Application of Big Data and Machine Learning in Hydrological Forecasting and Water Resource Management

Dear Colleagues,

In recent years, hydrology has entered a data-rich era with unprecedented volumes of information from satellite remote sensing, ground-based sensor networks, and climate reanalysis models. However, transforming these raw data into actionable insights requires advanced computational tools capable of handling high dimensionality, noise, and nonlinear dynamics characterizing hydrological systems. This Special Issue aims to showcase recent progress in machine learning (ML) and artificial intelligence (AI) methods tailored to hydrological science, emphasizing approaches that move beyond conventional black-box models toward interpretable, physics-informed, and reinforcement learning-based methodologies that align with real-world hydrological behavior and constraints.

The primary focus lies in innovative applications of deep neural networks, including CNNs, RNNs, and transformer architectures, as well as reinforcement learning algorithms for adaptive hydrological decision-making. We particularly encourage submissions advancing explainable AI (XAI) techniques and physics-aware frameworks that preserve fundamental conservation laws and process understanding inherent in hydrological systems. The scope encompasses theoretical advancements and practical applications across multiple scales, from local watershed management to global hydrological modeling, emphasizing interdisciplinary approaches bridging hydrology, data science, and climate systems to address contemporary water-related challenges.

This Special Issue addresses a critical gap in the existing literature where traditional hydrological modeling approaches struggle with modern data complexity and scale, while purely data-driven machine learning methods frequently lack the interpretability and physical consistency required for reliable predictions. Recent advances in physics-informed neural networks, explainable AI, and hybrid modeling have opened up new avenues for integrating domain knowledge with data-driven insights, yet comprehensive collections of these methodologies specifically tailored to hydrological applications remain limited. This Special Issue positions itself at the intersection of environmental AI and computational hydrology, extending beyond existing publications by specifically emphasizing unique challenges in hydrological systems, including non-stationarity, spatiotemporal dependencies, and the need for physically consistent predictions.

We welcome contributions spanning several interconnected research areas, including deep learning and reinforcement learning for hydrological forecasting using advanced architectures such as LSTMs, GRUs, attention mechanisms, and graph neural networks. Physics-informed machine learning approaches encompass physics-informed neural networks (PINNs), neural ordinary differential equations (ODEs), and constrained optimization methods incorporating fundamental hydrological principles. The interpretability and explainability of models constitute crucial dimensions, with particular interest in SHAP, LIME, attention visualization, and causal inference techniques that provide insights into model decision-making processes.

Hybrid modeling approaches combine physical simulation with data-driven learning through differentiable programming and neural–symbolic integration, leveraging the strengths of both paradigms. Remote sensing applications using multi-modal deep learning for water parameter estimation, spatiotemporal deep learning for flood and drought prediction, and data assimilation techniques fusing multiple observation sources represent rapidly evolving fields with significant practical implications. We also encourage submissions on reinforcement learning applications for water resource management, explainable AI frameworks for critical hydrological applications, physics-constrained deep learning models, benchmark datasets and open-source tools, and uncertainty quantification approaches using Bayesian deep learning and ensemble methods. This Special Issue welcomes the submission of both theoretical advancements and practical applications, emphasizing interdisciplinary work that advances understanding and prediction capabilities for complex water systems.

Dr. You-Gan Wang
Dr. Jing Xu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Water is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• big data
• machine learning
• physics-informed machine learning
• deep learning
• hydrology
• explainable AI
• water resources
• hydrological forecasting