Prof. Maxwell

I am currently an Assistant Professor in the Department of Geology and Geography at West Virginia University. I teach geospatial science courses for both undergraduate and graduate students. I am also the director of West Virginia View, a consortium of public, private, and non-profit remote sensing organizations in West Virginia, and a faculty director of the West Virginia GIS Technical Center. Prior to coming to West Virginia University, I was an Assistant Professor at Alderson Broaddus University. Prior to teaching, I worked as a Remote Sensing Analyst at the Natural Resource Analysis Center (NRAC) at West Virginia University.

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.

The primary objectives of my work are to investigate computational methods to extract useful information from geospatial data to make informed decisions and to train students to be effective and thoughtful geospatial scientists and professionals.

Prof. Maxwell

CV

WVU Geol. and Geog.

WVGISTC


Projects

  • Best practices for assessing deep learning output in remote sensing
  • Forest fuel load estimation with terrestrial LiDAR and machine learning regression
  • Deep learning semantic segmentation applied to historic topographic maps
  • Accuracy assessment using uncertain feature boundaries
  • Slope failure probabilistic mapping using LiDAR and random forests machine learning
  • Extracting geomorphic features from LiDAR data using deep learning
  • Forest type mapping using machine learning, time series data, and terrain variables
  • Large area, high spatial resolution land cover for the entire state of West Virginia using NAIP orthophotography, GEOBIA, and machine learning
  • Probabilistic wetland mapping using digital terrain data
  • Review of the the use of NAIP orthophotography in classification and feature extraction tasks
  • Surface mine mapping using multispectral data, LiDAR, and machine learning

Teaching

  • Geography 350/550: Introduction to GIScience
  • Geography 455/655: Introduction to Remote Sensing
  • Geography 456: Remote Sensing Applications
  • Geography 457/657: Open-Source Spatial Analytics
  • Geography 461/661: Client-Side Web GIS
  • Geography 462/662: Digital Cartography
  • Geography 520: Methods in Open Science

Research Interest

  • Spatial predictive modeling (classification and probabilistic prediction)
  • Accuracy assessment of remote sensing products
  • Application of machine learning, deep learning, and convolutional neural networks (CNNs) in the geospatial sciences
  • Deep learning semantic segmentation and object detection
  • Digital terrain analysis and LiDAR
  • Geographic object-based image analysis (GEOBIA)
  • High spatial resolution land cover mapping and assessment
  • Geomorphic mapping and modeling
  • Wetland and forest type classification

Graduate Students

  • Sarah Farhadpour (Geography PhD): TBD
  • Muhammad Ali (Geology PhD): TBD
  • Sara Lusher (Geography MA): TBD
  • Shannon Maynard (Geology MS): TBD
  • David Coleman (Geography MA): Accuracy Assessment of Deep Learning-Derived Building Footprints
  • Faith Hartley (Geography MA, completed): Using Landsat-Based Phenology Metrics, Terrain Variables, and Machine Learning for Mapping and Probabilistic Prediction of Forest Community Types in West Virginia
  • Jaimee Pyron (Geography MA, completed): Wetland mapping using machine learning, Sentinel-1, and digital terrain data
  • Caleb Malay (Geography MA, completed): Comparison of slope failure predictive models in different physiographic regions
  • Hartford Johnson (Geography MA, completed): Assessing fire recovery in California using time series analysis and the Landsat data archive

Publications

  1. Warner, T.A., Miller, T.A., La Puma, I.P., Nolan, L.A., Skowronski, N.S., and Maxwell, A.E., 2022. Exploring golden eagle habitat preference using lidar-based canopy bulk density. Remote Sensing Letters, 13(6), 556-567. https://doi.org/10.1080/2150704X.2022.2055985
  2. Maxwell, A.E. and C.M. Shobe, 2022. Land-surface parameters for spatial predictive mapping and modeling, Earth Science Reviews, 226: 103944. https://doi.org/10.1016/j.earscirev.2022.103944.
  3. Maxwell, A.E., M. Sharma, and K.A. Donaldson, 2021. Explainable boosting machines for slope failure spatial predictive modeling, Remote Sensing, 13(24): 4991. https://doi.org/10.3390/rs13244991.
  4. Gallagher, M.R., A.E. Maxwell, L.A. Guillen, A. Everland, E.L. Loudermilk, and N.S. Skowronski, 2021. Estimation of plot-level burn severity using terrestrial laser scanning, Remote Sensing, 13(20): 4168. https://doi.org/10.3390/rs13204168.
  5. Cribari, V., M.P. Strager, A.E. Maxwell, and C. Yuill, 2021. Landscape changes in the southern coalfields of West Virginia: Multi-level intensity analysis and surface mining transitions in the headwaters of the Coal River from 1976 to 2016, Land, 10(7): 748. https://doi.org/10.3390/land10070748.
  6. Maxwell, A.E., T.A. Warner, and L.A. Guillen, 2021. Accuracy assessment in convolutional neural network-based deep learning remote sensing studies – Part 2: Recommendations and best practices, Remote Sensing, 13(13): 2591. https://doi.org/10.3390/rs13132591
  7. Maxwell, A.E., T.A. Warner, and L.A. Guillen, 2021. Accuracy assessment in convolutional neural network-based deep learning remote sensing studies – Part 1: Literature review, Remote Sensing, 13(13): 2450. https://doi.org/10.3390/rs13132450
  8. Maxwell, A.E., M. Sharma, J.S. Kite, K.A. Donaldson, S.M. Maynard, and C.M. Malay, 2021. Assessing the generalization of machine learning-based slope failure prediction to new geographic extents, ISPRS International Journal of Geo-Information, 10(5): 293. https://doi.org/10.3390/ijgi10050293.
  9. Higgins, A.K. and A.E. Maxwell, 2021. Universal design for learning in the geosciences for access and equity in our classrooms, The Journal of Applied Instructional Design, 10(1).
  10. Ramezan, C.A., T.A. Warner, A.E. Maxwell, and B.S. Price, 2021. Effects of training set size on supervised machine-learning land-cover classification of large-area high-resolution remotely sensed data, Remote Sensing, 13(3): 368. https://doi.org/10.3390/rs13030368.
  11. Maxwell, A.E., M.S. Bester, L.A. Guillen, C.A. Ramezan, D.J. Carpinello, Y. Fan, F.M. Hartley, S.M. Maynard, and J.L. Pyron, 2020. Semantic segmentation deep learning for extracting surface mine extents from historic topographic maps, Remote Sensing, 12(24): 4145. https://doi.org/10.3390/rs12244145.
  12. Maxwell, A.E., and T.A. Warner, 2020. Thematic classification accuracy assessment with inherently uncertain boundaries: an argument for center-weighted accuracy assessment metrics, Remote Sensing, 12(12): 1905. https://doi.org/10.3390/rs12121905.
  13. Fang, F., B.E. McNeil, T.A. Warner, A.E. Maxwell, G.A. Dahle, E. Eutsler, and J. Li. 2020. Discriminating tree species at different taxonomic levels using multi-temporal WorldView-3 imagery in Washington D.C., USA, Remote Sensing of Environment, 246: 111811. https://doi.org/10.1016/j.rse.2020.111811.
  14. Maxwell, A.E., P. Pourmohammadi, and J. Poyner, 2020. Mapping the topographic features of mining-related valley fills using mask R-CNN deep learning and digital elevation data, Remote Sensing, 12(3): 547. https://doi.org/10.3390/rs12030547.
  15. Maxwell, A.E., M. Sharma, J.S. Kite, K.A. Donaldson, J.A. Thompson, M.L. Bell, and S.M. Maynard, 2020. Slope failure prediction using random forest machine learning and LiDAR in an eroded folded mountain belt, Remote Sensing, 12(3): 486. https://doi.org/10.3390/rs12030486.
  16. Maxwell, A.E., M.P. Strager, T.A. Warner, C.A. Ramezan, A.N. Morgan, and C.E. Pauley, 2019. Large-area, high spatial resolution land cover mapping using random forests, GEOBIA, and NAIP orthophotography: findings and recommendations, Remote Sensing, 11(12): 1409. https://doi.org/10.3390/rs11121409.
  17. Ramezan, C.A., T.A. Warner, and A.E. Maxwell, 2019. Evaluation of sampling and cross-validation tuning strategies for regional-scale machine learning classification, Remote Sensing, 11(2): 185. https://doi.org/10.3390/rs11020185.
  18. Maxwell, A.E., and T.A. Warner, 2019. Is high spatial resolution DEM data necessary for mapping palustrine wetlands?, International Journal of Remote Sensing, 40(1): 118-137. https://doi.org/10.1080/01431161.2018.1506184.
  19. Fang, F., McNeil, B.E., Warner, T.A., and A.E. Maxwell, 2018. Combining high spatial resolution multi-temporal satellite data with leaf-on LiDAR to enhance tree species discrimination at the crown-level, International Journal of Remote Sensing, 39(23): 9054-9072. https://doi.org/10.1080/01431161.2018.1504343.
  20. Maxwell, A.E., T.A. Warner, and F. Fang, 2018. Implementation of machine learning classification in remote sensing: an applied review, International Journal of Remote Sensing, 39(9): 2784-2817. https://doi.org/10.1080/01431161.2018.1433343.
  21. Liebermann, H., J. Schuler, M.P. Strager, and A. Maxwell, 2018. A work flow and evaluation of using unmanned aerial systems for deriving forest stand characteristics in mixed hardwoods of West Virginia, Geospatial Applications in Natural Resources, 2(1): 23-53.
  22. Maxwell, A.E., T.A. Warner, B.C. Vanderbilt, and C.A. Ramezan, 2017. Land cover classification and feature extraction from National Agriculture Imagery Program (NAIP) orthoimagery: A Review, Photogrammetric Engineering & Remote Sensing, 83(11): 737-747. https://doi.org/10.14358/PERS.83.10.737.
  23. Strager, M.S., M. Thomas-Van Gundy, A.E. Maxwell, 2016. Predicting post-fire change in the Central Appalachians from remotely-sensed data, Geospatial Applications in Natural Resources, 1(2): 1-17.
  24. Maxwell, A.E., T.A. Warner, and M.P. Strager, 2016. Predicting palustrine wetland probability using random forest machine learning and digital elevation data-derived terrain variables, Photogrammetric Engineering & Remote Sensing, 82(6): 437-447. https://doi.org/10.14358/PERS.82.6.437.
  25. Maxwell, A.E., and T.A. Warner, 2015. Differentiating mine-reclaimed grasslands from spectrally similar land cover using terrain variables and object-based machine learning classification, International Journal of Remote Sensing, 36(17): 4384-4410. https://doi.org/10.1080/01431161.2015.1083632.
  26. Maxwell, A.E., T.A. Warner, M.P. Strager, J.F. Conley, and A.L. Sharp, 2015. Assessing machine learning algorithms and image- and LiDAR-derived variables for GEOBIA classification of mining and mine reclamation, International Journal of Remote Sensing, 36(4): 954-978. https://doi.org/10.1080/01431161.2014.1001086.
  27. Merriam, E.R., J.T. Petty, M.P. Strager, A.E. Maxwell, and P.F. Ziemkiewicz, 2015. Complex contaminant mixtures in multi-stressor Appalachian riverscapes, Environmental Toxicology and Chemistry, 34(11): 2603-2610.
  28. Merriam, E.R., J.T. Petty, M.P. Strager, A.E. Maxwell, and P.F. Ziemkiewicz, 2015. Landscape-based cumulative effects models for predicting stream response to mountaintop mining in multi-stressor Appalachian watersheds, Freshwater Science, 34(3): 1006-1019.
  29. Strager, M.P., J.M. Strager, J.S. Evans, J.K. Dunscomb, B.J. Kreps, and A.E. Maxwell, 2015. Combining a spatial model and demand forecasts to map future surface coal mining in Appalachia, PLoS ONE, 10(6): e0128813.10.1371/journal.pone.0128813.
  30. Maxwell, A.E., M.P. Strager, T.A. Warner, N.P. Zégre, and C.B. Yuill, 2014. Comparison of NAIP orthophotography and RapidEye satellite imagery for mapping of mining and mine reclamation, GIScience & Remote Sensing, 51(3): 301-320. https://doi.org/10.1080/15481603.2014.912874.
  31. Zegre, N., A. Miller, A. Maxwell, and S. Lamont, 2014. Multi-scale analysis of hydrology in a mountaintop mine-impacted watershed, Journal of the American Water Resources Association, doi: 10.1111/jawr.12184.
  32. Maxwell, A.E., T.A. Warner, M.P. Strager, and M. Pal, 2014. Combining RapidEye satellite imagery and LiDAR for mapping of mining and mine reclamation, Photogrammetric Engineering & Remote Sensing, 80(2): 179-189. https://doi.org/10.14358/PERS.80.2.179-189.
  33. Pal, M., A.E. Maxwell, and T.A. Warner, 2013. Kernel-based extreme learning machine for remote-sensing image classification, Remote Sensing Letters, 4(9): 853-862. https://doi.org/10.1080/2150704X.2013.805279.
  34. Merriam, E.R., J.T. Petty, M.P. Strager, A.E. Maxwell, and P.F. Ziemkiewicz, 2013. Scenario analysis predicts context-dependent stream response to landuse change in a heavily mined central Appalachian watershed, Freshwater Science, 32(4): 1246-1259.
  35. Zegre, N., A. Maxwell, and S. Lamont, 2013. Characterizing streamflow response of a mountaintop-mined watershed to changing land use, Applied Geography, 39: 5-15.
  36. Maxwell, A.E., and M.P. Strager, 2013. Assessing landform alterations induced by mountaintop mining, Natural Science, 5(2A): 52A034. http://dx.doi.org/10.4236/ns.2013.52A034.
  37. Maxwell, A.E., M.P. Strager, C.B. Yuill, and J.T. Petty, 2012. Modeling critical forest habitat in the Southern Coal Fields of West Virginia, International Journal of Ecology, Volume 2012, Article ID 182683, 10 pages.