Evaluation of Machine Learning Techniques for Inflow Prediction in Lake Como, Italy
Michele Pini, Andrea Scalvini, Muhammad Usman Liaqat, Roberto Ranzi, Ivan Serina, Tahir Mehmood
Abstract
Accurate streamflow prediction is a fundamental task for integrated water resources management and flood risk mitigation. The purpose of this study is to forecast the water inflow to lake Como, (Italy) using different machine learning algorithms. The forecast is done for different days ranging from one day to three days. These models are evaluated by three statistical measures including Mean Absolute Error, Root Mean Squared Error, and the Nash-Sutcliffe Efficiency Coefficient. The experimental results show that Neural Network performs better for streamflow estimation with MAE and RMSE followed by Support Vector Regression and Random Forest.
Topics & Concepts
Mean squared errorInflowComputer scienceRandom forestArtificial neural networkSupport vector machineStreamflowRegressionApproximation errorFlood mythMean absolute errorTask (project management)Machine learningStatisticsMeteorologyAlgorithmMathematicsManagementDrainage basinTheologyGeographyEconomicsPhysicsPhilosophyCartographyHydrological Forecasting Using AIHydrology and Watershed Management StudiesFlood Risk Assessment and Management