Machine learning for hydrologic sciences: An introductory overview

Abstract

The hydrologic community has experienced a surge in interest in machine learning in recent years. This interest is primarily driven by rapidly growing hydrologic data repositories, as well as success of machine learning in various academic and commercial applications, now possible due to increasing accessibility to enabling hardware and software. This overview is intended for readers new to the field of machine learning. It provides a non-technical introduction, placed within a historical context, to commonly used machine learning algorithms and deep learning architectures. Applications in hydrologic sciences are summarized next, with a focus on recent studies. They include the detection of patterns and events such as land use change, approximation of hydrologic variables and processes such as rainfall-runoff modeling, and mining relationships among variables for identifying controlling factors. The use of machine learning is also discussed in the context of integrated with process-based modeling for parameterization, surrogate modeling, and bias correction. Finally, the article highlights challenges of extrapolating robustness, physical interpretability, and small sample size in hydrologic applications.

Estimating Irrigation Water Consumption Using Machine Learning and Remote Sensing Data in Kansas High Plains

“…Irrigation schemes implemented in LSMs often fall short of representing the socioeconomic controls on irrigation behavior. Machine learning algorithms and remote sensing data provide opportunities to capture human-water interactions that are hard to represent using physically based methods [39,[41][42][43][44][45]. Several studies have applied machine learning approaches in the High Plains region to map irrigated farmlands [46], identify irrigation driving factors [38], and estimate groundwater withdrawal from MODIS ET [47].…”

Capabilities of deep learning models on learning physical relationships: Case of rainfall-runoff modeling with LSTM

“…Deep learning has recently started to be widely applied to issues in hydrology. There are already numerous applications as summarized in Shen [Citation error], Reichstein et al (2019), Tahmasebi et al (2020), and Xu and Liang (2021). Those applications have shown the capability of deep learning to generate outputs with high accuracy.…”

Can machine learning accelerate process understanding and decision‐relevant predictions of river water quality?

“…Traditional ML models can produce physically inconsistent results (Karpatne et al, 2017; Kashinath et al, 2021) as they only look for statistical relationships in the training data and are unable to extrapolate outside of the training dataset used for building the ML model. The sparseness of water quality and related environmental datasets, and projected changes in climate and land use make it challenging to use ML models per se for predictions in unmonitored regions or for long‐term projections because they can only be trained, validated, and evaluated on past data (Duan et al, 2020; Kratzert, Klotz, Brandstetter, et al, 2019; Xu & Liang, 2021).…”