Research Interests

My research centers on developing spatiotemporal methodologies for the analysis and prediction of extreme weather events, such as dust storms, hurricanes, and extreme heat. Specifically, my research seeks to 1) understand the spatiotemporal dynamics of extreme weather events, 2) explore the relationship of these events with other physical and social factors, and 3) integrate heterogeneous data to enhance the predictability, response, and mitigation of extreme weather events.

Recent News

Sep 28, 2023. I gave a talk on “Spatiotemporal methodologies for extreme weather studies” at the CPGIS Educational Talk Series Fall 2023. [Youtube Link]

Sep 26, 2023. I’m organizing and moderating a webinar session on Digital Twins: Air Quality Modeling, featuring Dr. Mohammad Pourhomayoun from CALIFORNIA STATE UNIVERSITY, LOS ANGELES, who shares insights on using AI/ML to predict what we breathe; and Dr. Wenfu Tang from National Center for Atmospheric Research (NCAR), who presents the recent development Multi-Scale Infrastructure for Chemistry Modeling (MUSICA).

Apr 1, 2023. Funded project “Forest biodiversity modeling through the synthesis of hyperspectral, LiDAR, and tree inventories within a deep learning framework” by Penn State Institute for Computational and Data Sciences (ICDS) as Co-PI.

May 10, 2022. I was awarded E. Willard and Ruby S. Miller Faculty Fellow for 2022-2027 by Penn State College of Earth and Mineral Sciences.

Apr 1, 2022 Funded project “Integrating low-cost sensors and human mobility into air pollution exposure modeling.” by IEE-ICDS as PI.

Apr 1, 2022 Funded project “Facilitating environmental investigations employing a single column model” by Penn State Institutes of Energy and the Environment as Co-PI

Mar 1, 2022. I chaired the session “Integrating Earth observations, Internet of Things, and simulations to enhance air quality prediction across scales” at AAG Virtual Annual Meeting 2022.

Dec 22, 2021. Dr. Arif Masrur successfully defended his dissertation “Spatio-temporally Interpretable Geo-AI Approaches for Predictive Modeling of Geographic Events”.

Sep 16, 2021. I presented our work on “Producing high-resolution nitrogen dioxide measurements on an hourly basis using neural networks” at the 3rd NOAA AI Workshop.

August 4, 2021. Our new paper, Arif’s second dissertation work, “Interpretable machine learning for analyzing heterogeneous drivers of geographic events in space-time” was published in the International Journal of Geographical Information Science.

April 14, 2021. Penn State News about our paper “Deep learning-based downscaling of tropospheric nitrogen dioxide using ground-level and satellite observations” featured in the IEE newsletter.

April 10, 2021. Ph.D. student Arif Masrur won first place at the Robert Raskin Student Competition 2021, hosted by AAG CISG. Presented work on “Multi-scale machine learning for interpreting spatiotemporally heterogeneous drivers of geographic events”.

April 7, 2021. I presented our work on “Deep learning-based downscaling of tropospheric nitrogen dioxide using ground-level and satellite observations” at the AAG Virtual Annual Meeting 2021.

March 30, 2021. Latest paper “Deep learning-based downscaling of tropospheric nitrogen dioxide using ground-level and satellite observations” reported by Penn State News. Click here for the publication and the green open access preprint.

Feb 16, 2021. New paper “Deep learning-based downscaling of tropospheric nitrogen dioxide using ground-level and satellite observations” published in Science of The Total Environment. Click here for the publication and the green open access preprint.