Floods are no longer seen as just natural disasters, but as complex events intensified by climate change, rapid urbanization, floodplain encroachment, land use change, and socio-economic vulnerability.
A new study combining artificial intelligence (AI), machine learning (ML), remote sensing, geographic information system (GIS) and spatial analysis has found that almost 11.87% of the coastal state of Odisha falls under high to very high flood susceptibility zones and about 6.85% of the state faces significant flood risk.
Odisha is one of the most flood-prone states in India, with around 80% of its area vulnerable to multi-hazard natural disasters. The state’s unique geography makes it highly susceptible to both coastal and riverine flooding. Cumulative economic damage to crops, housing, and infrastructure has historically cost states billions of dollars.
A study conducted by researchers from four universities in India, the UK, Brazil and Saudi Arabia found that coastal areas such as Jagatsingapur, Kendrapara, Puri, Balasore, Bhadrak and Cuttack are the most flood-prone areas in Odisha, while major river basins such as Baitarani, Brahmani, Mahanadi, Budhbalanga, Sabbarnalekkha, Rushikriya and Korab basins are at high risk of flooding. Easy to flood.
Researchers said Odisha’s topography, characterized by deltaic plains, low-lying coastal belts, gentle slopes and heavy monsoon rains, is a major contributor to the repeated floods. More than 75 percent of the state’s annual rainfall occurs during the monsoon season, which often coincides with the cropping season, increasing the potential for flash floods.
“Coastal deltas and alluvial areas are particularly prone to flooding. Flat topography (less than 10 meters above sea level) and gentle slope (less than 2 degrees) result in high flood susceptibility, which is further exacerbated by heavy siltation and inadequate drainage. These conditions frequently lead to flash floods and embankment failures,” said Manoranjan Mishra, Head of Geography, FM. Universities in Orissa.
The study showed that the confluence of flood waters from the Baitarani, Brahmani and Mahanadi river systems, especially the occurrence of simultaneous high reaches, intensifies flooding in coastal areas. Storm surges and storm surges further worsen the situation by causing riverbank flooding and severe sedimentation in riparian areas.
Researchers used five advanced machine learning models – Random Forest (RF), Bagging, Support Vector Machine (SVM), K-Nearest Neighbor Model (KNN), and Generalized Linear Model (GLM) to generate flood hazard, vulnerability, and risk maps across Odisha.
They created a detailed flood inventory database using historical flood records from 2009 to 2015 obtained through the National Remote Sensing Center (NRSC)’s Bhuwan web map service. Approximately 1,600 flood and 1,600 non-flood locations were analyzed using GIS and statistical tools to train and validate the machine learning model.
Among all the models tested, the random forest model emerged as the most accurate and reliable. It achieved the highest prediction accuracy for both flood hazard and flood vulnerability assessment, recording AUC values of 0.963 and 0.956, respectively.
The study identified low altitude as the most important factor influencing flood risk in Odisha. “Area located below two meters above sea level showed significantly higher flood susceptibility due to poor drainage and water accumulation. Soil type, slope, topography and geology were also found to have a strong influence on flood patterns,” said Rajkumar Guria, another researcher.
On the socio-economic front, distance from flood shelters emerged as the most important vulnerability factor, indicating that communities with limited access to shelters face greater risk during floods. Population density, agricultural intensity, acreage, and illiteracy level were also identified as important indicators of vulnerability.
The findings revealed that densely populated coastal and deltaic regions are particularly vulnerable due to rapid land use change due to settlement expansion, increased encroachment into floodplains, and development and livelihood pressures.
The researchers emphasized that the findings will help policy makers and disaster management agencies develop district-level flood zoning systems, strengthen climate-resilient infrastructure, and improve real-time flood early warning mechanisms. The study also recommends wetland restoration, ecosystem-based flood management, and community-level disaster preparedness efforts.
“Data-driven scientific planning can play a transformative role in protecting vulnerable people, strengthening resilient agriculture, minimizing economic losses and ensuring sustainable development in coastal regions of Odisha and other climate-sensitive countries,” Mishra added.
