Environmental Statistics and Learning II

3.0 credits · Graduate

This course builds on concepts introduced in BEE 4310/6310 Environmental Statistics and Learning but does not require prior enrollment. It examines advanced statistical and machine learning methods for complex environmental datasets. Topics include unsupervised and supervised learning, such as clustering (hierarchical, k-means, Gaussian mixture models, DBSCAN), principal component analysis, k-nearest neighbors, Gaussian process regression, support vector machines, and neural networks. Students are introduced to explainable AI and deep learning concepts, including autoencoders, recurrent and long short-term memory networks, and convolutional neural networks. Applications span environmental science and engineering, emphasizing pattern recognition, prediction, and system understanding. The course prioritizes practical implementation, critical evaluation, and interpretation of results over black-box use, with hands-on programming and literature-based analysis.