Project Grant 2614590

The National Science Foundation Office of Integrative Activities awarded New Jersey Institute of Technology $448,384 on August 1, 2026, under the Geosciences program (CFDA 47.050) to develop artificial intelligence–enabled methods for forecasting thermospheric density from several hours to several days ahead with uncertainty quantification and explainability. The project will couple physics-aware density models with probabilistic predictions of solar and geomagnetic drivers, propagating driver uncertainty through nonlinear forecasting mappings to produce calibrated density forecasts and uncertainty estimates. A second component will enable multi-day ensemble forecasting using solar imagery and heliospheric inputs including solar wind and interplanetary magnetic field data to generate probabilistic scenarios for geomagnetic drivers that will drive ensembles of thermospheric density. The work will support space-weather preparedness and sustainable space operations while generating open-source models, datasets, and analysis tools made publicly available. The project includes workforce training for postdoctoral researchers, graduate students, and undergraduate students in artificial intelligence, uncertainty quantification, solar image processing, and thermospheric science, along with educational outreach to high-school teachers and students through hands-on research, seminars, tutorials, and outreach activities. Work is performed in Newark, New Jersey, with a period of performance from August 1, 2026, through July 31, 2029.