A systematic review and meta-analysis of groundwater level forecasting with machine learning techniques: Current status and future directions

Accurate and reliable groundwater level (GWL) forecasting is crucial for developing strategies and managing water resources. In recent years, Machine Learning (ML) has demonstrated its high efficiency and practicability for GWL forecast compared to other conventional models due to its capability to handle different sources simultaneously and its lower data, cost, and time requirements. This systematic review aims to provide a comprehensive overview and analysis of the ML models used in GWL modeling. A total of 168 original research articles published between 2000 and 2023 were examined, summarizing details such as country, keywords cooccurrence, type of algorithm, input variables, data split, performance metrics, time scale and study unit. Furthermore, we discuss potential future research directions, opportunities and recommendations for enhancing the application of ML models to GWL forecasting.