NH002
Applications of AI/ML using Remote Sensing, Social Sensing and Model Data to Study Hazard

Session ID#: 160855

Session Description:
Earth science data collected from spaceborne, airborne, and in-situ sensors, paired with numerical model simulations and social media data, provide a very large, heterogenous, real time dataset relative to hazards and extreme events.  However, our ability to collect data greatly surpasses our ability to analyze them, and it is leading to a data rich but knowledge poor environment.  Advanced AI/ML techniques are being used for a variety of applications related to hazards, including improving predictions, mapping impacted areas, assessing damage,  finding patterns, filling missing data, and generating synthetic data.  This session focuses on specific applications of AI/ML applied to hazard events.
Index Terms:

1914 Data mining [INFORMATICS]
1942 Machine learning [INFORMATICS]
4337 Remote sensing and disasters [NATURAL HAZARDS]
4341 Early warning systems [NATURAL HAZARDS]

Primary Convener:  Guido Cervone, Pennsylvania State University Main Campus, Department of Geography and Institute for Computational and Data Sciences, University Park, United States
Convener:  Qunying Huang, University of Wisconsin, Madison, Department of Geography, Madison, United States
Student/Early Career Convener:  Qunying Huang, University of Wisconsin, Madison, Department of Geography, Madison, United States
 
Factors Controlling Groundwater Radioactivity in Arid Environments: An Automated Machine Learning Approach (1042239)
Othman Fallatah, Department of Nuclear Engineering, Faculty of Engineering, King Abdulaziz University, P.O. Box 80204, Jeddah 21589, Saudi Arabia, Engineering, Jeddah, Saudi Arabia, Mohamed Ahmed, Texas A&M University-Corpus Christi, Department of Physical and Environmental Sciences, Corpus Christi, United States, Bimal Gyawali, Texas A&M University Corpus Christi, Physical and Environmental Sciences, Corpus Christi, TX, United States and Abdulsalam Alhawsawi, Department of Nuclear Engineering, Faculty of Engineering, King Abdulaziz University, P.O. Box 80204, Jeddah 21589, Saudi Arabia, Nuclear Engineering, Jeddah, Saudi Arabia
 
U-Net-Based Semantic Classification for Flood Extent Extraction Using SAR Images: A Case Study for 2019 Central US Flooding (1067857)
Zhouyayan Li, University of Iowa, Iowa City, IA, United States and Ibrahim Demir, University of Iowa, Iowa City, United States
 
Urban flood mapping using Sentinel-1 and RADARSAT Constellation Mission image based on Convolutional Siamese Network (1076404)
Nafiseh Ghasemian Sorboni, University of Western Ontario, Geography and Environment, London, ON, Canada, Jinfei Wang, University of Western Ontario, Geography, London, ON, Canada and Mohammad Reza Najafi, Western University, Civil and Environmental Engineering, London, ON, Canada
 
Deep-learning Characterization of Geohazards in Qinghai Tibet Engineering Corridor (1077262)
Yiling Lin, Facalty of Geography Science,Beijing Normal University, Beijing, China and Xie Hu, College of Urban and Environmental Sciences, Peking University, Beijing, China
 
Comparison between Random Forest and Convolutional Neural Networks on Forest Fire Early Detection using Geostationary Satellite Data (1078057)
Yoojin Kang, Ulsan National Institute of Science and Technology, Urban and Environmental Engineering, Ulsan, Korea, Republic of (South) and Jungho Im, Ulsan National Institute of Science and Technology, Urban and Environmental Engineering, Ulsan, South Korea
 
Big Data and GeoAI for Natural Hazards (1079629)
Qunying Huang1, Bo Peng2, Meiliu Wu3, Jirapa Vongkusolkit1, Boyuan Zou4, Xinyi Liu1 and Chris Scheele1,5, (1)University of Wisconsin Madison, Geography, Madison, United States, (2)University of Wisconsin Madison, Madison, United States, (3)University of Wisconsin Madison, Geography, Madison, WI, United States, (4)University of Wisconsin Madison, Computer Science, Madison, United States, (5)Arity, Chicago, United States
 
A Machine Learning Approach for the Remote Sensing Retrieval of Oil Spills from Polarimetric Measurements (1087383)
Matteo Ottaviani, NASA Goddard Institute for Space Studies, New York, NY, United States and Jacek Chowdhary, Columbia University in the City of New York, New York, NY, United States
 
Nearshore and Onshore Approximation of Tsunami Hazard using Autoencoder Approach (1088346)
Naveen Ragu Ramalingam1, Kendra Johnson2, Anirudh Rao2, Marco Pagani2 and Mario Lloyd Virgilio Martina1, (1)The University School for Advanced Studies - IUSS Pavia, Pavia, Italy, (2)Global Earthquake Model Foundation, Pavia, Italy
 
Machine Learning Reconstruction of Atmospheric Releases from Catastrophic Radiological Events (1094826)
Donald D Lucas and Nipun Gunawardena, Lawrence Livermore National Laboratory, Livermore, CA, United States
 
Efficient Recognition of Potential Landslides using Open Access Multi-Source Remotely Sensed Images with Deep Learning Approaches (1098742)
Zhijie Zhang, University of Arizona, School of Geography, Development and Environment, Tucson, United States, Xuan Wu, Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China, Yaning Yi, National Institute of Natural Hazards, Ministry of Emergency Management of China, Beijing, China, Chuanrong Zhang, University of Connecticut, Department of Geography, Storrs, CT, United States and Beth Tellman, University of Arizona, School of Geography, Development and Environment, Tucson, AZ, United States
 
Development of a Urban Flood Detection Method Using Image Data (1102290)
Lee Haneul1, Yu Jin Kang1, Hung Soo Kim1 and Soojun Kim2, (1)Inha University, Incheon, Korea, Republic of (South), (2)Inha University, Incheon, South Korea
 
Unwrapping of SAR Interferometric Phase Using Deep Learning Regression Model: Focusing on Optimization of Training Data and Model Structure (1103204)
Won-Kyung Baek and Hyung-Sup Jung, University of Seoul, Department of Geoinformatics, Seoul, South Korea
 
Deep Learning-based Flood Detection Model Using SAR Satellite Images and Topographic Data (1103337)
Seoyoung Jeon, Incheon National University, Environmental Engineering, Korea, Republic of (South) and Kyuhyun Byun, Incheon National University, Environmental Engineering, Incheon, South Korea
 
Application of Naïve Bayes Machine Learning algorithm and sensitivity analysis for landslide spatial modelling in the Himalayas. (1107651)
Ramandeep Kaur and Vikram Gupta, Wadia Institute of Himalayan Geology, Dehradun, India
 
Multi Hazard Assessment And Vulnerability Mapping Using GIS Integrated Approach, A Case of Sindhupalchowk District,Nepal (1115831)
Ajaya Shrestha, Environment and Engineering Research Center Pvt. Ltd, Consulting Organization, Kathmandu, Nepal, Kumud Raj Kafle, Kathmandu University, Environmental Science and Engineering, Dhulikhel, Nepal and Rabin Raj Niraula Dr., Knowledge and Information Manager Asia, Lalitpur, Nepal
 
Towards Enhancing Coastal Resilience by Using Social Media Data during Hurricanes (1122984)
Mohammadsepehr Karimiziarani1, Wanyun Shao2, Pouya Moghaddasi1 and Hamid Moradkhani3, (1)University of Alabama, Civil, Construction, and Environmental Engineering, Tuscaloosa, United States, (2)The University of Alabama, Center for Complex Hydrosystems Research, Tuscaloosa, AL, United States, (3)The University of Alabama, Civil, Construction, and Environmental Engineering, Tuscaloosa, United States
 
Spatiotemporal Characterization of a Hurricane Michael on Urban Vegetation Cover in the US Gulf Coast (1135682)
Syed Mohammad Asiful Alam, Deepak R Mishra and Puneet Dwivedi, University of Georgia, Athens, GA, United States
 
In-Situ Sensing of Stream Flow using Deep Learning Sound Classification with Tagged Images (1136574)
John Kemeny, University of Arizona and SUAVAI Geo Inc., Tucson, United States and Kwangmin Kim, SUAVAI Geo Inc., Ada, United States
 
Automatic Inundation Warning System Utilizing High-Precision Water Segmentation Deep Learning Model (1136915)
Hwisong Kim, Junwoo Kim and Duk-Jin Kim, Seoul National University, School of Earth and Environmental Studies, Seoul, South Korea
 
A GIS-Ensemble Machine Learning Model for Identification of Flood-prone Areas (1137646)
Roya Narimani1, Changhyun Jun1, Sayed M. Bateni2, Somayeh Moghimi Nezhad3, Jongyun Byun1 and Hoyoung Cha3, (1)Chung-Ang University, Department of Civil and Environmental Engineering, Seoul, South Korea, (2)University of Hawaii at Manoa, Department of Civil and Environmental Engineering and Water Resources Research Center, Honolulu, United States, (3)Chung-Ang University, Department of Smart Cities, Seoul, South Korea
 
A Self-evolving Deep Learning Algorithm for SAR-based Oil Spill Detection (1138279)
Chenglei Li1, Soyeon Park2, Junwoo Kim1, Hwisong Kim1, Juyoung Song1 and Duk-Jin Kim1, (1)Seoul National University, School of Earth and Environmental Studies, Seoul, South Korea, (2)Seoul National University, School of Earth and Environmental Studies, Seoul, Korea, Republic of (South)
 
Multi-resolution Multi-sensor Fusion of Remote Sensing Data to investigate Rock Slope Instabilities (1147577)
Marta Zocchi1, Anush Kumar Kumar Kasaragod2, Thomas Oommen3, Colin Brooks4, Chris Cook4, Abby Jenkins4, Richard Dobson4, Beau Taylor5 and Paolo Mazzanti1, (1)Sapienza University of Rome, Earth Sciences, Rome, Italy, (2)Michigan Technological University, Geological and Mining Engineering and Sciences, Houghton, MI, United States, (3)Michigan Technological University, Geological and Mining Engineering and Sciences, Houghton, United States, (4)Michigan Technological University, Michigan Tech Research Institute, Ann Arbor, United States, (5)Colorado Department of Transportation, Denver, United States
 
Markov-chain Monte Carlo Methods for Reconstructing Historical Earthquake-induced Tsunamis (1155936)
Jake Callahan1, Jared Whitehead1, Ronald A Harris2, Taylor Paskett1, Chelsey Noorda1 and Raelynn Wonnacott3, (1)Brigham Young University, Mathematics, Provo, United States, (2)Brigham Young University, Geology, Provo, United States, (3)Brigham Young University, Mathematics, Provo, UT, United States
 
Mapping Bedrock Outcrops in the Sierra Nevada using Machine Learning (1164123)
Apoorva R Shastry, Universities Space Research Association Moffett Field, Moffett Field, United States; USGS, Geology, Minerals, Energy and Geophysics Science Center, Moffett Field, CA, United States, Corina Cerovski-Darriau, USGS, Geology, Minerals, Energy and Geophysics Science Center, Menlo Park, CA, United States, Brian Coltin, NASA Ames Research Center, Moffett Field, United States and Jonathan D Stock, US Geological Survey, Menlo Park, CA, United States
 
Machine Learning Weather Analogs for Renewable Forecasting (1178392)
Weiming Hu1, Guido Cervone2, George s Young2 and Luca Delle Monache3, (1)University of California San Diego, La Jolla, CA, United States, (2)Pennsylvania State University Main Campus, University Park, PA, United States, (3)Scripps Institution of Oceanography, University of California San Diego, La Jolla, CA, United States
 
Flood Water Delineation for Heterogeneous Land Cover Using Machine Learning with Sentinel-1&2 Remote Sensing Imagery and Geospatial Data (1183602)
Dan Tian and Lei Wang, Louisiana State University, Baton Rouge, LA, United States
 
APPLICATION OF MACHINE LEARNING ALGORITHMS FOR FLOOD SUSCEPTIBILITY ASSESSMENT IN THE STATE OF KANSAS (1185249)
Prashant Rimal, Zelalem Demissie and Glyn Rimmington, Wichita State University, Geology Department, Wichita, United States
 
Machine Learning and Web-GIS Based Flood Forecasting-Cum-Warning System (1188035)
Anupriya Goyal and Himanshu Tyagi, Indian Institute of Technology Delhi, New Delhi, India
 
Landslide extraction by using Machine Learning algorithm on Google Earth Engine (1189415)
Saloni Jain1, Ashvani Kumar Gosain2 and Rakesh Khosa2, (1)Indian Institute of Technology Delhi, New Delhi, India, (2)Indian Institute of Technology Delhi, Department of Civil Engineering, New Delhi, India
 
Scalable Wildfire Classification Using Distributed Memory Parallel, GPU-enabled Support Vector Machines (1197961)
Richard T Mills1, Zachary Lance Langford2, Marek Pecha3, Jitendra Kumar2, Forrest M. Hoffman4 and David Horák3, (1)Argonne National Laboratory, Argonne, IL, United States, (2)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (3)Technical University of Ostrava, Ostrava-Poruba, Czech Republic, (4)Oak Ridge National Laboratory, Computational Sciences & Engineering Division and Climate Change Science Institute, Oak Ridge, TN, United States
 
High resolution water surface elevation (WSE) models generated by a UAV platform (1198382)
Nick Z. Fang1, Dongfeng Li1 and Kevin J Wienhold2, (1)University of Texas at Arlington, Civil Engineering, Arlington, TX, United States, (2)University of Texas at Arlington, Arlington, TX, United States
 
Data-Driven Approaches to Monitor Recovery and Resilience of Critical Infrastructures in Natural Hazards (1202286)
Yi Qiang, University of South Florida Tampa, Tampa, FL, United States, Jinwen Xu, University of South Florida Tampa, School of Geosciences, Tampa, United States, Song Gao, University of Wisconsin, Madison, United States, Lei Zou, Texas A&M University, Department of Geography, College Station, United States and Heng Cai, Texas A&M University College Station, College Station, United States
See more of: Natural Hazards
<< Previous Session Proposal | Next Session Proposal >>