Machine Learning for Hydrological Prediction and Water Management

Dear Colleagues,

Hydrological prediction and water management are increasingly challenged by climate variability and change, land-use dynamics, intensifying extremes, and evolving human–water interactions. Accurate and timely estimation of key hydroclimatic and hydrological variables, including precipitation, air temperature, evapotranspiration, soil moisture, snowmelt, streamflow, groundwater levels, and reservoir inflows, is essential for drought and flood preparedness, irrigation planning, hydropower scheduling, ecosystem protection, and the sustainable allocation of water resources. Nevertheless, reliable modeling remains challenging due to nonlinear process interactions, scale dependencies, data limitations, observational uncertainties, and non-stationarity across diverse hydroclimatic regimes.

Recent advances in machine learning (ML) and artificial intelligence (AI) offer substantial opportunities to enhance hydrological simulation and forecasting, integrate heterogeneous data sources (e.g., in situ observations, remote sensing products, reanalysis datasets, and IoT-based monitoring systems), and support informed decision-making in complex water systems. However, the responsible adoption of ML in hydrology requires rigorous model evaluation, uncertainty quantification, interpretability, reproducibility, and a clear linkage to operational and policy-relevant applications.

This Special Issue invites high-quality contributions that advance ML-enabled hydrological prediction and water management through methodological innovations, benchmarked model evaluations, and applied studies with clear scientific and practical relevance. We particularly welcome interdisciplinary research bridging hydrology, atmospheric sciences, data science, and water systems engineering, with the aim of strengthening climate adaptation, risk reduction, and sustainable water management under current and future hydroclimatic conditions.

Topics of Interest

Potential topics for submission include, but are not limited to, the following:

• Machine learning and AI for hydrological and hydroclimatic prediction, including streamflow, groundwater, evapotranspiration, soil moisture, snowmelt, and integrated water-balance components across scales.
• Data-scarce and ungauged basin hydrology, leveraging few-shot, semi-supervised, transfer, and self-supervised learning to improve robustness under limited observations.
• Explainable, trustworthy, and uncertainty-aware hydrological AI, covering interpretability, probabilistic and ensemble prediction, uncertainty quantification, and robustness to non-stationarity for operational and policy use.
• Hybrid process-based and AI-driven modeling, integrating conceptual or distributed hydrological models with physics-informed ML, surrogate modeling, and ML-compatible data assimilation.
• Copula–AI hybrid methods for multivariate extremes and compound events, enabling joint probability modeling, return-period estimation, and risk-informed decision-making.
• AI-driven analysis of extreme and compound hazards, including drought–heat interactions, flood forecasting under non-stationary climate conditions, cascading hazards, and multi-hazard risk analytics.
• ML-based optimization, control, and decision-making for water management, including reservoir operation, irrigation scheduling, water allocation, and multi-objective planning.
• AI-enabled operational and decision-support systems, including real-time ML-based forecasting, intelligent early warning, AI-powered digital twins, and scalable edge–cloud–HPC implementations.
• AI-based multi-source data fusion for hydrology, integrating remote sensing, reanalysis, in situ observations, citizen science, and IoT data for enhanced monitoring and forecasting.
• AI-driven downscaling, bias correction, and climate impact assessment, addressing non-stationarity and uncertainty in climate projections for adaptation, long-term planning, and risk management.
• Advanced and adaptive AI frameworks for hydrology and water management, encompassing probabilistic, generative, causal, and multimodal learning for integrated prediction, system understanding, and decision support.

Dr. Okan Mert Katipoğlu
Dr. Veysi Kartal
Prof. Dr. Mohammed Achite
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 250 words) can be sent to the Editorial Office for assessment.

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. Atmosphere is an international peer-reviewed open access monthly 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 2400 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.

• artificial intelligence
• machine learning
• hydrological prediction
• drought
• flood
• remote sensing
• reservoir operation
• climate change
• explainable AI
• water resources management