Outline: | 1) Google Colab, PyTorch, and TensorFlow
2) Deep learning: core ideas and basics I, II, III
3) Deep learning for vector and structured geographic data I, II, III
4) Convolutional Neural Network (CNN) for processing geospatial images I, II, III
5) Recurrent neural networks (RNN) for analyzing geospatial data I, II, III
6) Graph neural networks (GNN) for analyzing geospatial data I, II, III
7) Other neural network models: Transformer, Generative Adversarial Network, Variational Autoencoder, Sequence to Sequence model, PointNet |