Remote Sensing of Soil and Land Surface Processes

Monitoring, Mapping, and Modeling

1st Edition - October 31, 2023
Editors: Assefa Melesse, Omid Rahmati, Khabat Khsoravi
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 3 4 1 - 9
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 3 4 2 - 6

Remote Sensing of Soil and Land Surface Processes: Monitoring, Mapping, and Modeling couples artificial intelligence and remote sensing for mapping and modeling natural resources… Read more

Purchase options

LIMITED OFFER

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code is needed.

Institutional subscription on ScienceDirect

Request a sales quote

Remote Sensing of Soil and Land Surface Processes: Monitoring, Mapping, and Modeling couples artificial intelligence and remote sensing for mapping and modeling natural resources, thus expanding the applicability of AI and machine learning for soils and landscape studies and providing a hybridized approach that also increases the accuracy of image analysis. The book covers topics including digital soil mapping, satellite land surface imagery, assessment of land degradation, and deep learning networks and their applicability to land surface processes and natural hazards, including case studies and real life examples where appropriate.

This book offers postgraduates, researchers and academics the latest techniques in remote sensing and geoinformation technologies to monitor soil and surface processes.

Cover image
Title page
Table of Contents
Copyright
Contributors
Preface
Chapter 1. Introduction to soil and sediment
Chapter 2. DInSAR-based assessment of groundwater-induced land subsidence zonation map
2.1. Introduction
2.2. Application of DInSAR in monitoring of land subsidence
2.3. The DInSAR theory
2.4. Differential radar interferometry methodology
Chapter 3. Remotely sensed prediction of soil organic carbon
3.1. Introduction
3.2. Materials and methods
Chapter 4. Conceptual of soil moisture based on remote sensing and reanalysis dataset
4.1. Introduction
4.2. Scale dependency of soil moisture
4.3. Role of survey from space
4.4. Optical domain
4.5. Combine optical and thermal
4.6. Soil moisture using passive microwave
4.7. Soil moisture using active microwave
4.8. Soil moisture active passive (SMAP)
4.9. Soil moisture using reanalysis dataset
4.10. Future mission
4.11. Conclusion
Chapter 5. Dust-source monitoring using remote sensing techniques
5.1. Introduction
5.2. Aerosol and dust
5.3. Wind erosion and dust storms
5.4. Application of remote sensing in dust monitoring
5.5. Conclusion
Chapter 6. Land surface temperature and related issues
6.1. Introduction
6.2. Types of temperature
6.3. Methods to retrieve the land surface temperature
6.4. Land surface emissivity
6.5. Atmospheric transmissivity
6.6. Validation of LST
6.7. Future mission
6.8. Conclusion
Chapter 7. Unraveling the changes in soil properties availed by UAV-derivative data in an arid floodplain: Lessons learned and things to fathom
7.1. Introduction
7.2. Sampling design and soil analysis
7.3. Aerial images obtained from unmanned aerial vehicles and environmental covariates
7.4. Preparing of land suitability evaluation map
7.5. Case study
7.6. Conclusions
Chapter 8. Investigating the land use changes effects on the surface temperature using Landsat satellite data
8.1. Introduction
8.2. Remote sensing
8.3. Application of remote sensing in land use evaluation
8.4. The application of remote sensing in the assessment of land surface temperature
8.5. The land use change effects on the land surface temperature of Tehran city: As a case study
8.6. Conclusions
Chapter 9. The application of remote sensing on wetlands spatio-temporal change detection
9.1. Wetlands in our ecosystem
9.2. Remote sensing and wetlands
9.3. Vegetation indexes
9.4. Case study on wetland monitoring in Iran
Chapter 10. Machine learning modeling of the wind-erodible fraction of soils
10.1. Introduction
10.2. Wind-erodible fraction
10.3. Machine learning
10.4. Urmia Lake as an example
10.5. Physicochemical analysis and soil sampling
10.6. Wind-erodible fraction modeling
10.7. Modeling results
10.8. Main contributors
10.9. Conclusions
Chapter 11. Application of remote sensing techniques for evaluating land surface vegetation
11.1. Introduction
11.2. Vegetation indices
11.3. Various types of vegetation indices
11.4. Evaluating the vegetation variations trend
11.5. Conclusions
Chapter 12. A brief review of digital soil mapping in Iran
12.1. History of soil mapping in Iran
12.2. Digital soil mapping using advanced machine learning
12.3. Environmental covariates
12.4. Practical use of digital soil maps
12.5. Summary and future direction
Chapter 13. Impacts of land use and land cover changes on soil erosion
13.1. Introduction
13.2. Soil erosion in agricultural areas
13.3. Soil erosion in forest areas
13.4. Soil erosion in urban areas
13.5. Remote sensing in supporting soil erosion assessments
13.6. Final considerations
Chapter 14. Road-side slope erosion using MLS and remote sensing
14.1. Soil erosion and forest roads
14.2. Road erosion measurement
Chapter 15. Suspended sediment load prediction and tree-based algorithms
15.1. Introduction
15.2. Tree-based models
15.3. Example
15.4. Results and discussion
15.5. Qssl, ML, and remote sensing technique
15.6. Conclusion
Chapter 16. Soil erosion and sediment change detection using UAV technology
16.1. Introduction
16.2. Remote sensing for earth surface studies
16.3. RS-based earth surface change detection for sediment and soil erosion modeling
16.4. Conclusion
Chapter 17. Monitoring and detection of land subsidence
17.1. Introduction
17.2. Review and definitions
17.3. Material and methods
17.4. Results
17.5. Discussion
17.6. Conclusion
Appendix
Chapter 18. Drought mapping, modeling, and remote sensing
18.1. Introduction
18.2. Modeling temporal and spatial changes in drought
18.3. Monitoring temporal changes in drought
18.4. Change detection in drought intensity time series
18.5. Remotely sensed monitoring of changes in ecosystems in response to drought
18.6. Conclusions
Chapter 19. Predictive pedometric mapping of soil texture in small catchments: Application of the integrated computer-assisted digital maps, machine learning, and limited soil data
19.1. Introduction
19.2. Case studies across Iran
19.3. A rigorous predictive approach for pedometric mapping of soil texture
19.4. Soil development in different paired catchments
19.5. Prediction map of soil texture classes
19.6. Conclusions
Chapter 20. Object-based image analysis approach for gully erosion detection
20.1. Introduction
20.2. Soil erosion as a natural hazard
20.3. Types of soil erosion
20.4. The effects of soil erosion
20.5. Effects of gully erosion on land degradation
20.6. The effects of gully erosion on sediment production
20.7. The importance of monitoring gully erosion
20.8. Digital surface model generation
20.9. Gully extraction
Chapter 21. Landslide detection and monitoring using remote sensing approach
21.1. Introduction
21.2. Definition of landslide types
21.3. Identification, detection, mapping, and monitoring
21.4. Zagros area (Iran) as a case study
21.5. Conclusion
Chapter 22. Classification algorithms for remotely sensed images
22.1. Introduction
22.2. Different image classification approaches
22.3. The comparison between different image classification algorithms
22.4. Factors affect classification results
22.5. Conclusion
Chapter 23. Spatial analysis of sediment connectivity and its applications
23.1. Introduction
23.2. Sediment connectivity
23.3. Sediment transport
23.4. Measuring connectivity
23.5. Sediment fingerprinting
23.6. Index of sediment connectivity
23.7. Applications of sediment connectivity to assess and predict impact
23.8. Effects of sediment accumulation on check dams
23.9. Conclusions
Chapter 24. Soil properties mapping using the Google Earth Engine platform
24.1. Introduction
24.2. Soil properties
24.3. Google Earth Engine (GEE)
24.4. Case study
24.5. Conclusions
Chapter 25. Supportive role of remote sensing techniques for landslide susceptibility modeling
25.1. Introduction
25.2. Data
25.3. Method and experiments
25.4. Conclusions
Chapter 26. An overview of remotely sensed fuel variables for the prediction of wildfires
26.1. Introduction
26.2. Remotely sensed fuel moisture related variables
26.3. Remotely sensed fuel load-related variables
26.4. Conclusions
Chapter 27. Improving landslide susceptibility mapping using integration of ResU-Net technique and optimized machine learning algorithms
27.1. Introduction
27.2. Methodology
27.3. Description of ML models
27.4. Case study
27.5. Conclusion
Index

Assefa Melesse

Professor Assefa M. Melesse is a Professor of Water Resources Engineering at Florida International University. He earned his ME (2000) and PhD (2002) from the University of Florida in Agricultural Engineering. His areas of research and experience include climate change impact modeling, watershed modeling, ecohydrology, sediment transport, surface and groundwater interactions modeling, water–energy–carbon fluxes coupling and simulations, remote sensing hydrology, river basin management, and land cover change detection and scaling. Dr. Melesse is a registered Professional Engineer (PE) and also Diplomate of Water Resources Engineer (D. WRE) with over 30 years of teaching and research experience, and has authored/edited 7 books, over 215 journal articles, and over 90 book chapters.

Affiliations and expertise

Professor of Water Resources Engineering, Florida International University, Miami, FL, USA

Omid Rahmati

Dr. Omid Rahmati is a Geo-environmental Researcher and Assistant Professor at the AREEO institute, Iran. He has widespread research interests in risk, modeling, uncertainty, and decision-making in relation to natural hazards and natural resources management. He has published over 70 articles in international peer-reviewed journals and has been cited over 7000 times. He has been selected as the Highly Cited Researchers (the world’s top 1% scientists) in 2022 and 2023 based on the Web of Science (Clarivate) who has demonstrated broad and significant influence reflected in his publications over the last decade.

Affiliations and expertise

Department of Watershed Management, Kurdistan Agricultural and Natural Resources Research and Education Center, Agricultural Research Education and Extension Organization, Iran

Khabat Khsoravi

Dr. Khabat Khosravi is a Postdoctoral Researcher at Florida International University. His research areas are watershed hydrology, flood modeling, river engineering and bed-load sediment transport modeling, and the application of RSGIS and machine learning models in water/soil science and natural hazard assessment. In 2020, 2021, and 2022, he was in the world’s top 2% scientists list based on Stanford University data. In addition, he is an Associate Editor in Natural Hazards, Acta Geophysica, and Earth Science Informatics journals.

Affiliations and expertise

Postdoctoral Researcher, Florida international University and Ferdowsi University of Mashhad, USA