Researchers developed Atlas-Chat, a collection of LLMs for dialectal Arabic, focusing on Moroccan Arabic (Darija). They constructed an instruction dataset by consolidating existing Darija language resources and translating English instructions. Atlas-Chat models (2B, 9B, 27B) outperform state-of-the-art and Arabic-specialized LLMs like LLaMa, Jais, and AceGPT on Darija NLP tasks. Why it matters: This work addresses the gap in LLM support for low-resource Arabic dialects, providing a methodology for instruction-tuning and benchmarks for future research.
KAUST researchers are contributing new information about desert and mangrove plants to support Saudi Arabia's Green Initiative. They are creating a soil atlas for Saudi Arabia, studying soil profiles and microbial populations in hyperarid regions. The team has also compiled the world’s largest biobank of desert microbes, sequencing each microbe's genome. Why it matters: This research is crucial for ensuring the success and sustainability of large-scale greening efforts in arid environments like Saudi Arabia.
Researchers have developed a scalable pre-screening framework that integrates climate and remote sensing data to identify cost-efficient sites for sustainable dryland restoration, using Saudi Arabia as a case study. The framework employs machine learning models to derive a Climate Suitability Score (CSS), which captures climatic dependencies on vegetation persistence. National-scale prediction maps were generated using multi-year ERA5-Land data for Saudi Arabia, leading to the identification of thirteen priority locations with an estimated potential for a 2.5-fold increase in vegetation coverage. Why it matters: This approach significantly reduces the search space and costs associated with restoration efforts, supporting more resilient and sustainable ecosystem recovery planning in water-limited regions of the Middle East.