Foundations of ML: From Architecture to Optimization
Day 1 Session 1 (10:30AM)
Presenters:
Savalan Neisary (University of Alabama)
Leo Lonzarich (Penn State University)
This introductory workshop provides a practical foundation for building machine-learning workflows for hydrologic applications. Participants will explore major machine learning model classes and develop end-to-end modeling pipelines, including data preprocessing, model architecture design, and hyperparameter tuning.
Through guided, hands-on exercises, attendees will examine key concepts such as overfitting, validation strategies, and model generalization. The session emphasizes reproducible workflow design and practical decision-making for selecting models suited to forecasting, classification, and environmental prediction tasks. Participants will leave with the knowledge needed to apply machine learning methods effectively within operational hydrology and research environments.
Learning Outcomes:
- Understand common machine learning algorithm classes and appropriate hydrologic use cases
- Build complete machine learning pipelines from preprocessing through model evaluation
- Diagnose overfitting and generalization issues in hydrologic ML applications
- Apply optimization and tuning strategies to improve model performance