Time series predictions in unmonitored sites: a survey of machine learning techniques in water resources

Abstract

Prediction of dynamic environmental variables in unmonitored sites remains a long-standing challenge for water resources science. The majority of the world’s freshwater resources have inadequate monitoring of critical environmental variables needed for management. Yet, the need to have widespread predictions of hydrological variables such as river flow and water quality has become increasingly urgent due to climate and land use change over the past decades, and their associated impacts on water resources. Modern machine learning methods increasingly outperform their process-based and empirical model counterparts for hydrologic time series prediction with their ability to extract information from large, diverse data sets. We review relevant state-of-the art applications of machine learning for streamflow, water quality, and other water resources prediction and discuss opportunities to improve the use of machine learning with emerging methods for incorporating watershed characteristics and process knowledge into classical, deep learning, and transfer learning methodologies. The analysis here suggests most prior efforts have been focused on deep learning frameworks built on many sites for predictions at daily time scales in the United States, but that comparisons between different classes of machine learning methods are few and inadequate. We identify several open questions for time series predictions in unmonitored sites that include incorporating dynamic inputs and site characteristics, mechanistic understanding and spatial context, and explainable AI techniques in modern machine learning frameworks. Impact statement This review addresses a gap that different types of ML methods for hydrological time series prediction in unmonitored sites are often not compared in detail and best practices are unclear. We consolidate and synthesize state-of-the-art ML techniques for researchers and water resources management, where the strengths and limitations of different ML techniques are described allowing for a more informed selection of existing ML frameworks and development of new ones. Open questions that require further investigation are highlighted to encourage researchers to address specific issues like training data and input selection, model explainability, and the incorporation of process-based knowledge.