Funded Projects

The main objectives of this project are: 1) to generate a vulnerability map in BHF based on the dryness potential using elevation and spectral canopy index, such as the normalized difference vegetation index (NDVI), and 2) to evaluate the impact of past instances of flooding and drought events on the growth and physiological performance of mature trees of red oak species differing in flood tolerance, and relate tree performance to expected future climate.

Project team members: Marco Yáñez (PI) with Hamdi A. Zurqani and Benjamin A. Babst (Co-PIs)

Funds:

Southeast Climate Adaptation Science Center (SE CASC), USA. 08/01/2024-07/31/2026, $124,779$$$

Research Outcomes:

Coming soon!

This study presents a case study of the first generation of the Forest Canopy Cover (FCC) dataset at a spatial resolution of 1 meter using a high-resolution aerial imagery dataset on the Google Earth Engine (GEE) platform. 

Project team members: Hamdi A. Zurqani (PI)

Funds:

Financial support for this project was provided by the University of Arkansas Agricultural Experiment Station, the Research Incentive Grant Award (DS77512-UADA-AES-UAMF-RIG). 06/01/2023-05/31/2025, $29,948$$$

Research Outcomes:

Note: Students' names are denoted with an asterisk (i.e., Student Name*)

Articles:

• INVITED: Zurqani, H.A. 2024. An Automated Approach for Developing a Regional-Scale 1-m Forest Canopy Cover Dataset Using Machine Learning and Google Earth Engine Cloud Computing Platform. Software Impacts, 19, p.100607.

• INVITED: Zurqani, H.A. 2024. The First Generation of a Regional-Scale 1-m Forest Canopy Cover Dataset Using Machine Learning and Google Earth Engine Cloud Computing Platform: A Case Study of Arkansas, USA. Data in Brief, 52, p.109986.

• Zurqani, H.A. 2024. High-Resolution Forest Canopy Cover Estimation in Ecodiverse Landscape Using Machine Learning and Google Earth Engine: Validity and Reliability Assessment. Remote Sensing Applications: Society and Environment, 33, p.101095.

Conference Proceedings:

• Subedi*, P.B., and H.A., Zurqani. 2025. Estimating Above Ground Forest Biomass Using High-Resolution NAIP Imagery, Machine Learning, and Google Earth Engine. In 2024 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS), Surabaya, Indonesia, 2024, Dec 13–14, 2024.

• H.A. Zurqani. 2023. Using Machine Learning and Google Earth Engine to Develop A High-Resolution Forest Canopy Cover Dataset: A Case Study in Arkansas, USA. IGARSS 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 2023, pp. 3074–3077, doi:10.1109/IGARSS52108.2023.10283140.

Abstracts and Posters:

• • Subedi*, P.B., and H.A., Zurqani. 2025. Estimating Above Ground Forest Biomass Using High-Resolution NAIP Imagery, Machine Learning, and Google Earth Engine. Session: D1S3: GIS and City Development from Fri, December 13, 2024 14:00 WITA until 17:00 (3rd paper) In 2024 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS), Surabaya, Indonesia, 2024, Dec 13–14, 2024.

  • Subedi*, P.B., H.A., Zurqani, M.A., Blazier, M., Yanez, and K. Cunningham. 2024. Comparison of Supervised Machine Learning Algorithms for Extracting Tree Canopy Cover Using High-Resolution Imagery and Google Earth Engine. The Society of American Foresters (SAF) National Convention. Loveland, Colorado, September 17–20, 2024.

  • Adedapo*, S.M., H.A., Zurqani, M.A., Blazier, J. McAlpine, and K. Cunningham. 2024. Early Detection of Pine Disease in Southeast US Forests: A Deep Learning Approach Using UAV Imagery. The 2024 International Conference on Smart Computing, IoT and Machine Learning (SIML), Surakarta, Indonesia, 2024, pp. 256-261, doi: 10.1109/SIML61815.2024.10578138. (Conference Proceeding) "Won the presentation award".

  • Subedi*, P.B., H.A., Zurqani, M.A., Blazier, M., Yanez, and K. Cunningham. 2023. Using Machine Learning and Google Earth Engine to Enhance the Forest Canopy Cover Analysis and Individual Tree-Crown Detection. The 14th Southern Forestry and Natural Resource Management GIS conference (SOFOR GIS), Athens, Georgia, December 11–12, 2023.

  • H.A. Zurqani. 2023. Using Machine Learning and Google Earth Engine to Develop A High-Resolution Forest Canopy Cover Dataset: A Case Study in Arkansas, USA. The 43rd annual International Geoscience and Remote Sensing Symposium, Session: TUP.P19: Forest and Vegetation Mapping Through Machine Learning Methods II, Paper TUP.P19.4., Pasadena, CA, July 16–21, 2023.

This project aims to provide a remote sensing integrated approach that can substantially improve the resolution and accuracy of the classifications of emergent marsh within the study area and will demonstrate the energetic value of emergent marsh wetlands for waterfowl.

Project team members: Hamdi A. Zurqani (PI) with Osborne Douglas and Ryan Askren (Co-PIs)

Funds:

This project is funded by the Lower Mississippi Valley Joint Venture (F23AC02581-00-UADA-AES-UAMF-USFWS). 08/02/2023-08/01/2025, $51,153$$$

Research Outcomes:

Note: Students' names are denoted with an asterisk (i.e., Student Name*)

Conference Proceedings:

• Ogwo*, C.M., H.A., Zurqani, D.C., Osborne, A., Ryan, and A., Mini. 2025. Deep Learning-Based Wetland Vegetation Classification: The Impact of Spectral and Spatial Features. In 2024 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS), Surabaya, Indonesia, 2024, Dec 13–14, 2024.

Abstracts and Posters:

• • Ogwo*, C.M., H.A., Zurqani, D.C., Osborne, A., Ryan, and A., Mini. 2025. Deep Learning-Based Wetland Vegetation Classification: The Impact of Spectral and Spatial Features. Session: D2S4: Geoscience and Hazard Modeling from Sat, December 14, 2024 15:00 WITA until 17:00 (2nd paper)  In 2024 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS), Surabaya, Indonesia, 2024, Dec 13–14, 2024.

The aim of this project is to help NWR staff better understand the effects of the drawdown to support adaptive management using new technology, partnerships, and leverage.

Project team members: Hamdi A. Zurqani (PI) with Douglas C. Osborne (Co-PI)

Funds:

This project is funded by the U.S. Fish and Wildlife Service (F23AC02581-00-UADA-AES-UAMF-USFWS). 08/15/2023-12/31/2024, $32,000$$$

Research Outcomes:

Note: Students' names are denoted with an asterisk (i.e., Student Name*)

Book Chapter:

• Schroyer, K.A., H.A. Zurqani, S. Rimer, H.M. Hagy, R. J. Askren, and D.C. Osborne. 2024. A New Era for Wetland Monitoring: Exploring Remote Sensing Options for Monitoring Wetland Vegetation Communities. In Geospatial Artificial Intelligence in Environmental and Natural Resources Management. Earth and Environmental Sciences Library. Switzerland. Springer International Publishing AG. (In press).

This project aims to help the National Wildlife Refuge (NWR) staff better understand the effects of the drawdown and inform the timing and frequency of this practice in the future.

Project team members: Hamdi A. Zurqani (PI) with Douglas C. Osborne (Co-PI)

Funds:

This project is funded by the U.S. Fish and Wildlife Service (F22AC03106-UADA-AES-UAMF-FWA). 08/15/2022-12/31/2024, $24,000$$$

Research Outcomes:

Note: Students' names are denoted with an asterisk (i.e., Student Name*)

Unpublished Report - (Public Release Version):

• Hagy, H., K. Schroyer*, G. Wilkerson, P. Stinson, B. Fortier, and J. Wortham. 2023. Midwinter Aerial Waterfowl Surveys on National Wildlife Refuges in the Southeast, 2023. U.S. Fish and Wildlife Service Report. https://ecos.fws.gov/ServCat/Reference/Profile/157221.

Abstracts and Posters:

• • Schroyer*, K.A., H.A. Zurqani, S. Rimer, H.M. Hagy, and D.C. Osborne. 2023. Modeling Vegetation Community Change and Analyzing Waterbird Use During a Drawdown on Big Lake National Wildlife Refuge. 2023: Five Oaks Research Symposium.

  • Schroyer*, K.A., H.A. Zurqani, S. Rimer, H.M. Hagy, and D.C. Osborne. 2022. Waterbird and Vegetation Response to the Drawdown of Big Lake National Wildlife Refuge. Lower Mississippi Valley Joint Venture Waterfowl Symposium, 2022.

This research project involves sampling and analyzing soils from green-tree reservoirs in the Lower Mississippi Alluvial Valley, followed by modeling using various digital soil mapping (DSM) techniques to develop a robust approach capable of estimating soil properties at unsampled locations.

Project team members: Hamdi A. Zurqani (PI) with Robert Ficklin and Osborne C. Douglas (Co-PIs)

Funds:

This project is funded by the Five Oaks Agriculture Research and Education Center (DS18849-UADA-AES-UAMF-Five Oaks) in partnership with the University of Arkansas at Monticello, College of Forestry Agriculture and Natural Resources (CC001251-UAM-CFANR). The project is scheduled to run from 07/01/2022 to 06/30/2024 with a total fund of ($114,304$$$) from FoAgREC. Besides, the UAM-CFANR is contributing ($180,000$$$), which includes funding for two graduate assistants and one program technician. This brings the total funding amount to ($294,304$$$).

Research Outcomes:

Note: Students' names are denoted with an asterisk (i.e., Student Name*)

Research Articles:

• Adedapo*, S.M., and H.A. Zurqani. 2024. Evaluating the Performance of Various Interpolation Techniques on Digital Elevation Models in Highly Dense Forest Vegetation Environment. Ecological Informatics, 81, 102646.

Conference Proceedings:

• Adedapo*, S.M., H.A., Zurqani, R.L., Ficklin, and D.C., Osborne. 2024. Applications of Machine Learning Techniques in Predicting Selected Soil Properties in Lower Mississippi Alluvial Valley Green Tree Reservoir. In IEEE Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS), Oran, Algeria, 2024, pp. 487-491, doi:10.1109/M2GARSS57310.2024.10537504.

• Adedapo*, S.M., and H.A. Zurqani. 2023. Development of Digital Terrain Model Under High Dense Forest Cover Using USGS and Drone LiDAR Data. In IGARSS 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, pp. 1126-1129, doi:10.1109/IGARSS52108.2023.10282409.

Abstracts and Posters:

• • Adedapo*, S.M., H.A., Zurqani, R.L., Ficklin, and D.C., Osborne. 2023. Application of Machine Learning in Predicting Selected Soil Properties in Lower Mississippi Alluvial Valley Green Tree Reservoir. The 14th Southern Forestry and Natural Resource Management GIS conference (SOFOR GIS), Athens, Georgia, December 11–12, 2023.

  • Dhungana*, D., R. L., Ficklin, H. A., Zurqani, and S. Wilson. 2023. Spatial Variability of Soil Series Chemical Properties and Development of Best-Fit Spatial Interpolation Models. The Society of American Foresters (SAF) National Convention. Sacramento, CA. October 25–28, 2023.

  • Adedapo*, S.M., and Zurqani, H.A. 2023. Development of Digital Terrain Model Under High Dense Forest Cover Using USGS and Drone LiDAR Data. The 43rd annual International Geoscience and Remote Sensing Symposium, Session: WE3.R11: Standards Evolution I: Sensors, Derived Products, and Data Fusion, Paper WE3.R11.4., Pasadena, CA, July 16 - 21, 2023.

  • Adedapo*, S.M., and Zurqani, H.A. 2023. A Comparative Analysis of Spatial Interpolation Methods on Digital Terrain Models Under High Dense Forest Cover. The Arkansas GIS Users Forum, the Arkansas GIS Spring Meeting, Jacksonville, AR, April 12, 2023.

This study aims to use remote sensing indices to assess the relationship between drought and vegetation in Arkansas, USA. The primary goal is to develop Google Earth Engine (GEE)-based datasets, tools, and maps that can evaluate the impact of drought on vegetation cover in Arkansas over the past decades and make them publicly available on the geospatial web to support the development of sustainable water management in Arkansas.

Project team members: Hamdi A. Zurqani (PI) with Don White Jr. (Co-PI)

Funds:

This project is funded by the United States Geological Survey (USGS) 104B Grant Program from the Arkansas Water Resources Center (USGS-G21AP10581-01) and the University of Arkansas at Monticello, College of Forestry Agriculture and Natural Resources (CC001251-UAM-CFANR). 09/01/2022-08/31/2023, $25,440$$$

Research Outcomes:

Note: Students' names are denoted with an asterisk (i.e., Student Name*)

Research Articles:

• Alzurqani*, S.A., Zurqani, H.A., D.J., White, K.A., Bridges, and S.A. Jackson. 2024. Google Earth Engine Application for Mapping and Monitoring Drought Patterns and Trends: A Case Study in Arkansas, USA. Ecological Indicators, 168, p.112759.

Conference Proceedings:

• Alzurqani*, S.A., Zurqani, H.A., D.J., White, K.A., Bridges, and S.A. Jackson. 2023. Mapping and Monitoring the Spatial and Temporal Variation of Drought and Its Impact on Vegetation Cover in Arkansas, USA. In IGARSS 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, pp. 1126-1129, doi:10.1109/IGARSS52108.2023.10281403.

Abstracts and Posters:

• • Alzurqani*, S.A., Zurqani, H.A., White, D.J., Bridges, K.A., and S.A. Jackson. 2023. Google Earth Engine Application for Mapping and Monitoring Drought Patterns and Its Impact on Vegetation Cover in Arkansas, USA. South Dakota Student Water Conference, Brookings, SD, October 10, 2023

  • Alzurqani*, S.A., Zurqani, H.A., White, D.J., Bridges, K.A., and S.A. Jackson. 2023. Mapping and Monitoring the Spatial and Temporal Variation of Drought and its Impact on Vegetation Cover in Arkansas, USA. The 43rd annual International Geoscience and Remote Sensing Symposium (IGARSS), Pasadena, CA, July 16 - 21, 2023

  • Alzurqani*, S.A., Zurqani, H.A., White, D.J., Bridges, K.A., and S.A. Jackson. 2023. Mapping and Monitoring the Spatial and Temporal Variation of Drought and its Impact on Vegetation Cover in Arkansas, USA. The Arkansas GIS Users Forum, the Arkansas GIS Spring Meeting, Jacksonville, AR. 12 April 2023.

The purpose of this research is to fill knowledge gaps in our understanding of how environmental and anthropogenic stressors directly impact mallard movement and behaviors in the Lower Mississippi Alluvial Valley.

Project team members: Douglas C. Osborne (PI) with Hamdi A. Zurqani and Ryan Askren (Co-PIs)

Funds:

This project is funded by Five Oaks Agriculture Research, Arkansas, USA. 05/15/2021-05/14/2024, $110,000$$$