The Aral Sea region faces a severe environmental crisis driven by the shrinking of the Aral Sea, low precipitation, extreme drought, and desertification, which have intensified the frequency of dust, salt, and sand storms. Each year, massive amounts of dust and salt particles rise from the dried seabed into the atmosphere and spread across vast areas, accelerating drought, reducing rainfall, and increasing wind speed variability. These processes significantly affect ecosystems, public health, and local livelihoods.

This project aims to develop a non-stationary modeling system to forecast the formation and dispersion of dust storms in the Aral Sea region. The research integrates remote sensing, meteorological and aerological data, artificial intelligence, machine learning, and advanced simulation methods to overcome the challenges of data scarcity and low-quality observations. The study will analyze the mechanisms of dust storm formation, identify key environmental factors such as wind speed, temperature, humidity, and land use, and design predictive models with higher accuracy and reliability.

Innovative approaches include:

-             application of non-stationary models adaptable to changing climate and land-use conditions;

-             use of remote sensing and artificially generated proxy datasets to fill information gaps;

-             deployment of Gaussian diffusion-dispersion, Eulerian turbulence diffusion, receptor modeling, and data assimilation techniques;

-             development of dedicated software tools to provide timely and precise forecasts to local authorities, industries, and communities.

The project’s novelty lies in the integration of big data analytics, AI-based pattern recognition, and multi-disciplinary collaboration (meteorology, physics, chemistry, environmental science, informatics). The expected outcomes include a robust forecasting system, new criteria for locating socio-economic and industrial facilities under dust storm risk, and practical recommendations for mitigating adverse impacts.

By improving predictive capacity, this research will support evidence-based decision-making, reduce ecological and health risks, and contribute to sustainable development in the Aral Sea region.