Advanced Machine Learning Techniques to Improve Hydrological Prediction: A Comparative Analysis of Streamflow Prediction Models

Abstract

The management of water resources depends heavily on hydrological prediction, and advances in machine learning (ML) present prospects for improving predictive modelling capabilities. This study investigates the use of a variety of widely used machine learning algorithms, such as CatBoost, ElasticNet, k-Nearest Neighbors (KNN), Lasso, Light Gradient Boosting Machine Regressor (LGBM), Linear Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Ridge, Stochastic Gradient Descent (SGD), and the Extreme Gradient Boosting Regression Model (XGBoost), to predict the river inflow of the Garudeshwar watershed, a key element in planning for flood control and water supply. The substantial engineering feature used in the study, which incorporates temporal lag and contextual data based on Indian seasons, leads it distinctiveness. The study concludes that the CatBoost method demonstrated remarkable performance across various metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values, for both training and testing datasets. This was accomplished by an in-depth investigation and model comparison. In contrast to CatBoost, XGBoost and LGBM demonstrated a higher percentage of data points with prediction errors exceeding 35% for moderate inflow numbers above 10,000. CatBoost established itself as a reliable method for hydrological time-series modelling, easily managing both categorical and continuous variables, and thereby greatly enhancing prediction accuracy. The results of this study highlight the value and promise of widely used machine learning algorithms in hydrology and offer valuable insights for academics and industry professionals.

Enhancing Cookie Formulations with Combined Dehydrated Peach: A Machine Learning Approach for Technological Quality Assessment and Optimization

“…The RMSE values serve as indicators of the model’s efficiency by assessing the agreement between calculated values and experimentally measured values. On the other hand, MBE values are employed to ascertain the standard deviation between the predicted and measured values [ 36 , 37 , 38 ]. These statistical parameters were calculated using equations [ 39 ].…”

Hydro-Meteorological Disaster Incidents and Associated Weather Systems in Sri Lanka

“…The accurate prediction of river discharge is an important factor in improving water resource management (Roushangar et al, 2021). Machine learning models have been applied in various domains, for water resource management and predicting river inflow accurately for making informed decisions regarding water allocation, flood management, and hydropower generation (Kumar et al, 2023a). Hydrological vulnerability for flooding was identified with the use of the above data together with the streamflow records and the hydrological model outputs.…”

Optimization of 2024-T3 Aluminum Alloy Friction Stir Welding Using Random Forest, XGBoost, and MLP Machine Learning Techniques

“…The comprehensive insights derived from these machine learning models, which demonstrated the near-equal importance of both independent variables-tool rotational speed and welding speed-on the dependent variable (UTS), underscore the adequacy of the methods employed. Given the complexity and the non-linear interactions between features captured by these models, ANOVA, which is traditionally used for comparing means across groups and assumes linear relationships, might not provide additional or more insightful information in this specific case [43].…”