Research Biography

Dr. Farnaz Hosseinpour is an Assistant Research Professor at the Desert Research Institute, founder and Director of theSMART Laboratory Science & Mathematics of AI Modeling for Research and Technology Graduate Faculty in the Atmospheric Science Graduate Program at the University of Nevada, Reno, and Associate Director of Nevada NASA EPSCoR and Space Grant Programs. Her research develops hybrid, physics-informed computational frameworks that couple artificial intelligence and machine learning with process-based environmental models and multi-source satellite, airborne, and ground-based observations. This integrated approach combines hierarchical modeling, environmental data fusion, and predictive analytics to advance understanding, forecasting, and decision support for complex Earth system processes, including wildfire, smoke, air quality, extreme weather, and climate-related hazards.

Dr. Hosseinpours research spans coupled Earth system processes in which land, atmosphere, fire, emissions, aerosols, and climate variability interact across spatial and temporal scales. She develops artificial intelligenceenabled and digital-twin modeling systems that integrate satellite, airborne, and ground-based observations with fireweather, atmospheric, air-quality, and Earth system modeling. Her work advances the representation, evaluation, and forecasting of wildfire behavior, fire emissions, smoke transport, aerosolcloudradiation interactions, background ozone, vegetation and humidity variability, and other environmental extremes.

Through the SMART Laboratory, which she founded and directs, Dr. Hosseinpour advances research-to-application pathways that connect scientific discovery with operational needs in wildfire, smoke, and air-quality management. She has led NASA-, NOAA-, EPA-, CAL FIRE-, DOD-, EPRI-, USFS-, and state-funded projects focused on probabilistic prediction, uncertainty characterization, bias correction, model evaluation, prescribed-fire planning, smoke exposure assessment, and satellite product enhancement. Her work bridges research and application by translating observations, model outputs, and artificial intelligenceenabled analytics into actionable environmental intelligence for fire management, air-quality planning, public health, land-management, and stakeholder decision-making.

Dr. Hosseinpour is actively engaged in graduate education, interdisciplinary mentorship, and professional service in atmospheric and environmental science. She has developed and taught graduate-level courses in Satellite Remote Sensing and Graduate Seminar and mentors undergraduate and graduate students, postdoctoral researchers in atmospheric science, machine learning, satellite remote sensing, and environmental modeling. She also serves the scientific community through proposal review for NASA and NSF programs, peer review for leading atmospheric science journals, and invited presentations on artificial intelligenceenabled environmental prediction and wildfire-smoke research.

Research Areas

Hybrid artificial intelligencephysics modeling; physics-guided machine learning for Earth system prediction; digital-twin frameworks for environmental prediction and decision support; hierarchical and probabilistic environmental modeling; multi-source satellite, UAV, and ground-based data fusion; data assimilation; uncertainty-aware forecasting; wildfire behavior, fire emissions, coupled fireatmosphere processes, fireweather prediction, smoke transport, smoke-risk and exposure assessment, prescribed-fire planning, wildfire resilience, and operational fire-management support; air-quality modeling, background ozone, atmospheric composition, aerosol product enhancement, and air-quality management; aerosolcloudradiation interactions; vegetation greenness and vegetation health for wildfire risk assessment; climate-related hazards and environmental extremes; and environmental sensing under variable atmospheric and surface conditions.

Technical Skills

Physics-informed artificial intelligence and machine learning for Earth system prediction; hybrid artificial intelligencephysics modeling; digital-twin framework development; hierarchical and probabilistic modeling; multi-source environmental data fusion; data assimilation; multiscale physical modeling; satellite remote sensing and Earth observation analytics; atmospheric, fireweather, air-quality, and Earth system modeling; coupled fireatmosphere process modeling; uncertainty quantification; probabilistic forecasting; bias correction; model calibration, evaluation, and validation; high-dimensional environmental data analytics; geospatial intelligence; scalable computational workflows; high-performance computing; and research-to-application development of environmental prediction and decision-support systems.

Teaching, Advising, and Mentorship

Advising and mentoring of undergraduate and graduate students, postdoctoral researchers in atmospheric science, artificial intelligence, machine learning, satellite remote sensing, environmental modeling, and Earth system prediction. Graduate instruction includes courses in Satellite Remote Sensing and Atmospheric Science seminars, with additional training activities supporting interdisciplinary research, proposal development, and workforce preparation.

Program Leadership and Service

Founder and Director of the SMART Laboratory; Associate Director of Nevada NASA EPSCoR and Space Grant Programs; Graduate Faculty in the Atmospheric Science Graduate Program at the University of Nevada, Reno; service on NASA and NSF proposal review panels; peer review for leading atmospheric science journals; and invited presentations on artificial intelligenceenabled environmental prediction, wildfire-smoke modeling, and Earth system predictability.

Education

Postdoctoral Research, Atmospheric Sciences, Desert Research Institute
Ph.D., Atmospheric Sciences, University of Nevada, Reno

Keywords

Artificial Intelligence, Machine Learning, Deep Learning, Physics-Informed Artificial Intelligence, Physics-Informed Machine Learning, Hybrid AI–Physics Modeling, Digital Twin Frameworks, Hierarchical Modeling, Probabilistic Modeling, Probabilistic Forecasting, Multi-Source Environmental Data Fusion, Data Assimilation, Multiscale Physical Modeling, Satellite Remote Sensing, Earth Observation, Environmental Intelligence, Geospatial Intelligence, High-Dimensional Environmental Data Analytics, High-Performance Computing, Uncertainty Quantification, Bias Correction, Model Calibration, Model Evaluation, Model Validation, Atmospheric Modeling, Fire–Weather Modeling, Air-Quality Modeling, Earth System Modeling, Coupled Fire–Atmosphere Modeling, Wildfire Prediction, Wildfire Behavior, Fire Emissions, Smoke Emissions, Smoke Transport, Smoke Exposure Assessment, Smoke Risk Assessment, Prescribed Fire, Biomass Burning, Aerosols, Atmospheric Composition, Aerosol–Cloud–Radiation Interactions, Air Quality, Background Ozone, PM2.5, Climate-Related Hazards, Environmental Extremes, Vegetation Greenness, Vegetation Health, Humidity Variability, Drought, Land–Atmosphere Interactions, Decision-Support Systems, Research-to-Application Frameworks.