MBZUAI researchers developed AirCast, a novel AI model for improved air pollution forecasting, which won the best paper award at the TerraBytes workshop during ICML. AirCast fuses weather and chemistry data using a Vision Transformer and frequency-weighted MAE to better predict extreme events like Saharan dust storms. In tests across the Middle East and North Africa, AirCast reduced PM2.5 error by 33% compared to a persistence baseline and outperformed the CAMS physics model. Why it matters: Accurate air pollution forecasting is critical for public health in the GCC region, and this research demonstrates a significant advancement using AI to address this challenge.
KAUST's Atmospheric and Climate Modeling group, led by Georgiy Stenchikov, is using high-resolution global and regional climate models to predict climate change in the Middle East, focusing on local atmospheric and oceanic processes. The group developed coupled regional atmospheric and oceanic models for the Red Sea, accounting for the climate effect of aerosols, especially dust, which is significant in the region. They found that dust strongly affects the Red Sea, causing high optical depth and solar cooling effect, particularly in the southern part, impacting energy balance and circulation. Why it matters: Improving regional climate models with specific attention to dust and aerosols is crucial for predicting and mitigating the environmental impacts of climate change in arid regions like the Middle East.
KAUST and the National Center for Environmental Compliance (NCEC) are expanding their partnership to address environmental challenges in Saudi Arabia. They plan to develop an advanced air quality forecasting system leveraging KAUST’s Shaheen III supercomputer. The collaboration also focuses on ensuring reliable communication systems for secure air quality data transfer across the national network. Why it matters: This partnership can enhance Saudi Arabia's environmental monitoring, strategic planning, and ability to respond to air quality emergencies, aligning with its sustainability goals.
MBZUAI Professor Agathe Guilloux developed the SigLasso model to forecast hospitalizations using real-time data from Google and Météo France during the COVID-19 pandemic. The model integrates mobility data and weather patterns to predict hospitalization rates 10-14 days in advance. SigLasso outperformed industry standards like GRU and Neural CDE in reducing reconstruction error. Why it matters: This research demonstrates the potential of AI to improve healthcare resource allocation and crisis management by accurately predicting patient flow using readily available data.
KAUST and SARsatX have developed a method using Generative Adversarial Networks (GANs) to generate synthetic SAR imagery for training deep learning models to detect oil spills. Starting with just 17 real SAR images, they generated over 2,000 synthetic images to train a Multi-Attention Network (MANet) model. The MANet model, trained exclusively on synthetic data, achieved 75% accuracy in identifying oil spill areas, matching the performance of models trained on larger real datasets. Why it matters: This advancement enables faster and more reliable environmental monitoring using AI, even when real-world data is scarce, reducing the need to wait for actual disasters to occur.