IN011
AI/ML for Wetlands: Remote Sensing-Driven Solutions for Climate-Resilient Ecosystem Management
Session ID#: 247690
Session Description:
Wetlands are dynamic and diverse ecosystems that support biodiversity, regulate water cycles, prevent soil erosion, provide carbon sequestration, and buffer against climate impacts such as floods and droughts. However, their degradation and loss are accelerating due to climate change and human activities. Accurate mapping of wetlands is essential for their conservation and sustainable management. This session emphasizes the integration of Artificial Intelligence (AI), Machine Learning (ML), and remote sensing technologies to address these challenges through innovative wetland monitoring and management strategies. With advancements in high-resolution satellite imagery and platforms like Google Earth Engine, spatiotemporal data analysis becomes more efficient and insightful for wetland science. The integration of AI/ML models enhances the accuracy of detecting wetland boundaries, monitoring hydrological dynamics, classifying land cover, and identifying restoration opportunities. This session invites interdisciplinary research showcasing scalable, transferable, and open-source approaches that promote climate-resilient ecosystem management through cutting-edge, AI-driven remote sensing and mechanistic modeling
Co-Sponsor(s):
Index Terms:
0480 Remote sensing [BIOGEOSCIENCES]
0481 Restoration [BIOGEOSCIENCES]
0497 Wetlands [BIOGEOSCIENCES]
1942 Machine learning [INFORMATICS]
Primary Convener: Zhenghong Tang, University of Nebraska Lincoln, College of Architecture, Community and Regional Planning, Lincoln, United States
Conveners: Jahangeer Jahangeer, University of Nebraska Lincoln, College of Architecture, Community and Regional Planning, Lincoln, NE, United States and Aditya Kapoor, USDA ARS, Adaptive Cropping System Laboratory, Beltsville, United States
Student/Early Career Convener: Rimsha Hasan, University of Nebraska Lincoln, School of Natural Resources, Lincoln, United States
Wetland Mapping with Multi-temporal Aerial Imagery and GeoAI (Invited) (1848196)
Qiusheng Wu1, Charles R. Lane2, Jay Christensen3, Heather E Golden3, Joseph Prenger4 and Adnan Rajib5, (1)University of Tennessee, Knoxville, Department of Geography & Sustainability, Knoxville, United States, (2)US Environmental Protection Agency, Athens, United States, (3)US Environmental Protection Agency, Office of Research & Development, Cincinnati, United States, (4)USDA Beltsville Agricultural Research Center, Beltsville, United States, (5)University of Texas at Arlington, Hydrology & Hydroinformatics Innovation Lab, Department of Civil Engineering, Arlington, TX, United States
Simulation of Water Table Depths in a Forested Wetland System in the Carolinas using data-driven approaches (Invited) (1850014)
Sushant Mehan, South Dakota State University, Department of Agricultural and Biosystems Engineering, Brookings, SD, United States, Alokesh Manna, University of Connecticut, Storrs, United States and Devendra Man Amatya, USDA Forest Service Southern Research Station, Cordesville, United States
Advanced Multisensor Approach for Wetland Dynamics Monitoring using ML Classifiers in Sambhar Lake Ramsar Site (India) (1891535)
Basant Bijarniya, Central University of Rajasthan, Environmental Science, Jaipur, India, Prof Laxmi Kant Kant Sharma, Central University of Rajasthan, Environmental Science, Kishangarh, India and Mr. Shubham Kumar, Ph.D., Central University of Rajasthan, Environmental Science, Ajmer, India
Assessing Inundation and Ecosystem Benefits in CRP Lands Using AI and ML (1900406)
Jahangeer Jahangeer, University of Nebraska Lincoln, College of Architecture, Community and Regional Planning, Lincoln, NE, United States, Aditya Kapoor, USDA ARS, Adaptive Cropping System Laboratory, Beltsville, United States and Zhenghong Tang, University of Nebraska Lincoln, College of Architecture, Community and Regional Planning, Lincoln, United States
Leveraging Machine Learning for Coastal Freshwater Floodplain Wetland Identification and Habitat Suitability (2000949)
Elliott White Jr.1, Layla Tadjpour2, Margaux Masson-Forsythe2, Nikhil Raj DEEP3, Aaron Hirsh2 and layla, (1)Stanford University, Earth System Science, Stanford, United States, (2)Collaborative Earth, Berkeley, United States, (3)University of Florida, Gainesville, United States
Assessing Deep Learning Robustness for Phragmites australis Classification Using Multi-Year Integrated Sentinel‑2 Time Series in the Mississippi River Delta (2003377)
Manisha K C1, Xuelian Meng2 and Basant Awasthi1, (1)Louisiana State University, Geography and Anthropology, Baton Rouge, LA, United States, (2)Louisiana State University, Department of Geography and Anthropology, Baton Rouge, United States
