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

Water, Journal Year: 2023, Volume and Issue: 15(4), P. 620 - 620

Published: Feb. 5, 2023

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

Language: Английский

---

A Comprehensive Survey of Machine Learning Methodologies with Emphasis in Water Resources Management

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(22), P. 12147 - 12147

Published: Nov. 8, 2023

This paper offers a comprehensive overview of machine learning (ML) methodologies and algorithms, highlighting their practical applications in the critical domain water resource management. Environmental issues, such as climate change ecosystem destruction, pose significant threats to humanity planet. Addressing these challenges necessitates sustainable management increased efficiency. Artificial intelligence (AI) ML technologies present promising solutions this regard. By harnessing AI ML, we can collect analyze vast amounts data from diverse sources, remote sensing, smart sensors, social media. enables real-time monitoring decision making applications, including irrigation optimization, quality monitoring, flood forecasting, demand enhance agricultural practices, distribution models, desalination plants. Furthermore, facilitates integration, supports decision-making processes, enhances overall sustainability. However, wider adoption faces challenges, heterogeneity, stakeholder education, high costs. To provide an management, research focuses on core fundamentals, major (prediction, clustering, reinforcement learning), ongoing issues offer new insights. More specifically, after in-depth illustration algorithmic taxonomy, comparative mapping all specific tasks. At same time, include tabulation works along with some concrete, yet compact, descriptions objectives at hand. leveraging tools, develop plans address world’s supply concerns effectively.

Language: Английский

---

A new frontier in streamflow modeling in ungauged basins with sparse data: A modified generative adversarial network with explainable AI

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101920 - 101920

Published: Feb. 15, 2024

Streamflow forecasting is crucial for effective water resource planning and early warning systems, especially in regions with complex hydrological behaviors uncertainties. While machine learning (ML) has gained popularity streamflow prediction, many studies have overlooked the predictability of future events considering anthropogenic, static physiographic, dynamic climate variables. This study, first time, used a modified generative adversarial network (GAN) based model to predict streamflow. The training concept modifies enhances existing data embed featureful information enough capture extreme rather than generating synthetic instances. was trained using (sparse data) combination variables obtained from an ungauged basin monthly GAN-based interpreted time local interpretable model-agnostic explanations (LIME), explaining decision-making process model. achieved R2 0.933 0.942 0.93–0.94 testing. Also, testing period been reasonably well captured. LIME generally adhere physical provided by related work. approach looks promising as it worked sparse basin. authors suggest this research work that focuses on learning-based predictions.

Language: Английский

---

Artificial Intelligence Techniques in Hydrology and Water Resources Management

Water, Journal Year: 2023, Volume and Issue: 15(10), P. 1846 - 1846

Published: May 12, 2023

The sustainable management of water cycles is crucial in the context climate change and global warming. It involves managing global, regional, local cycles—as well as urban, agricultural, industrial cycles—to conserve resources their relationships with energy, food, microclimates, biodiversity, ecosystem functioning, anthropogenic activities. Hydrological modeling indispensable for achieving this goal, it essential mitigation natural disasters. In recent decades, application artificial intelligence (AI) techniques hydrology has made notable advances. face hydro-geo-meteorological uncertainty, AI approaches have proven to be powerful tools accurately complex, non-linear hydrological processes effectively utilizing various digital imaging data sources, such ground gauges, remote sensing tools, situ Internet Things (IoTs). thirteen research papers published Special Issue make significant contributions long- short-term under changing environments using coupled analytics tools. These contributions, which cover forecasting, microclimate control, adaptation, can promote direct policy making toward integrated management.

Language: Английский

---

Flood Simulations Using a Sensor Network and Support Vector Machine Model

Water, Journal Year: 2023, Volume and Issue: 15(11), P. 2004 - 2004

Published: May 25, 2023

This study aims to couple the support vector machine (SVM) model with a hydrometeorological wireless sensor network simulate different types of flood events in montane basin. The was tested mid-latitude basin Vydra Šumava Mountains, Central Europe, featuring complex physiography, high dynamics processes, and occurrence floods. is equipped operating headwaters along conventional long-term monitoring outlet. trained validated using hydrological observations from 2011 2021, performance assessed metrics such as R2, NSE, KGE, RMSE. run both hourly daily timesteps evaluate effect timestep aggregation. Model setup deployment utilized KNIME software platform, LibSVM library, Python packages. Sensitivity analysis performed determine optimal configuration SVR parameters (C, N, E). Among 125 simulation variants, an parameter identified that resulted improved better fit for peak flows. sensitivity demonstrated robustness model, variations yielded reasonable performances, NSE values ranging 0.791 0.873 year. Simulation results scenarios showed reliability reconstructing accurately captured trend fitting, event timing, peaks, volumes without significant errors. Performance generally higher timestep, mean metric R2 = 0.963 0.880, compared 0.913 0.820 all 12 scenarios. very good even rain-on-snow floods combined fast computation makes this promising approach applications.

Language: Английский

---

Revolutionizing the Future of Hydrological Science: Impact of Machine Learning and Deep Learning amidst Emerging Explainable AI and Transfer Learning

Applied Computing and Geosciences, Journal Year: 2024, Volume and Issue: 24, P. 100206 - 100206

Published: Nov. 9, 2024

Language: Английский

---

Futuristic Streamflow Prediction Based on CMIP6 Scenarios Using Machine Learning Models

Water Resources Management, Journal Year: 2023, Volume and Issue: 37(15), P. 6089 - 6106

Published: Oct. 26, 2023

Language: Английский

---

Generative deep learning for probabilistic streamflow forecasting: Conditional variational auto-encoder

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 629, P. 130498 - 130498

Published: Nov. 21, 2023

Language: Английский

---

Utilizing Hybrid Machine Learning Techniques and Gridded Precipitation Data for Advanced Discharge Simulation in Under-Monitored River Basins

Hydrology, Journal Year: 2024, Volume and Issue: 11(4), P. 48 - 48

Published: April 4, 2024

This study addresses the challenge of utilizing incomplete long-term discharge data when using gridded precipitation datasets and data-driven modeling in Iran’s Karkheh basin. The Multilayer Perceptron Neural Network (MLPNN), a rainfall-runoff (R-R) model, was applied, leveraging from Asian Precipitation—Highly Resolved Observational Data Integration Toward Evaluation (APHRODITE), Global Precipitation Climatology Center (GPCC), Climatic Research Unit (CRU). MLPNN trained Levenberg–Marquardt algorithm optimized with Non-dominated Sorting Genetic Algorithm-II (NSGA-II). Input were pre-processed through principal component analysis (PCA) singular value decomposition (SVD). explored two scenarios: Scenario 1 (S1) used situ for calibration dataset testing, while 2 (S2) involved separate calibrations tests each dataset. findings reveal that APHRODITE outperformed S1, all showing improved results S2. best achieved hybrid applications S2-PCA-NSGA-II S2-SVD-NSGA-II GPCC CRU. concludes datasets, properly calibrated, significantly enhance runoff simulation accuracy, highlighting importance bias correction modeling. It is important to emphasize this approach may not be suitable situations where catchment undergoing significant changes, whether due development interventions or impacts anthropogenic climate change. limitation highlights need dynamic approaches can adapt changing conditions.

Language: Английский

---

A New Custom Deep Learning Model Coupled with a Flood Index for Multi-Step-Ahead Flood Forecasting

Hydrology, Journal Year: 2025, Volume and Issue: 12(5), P. 104 - 104

Published: April 26, 2025

Accurate and prompt flood forecasting is essential for effective decision making in control to help minimize or prevent damage. We propose a new custom deep learning model, IF-CNN-GRU, multi-step-ahead that incorporates the index (IF) improve prediction accuracy. The model integrates convolutional neural networks (CNNs) gated recurrent (GRUs) analyze spatiotemporal characteristics of hydrological data, while using recursive network adjusts unit output at each moment based on index. IF-CNN-GRU was applied forecast floods with lead time 1–5 d Baihe station middle reaches Han River, China, accompanied by an in-depth investigation uncertainty. results showed incorporating IF improved precision up 20%. analysis uncertainty revealed contributions modeling factors, such as datasets, structures, their interactions, varied across periods. interaction factors contributed 17–36% uncertainty, contribution datasets increased period (32–53%) structure decreased (32–28%). experiment also demonstrated data samples play critical role improving accuracy, offering actionable insights reduce predictive providing scientific basis early warning systems water resource management.

Language: Английский

---