Authors: Pratiksha Chaudhari – The University of Alabama
Title: Integrating ML Algorithms for Hydrological Workflow Optimization
Presentation Type: Poster
Abstract: This study advances the integration of machine learning (ML) techniques into operational hydrology to improve predictive modeling and support data-driven decision-making. Leveraging current hydrological modeling efforts, we evaluate the performance of algorithms such as LSTM, CNN, XGBoost, and MLP in addressing challenges associated with hydrological data analysis. The research focuses on optimized data processing, model training and evaluation, and effective result visualization. By refining these workflows, the study aims to establish a robust framework for applying ML in hydrology, enhancing the accuracy and reliability of predictions for complex environmental systems.