Research

[AI Predicts More "Super Floods" and "Extreme Droughts" for Pakistan]

A new study led by Professor Jonghun Kam's team at POSTECH(Pohang University of Science and Technology) has uncovered a shocking forecast for Pakistan's future. Using a cutting-edge AI model, the research predicts that the country will face unprecedented "super floods" and "extreme droughts" on a periodic basis. This dire prediction is a direct result of accelerating global warming, which is causing more frequent and severe extreme weather events around the world, particularly in vulnerable high-altitude regions where glacies are melting.

The team focused on Pakistan because its major rivers, like the Indus, are the country’s lifeline, but climate change has made water resources management increasingly difficult. As a "Global South"^*1  nation, Pakistan is especially vulnerable to climate change and lacks the economic and technological infrastructure to conduct extensive research.

AI Tackles Inaccurate Climate Models

To overcome these challenges, Professor Kam's team turned to artificial intelligence. Traditional climate models often struggle with complex terrains like Pakistan's steep mountains and narrow valleys. They tend to underestimate changes in these areas or overestimate rainfall, which makes their predictions unreliable.

The researchers trained several AI models by comparing past river flow data with actual observations, which dramatically improved the accuracy of their predictions for past extreme weather events. This AI-corrected data proved to be far more reliable than existing models.

What Does the AI Forecast?

The analysis revealed a disturbing pattern. The upper Indus River could experience major floods and severe droughts approximately every 15 years. Surrounding rivers could face the same extreme events even more frequently, roughly every 11 years. This projection is a clear call to action, urging the Pakistani government to adopt tailored water management strategies for each river basin instead of relying on a one-size-fits-all approach. Professor Kam stated that this new AI technology will be crucial for producing reliable climate data not only for Pakistan but also for other climate-vulnerable and data-poor regions around the globe.

This research was conducted by the team of Professor Jonghun Kam from POSTECH's Division of Environmental Science and Engineering and doctoral student Hassan Raza, in collaboration with Professor Dagang Wang's team from Sun Yat-sen University in China. The study was published in the international academic journal Environmental Research Letters, and was supported by the National Research Foundation of Korea's Individual Basic Research Program and the BK21 FOUR Program. Hassan Raza received support from the ‘Global Korean Scholarship’.

DOI: https://iopscience.iop.org/article/10.1088/1748-9326/adf130

1. Global South: Refers to countries that have contributed less to climate change but are disproportionately exposed to its risks.