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
- Kritesh Kumar Gupta (ORCID: https://orcid.org/0000-0002-8393-2203)
- Parthasarathi Choudhury (ORCID: https://orcid.org/0000-0003-0688-9544)
- Ankush Kumar (ORCID: https://orcid.org/0000-0001-9024-3433)
Institutions
- National Institute Of Technology Silchar (IN)
- Amrita Vishwa Vidyapeetham (IN)
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