GC003
Addressing environmental challenges and sustainable development through Earth science applications utilizing Machine Learning

Session ID#: 161284

Session Description:
Applications of Machine Learning (ML), Deep Learning (DL), and Artificial Intelligence (AI) employing Earth observations have experienced a dramatic increase over the past decade. Examples of such applications to address ongoing environmental challenges and global initiatives include near real-time mapping of flooded areas, improved crop yield, type, and condition estimation, downscaled and locally calibrated air quality products, as well as enhanced land use and land cover methods. This session calls for novel research and applications of ML, DL, and AI, in data-sparse regions, with the goal of addressing environmental development challenges while promoting open data access, cloud computing, capacity-building efforts, as well as data democracy. This session looks to bring together thought leaders, non-profits, and applied scientists to build cooperation and collaboration in leveraging cutting edge technology for driving a positive impact in developing regions and across the globe.
Index Terms:

1640 Remote sensing [GLOBAL CHANGE]
1928 GIS science [INFORMATICS]
1942 Machine learning [INFORMATICS]
1980 Spatial analysis and representation [INFORMATICS]

Primary Convener:  Timothy Mayer, University of Alabama in Huntsville, Huntsville, AL, United States
Conveners:  Nicholas Clinton, Google Inc., Mountain View, CA, United States, Lillianne Thomas, Development Seed, Venice, CA, United States and Iksha Gurung, University of Alabama in Huntsville, Huntsville, AL, United States
 
Surface Urban Heat Island Distribution and Socioeconomic Inequalities in Mexico City: A Machine Learning Approach. (1051989)
Jorge Mendez Astudillo, National Autonomous University of Mexico, Ciudad de Mexico, Mexico and Ernesto dos Santos Caetano Neto, National Autonomous University of Mexico, Mexico City, Mexico
 
AutoML-Based Drought Forecasting with Meteorological Variables (1053766)
Shiheng Duan1,2, Paul Aaron Ullrich3 and Giuliana Pallotta2, (1)University of California Davis, Land Air & Water Resources, Davis, CA, United States, (2)Lawrence Livermore National Laboratory, Livermore, United States, (3)University of California Davis, Land, Air & Water Resources, Davis, CA, United States
 
Bias Correcting Historical Streamflow Prediction Tool (SPT) data for Cambodia using Machine Learning Techniques (1054254)
Biplov Bhandari1, Kel Markert2, Vikalp Mishra3, Amanda Markert1 and Robert Griffin4, (1)University of Alabama in Huntsville, Earth System Science Center, Huntsville, AL, United States, (2)Brigham Young University, Department of Civil and Construction Engineering, Provo, United States, (3)University of Alabama in Huntsville, Huntsville, AL, United States, (4)University of Alabama in Huntsville, Atmospheric and Earth Science, Huntsville, AL, United States
 
The potential Use of a Non-calibrated Physically-based Lumped Model, ERA5 Satellite Products, and an Artificial Neuronal Network (ANN) to Estimate Flow in Poorly Gauged Catchments in the Coastal Range of Southern-central Chile (1057238)
Francisco Balocchi, Bioforest SA, Coronel, Chile; Universidad de Concepción, Water resources and energy for agriculture PhD program, Water Resources department, Chillán, Chile and Diego Rivera, Universidad de Desarrollo, Facultad de Ingeniería, ANID / FONDAP / 15130015, Santiago, Chile
 
Mapping Salt–Impacted Coastal Farmlands of Delmarva Peninsula Using Sentinel-2 Imagery (1059384)
Manan Sarupria1, Matthew Walter1 and Pinki Mondal2, (1)University of Delaware, Department of Geography and Spatial Sciences, Newark, United States, (2)University of Delaware, Newark, DE, United States
 
Prototyping of Carbon Fluxes Products with Geostationary MSG Data and Machine Learning (1071408)
Beatriz Martinez, University of Valencia, Department of Earth Physics and Thermodinamics, Burjassot, Spain, Manuel Campos-Taberner, University of Valencia, Department of Earth Physics and Thermodynamics, València, Spain, Sergio Sánchez-Ruiz, University of Valencia, Department of Physics and Thermodinamics, Burjassot, Spain, Javier Garcia-Haro, University of Valencia, Valencia, Spain and Maria-Amparo Gilabert, University of Valencia, Burjassot, Spain
 
Comparison of Machine Learning Methods for Grid-Based Flood Risk Assessment and Mapping (1084314)
Jihye Han, Changjae Kwak, Jiwon Moon Dr., Kuyoon Kim and Miran Lee, National Disaster Management Research Institute, Ulsan, South Korea
 
Random Forest, EXtreme Gradient Boosting performance comparison for PM concentration prediction (1084338)
Minji Ryu1, Sanghun Son1, Jaegu Bae1, Doi Lee1, So Ryeon PARK2 and Jinsoo Kim3, (1)Pukyong National University, Spatial Information Engineering, Busan, South Korea, (2)Pukyong National University, Busan, South Korea, (3)Pukyong National University, Department of Spatial Information Engineering, Busan, South Korea
 
Unet-based waterbody detection using Sentinel-1 SAR image (1084380)
Doi Lee1, Jaegu Bae1, Sanghun Son1, Minji Ryu1, So Ryeon PARK2 and Jinsoo Kim3, (1)Pukyong National University, Spatial Information Engineering, Busan, South Korea, (2)Pukyong National University, Busan, South Korea, (3)Pukyong National University, Department of Spatial Information Engineering, Busan, South Korea
 
Machine Learning Techniques and hydrological Modeling for Flood Susceptibility and Inundation Mapping: Case study VGTB River Basin, Vietnam (1086244)
Mohamed Saber1, Tayeb Boulmaiz2, Mawloud Guermoui3, Karim I Abdrabo1, Sameh Kantosh1, Tetsuya Sumi4, Hamouda Boutaghane5, Doan Van Binh1, Binh Quang Nguyen6, Bui Thi Phuong Thao4, Ngoc Duong Vo7, Emad H Habib8 and Emad Mabrouk9, (1)Disaster Prevention Research Institute, Kyoto University, Kyoto, Japan, (2)Ghardaia University, Algeria, Algeria, (3)Centre de Développement des Energies Renouvelables, Ghardaïa, Algeria, (4)Kyoto University, Disaster Prevention Research Institute, Kyoto, Japan, (5)Badji Mokhtar-Annaba University, Annaba, Algeria, (6)The University of Danang-University of Science and Technology, Water Resources Engineering, Danang, Vietnam, (7)The University of Danang - University of Science and Technology, Danang, Vietnam, (8)University of Louisiana at Lafayette, Civil Engineering, Lafayette, United States, (9)Faculty of Science, Assiut University, Department of Mathematics, Assiut, Egypt
 
GIS and Remote Sensing Based Potential Mapping of Springs in the Indian Himalayan Region Using Machine Learning (1089264)
Rishudh Thakur1, Shikshita Bhandari1, Manish Kumar2 and Sumit Sen3, (1)Stanford University, Civil and Environmental Engineering, Stanford, CA, United States, (2)International Water Management Institute, Delhi, India, (3)Indian Institute of Technology Roorkee, Department of Hydrology, Roorkee, India
 
rassta: Raster-Based Spatial Stratification Algorithms for Environmental Modeling (1089737)
Bryan Fuentes, The Honduran Institute of Forest Conservation and Development, Department of Forest Informatics, Tegucigalpa, Honduras, Minerva J. Dorantes, University of Arkansas, Department of Crop, Soil, and Environmental Sciences, Fayetteville, AR, United States and John R. Tipton, University of Arkansas, Department of Mathematical Sciences, Fayetteville, United States
 
Deep Learning for Monitoring Large-Scale Croplands in sub-Saharan Africa (1091652)
Jonathan Sullivan, University of Arizona, School of Geography, Development & Environment, Tucson, United States, Daniel G Brown, University of Washington Seattle Campus, School of Environmental and Forest Sciences, Seattle, United States, Eric Wengrowski, Steg AI, New York City, United States, Rohit Mukherjee, University of Arizona, School of Geography, Development and Environment, Tucson, United States, Meha Jain, University of Michigan, Ann Arbor, United States and Arun Agrawal, University of Michigan, School for Environment and Sustainability, Ann Arbor, MI, United States
 
A dynamic Landslide hazard forecasting Framework for the Lower Mekong Region (1110038)
Nishan Kumar Biswas1, Thomas Stanley2, Dalia Kirschbaum3, Miguel Laverde4, Chinaporn Meechaiya4 and Peeranan Towashiraporn4, (1)NASA Goddard Space Flight Center, Hydrological Sciences Laboratory, Greenbelt, MD, United States, (2)University of Maryland Baltimore County, GESTAR-II, Baltimore, United States, (3)NASA Goddard Space Flight Center, Earth Sciences Division, Greenbelt, United States, (4)Asian Disaster Preparedness Center, SERVIR-Mekong, Bangkok, Thailand
 
Forecasting Ambient PM2.5 for megacity Kolkata using Machine Learning Model (1117878)
Kirtika Sharma, Indian Institute of Technology Delhi, New Delhi, India, Rishabh Pipalwa, Amity University, Kolkata, India and Sagnik Dey, IIT Delhi, New Delhi, India
 
Toward a Deep-Learning-Based Cloud-Masking Framework for Enhanced Multimission Monitoring of Aquatic Ecosystems (1126054)
Ruby Ramirez1, Akash Ashapure1,2 and Nima Pahlevan1,2, (1)Science Systems and Applications, Inc., Lanham, United States, (2)NASA Goddard Space Flight Center, Greenbelt, United States
 
Assessing Deep Learning Models Trained on Public versus Commercial Data using FloodPlanet, a High-Resolution Commercial Imagery Flood Dataset, for Inundation Detection (1132992)
Zhijie Zhang1, Jonathan Giezendanner1, Alexander Melancon2, Rohit Mukherjee1, Iksha Gurung2, Sarah Luca3, Upmanu Lall4, Kobus Barnard5, Andrew Molthan6 and Beth Tellman7, (1)University of Arizona, School of Geography, Development and Environment, Tucson, United States, (2)University of Alabama in Huntsville, Huntsville, AL, United States, (3)University of Arizona, Department of Mathematics, Tucson, AZ, United States, (4)Columbia University, Earth and Environmental Engineering, New York, United States, (5)University of Arizona, Computer Science, Tucson, United States, (6)NASA Marshall Space Flight Center, Huntsville, AL, United States, (7)University of Arizona, School of Geography, Development and Environment, Tucson, AZ, United States
 
Evaluating the generalization capability of spatio-temporal classifiers for crop mapping using Sentinel-1 data (1134234)
Abdul Qadir, University of Maryland College Park, College Park, MD, United States, Sergii Skakun, University of Maryland College Park, Department of Geographical Sciences, College Park, United States, Leonid Shumilo, University of Maryland College Park, College Park, United States, Meghavi Prashnani, Researcher, north estern space applications centre, Umiam, India and Nataliia Kussul, Space Research Institute NAS Ukraine and SSA Ukraine, Kyiv, Ukraine
 
A Deep Learning Approach to Identifying Flood Inundation from SAR Data (1138204)
Hetal Priyadarshi, Nirdesh Sharma and Manabendra Saharia, Indian Institute of Technology Delhi, Department of Civil Engineering, New Delhi, India
 
Predicting deforestation risk for REDD+ projects: using satellite-based land use cover maps and machine learning for robust deforestation baseline projections (1140609)
Pedro Ribeiro Piffer, Columbia University, New York, United States and Stephen Klosterman, Harvard University, Cambridge, MA, United States
 
A Data Fusion Approach to Induced Seismic Risk Assessment in Enhanced Geothermal Systems (1142544)
Sara Hanson-Hedgecock, Mediterranean Institute for Advanced Studies-CSIC, Esporles, Spain and Victor Vilarrasa, Mediterranean Institute for Advanced Studies-CSIC, Global Change Group, Esporles, Spain
 
Accurate Local Soil Carbon Modelling Using Deep Transfer Learning on Large Soil Spectral Libraries (1144357)
Zefang Shen and Raphael Viscarra Rossel, Soil and Landscape Science Group, School of Molecular and Life Sciences, Curtin University, Perth, Western Australia, Australia
 
Towards flood warnings everywhere - data-driven rainfall-runoff modeling at global scale (Invited) (1144384)
Frederik Kratzert1, Martin Gauch1,2, Daniel Klotz3, Asher Metzger4, Grey Stephen Nearing5, Guy Shalev4, Shlomo Shenzis4, Tadele Yednkachw Tekalign6, Dana Weitzner4, Oren Gilon4 and Sella Nevo4, (1)Google Research, Vienna, Austria, (2)Johannes Kepler University, Institute of Machine Learning, Linz, Austria, (3)Johannes Kepler University, Institute for Machine Learning, Linz, Austria, (4)Google Research, Tel Aviv, Israel, (5)Google Research, Mountain View, United States, (6)Google Research, Accra, Ghana
 
Detecting Winter Wheat at a Regional Scale using Greenest Pixel Composite and Deep Learning-Based Techniques (1146766)
Abhasha Joshi, University of Technology Sydney, Ultimo, NSW, Australia and Biswajeet Pradhan, University of Technology Sydney, Centre for Advanced Modelling and Geospatial Information Systems, Faculty of Engineering and IT, Sydney, NSW, Australia
 
Gradient Boosted-Regression Modeling of Naturalized Catchment Conditions to Inform the New Land and Water Regional Plan for Otago, NZ (1149679)
Michael J Friedel1,2, Dave Stewart3, Pete Stevenson2 and Xiao Feng Lu2, (1)University of Colorado Denver, Physics, Denver, CO, United States, (2)Otago Regional Council, Hydrology, Dunedin, New Zealand, (3)Raineffects, Director, Dunedin, New Zealand
 
Automatic Segmentation and Counting of Roosting Common Cranes (Grus grus) Using UAV Thermal Images, Computer Vision, and Machine Learning in the Hula Valley, Israel (1151237)
Assaf Chen, MIGAL - Galilee Research Institute, Soil water and environment, Kiryat Shemona, Israel and Motti Charter, Shamir Research Institute and University of Haifa, Geography and Environmental Studies, Haifa, Israel
 
Monitoring Smallholder Agriculture at Scale with Convolutional Networks and Data Augmentation (1151876)
Isabella Hinks1 and Josh Gray1,2, (1)North Carolina State University Raleigh, Center for Geospatial Analytics, Raleigh, United States, (2)North Carolina State University Raleigh, Forestry and Environmental Resources, Raleigh, United States
 
Intercomparison of Earth Observation based Crop Yield Forecasting Models in Kenya (1158178)
Aparna Phalke1, Eric Ross Anderson2, Ashutosh S Limaye3, Frank Davenport4, Catherine Lilian Nakalembe5, Ritvik Sahajpal6, Benson Kemboi Kenduiywo7, Sara Miller8, Vikalp Mishra8, Emily Caitlin Adams2 and Falguni P9, (1)NASA Marshall Space Flight Center, SERVIR Science Coordination Office, Huntsville, United States, (2)NASA Marshall Space Flight Center, Huntsville, United States, (3)NASA Marshall Space Flight Center, SERVIR Science Coordination Office, Huntsville, AL, United States, (4)University of California Santa Barbara, Santa Barbara, CA, United States, (5)University of Maryland College Park, Geographical Sciences, College Park, MD, United States, (6)University of Maryland, College Park, MD, United States, (7)Regional Centre for Mapping of Resources for Development, Nairobi, Kenya, (8)University of Alabama in Huntsville, Huntsville, AL, United States, (9)NASA Marshall Space Flight Center, SERVIR, Huntsville, United States
 
Scalable Cropland and Crop Type Mapping with Machine Learning and Earth Observations for Field-scale Agriculture and Food Security Monitoring (1165674)
Hannah Rae Kerner1, Catherine Lilian Nakalembe1, Ivan Zvonkov2, Gabriel Tseng3, Adam Yang3 and Inbal Becker-Reshef1, (1)University of Maryland College Park, Geographical Sciences, College Park, MD, United States, (2)University of Maryland College Park, College Park, MD, United States, (3)University of Maryland/NASA Harvest, College Park, United States
 
Forest above-ground biomass retrieval from L-band full polarimetric SAR and LIDAR data using Gaussian process regression. (1167689)
Swarnendu Sekhar Ghosh, Indian Institute of Technology Bombay, Centre of Studies in Resources Engineering, Mumbai, India, Unmesh Khati, Indian Institute of Technology Indore, Indore, India, Avik Bhattacharya, Indian Institute of Technology Bombay, Center of Studies in Resources Engineering, Mumbai, India and Marco Lavalle, Jet Propulsion Laboratory, Pasadena, CA, United States
 
Rice area mapping in Bangladesh: Harnessing the power of time-series of Sentinel data and Google Earth Engine (1170613)
Varun Tiwari1, Mirela G Tulbure1, Mollie Gaines2 and Vinicius Perin1, (1)North Carolina State University Raleigh, Center for Geospatial Analytics, Raleigh, United States, (2)North Carolina State University Raleigh, Center for Geospatial Analytics, Raleigh, NC, United States
 
A Novel Phenology-Guided Bayesian-CNN Framework for Crop Yield Estimation (1171748)
Chishan Zhang, University of Illinois Urbana-Champaign, Department of Geogarphy & Geographic Information Science, Urbana, United States and Chunyuan Diao, University of Illinois at Urbana-Champaign, Department of Geography & Geographic Information Science, Urbana, United States
 
Large-scale agricultural field delineation in India using deep learning and weak supervision (1175406)
Sherrie Wang, University of California Berkeley, Goldman School of Public Policy, Berkeley, United States and David B Lobell, Stanford University, Stanford, CA, United States
 
Medium Resolution Data and Deep Learning Unlock Parametric Flood Insurance (1178143)
Colin Doyle1, Maxwell C. Goodman1, Beth Tellman2,3, Nicholas Leach1, Philip Popien4, Veda Sunkara3, Subit Chakrabarti4, Nikoo Ekhtiari4, Cole Erickson3 and Katya Potapov4, (1)Cloud to Street, Brooklyn, United States, (2)University of Arizona, Tucson, United States, (3)Cloud to Street, New York, NY, United States, (4)Cloud to Street, New York, United States
 
Informing Decarbonization through Machine Learning (ML): A Geospatial ML Pipeline for Estimating Heating Loads (1182441)
Vidisha Chowdhury1, Shamsi Soltani2, Philippe Schicker1, Madelyn Gaumer3, Nicholas Bolten4 and Erin Trochim5, (1)Heinz College of Information Systems and Public Policy, Carnegie Mellon University, Pittsburgh, United States, (2)Department of Epidemiology & Population Health, Stanford University School of Medicine, Stanford, CA, United States, (3)Department of Applied Mathematics, University of Washington, Seattle, United States, (4)Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, United States, (5)University of Alaska Fairbanks, Fairbanks, AK, United States
 
Mapping and Dynamic Monitoring of Military Training Induced Vegetation Cover Loss Using Satellite Images (1182969)
Xiaoyu Xu, Southern Illinois University Carbondale, Carbondale, IL, United States, Bibek Ban, Sothern Illinois University Carbondale, Carbondale, United States, Heidi R. Howard, US Army Construction Engineering Research Laboratory, Champaign, United States and Guangxing Wang, Southern Illinois University Carbondale, Carbondale, United States
 
Unsupervised Classification of Tropical Cyclone Precursors in Geostationary Satellite Images (1185289)
James A Franke, University Of Chicago, Department of the Geophysical Sciences, Center for Robust Decision-making on Climate and Energy Policy, Chicago, United States
 
Mapping the global potential of reforestation projects using ground observations, remote sensing, and machine learning (1185690)
Stephen Klosterman1, Trevor F Keenan2, Margaux Masson-Forsythe1, Brookie P Guzder-Williams3, Pedro Ribeiro Piffer1, Anika Staccone1 and M. Joseph Hughes1, (1)Earthshot Labs, Mill Valley, United States, (2)Lawrence Berkeley National Laboratory, Climate and Ecosystem Sciences Division, Berkeley, United States, (3)World Resources Institute, San Francisco, CA, United States
 
Mapping Urban Informal Settlements (UIS): A Deep Learning based case study from India (1188597)
Santonu Goswami1, Ruchika Bhattacharjee2, Bhuswarna Kashyap2, Kunjal Sarma3, Subrat Kishore Dutta4 and Harini Nagendra1, (1)Azim Premji University, Centre for Climate Change and Sustainability, Bangalore, India, (2)Assam Engineering College, Guwahati, India, (3)Assam Engineering College, Computer Science, Guwahati, India, (4)Saarland University, Saarbrücken, Germany
 
Evaluation of machine learning models to assess relationships between climate and corn suitability in the U.S. (1193014)
Dan Pisut1, Abigail Fitzgibbon2, David Fleisher3 and Sean Breyer1, (1)Esri, Living Atlas of the World, Redlands, CA, United States, (2)Esri, Living Atlas of the World, Redlands, United States, (3)USDA Beltsville Agricultural Research Center, Beltsville, United States
 
Deep learning assisted downscaling of national-scale socioeconomic data for assessing poverty-biodiversity relationships in India. (1194085)
Aditya Singh, University of Florida, Center for Remote Sensing, Department of Agricultural & Biological Engineering, Ft Walton Beach, FL, United States and Aditya Dutt, University of Florida, Computer and Information Systems Engineering, Gainesville, United States
 
Estimating crop type and yield of small holder fields in Burkina Faso using multi-day Sentinel-2 (1198599)
William Wagner1, Mark Carroll2, Akiko Elders1, Christopher S R Neigh3, Anthony Louis D'Agostino4, Margaret Wooten5, Christopher Ksoll6 and Molly Elizabeth Brown7, (1)NASA Goddard Space Flight Center, Greenbelt, United States, (2)NASA Goddard Space Flight Center, Data Science Group, Greenbelt, United States, (3)NASA Goddard Space Flight Center, Biospheric Sciences Laboratory, Greenbelt, MD, United States, (4)Mathematica, Oakland, United States, (5)NASA Goddard Space Flight Center, Biospheric Science Lab, Greenbelt, MD, United States, (6)University of Greenwich, NRI, London, United Kingdom, (7)Department of Geographical Sciences, University of Maryland, Greenbelt, United States
 
Evaluation of Machine-Learning Architectures and Expanded Feature Sets for GEDI Footprint Aboveground Biomass Density Prediction (1203050)
Eugene Seo1, John David Armston2, Laura Duncanson3, James Bryan Blair4, Jamis Bruening5, Tiago de Conto5, Ralph Dubayah6, Steven Hancock7, Sean Healey8, Michelle A Hofton5, Scott B Luthcke9, David Minor3, Paul L Patterson10, Hao Tang11, Matthew Harrison1 and James R Kellner12, (1)Brown University, Applied Math, Providence, United States, (2)University of Maryland College Park, College Park, United States, (3)University of Maryland College Park, Geographical Sciences, College Park, United States, (4)NASA Goddard Space Flight Center, Code 61A, Greenbelt, MD, United States, (5)University of Maryland College Park, Geographical Sciences, College Park, MD, United States, (6)University of Maryland College Park, Department of Geographical Sciences, College Park, United States, (7)University of Edinburgh, School of Geosciences, Edinburgh, United Kingdom, (8)Rocky Mountain Research Station, Ogden, UT, United States, (9)NASA Goddard Space Flight Center, Geodesy and Geophysics Lab, Greenbelt, MD, United States, (10)Rocky Mountain Research Station, Ogden, United States, (11)National University of Singapore, Geography, Singapore, Singapore, (12)Brown University, Providence, RI, United States
See more of: Global Environmental Change
<< Previous Session Proposal | Next Session Proposal >>