
Aaron Maxwell
Geospatial Teaching and Research

e-mail: Aaron.Maxwell@mail.wvu.edu or maxwellgeospatial@gmail.com
Phone: (304) 293-2026
Office:
Brooks Hall Room 141
West Virginia University
My interests include:
Spatial analysis
Image classification
Object-based image analysis
Machine learning
Geospatial education
Education through travel
​
​
About
I am currenlty an Assistant Professor of Geography in the Department of Geology and Geography at West Virginia University. I teach mainly geospatial and physical geography courses for both undergraduates and graduates.
Prior to coming to West Virginia University, I was an Assistant Professor at Alderson Broaddus University. As AB is primarily a teaching institution, I taught a wide variety of coursework related to GIS/remote sensing, environmental science, and geology.
​
Prior to teaching, I worked as a Remote Sensing Analyst at the Natural Resource Analysis Center (NRAC) at West Virginia University. There I was tasked with mapping and geospatial modeling tasks related to natural resource management.
I am a graduate of Alderson Broaddus where I received bachelor degrees in biology, chemistry, and environmental science. I then attended West Virginia University where I earned a master degree in geology followed by a PhD in geology. I also hold a geographic information systems professional (GISP) certification from the GIS Certification Institute.
I am a native of West Virginia. I grew up in Preston County, where my parents still live. I have a twin sister, who is a school teacher in Morgantown, WV and a younger brother, who is a software engineer in Charleston, WV.
​
My research interests include land cover mapping, machine learning, LiDAR, image analysis, geomorphology, and landscape change. I am also very interested in geospatial education and effective teaching techniques.
​
Current Research Projects
-
Statewide object-based land cover mapping in West Virginia
-
Mapping forest types using spectral and terrain data
-
Mapping wetlands with spectral and terrain data using machine learning
-
Modeling fire induced forest canopy loss
-
Slope failure predictions using machine learning
Past Projects
​
-
Importance of DEM source for wetland mapping
-
Practical considerations when using machine learning for remote sensing image classification
-
Review of NAIP orthophotography for land cover mapping
-
Land cover mapping of Preston County, WV using object-based image analysis, mulitple data sets, and machine learning
-
Land cover mapping in the southern coalfields of West Virginia using RapidEye satellite data and LiDAR
-
Mapping forest stand types in the Monongahelia National Forest
-
Wetland topographic probabalistic modeling using random forests
-
Separating mine reclamation from spectrally similar cover types using terrain characteristics