Un séminaire du LEESU aura lieu le jeudi 10 septembre 2026 à 10h00 à l’ENPC dans la salle de doc et de réunion du Leesu.
 
Il sera constitué d’une intervention de Dr John Xiaogang Shi, Associate Professor in Water Resources à l’University of New Brunswick (Canada).

Son intervention s’intitule "Advancing Drought Early Warning in the Mekong Delta with an AI-based Framework Informed by Moisture Tracking".

Abstract

As climate change intensifies hydroclimatic extremes, advancing drought prediction capabilities has become critical for building resilience in vulnerable agricultural deltas. This urgency is acute in the Mekong Delta, where severe droughts have repeatedly caused profound social and economic damage, underscoring the need for improved forecasting to inform mitigation and preparedness. This study presents an AI-based framework that integrates precipitation moisture diagnostics with deep learning to significantly improve drought prediction in the Vietnamese Mekong Delta (VMD). First, moisture source contributions were quantified using the Water Accounting Model-2layers (WAM-2layers), a moisture tracking tool with ERA5 reanalysis data as inputs, revealing that over 60% of VMD precipitation originates from upwind source regions, with humidity and wind speed identified as dominant causal drivers of drought-period deficits. Building on this physical insight, a Convolutional Gated Recurrent Unit (ConvGRU) model was employed and explicitly trained with these external atmospheric variables. The model demonstrated robust multi-type drought forecasting skill at a 3-month lead, accurately detecting 90% of meteorological and 80% of agricultural droughts with low false-alarm rates (<10%), and reliably reconstructing major historical drought events. This work establishes a synergistic methodology, in which process-based diagnostics inform and validate an AI-driven prediction system, directly contributing to more reliable, physically interpretable early warning and supporting agricultural resilience and economic stability in this climate-sensitive delta.

Biography

Dr. John Xiaogang Shi is an Associate Professor in Water Resources at the University of New Brunswick, Canada. He earned his PhD from the University of Washington and subsequently held an NSERC Visiting Fellowship at Environment Canada’s National Hydrology Research Centre. With an international career spanning four continents, Dr. Shi has held academic appointments as a Senior Lecturer at the University of Glasgow, a Lecturer at Lancaster University and Xi’an Jiaotong-Liverpool University, and a Research Scientist at CSIRO Land and Water in Australia. His leadership roles include serving as Director of Research and MSc Programme Director at the University of Glasgow, where he also co-founded the Environmental Sustainability Initiative. Dr. Shi contributes to the global research community as a member of both the UKRI NERC Peer Review College and Talent Peer Review College, and serves as an Associate Editor for Environmental Impact Assessment Review. He also provides expert advisory input as a member of the Technical Reference Group for the Permanent Okavango River Water Commission in Africa. His work bridges data science, hydrological modelling, and artificial intelligence to develop solutions for critical water resources and environmental challenges, with a focus on the integrated management of water resources under changing environmental conditions.