UAE AI Cloud Seedability Project Advances Towards Real-Time Rain Forecast
The UAE Research Program for Rain Enhancement Science (UAEREP) has reached an important milestone in its ongoing efforts to secure fresh water for the country and the region. The Strategic Directions Committee (SDC) recently conducted a midterm site visit to Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) to review progress on a key Cycle 5 research project. This project, titled “Identification of Clouds’ Microphysical Seedability in an Actionable Manner,” is among the most advanced and internationally collaborative initiatives in the field of rain enhancement.
The project is led by Professor Daniel Rosenfeld from the Hebrew University of Jerusalem (HUJI) and brings together an international team of researchers from the UAE, China, and the United States. Key partners include MBZUAI and the National Centre of Meteorology (NCM) in the UAE, Wuhan University (WHU) in China, and University of California San Diego (UCSD) in the U.S.
The main goal of the project is to create a real-time, data-driven system that can assess which clouds are ready for seeding. This system aims to guide cloud seeding operations effectively and predict the potential rainfall that may result from each operation. By integrating advanced simulations, satellite data, and machine learning, the project represents a significant step forward in science-based rain enhancement.
Global Collaboration for Water Security
The UAEREP project highlights how nations can work together to address water security, which is a growing concern in arid regions like the UAE and many parts of the world. By combining expertise, data, and resources, these countries are taking a collaborative approach to tackle one of the most pressing environmental challenges of our time.
The UAE’s National Centre of Meteorology (NCM) plays a crucial role in this collaboration by providing advanced infrastructure, technical support, and facilities. This ensures that data sharing, research development, and knowledge exchange are seamless across all partner institutions.
Speaking at the site visit, Dr. Abdulla Al Mandous, Director General of NCM and President of the World Meteorological Organization (WMO), emphasized the importance of international cooperation:
“By bringing together leading institutions from around the world, the programme is driving a shared scientific vision. This model strengthens the quality and impact of research and highlights the UAE’s role as a global convener in addressing water security challenges through innovation and partnership.”
Alya Al Mazroui, Director of UAEREP, added that integrating artificial intelligence (AI) and modelling into seedability studies marks a transformative step in rain enhancement science. She explained that combining satellite observations, machine learning, and validated simulations allows the creation of a tool that can evaluate clouds almost in real time, which is critical for operational decision-making in weather modification.
Key Milestones Achieved
During the midterm visit, the team presented a number of achievements that demonstrate the project’s progress. These milestones show how far the research has come and the technological innovations being implemented.
-
Cloud Simulations on Supercomputer
The project has successfully run the first WRF-SBM cloud-scale simulation over the UAE on NCM’s Atmosphere supercomputer. WRF-SBM, which stands for Weather Research & Forecasting – Spectral Bin Microphysics, is a high-resolution cloud model that simulates detailed cloud processes. These simulations provide the foundation for the AI-powered Seedability Guidance Tool being developed in collaboration with UCSD.
By running these simulations at such a detailed level, researchers can better understand cloud dynamics and predict which cloud formations are most likely to respond to seeding. This ensures that cloud seeding operations are more precise and effective.
-
Enhanced Satellite Images
Satellite imagery plays a key role in rain enhancement research. MBZUAI researchers have applied super-resolution techniques to improve Meteosat geostationary satellite images. This technology sharpens the images, allowing scientists to detect smaller cloud features that may indicate a cloud is ready for seeding.
Enhanced satellite data improves both accuracy and confidence in seedability assessments. It allows researchers to identify patterns and trends in cloud development that may otherwise go unnoticed in lower-resolution imagery.
-
Automated Cloud Analysis
Wuhan University has developed software that automates the sampling and visualisation of cloud microphysical properties. This means that data about cloud droplets, ice particles, and other microphysical parameters can now be processed automatically. The software helps generate reliable information needed to assess whether a cloud is seedable and how effective seeding is likely to be.
Automation reduces the manual work required and speeds up the decision-making process. It also ensures that cloud data is standardized, making it easier to integrate with AI models.
-
Training the Next Generation
The project actively involves graduate students and postdoctoral researchers from HUJI, MBZUAI, WHU, and UCSD. This ensures that future scientists are trained in data-driven rain enhancement research and AI applications in meteorology.
By building a skilled workforce, UAEREP not only advances current research but also creates a lasting legacy of expertise that will benefit the UAE and partner countries for years to come.
How the System Works
The technical framework of the project combines satellite images, weather data, computer simulations, and machine learning to produce near real-time assessments of cloud seedability. The process can be summarized in four steps:
-
Simulations and Validation
- Cloud-scale simulations are run using WRF-SBM.
- Simulations are compared with real-world observations from radars, aircraft, and other instruments.
- Validated simulations provide data to train AI models.
-
Satellite Imagery
- Simulated clouds are transformed into synthetic satellite images using radiative transfer models.
- This helps AI models learn the relationship between observed cloud features and their seedability.
-
Machine Learning
- AI models are trained using satellite imagery and meteorological data.
- The models predict whether clouds are seedable and estimate the potential rainfall from seeding.
-
Decision Support Tool
- Real-time weather and satellite data are processed by the tool.
- It provides recommendations for seeding operations, including which clouds to target and expected outcomes.
This system allows cloud seeding to be more targeted, efficient, and reliable. It reduces wasted effort and ensures that operations have the best possible chance of increasing rainfall.
Why This Project Matters
The midterm review marks the transition from research and development to operational readiness. The benefits of the project extend beyond science and technology:
- Better Cloud Seeding DecisionsThe system helps identify clouds that are most likely to respond to seeding, improving the effectiveness of operations.
- Support for Water Security
In a region with limited freshwater resources, AI-driven cloud seeding can contribute to sustainable water management and climate resilience. - Global Leadership
The UAE is establishing itself as a hub for advanced environmental science, attracting international collaboration and talent. - Capacity Building
Training students and young scientists in AI and meteorology creates a new generation of experts ready to tackle future challenges. - Global Potential
Once mature, the system can be adapted for use in other arid regions facing water scarcity, potentially benefiting millions of people worldwide.
UAE’s Role as a Global Innovator
Through projects like this, the UAE demonstrates a strong commitment to science-backed water management and climate adaptation strategies. By bringing together international partners, the country not only advances technology but also promotes knowledge sharing and collaboration.
The UAE’s investment in AI and supercomputing capabilities, combined with its strategic partnerships, allows it to lead global research in rain enhancement science. This positions the country as both a technological leader and a facilitator of solutions to water scarcity.
