Strategic flood mitigation: leveraging machine learning for dynamic flow abstraction and release

Purpose This study aims to propose an effective framework for flood mitigation that can help prevent damage to infrastructure and disruption in transportation, which not only causes distress to society but also propagates to the nation as a whole. Design/methodology/approach The proposed computational framework utilises the generalisation capability of Gaussian process regression for establishing the relationship between inflow discharge of the river upstream, tributaries and the downstream outflow discharge. The developed predictive framework is capable of predicting the downstream outflow discharge at Badarpur Ghat in the Barak River network of Assam province of North Eastern India, given the combination of inflow discharge at Fulertal (River upstream) and the corresponding tributaries. Such an efficient predictive framework is deployed for performing sensitivity analysis based on the relative coefficient of variation to identify the tributaries where the flow regulation scheme can be applied. Findings The implementation of the proposed computational scheme in simulating strategic flow abstraction and release resulted in successful mitigation of floods during the peak monsoon season, when the flow of Sonai, Katakhal, Ghaghra and Dhaleswari is regulated (by 50% reduction in discharge). Research limitations/implications While regulating tributary flow by 50% may represent an idealised “best-case scenario” for modelling purposes, its full-scale implementation in real-world settings might face several infrastructural and policy challenges. Practical implications The proposed strategy allows for the identification of optimal inflow reduction points using relatively smaller-scale interventions – such as check dams, wetlands or upstream storage – without the need for large reservoirs. Originality/value This investigation aims to deploy the capabilities of machine learning prediction in developing intervention strategies for flood mitigation.

Authors

Institutions

Publication Details

Journal
International Journal of Disaster Resilience in the Built Environment
Published
2025-09-04
DOI
https://doi.org/10.1108/ijdrbe-02-2025-0020
Primary Topic
Flood Risk Assessment and Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Strategic flood mitigation: leveraging machine learning for dynamic flow abstraction and release

Kritesh Kumar Gupta, Parthasarathi Choudhury, Ankush Kumar
International Journal of Disaster Resilience in the Built Environment
Flood Risk Assessment and Management
article

Strategic flood mitigation: leveraging machine learning for dynamic flow abstraction and release

Kritesh Kumar Gupta, Parthasarathi Choudhury, Ankush Kumar
article en

Abstract

Purpose This study aims to propose an effective framework for flood mitigation that can help prevent damage to infrastructure and disruption in transportation, which not only causes distress to society but also propagates to the nation as a whole. Design/methodology/approach The proposed computational framework utilises the generalisation capability of Gaussian process regression for establishing the relationship between inflow discharge of the river upstream, tributaries and the downstream outflow discharge. The developed predictive framework is capable of predicting the downstream outflow discharge at Badarpur Ghat in the Barak River network of Assam province of North Eastern India, given the combination of inflow discharge at Fulertal (River upstream) and the corresponding tributaries. Such an efficient predictive framework is deployed for performing sensitivity analysis based on the relative coefficient of variation to identify the tributaries where the flow regulation scheme can be applied. Findings The implementation of the proposed computational scheme in simulating strategic flow abstraction and release resulted in successful mitigation of floods during the peak monsoon season, when the flow of Sonai, Katakhal, Ghaghra and Dhaleswari is regulated (by 50% reduction in discharge). Research limitations/implications While regulating tributary flow by 50% may represent an idealised “best-case scenario” for modelling purposes, its full-scale implementation in real-world settings might face several infrastructural and policy challenges. Practical implications The proposed strategy allows for the identification of optimal inflow reduction points using relatively smaller-scale interventions – such as check dams, wetlands or upstream storage – without the need for large reservoirs. Originality/value This investigation aims to deploy the capabilities of machine learning prediction in developing intervention strategies for flood mitigation.

International Journal of Disaster Resilience in the Built EnvironmentVol. 16(5)
National Institute Of Technology Silchar (IN), Amrita Vishwa Vidyapeetham (IN)
Openalex Percentile: Top 78%
Flood Risk Assessment and Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.