Bhubaneswar: In a breakthrough that could significantly improve disaster preparedness in the Himalayan region, researchers from IIT Bhubaneswar have claimed to have developed a deep learning-based model capable of predicting cloudburst events in Himachal Pradesh and Uttarakhand up to 72 hours in advance with far greater accuracy than conventional weather models.A study, published by five researchers of IIT Bhubaneswar in Neural Computing and Applications (a Springer Nature journal) on June 1, analysed the devastating cloudburst and extreme rainfall events that struck the northwestern Himalayas between Aug 12 and 16, 2023, killing more than 140 people, and triggering flash floods and landslides across the region.Researchers Sandeep Pattnaik, Hemant Kumar, Dhananjay Trivedi, Omveer Sharma and Niladri Bihari Puhan mentioned in the study that traditional numerical weather prediction models often fail to estimate the timing and intensity of short-duration heavy rainfall events over mountainous terrain accurately. To address this, the team designed a “dual-encoder cross-attention fusion transformer” deep learning model that combines district- and state-level weather patterns for improved forecasting.“With a mean absolute error of less than 9 mm, the suggested model demonstrated superior rainfall estimation, outperforming the ensembles of Weather Research and Forecasting (WRF) model,” the study noted.The model captured more than six cloudburst events that occurred across Himachal Pradesh and Uttarakhand during the 2023 disaster period. According to the study, the AI system accurately tracked temporal rainfall variations in key districts such as Mandi, Dehradun, Haridwar and Pauri Garhwal, while conventional WRF models “barely predict any events”.“The DL model successfully captures the rainfall variation between 36 and 48 hours in the case of Mandi, Dehradun, Haridwar and Pauri Garhwal, whereas the WRF ensemble model is not able to capture this event in any district,” read the study.The study found the deep learning system achieved heavy rainfall prediction accuracy of 68.4% in Mandi, 67.33% in Dehradun, 54.66% in Haridwar and 77.7% in Pauri Garhwal.Researchers’ findings could help authorities issue more reliable early warnings in ecologically fragile Himalayan regions that are increasingly vulnerable to extreme weather events linked to climate change. “This is landmark research with direct implications for improving early warning, disaster preparedness and mitigation,” the paper said.
