“…Perhaps the most immediate and powerful use of data science methods in hydrology, and specifically of machine and deep learning methods, is for prediction and forecasting. A number of papers in this issue provide interesting examples of the use of gradient‐boosted decision trees and long short‐term memory networks to forecast sediment concentration and transport (Kim et al, 2022; Lund et al, 2022); the use of a range of machine learning methods for evapotranspiration estimation (Mangalath Ravindran et al, 2022) using AutoML, a framework designed to bring machine learning methods to non‐experts; or the use of support vector machines to forecast nitrate concentration in rivers and inform the development of water‐quality sensor networks (Balson & Ward, 2022). These papers show the growing interest in Machine and Deep Learning methods for prediction and forecasting in our field, among other things because these methods typically outperform classic hydrologic models.…”