Ahmed Khan Salman
(Postdoctoral Research Scientist)
| Email: | ahmedkhan.salman@nasa.gov |
| Org Code: | |
| Address: |
NASA/GSFC Mail Code 618 Greenbelt, MD 20771 |
| Employer: | EARTH RESOURCES TECHNOLOGY, INC. |
Brief Bio
Dr. Ahmed Khan Salman is a Postdoctoral Research Scientist with GESTAR II at NASA Goddard Space Flight Center. His research combines satellite remote sensing, ground-based observations, atmospheric modeling, and deep learning to advance aerosol and air-quality science for applied and public-health applications. At GSFC, Dr. Salman develops data-driven methods for aerosol retrieval, PM2.5 estimation, cloud screening, wildfire-smoke applications, and foundation-model-based air-quality modeling. His work emphasizes multi-sensor data fusion, satellite validation, explainable AI, and uncertainty quantification to support decision-relevant Earth science.
Before joining GSFC, Dr. Salman worked with NASA SERVIR at NASA Marshall Space Flight Center, supporting air-quality and health applications across SERVIR regional hubs. His work included preparing SERVIR closure report for air-quality activities, AWS-based workflow development, and planning for high-spatiotemporal satellite downscaling applications. During his Ph.D. research at the University of Houston, Dr. Salman worked on applied atmospheric modeling projects supported by the NASA Aura Science Team, the National Institute of Environmental Research, and the Korean Meteorological Administration. His doctoral work developed deep-learning methods for CMAQ emulation, inverse modeling, ozone forecasting, explainability, uncertainty quantification, and physics-informed atmospheric transport modeling.
Current Projects
HAQAST: Satellite-Based Aerosol and PM2.5 Estimation over Africa
Aerosol Remote Sensing and Modeling
Develops machine-learning workflows for aerosol optical depth and PM2.5 estimation over Africa using MTG-I FCI observations, surface albedo, cloud-screening information, meteorology, and AERONET observations. This work supports applied air-quality product development for regions with sparse ground monitoring.
AERONET: Cloud Screening and Quality Control
Aerosols & Clouds
Develops machine-learning-based cloud classification and quality-control methods using AERONET observations. The goal is to improve cloud screening at nighttime and support the reliability of aerosol retrieval and satellite-validation datasets.
Prithvi-Guided Nowcasting of Wildfire-Smoke PM2.5 over CONUS
Air Quality
Develops an approximately 2 km hourly probabilistic framework for wildfire-smoke PM2.5 nowcasting over CONUS. The project integrates HRRR-Smoke, GOES-R ABI, TEMPO, and ground-based PM2.5 observations, while leveraging Prithvi WxC and Prithvi EO foundation models for meteorological and satellite feature representation.
Research Interests
Machine Learning for Atmospheric Composition and Air Quality
Earth Science: Air QualityMachine learning, deep learning, and foundation models for satellite remote sensing of air quality; aerosol optical depth retrieval; PM2.5 estimation; wildfire-smoke nowcasting; AERONET cloud screening and quality control; multi-sensor data fusion; explainable AI; uncertainty quantification; and physics-informed machine learning.
Positions/Employment
Postdoctoral Research Scientist
GESTAR II - NASA GSFC - Greenbelt, MD
July 2025 - Present
Associate Scientist
USRA - NASA MSFC - Huntsville, AL
January 2025 - July 2025
Research Assistant
University of Houston - Houston, TX
January 2020 - December 2024
Teaching Experience
Teaching Assistant
University of Houston, Department of Earth and Atmospheric Sciences
January 2021 – May 2022
- Supported instruction for Deep Learning for Big Data Analytics and Global Climate Change.
- Facilitated deep-learning labs and developed Python-based instructional materials.
- Guided student class projects, grading, and academic inquiries.
Education
Ph.D., Atmospheric Sciences, University of Houston
M.S., Mechanical Engineering, University of Houston
B.E., Mechanical Engineering, Rajiv Gandhi Proudyogiki Vishwavidyalaya, India
Professional Service
Guest Editor
Special Issue: “Advances in Deep Learning for Air Pollution and Climate Science Research”
AI, MDPI (2026–2027)
Guest Editor Assistant
Special Issue: “Advances in Machine Learning Algorithms for Atmospheric Remote Sensing”
Remote Sensing, MDPI (2025–2026)
Publications
Refereed
2026. "Jacobian-regularized emulator for NOx emissions over the contiguous United States.", Atmospheric Environment, 382 122227 [10.1016/j.atmosenv.2026.122227] [Journal Article/Letter]
2026. "Advances in air quality modeling through artificial intelligence, machine learning, and deep learning: A comprehensive review.", Science of The Total Environment, 1021 181593 [10.1016/j.scitotenv.2026.181593] [Journal Article/Letter]
2025. "Forecasting PM2.5 and Assessing Health Impacts in Texas Using Advanced Deep Learning Models.", Earth Systems and Environment, 10 (1): 819-840 [10.1007/s41748-025-00634-x] [Journal Article/Letter]
2025. "Temporal CNN-based 72-h ozone forecasting in South Korea: Explainability and uncertainty quantification.", Atmospheric Environment, 343 120987 [10.1016/j.atmosenv.2024.120987] [Journal Article/Letter]
2024. "AGATNet: An Adaptive Graph Attention Network for Bias Correction of CMAQ‐Forecasted PM2.5 Concentrations Over South Korea.", Journal of Geophysical Research: Machine Learning and Computation, 1 (3): e2024JH000244 [10.1029/2024jh000244] [Journal Article/Letter]
2024. "Deep-BCSI: A deep learning-based framework for bias correction and spatial imputation of PM2.5 concentrations in South Korea.", Atmospheric Research, 301 107283 [10.1016/j.atmosres.2024.107283] [Journal Article/Letter]
2024. "A 1D CNN-Based Emulator of CMAQ: Predicting NO2 Concentration over the Most Populated Urban Regions in Texas.", Artificial Intelligence for the Earth Systems, 3 (2): [10.1175/aies-d-23-0055.1] [Journal Article/Letter]
2024. "Deep learning based emulator for simulating CMAQ surface NO2 levels over the CONUS.", Atmospheric Environment, 316 120192 [10.1016/j.atmosenv.2023.120192] [Journal Article/Letter]
2023. "Spatiotemporal estimation of TROPOMI NO2 column with depthwise partial convolutional neural network.", Neural Computing and Applications, 35 (21): 15667-15678 [10.1007/s00521-023-08558-1] [Journal Article/Letter]
2023. "Development of Deep Convolutional Neural Network Ensemble Models for 36-Month ENSO Forecasts.", Asia-Pacific Journal of Atmospheric Sciences, 59 (5): 597-605 [10.1007/s13143-023-00319-3] [Journal Article/Letter]
2023. "A Deep Convolutional Neural Network Model for Improving WRF Simulations.", IEEE Transactions on Neural Networks and Learning Systems, 34 (2): 750-760 [10.1109/tnnls.2021.3100902] [Journal Article/Letter]
2022. "Deep learning solver for solving advection–diffusion equation in comparison to finite difference methods.", Communications in Nonlinear Science and Numerical Simulation, 115 106780 [10.1016/j.cnsns.2022.106780] [Journal Article/Letter]
2022. "CNN-based model for the spatial imputation (CMSI version 1.0) of in-situ ozone and PM2.5 measurements.", Atmospheric Environment, 289 119348 [10.1016/j.atmosenv.2022.119348] [Journal Article/Letter]
2021. "Application of a Partial Convolutional Neural Network for Estimating Geostationary Aerosol Optical Depth Data.", Geophysical Research Letters, 48 (15): e2021GL093096 [10.1029/2021gl093096] [Journal Article/Letter]
2021. "A novel CMAQ-CNN hybrid model to forecast hourly surface-ozone concentrations 14 days in advance.", Scientific Reports, 11 (1): 10891 [10.1038/s41598-021-90446-6] [Journal Article/Letter]
2021. "Bias correcting and extending the PM forecast by CMAQ up to 7 days using deep convolutional neural networks.", Atmospheric Environment, 253 118376 [10.1016/j.atmosenv.2021.118376] [Journal Article/Letter]
2021. "Estimating daily high-resolution PM2.5 concentrations over Texas: Machine Learning approach.", Atmospheric Environment, 247 118209 [10.1016/j.atmosenv.2021.118209] [Journal Article/Letter]
2020. "Using wavelet transform and dynamic time warping to identify the limitations of the CNN model as an air quality forecasting system.", Geoscientific Model Development, 13 (12): 6237-6251 [10.5194/gmd-13-6237-2020] [Journal Article/Letter]
2019. "A data ensemble approach for real-time air quality forecasting using extremely randomized trees and deep neural networks.", Neural Computing and Applications, 32 (11): 7563-7579 [10.1007/s00521-019-04287-6] [Journal Article/Letter]