Artificial Intelligence in Remote Sensing for Disaster Management

Neelam Dahiya, PhD is an assistant professor in the Department of Computer Applications at Chitkara University, Punjab, India. She has authored over ten articles in international journals and filed more than ten patents with the Indian Patent Office, five of which were granted. She has also reviewed various articles for renowned journals and conferences. Her research interests include remote sensing, digital image processing, deep learning, and hyperspectral imaging. Gurwinder Singh, PhD is an associate professor at the Institute of Computing at Chandigarh University, India. He has internationally published over 35 articles, conference papers, and book chapters, as well as one patent. He also serves as a member of the International Society for Photogrammetry and Remote Sensing and the Indian Society of Remote Sensing. His research interests include remote sensing, digital image processing, agricultural land use classification, machine learning, and deep learning. Sartajvir Singh, PhD is a professor and the Associate Director for the University Institute of Engineering at Chandigarh University, Punjab, India. He has filed over 50 patents with the Indian Patent Office, with over half granted. He has authored over 50 articles in international journals and edited various proceedings for conferences and symposia in addition to serving as an editor for several international journals. His research interests include electronics, remote sensing, and digital image processing. Apoorva Sharma is a digital analyst and assistant professor in the Department of Computer Science and Engineering, Chandigarh University, Punjab, India. She has published three articles in internationally reputed journals and conferences and contributed to innovative wearable and geospatial technologies. Her research interests include remote sensing, digital image processing, agriculture and cryosphere studies, machine learning, and deep learning.

• Preface xvii1 Introduction to Natural Hazards, Challenges, and Managing Strategies 1Puninder Kaur, Taruna Sharma, Jaswinder Singh and Neelam Dahiya1.1 Introduction 11.2 Terminology Used 31.2.1 Hazard 31.2.2 Mitigation 31.2.3 Vulnerability 41.2.4 Disaster 41.2.5 Risk 41.3 Classification of Natural Hazards 51.3.1 Biological Natural Hazards 51.3.2 Geological Hazards 61.3.3 Hydrological Hazards 61.3.4 Meteorological Hazards 61.4 Challenges and Risks of Natural Hazards 71.4.1 Loss of Life 71.4.2 Property Damage and Economic Losses 81.4.3 Disruption of Critical Infrastructure 81.4.4 Health Risks and Disease Outbreaks 81.4.5 Environmental Degradation 91.4.6 Social and Economic Disparities 91.4.7 Psychosocial Impacts 91.5 Strategies to Prevent Natural Hazards 101.5.1 Planning and Regulation for Reducing Risk on Land 101.5.1.1 Zoning Regulations 101.5.1.2 Building Codes and Standards 101.5.1.3 Setback Requirements 111.5.1.4 Erosion Control Measures 111.5.1.5 Floodplain Management 111.5.2 Environmental Conservation and Restoration 111.5.2.1 Protecting Natural Ecosystems 111.5.2.2 Restoring Degraded Ecosystems 121.5.2.3 Floodplain Management 121.5.2.4 Coastal Protection 121.5.2.5 Sustainable Land Management 121.5.3 Early Warning Systems and Preparedness 131.5.3.1 Hazard Monitoring and Forecasting 131.5.3.2 Risk Assessment and Planning 131.5.4 Education and Awareness 131.5.4.1 Understanding Hazards and Risks 131.5.4.2 Promoting Risk Reduction Measures 141.5.4.3 School Curriculum Integration 141.5.5 Climate Change Mitigation 141.5.5.1 Reducing Greenhouse Gas Emissions 141.5.5.2 Promoting Renewable Energy 151.5.5.3 Enhancing Energy Efficiency 151.6 Role of Remote Sensing Device to Prevent Natural Disasters 151.6.1 Hazard Detection and Monitoring 151.6.2 Early Warning Systems 161.6.3 Risk Assessment and Vulnerability Mapping 161.6.4 Environmental Monitoring 161.6.5 Mapping and Damage Assessment 161.7 Conclusion 17Acknowledgments 17References 172 Role of Remote Sensing for Emergency Response and Disaster Rehabilitation 21Mochamad Irwan Hariyono and Aptu Andy Kurniawan2.1 Introduction 212.2 Method 252.3 Disaster Management 252.4 Result and Discussion 262.4.1 Floods 262.4.2 Earthquakes 282.4.3 Drought 292.4.4 Landslides 292.4.5 Land/Forest Fire 302.4.6 Volcanic Eruption 312.5 Conclusion 32References 333 Fundamentals of Disaster Management Using Remote Sensing 35Garima and Narayan Vyas3.1 Introduction 353.2 Importance of Remote Sensing in Disaster Management 363.2.1 Role in Emergency Response 373.2.2 Impact on Disaster Rehabilitation 383.2.3 Remote Sensing Taxonomy 393.3 Remote Sensing Applications in Emergency Response 403.3.1 Damage Assessment 403.3.1.1 Techniques and Methods 413.3.1.2 Integration with Other Data Sources 423.3.1.3 Feature Extraction from Pre- and Post- Disaster Imagery 433.4 Acquisition of Disaster Features 453.4.1 Acquisition of Tsunami Features with Remote Sensing 453.4.2 Acquisition of Earthquake Features with Remote Sensing 483.4.3 Acquisition of Wildfire Features with Remote Sensing 50Conclusion 55References 554 Remote Sensing for Monitoring of Disaster-Prone Region 59Navdeep Singh Sodhi and Sofia Singla4.1 Introduction 604.2 Related Existing Work 634.3 Comparison Table 684.4 Graphical Analysis 724.5 Conclusion and Future Scope 74Acknowledgments 74References 755 Artificial Intelligence Tools in Disaster Risk Reduction and Emergency Management 79Rupinder Singh, Manjinder Singh and Jaswinder Singh5.1 Introduction 805.1.1 Role of AI Tools and Technologies 805.1.2 Purpose and Objectives of the Research Paper 825.2 AI Tools and Technologies in Disaster Risk Reduction 835.3 Ethical and Social Implications of Using AI Tools in Disaster Management 915.4 Impact and Effectiveness of AI Tools and Technologies 925.5 AI for Dismantling Difficulties in Disaster Management 945.6 Future Directions and Recommendations 955.7 Conclusion 95Acknowledgments 96Funding 96References 966 AI Tools and Technologies in Disaster Risk Reduction and Management 99Alisha Sinha and Laxmi Kant Sharma6.1 Introduction 1006.2 AI Tools in Different Phases of Disaster Management 1016.2.1 Before Disaster 1016.2.2 During Disaster 1026.2.3 After Disaster 1026.3 Use of Geospatial Technologies and AI in Disaster Management 1036.4 Future Challenges and Goals with AI 1166.5 Conclusions 116Acknowledgment 117References 1177 AI-Based Landslide Susceptibility Evaluation 125Amanpreet Singh and Payal Kaushal7.1 Introduction 1267.2 Principle of Support Vector Machines (SVM) 1287.3 Conclusion 132Acknowledgments 132References 1338 Navigating Risk: A Comprehensive Study of Landslide Susceptibility Mapping and Hazard Assessment 139Gaurav Kumar Saini and Inderdeep Kaur8.1 Introduction 1408.1.1 Challenges in Factor Selection and Weighting 1418.1.2 Combination of Subjective and Objective Approaches 1418.2 Factors Responsible for Landslides 1418.2.1 External 1418.2.2 Internal 1428.3 Types of Landslides 1438.4 Landslide Detection Techniques 1448.5 Landslide Monitoring Techniques 1468.6 Use of Machine Learning in Landslide Mapping 1478.7 Use of Deep Learning in Landslide Mapping 1488.8 Use of Ensemble Techniques 1488.9 Limitations of Existing Algorithms 1498.10 Dataset Used 1498.11 Model Architecture 1538.12 Results and Discussion 154Acknowledgment 157References 1589 Application of Geospatial Technology for Disaster Risk Reduction Using Machine Learning Algorithm and OpenStreetMap in Batticaloa District, Eastern Province, Sri Lanka 161Zahir I.L.M., Suthakaran S., Iyoob A.L., Nuskiya M.H.F. and Fowzul Ameer M.L.9.1 Introduction 1629.1.1 Geospatial Technology in DRR 1639.1.2 MLAs in DRR 1649.1.3 OSM in DRR 1649.1.4 Integrated Approach of Geospatial Technology, Machine Learning, and OSM 1659.2 Significance of the Study 1659.3 Objectives 1679.4 Methodology 1679.4.1 Study Area 1679.4.2 Data Collection 1699.4.2.1 MLAs for DRR 1699.4.2.2 Integration with OSM 1719.5 Results and Discussion 1749.6 Conclusion and Recommendations 179References 18010 Landslide Displacement Forecasting With AI Models 185Sangeetha Annam10.1 Introduction 18610.1.1 Technology Classifications for Remote Sensing 18710.1.2 Architecture of Risk Management 18910.2 Artificial Intelligence-Based Forecasting of Landslide Displacement 19110.3 Performance Metrics 19510.4 Limitations in Assessing the AI Models for Landslide Displacement Prediction 19610.5 Technologies Integrated with AI Models 19710.6 Conclusion 198References 19911 Estimation of Snow Avalanche Hazardous Zones With AI Models 201Rajinder Kaur, Sartajvir Singh and Ganesh Kumar Sethi11.1 Introduction 20211.2 Study Site and Data 20311.3 Methodology 20411.4 Results and Discussion 20811.5 Conclusion 209References 21012 Predicting and Understanding the Snow Avalanche Event 213Nitin Arora and Sakshi12.1 Introduction 21412.2 Snow Avalanche 21412.2.1 Types of Snow Avalanche 21612.2.1.1 Sluff Avalanche 21612.2.1.2 Slab Avalanche 21612.2.2 Basic Reason Behind Snow Avalanche 21712.2.3 Role of Remote Sensing in Snow Avalanche Prediction 21812.3 Contributory Factors 21912.3.1 Terrain 22012.3.2 Precipitation 22012.3.2.1 Snow Accumulation 22012.3.2.2 Formation of Weak Layers 22012.3.2.3 Load and Stress Increases 22012.3.2.4 Rain-on-Snow Effect 22012.3.3 Wind Temperature 22112.3.4 Snowpack Stratigraphy 22112.4 Remote Sensing and Avalanche Prediction 22112.4.1 Basic Principle Behind Radar-Based Remote Sensing 22212.4.2 Need for Remote Sensing 22312.5 Methodology 22312.5 Conclusion and Future Scope 225References 22513 A Systematic Review on Challenges and Opportunities in Snow Avalanche Risk Assessment and Analysis 229Apoorva Sharma, Bhavneet Kaur and Sartajvir Singh13.1 Introduction 23013.2 Advanced Tools for Snow Avalanche Monitoring System 23313.3 Snow Avalanche Risk Assessment and Analysis 23413.4 Challenges in Snow Avalanche Risk Assessment and Analysis 23713.5 Opportunities in Snow Avalanche Risk Assessment and Analysis 23713.6 Summary 239References 23914 AI-Based Modeling of GLOF Process and Its Impact 243Jaswinder Singh, Rajwinder Kaur, Puninder Kaur and Rupinder Singh14.1 Introduction 24414.1.1 The Andes 24514.1.2 High Mountain Asia (HMA) 24514.1.3 Other Regions 24514.2 Artificial Intelligence and GLOF 24614.2.1 Modeling the GLOF Process 24614.2.2 Impact Assessment 24614.2.3 Benefits of Using AI 24714.2.4 AI Techniques for the Prediction of GLOF 24714.2.4.1 Machine Learning (ML) 24814.2.4.2 Deep Learning (DL) 24814.2.4.3 Time Series Analysis 24814.2.4.4 Integration with Other Techniques 24914.3 Machine Learning Techniques for GLOF 24914.3.1 Use of Supervised Learning in GLOF 24914.3.1.1 Data Preparation 24914.3.1.2 Feature Engineering 25014.3.1.3 Model Training 25014.3.1.4 Prediction 25014.3.1.5 Benefits of Using Supervised Learning for GLOF Prediction 25014.3.1.6 Various Supervised Algorithms for the GLOF Process 25114.3.1.7 Choosing the Right Algorithm 25214.3.2 Use of Unsupervised Learning in GLOF 25314.3.2.1 Anomaly Detection 25314.3.2.2 Feature Discovery 25414.3.2.3 Data Preprocessing 25414.3.2.4 Unsupervised Learning Algorithms for GLOF Analysis 25514.3.2.5 Choosing the Right Algorithm 25614.3.2.6 Objective 25714.3.2.7 Data Characteristics 25714.3.2.8 Benefits of Using Unsupervised Learning for GLOF 25714.3.2.9 Challenges and Considerations 25714.4 Deep Learning for GLOF Modeling 25814.4.1 Convolutional Neural Networks (CNNs) 25814.4.2 Recurrent Neural Networks (RNNs) 25814.4.3 Combining Different Deep Learning Techniques 25914.5 Existing Models for GLOF Modeling: A Comparison 26014.5.1 Statistical Models 26014.5.2 Machine Learning Models 26114.5.3 Deep Learning Models 26114.5.4 Comparison 26214.5.5 Choosing the Right Model 26214.5.6 Additional Considerations 26214.6 Future Models for GLOF Modeling 26314.6.1 Integration of Diverse Data Sources 26314.6.2 Explainable AI (XAI) 26314.6.3 Advanced Deep Learning Techniques 26414.6.4 Integration with Physical Modeling 26414.7 AI Challenges and Limitations 26514.8 Insights and Findings from AI-Based Modeling of GLOF Processes 26514.9 Evaluation of Methodology Used for AI-Based Modeling of GLOF Processes 26614.10 Conclusion 268References 26815 A Systematic Review of the GLOF Susceptibility Assessment Techniques 271Oushnik Banerjee, Anshu Kumari and Apoorva Shamra15.1 Introduction 27215.2 Glacial Lakes in the Western Himalayas 27315.2.1 Gangotri Glacier (Supra Glacial Lake) 27415.2.2 Samudra Tapu (Pro Glacial Lake) 27515.2.3 South Lhonak Lake (Unconnected Glacial- Fed Lake) 27515.2.4 Dal Lake (Non-Glacial-Fed) 27515.3 Sensitive Glacial Lake in the Western Himalayas 27615.3.1 Samudra Tapu Glacier 27615.4 GLOF Susceptibility Mapping Techniques 27715.4.1 Satellite Imagery Analysis 27715.4.2 Semi-Automated GLOF Susceptibility Assessment System 27815.4.3 Glacial Lake Mapping 27915.5 Stages of Glaciations 27915.6 Glacier Retreat 28115.7 Causes of Glacial Lake Change 28215.8 Depiction and Categorization of Glacial Lakes 28215.9 Study of Evaluating Parameters 28315.9.1 Sensitivity Evaluation 28315.9.2 Calculation of Weights and GLOF Susceptibility Index 28315.10 Summary 284Acknowledgment 285References 28516 Challenges of GLOF Estimation and Prediction 289Neelam Dahiya, Sartajvir Singh and Puninder Kaur16.1 Introduction 29016.2 Types of GLOF 29116.2.1 Glacial Lakes 29116.2.2 Moraine-Dammed Lake 29116.2.3 Ice-Dammed Lakes 29216.3 Reasons for GLOF Occurrence 29216.3.1 Glacial Retreat 29216.3.2 Geothermal Activity 29316.3.3 Avalanches 29316.3.4 Earthquakes and Landslides 29416.3.5 Human Activities 29416.3.6 Glacial Moraine Failure 29516.3.7 Glacier Lake Expansion 29516.3.8 Glacier Surging and Calving 29516.4 Challenges Faced for GLOF Estimation 29616.4.1 Early Detection 29616.4.2 Infrastructure Damage 29716.4.3 Loss of Life 29716.4.4 Economic Impact 29816.4.5 Environmental Degradation 29816.4.6 Climate Changes 29916.5 GLOF Solution 29916.6 Conclusion 299References 30017 Real-Time Earthquake Monitoring with Remote Sensing and AI Technology 303Koushik Sundar, Narayan Vyas and Neha Bhati17.1 Introduction 30417.2 Basics of AI and Remote Sensing 30517.2.1 AI Applications in Earthquake Monitoring 30617.2.1.1 Optical Remote Sensing 30617.2.1.2 Microwave Remote Sensing 30717.2.2 Satellites and Sensors 30817.2.3 AI and Remote Sensing for Integration in Monitoring Earthquakes 30817.2.4 Challenges and Future Directions 31017.3 Advances in Satellite Remote Sensing Techniques for Improved Earthquake Monitoring 31017.3.1 Comparative Analysis of Remote Sensing Satellites 31017.3.2 Comparison of Optical and Microwave Satellite Imagery 31117.3.3 Case Study on Pre- and Post-images of Earthquake in Doti District of Nepal 31317.4 How AI Is Currently Being Used in Remote Sensing to Monitor Earthquakes 31517.4.1 Automated Image Processing 31517.4.2 Seismic Data Augmentation 31617.4.3 Risk Assessment and Management 31617.4.4 Integrated Monitoring Systems 31717.5 Ongoing and Future Practical AI Applications in Remote Sensing 31817.5.1 More Sophisticated Prediction Models 31817.5.2 Real-Time Data Processing 31817.5.3 Damage and Recovery 31917.5.4 Public Safety and Community Resilience 31917.6 Conclusion 320References 32118 Enhancing Seismic-Events Identification and Analysis Using Machine Learning Approach 323Gurwinder Singh, Harun and Tejinder Pal Singh18.1 Introduction 32418.2 Methodology 32618.3 Results and Discussion 32918.3.1 ml Models 33318.3.2 ARIMA Models 33418.3.3 Neural Network Models 33518.3.4 Spatial Analysis 33818.4 Limitations 34018.5 Future Directions 34018.6 Conclusion and Future Scope 341References 341Index 343