Application of Machine Learning in Water Resources Management: A Systematic Literature Review

Abstract

In accordance with the rapid proliferation of machine learning (ML) and data management, ML applications have evolved to encompass all engineering disciplines. Owing to the importance of the world’s water supply throughout the rest of this century, much research has been concentrated on the application of ML strategies to integrated water resources management (WRM). Thus, a thorough and well-organized review of that research is required. To accommodate the underlying knowledge and interests of both artificial intelligence (AI) and the unresolved issues of ML in WRM, this overview divides the core fundamentals, major applications, and ongoing issues into two sections. First, the basic applications of ML are categorized into three main groups, prediction, clustering, and reinforcement learning. Moreover, the literature is organized in each field according to new perspectives, and research patterns are indicated so attention can be directed toward where the field is headed. In the second part, the less investigated field of WRM is addressed to provide grounds for future studies. The widespread applications of ML tools are projected to accelerate the formation of sustainable WRM plans over the next decade.

Unravelling the potential of Big Data-driven decision-making in sustainable water irrigation: An AI perspective

“…Water is pooled into the soil using this technique, however, water management takes many factors into account. The researchers proposed an autonomous watering system that is based on the IoT with a variety of components, including a microcontroller, Wi-Fi node and Raspberry Pi 3 (Ghobadi & Kang 2023).…”

A call for a fundamental shift from model-centric to data-centric approaches in hydroinformatics

“…When it comes to water-related challenges, a brief overview of the most current and trending topics in hydroinformatics reveals a significant focus on adopting and fine-tuning sophisticated models (e.g., Bozorg-Haddad et al, 2018;Yaseen et al, 2019) and/or comparing the performance of these models (e.g., Chen et al, 2020;Yaghoubzadeh-Bavandpour et al, 2022), that is, the modelcentric approach. In theory, these model-centric efforts have yielded promising results (e.g., Sun and Scanlon, 2019;Aliashrafi et al, 2021;Ghobadi and Kang, 2023). Often, such approaches place significant emphasis on the 'model' component within the CI/AIbased frameworks, primarily concentrating on improving or comparing such models.…”

Reinforcement learning for watershed and aquifer management: a nationwide view in the country of Mexico with emphasis in Baja California Sur

“…In response to these challenges, new technologies such as RL have emerged as a promising avenue for optimizing public policy (Binas et al, 2019;Strnad et al, 2019;Chen et al, 2021;Skirzyński et al, 2021;Emamjomehzadeh et al, 2023;Ghobadi and Kang, 2023;Sivamayil et al, 2023). RL allows computers to learn from experience, enabling intelligent decision-making in complex environments (Lee et al, 2022).…”