EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

A methodological review of AI/ML and evolutionary computation in hydrology and hydraulics: from ANN/SVM to deep learning, symbolic regression, and physics-informed models

Maritza Liliana Arganis-Juárez iD, M Preciado iD

Water Science & Technology · 01.07.2026 · 94 (1) · 166-179

DOI: 10.2166/wst.2026.304 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Water Science & Technology, online erschienen am 23.06.2026. Verfasst von Maritza Liliana Arganis-Juárez und 1 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Ingeniería, Universidad Nacional Autónoma de México, CDMX, México. Hauptthemen laut MEDLINE: Artificial Intelligence, Models, Theoretical. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Schematic workflow showing hydrology data inputs, preprocessing, artificial intelligence models, and a hybrid physics-informed block combining hydrological knowledge and machine learning, leading to applications such as flood prediction, reservoir operation, groundwater management, and decision-making. Integrated framework linking hydrologic data, AI/ML methods, and physics-informed modeling. Source: Human-designed concept, AI-assisted rendering. This review synthesizes the methodological evolution of artificial intelligence and evolutionary computation in hydrology and hydraulics, from early machine learning (artificial neural networks, support vector machines, fuzzy systems, metaheuristics) to recent advances, including deep learning (long short-term memory, Convolutional Neural Network (CNN), Convolutional Long Short-Term Memory (ConvLSTM), graph neural networks), symbolic regression, and physics-informed modeling. Evidence is organized by application domain: model calibration, streamflow forecasting, hydrological regionalization, reservoir operation, and surrogate models for hydraulic simulation. We emphasize that algorithm selection should reflect hydrologic understanding, data constraints, and operational needs – not model complexity. Beyond cataloging techniques, the shift from purely data-driven prediction toward hybrid, physics-aware, uncertainty-quantified frameworks is described here. Case studies from Mexico illustrate end-to-end workflows, including reservoir operation using dynamic programming and genetic algorithms, guide-curve optimization in the Cutzamala System, stochastic dual dynamic programming applications in the Miguel Alemán-Cerro de Oro system, and flood mapping with U-Net using Sentinel-1 imagery. A public repository provides reproducible scripts and a structured reference database. This review concludes with a research agenda addressing extreme events, uncertainty, interpretable surrogates, and standardized multibasin evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceModels, TheoreticalHydrologyNeural Networks, ComputerDeep LearningSupport Vector Machine

Stichwörter der Autor:innen

deep learningevolutionary computationhydrologyphysics-informed learningreservoir operationsymbolic regression

Autor:innen und Institutionen

  • Instituto de Ingeniería, Universidad Nacional Autónoma de México, CDMX, México.
  • Facultad de Ingeniería, Universidad Nacional Autónoma de México, CDMX, México E-mail: marganisj@iingen.unam.mx.
  • Instituto Mexicano de Tecnología del Agua, Jiutepec, Mor., México.

ORCID-Profile: Maritza Liliana Arganis-Juárez, M Preciado

Zitieren

APA

Arganis-Juárez, M. L., & Preciado, M. (2026). A methodological review of AI/ML and evolutionary computation in hydrology and hydraulics: from ANN/SVM to deep learning, symbolic regression, and physics-informed models. Water Science & Technology, 94(1), 166-179. https://doi.org/10.2166/wst.2026.304

Vancouver

Arganis-Juárez ML, Preciado M. A methodological review of AI/ML and evolutionary computation in hydrology and hydraulics: from ANN/SVM to deep learning, symbolic regression, and physics-informed models. Water Science & Technology. 2026;94(1):166-179. doi:10.2166/wst.2026.304

BibTeX
@article{ArganisJurez2026,
  author = {Arganis-Juárez, Maritza Liliana and Preciado, M},
  title = {A methodological review of AI/ML and evolutionary computation in hydrology and hydraulics: from ANN/SVM to deep learning, symbolic regression, and physics-informed models},
  journal = {Water Science & Technology},
  year = {2026},
  volume = {94},
  number = {1},
  pages = {166--179},
  doi = {10.2166/wst.2026.304}
}
Kostenlos starten →