KAUST has been awarded the ACM Gordon Bell Prize for Climate Modelling, considered the "Nobel" of high-performance computing, for their work on exascale climate emulators. The winning paper, a collaborative effort with institutions including the NSF National Center for Atmospheric Research, addresses the computational and storage demands of high-resolution earth system models. The KAUST team included Sameh Abdulah, Marc G. Genton, David E. Keyes, and others. Why it matters: This is the first time an institution in the Middle East has won the prize, highlighting KAUST's leadership in high-performance computing and climate research in the region.
A new study introduces Sporo AraSum, a language model designed for Arabic clinical documentation, and compares it to JAIS using synthetic datasets and modified PDQI-9 metrics. Sporo AraSum significantly outperformed JAIS in quantitative AI metrics and qualitative attributes related to accuracy, utility, and cultural competence. The model addresses the nuances of Arabic while reducing AI hallucinations, making it suitable for Arabic-speaking healthcare. Why it matters: The model offers a more culturally and linguistically sensitive solution for Arabic clinical documentation, potentially improving healthcare workflows and patient outcomes in the region.
Saudi Electricity Company (SEC) and KAUST have launched a pilot study at SEC’s Rabigh power plant to demonstrate a cryogenic technology that captures multiple pollutants and greenhouse gases, including carbon dioxide. The technology captures over 98% of carbon dioxide from flue gas, as well as sulfur dioxide, nitrogen oxides, and particulate matter, using a single system, unlike current technologies. The streamlined post-processing has a smaller environmental footprint and lower costs. Why it matters: This project supports Saudi Arabia's net-zero carbon goals and offers a potentially more efficient and cost-effective method for retrofitting existing power plants.
KAUST and MEWA's Aquaculture Development Program (ADP) showcased achievements at the 6th International Saudi Aquaculture Development Workshop. New fish nutrition formulations developed by KAUST Beacon Development (KBD) could save Saudi Arabia $417 million per year in aquaculture production costs by 2030 through improved feed conversion ratios. KBD has also established complete production cycles for Sobaity and Gilthead seabream under Red Sea conditions. Why it matters: These advancements boost Saudi Arabia's food security and promote sustainable aquaculture, reducing reliance on imports and diversifying the economy in line with Vision 2030.
A new study uses the UNet++ deep learning model and Sentinel-2 satellite data to monitor mangrove dynamics in the UAE from 2017 to 2024. The model achieved a mean Intersection over Union (mIoU) of 87.8% on the validation set. Results indicate a significant increase in mangrove area, primarily in Abu Dhabi, contributing to enhanced carbon sequestration across the UAE.
Researchers introduce Swan, a family of Arabic-centric embedding models including Swan-Small (based on ARBERTv2) and Swan-Large (based on ArMistral). They also propose ArabicMTEB, a benchmark suite for cross-lingual, multi-dialectal Arabic text embedding performance across 8 tasks and 94 datasets. Swan-Large achieves state-of-the-art results, outperforming Multilingual-E5-large in most Arabic tasks. Why it matters: The new models and benchmarks address a critical need for high-quality Arabic language models that are both dialectally and culturally aware, enabling more effective NLP applications in the region.