Author comment: A call for a fundamental shift from model-centric to data-centric approaches in hydroinformatics — R0/PR1 DOI Creative Commons
Babak Zolghadr‐Asli

Published: Dec. 23, 2023

Over the years, data-driven models have gained notable traction in water and environmental engineering. The adoption of these cutting-edge frameworks is still progress grand scheme things, yet for most part, such attempts been centered around themselves, their internal computational architecture, that is, model-centric approach. These endeavors can certainly pave way more tailor-fitted capable producing accurate results. However, a perspective often neglects fundamental assumption models, which importance reliability, correctness, accessibility data used constructing them. This challenge arises from prevalent paradigm thinking field. An alternative approach, however, would prioritize placing at focal point, focusing on systematically enhancing current datasets devising to improve collection schemes. suggests shift toward data-centric Practically, this not without challenges necessitates smarter rather than an excessive one. Equally important ethical data, making it available everyone while safeguarding rights individuals other legal entities involved process.

Language: Английский

Enhancing Water Level Prediction Using Ensemble Machine Learning Models: A Comparative Analysis DOI
Saleh Alsulamy, Vijendra Kumar, Özgür Kişi

et al.

Water Resources Management, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 11, 2025

Language: Английский

Citations

3
Predictive Tools and Advances in Sustainable Water Resources Through Atmospheric Water Generation Under Changing Climate: A Review DOI Open Access
Pooja P. Preetha,

Jejal Reddy Bathi,

Manoj Kumar

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(4), P. 1462 - 1462

Published: Feb. 11, 2025

Climate change continues to exacerbate water scarcity by altering global weather patterns and intensifying extreme climatic events. This review examines the potential of atmospheric generation technologies mitigate under such conditions. By leveraging a multidisciplinary approach, we advancements in fog harvesting, sorption-based systems, membrane technologies, radiative sky cooling, cloud seeding. A special emphasis is placed on passive systems utilizing renewable energy address challenges high demands. Predictive tools as machine learning, climate models, geographic information are explored optimize deployment shifting article outlines critical innovations materials, economic considerations, policy frameworks required for transition from niche mainstream solutions. These findings aim inform sustainable strategies tackling context challenges.

Language: Английский

Citations

1
Multimodal Fusion of Optimized GRU–LSTM with Self-Attention Layer for Hydrological Time Series Forecasting DOI
Hüseyin Çağan Kılınç,

Sina Apak,

Furkan Ozkan

et al.

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(15), P. 6045 - 6062

Published: Aug. 17, 2024

Language: Английский

Citations

6
Multi-Criteria Assessment of Flood Risk on Railroads Using a Machine Learning Approach: A Case Study of Railroads in Minas Gerais DOI Creative Commons
Fernanda Oliveira de Sousa, Victor Andre Ariza Flores, Christhian Santana Cunha

et al.

Infrastructures, Journal Year: 2025, Volume and Issue: 10(1), P. 12 - 12

Published: Jan. 8, 2025

In a climate change scenario where extreme precipitation events occur more frequently and intensely, risk assessment plays critical role in ensuring the safety operational efficiency of facilities. This case study uses combination multi-criteria analysis approach hydrological studies that use machine learning algorithms to simulate new rainfall order estimate flooding on railroads. Risk variables, including terrain, drainage capability, accumulated flow, land cover, will be weighed using multicriteria approach. A methodical evaluation most vulnerable locations railroad network possible thanks these parameters based geographic information system (GIS) meantime, historical precipitation, balance data used calibrate validate models. The database required for model can created with data. research regions are situated densely rail-networked state Minas Gerais. geographical climatic diversity Gerais makes it perfect place test suggested approaches. models evaluated included linear regression, random forest, decision tree, support vector machines. Among models, Linear Regression emerged as best-performing an R2 value 0.999998, mean squared error (MSE) 0.018672, low tendency overfitting (0.000011).

Language: Английский

Citations

0
Future Research Imperatives in Hydrogeology DOI
Rakesh Roshan Gantayat, Vetrimurugan Elumalai, Peiyue Li

et al.

Springer hydrogeology, Journal Year: 2025, Volume and Issue: unknown, P. 365 - 385

Published: Jan. 1, 2025

Language: Английский

Citations

0
Review of machine learning and WEAP models for water allocation under climate change DOI Creative Commons
Deme Betele Hirko, J A du Plessis, A. Bosman

et al.

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(3)

Published: March 1, 2025

Language: Английский

Citations

0
Coupling Interpretable Feature Selection with Machine Learning for Evapotranspiration Gap Filling DOI Open Access

Lizheng Wang,

Lixin Dong, Qiutong Zhang

et al.

Water, Journal Year: 2025, Volume and Issue: 17(5), P. 748 - 748

Published: March 4, 2025

Evapotranspiration (ET) plays a pivotal role in linking the water and carbon cycles between land atmosphere, with latent heat flux (LE) representing energy manifestation of ET. Due to adverse meteorological conditions, data quality filtering, instrument malfunctions, LE measured by eddy covariance (EC) is temporally discontinuous at hourly daily scales. Machine-learning (ML) models effectively capture complex relationships its influencing factors, demonstrating superior performance filling gaps. However, selection features ML often relies on empirical knowledge, identical frequently used across stations, leading reduced modeling accuracy. Therefore, this study proposes an gap-filling model (SHAP-AWF-BO-LightGBM) that combines Shapley additive explanations adaptive weighted fusion method Bayesian optimization light gradient-boosting machine algorithm. This tested using from three stations Heihe River Basin, China, different plant functional types. For 30 min interval missing data, RMSE ranges 17.90 W/m2 20.17 W/m2, while MAE 10.74 14.04 W/m2. The SHAP-AWF for feature selection. First, importance SHAP multiple ensemble-learning adaptively as basis input into BO-LightGBM algorithm, which enhances interpretability transparency model. Second, redundancy cost collecting other during training are reduced, improving calculation efficiency (reducing initial number 42, 46, 48 10, 15, 8, respectively). Third, under premise ensuring accuracy much possible, ratio improved, adaptability only automatic weather station observation enhanced (the improvement range 7.46% 11.67%). Simultaneously, hyperparameters LightGBM algorithm optimized further enhancing provides new approach perspective fill EC measurement.

Language: Английский

Citations

0
High-Performance Computing and Parallel Algorithms for Urban Water Demand Forecasting DOI Creative Commons

Georgios Myllis,

Alkiviadis Tsimpiris,

Stamatios Aggelopoulos

et al.

Algorithms, Journal Year: 2025, Volume and Issue: 18(4), P. 182 - 182

Published: March 22, 2025

This paper explores the application of parallel algorithms and high-performance computing (HPC) in processing forecasting large-scale water demand data. Building upon prior work, which identified need for more robust scalable models, this study integrates frameworks such as Apache Spark distributed data processing, Message Passing Interface (MPI) fine-grained execution, CUDA-enabled GPUs deep learning acceleration. These advancements significantly improve model training deployment speed, enabling near-real-time processing. Spark’s in-memory handling optimize preprocessing while MPI provides enhanced control over custom algorithms, ensuring high performance complex simulations. By leveraging these techniques, urban utilities can implement scalable, efficient, reliable solutions critical sustainable resource management increasingly environments. Additionally, expanding models to larger datasets diverse regional contexts will be essential validating their robustness applicability different settings. Addressing challenges help bridge gap between theoretical practical implementation, that HPC-driven provide actionable insights real-world decision-making.

Language: Английский

Citations

0
Irrigation Water Quality Prognostication: An Innovative Ensemble Architecture Leveraging Deep Learning and Machine Learning for Enhanced SAR and ESP Estimation in the East Coast of India DOI
Alok Kumar Pati, Alok Ranjan Tripathy, Debabrata Nandi

et al.

Journal of environmental chemical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 116433 - 116433

Published: April 1, 2025

Language: Английский

Citations

0
A call for a fundamental shift from model-centric to data-centric approaches in hydroinformatics DOI Creative Commons
Babak Zolghadr‐Asli, Ahmad Ferdowsi, Dragan Savić

et al.

Cambridge Prisms Water, Journal Year: 2024, Volume and Issue: 2

Published: Jan. 1, 2024

Abstract Over the years, data-driven models have gained notable traction in water and environmental engineering. The adoption of these cutting-edge frameworks is still progress grand scheme things, yet for most part, such attempts been centered around themselves, their internal computational architecture, that is, model-centric approach. These endeavors can certainly pave way more tailor-fitted capable producing accurate results. However, a perspective often neglects fundamental assumption models, which importance reliability, correctness, accessibility data used constructing them. This challenge arises from prevalent paradigm thinking field. An alternative approach, however, would prioritize placing at focal point, focusing on systematically enhancing current datasets devising to improve collection schemes. suggests shift toward data-centric Practically, this not without challenges necessitates smarter rather than an excessive one. Equally important ethical data, making it available everyone while safeguarding rights individuals other legal entities involved process.

Language: Английский

Citations

2