Cover Image

Google Earth Engine and Artificial Intelligence for Earth Observation : Algorithms and Sustainable Applications /

Show other versions (1)

Google Earth Engine and Artificial Intelligence for Earth Observation: Algorithms and Sustainable Applications explores a wide range of transformative data fusion techniques of Artificial Intelligence (AI) technologies applied to Google Earth Engine (GEE) techniques. It includes a wide range of scie...

Full description

Bibliographic Details
Corporate Author: ScienceDirect (Online service)
Other Authors: Sood, Vishakha
Format: eBook
Language:English
Published: Amsterdam : Elsevier, 2025.
Series:Earth observation series.
Subjects:
Google Earth.
Earth sciences > Remote sensing.
Earth (Planet)
Artificial intelligence > Geophysical applications.
Sciences de la terre > Télédétection.
Terre.
Intelligence artificielle > Applications géophysiques.
Electronic books.
Online Access:Connect to the full text of this electronic book
Table of Contents:
  • Front Cover
  • Google Earth Engine and Artificial Intelligence for Earth Observation
  • Google Earth Engine and Artificial Intelligence for Earth Observation: Algorithms and Sustainable Applications
  • Copyright
  • Contents
  • Contributors
  • A
  • Introduction of AI-driven GEE cloud computing-based remote sensing
  • 1
  • Introduction to Google Earth Engine: A comprehensive workflow
  • 1. Introduction
  • 2. Difference between AWS and GEE
  • 3. Platform overview
  • 4. Data category
  • 5. Earth Engine basics
  • 5.1 Hello world
  • 5.2 Basic variables and objects
  • 5.3 Importing data from satellites
  • 5.4 Monitoring rainfall pattern of India
  • 5.5 Representing the monitored data in the form of chart
  • 5.6 Extracting the data in CSV format
  • 6. Area of improvement
  • 7. Conclusion and future scope
  • References
  • 2
  • Role of GEE in earth observation via remote sensing
  • 1. Introduction
  • 2. AI/ML based remote sensing data analysis
  • 2.1 GEE applications for LULC
  • 3. GEE applications in UHI and challenges
  • 4. GEE in water resource management
  • 5. Conclusions
  • References
  • 3
  • A meta-analysis of Google Earth Engine in different scientific domains
  • 1. Introduction
  • 2. Material and methods
  • 3. Meta-analysis
  • 3.1 Overall trend of GEE-related papers in the Scopus repository
  • 3.2 Country-wise research contributions to GEE
  • 3.3 Publications by journals
  • 3.4 Research discipline or subject areas
  • 3.5 Keywords analysis by cooccurrence network
  • 4. Conclusion
  • References
  • 4
  • Exploration of science of remote sensing and GIS with GEE
  • 1. Introduction
  • 1.1 GIS remote sensing
  • 1.2 Importance of remote sensing
  • 1.3 Advantages of microwave remote sensing
  • 2. Key features and capabilities of GEE
  • 2.1 Remote sensing data resources
  • 2.2 Orbits
  • 2.3 Utilizing the electromagnetic spectrum for observation
  • 2.4 Sensors.
  • 2.5 Image processing and analysis with GEE
  • 2.6 Preprocessing
  • 2.7 Enhancement
  • 2.8 Spectral analysis
  • 2.9 Image classification
  • 2.10 Change detection
  • 2.11 Data fusion
  • 2.12 Image compression and storage
  • 2.13 Accessing and importing image
  • 3. Image classification techniques
  • 3.1 Types of image classification
  • 3.1.1 Supervised classification
  • 3.1.2 Unsupervised classification
  • 3.1.3 Object-based image analysis (OBIA)
  • 3.1.4 Role of machine learning algorithms
  • 4. Implementation in GEE
  • 4.1 Loading training data
  • 4.2 Supervised classification
  • 4.3 Unsupervised classification
  • 4.4 Assessment and validation
  • 4.5 Considerations and limitations
  • 4.6 Integration with spatial analysis
  • 5. Spatial analysis and GIS functions in GEE
  • 5.1 Spatial analysis by using GIS.
  • 5.2 Overlay analysis
  • 5.3 Spatial analysis techniques
  • 5.4 Leveraging GEE for time series analysis
  • 5.5 Temporal image collections
  • 5.6 Temporal filters
  • 5.7 Image stacking
  • 5.8 Temporal operations
  • 5.9 Visualization tools
  • 6. Monitoring changes over time using temporal satellite imagery
  • 6.1 Land cover change detection
  • 6.1.1 NDVI time series
  • 6.1.2 Land cover transitions
  • 6.1.3 Urban expansion and development
  • 7. Vegetation dynamics
  • 8. Water bodies and hydrological changes
  • 9. Case studies demonstrating the application of time series analysis
  • 9.1 Agricultural monitoring
  • 9.2 Management of natural resources
  • 9.3 Impact studies on climate change
  • 9.4 Disaster monitoring and response
  • 9.5 Considerations and best practices
  • 9.6 Integration with other GEE capabilities
  • 10. Various applications of GIS and remote sensing
  • 10.1 Analysis and visualization of particular sites
  • 10.2 Sustainable planning and development
  • 10.3 Infrastructure safety
  • 10.4 Land cover mapping.
  • 10.5 Agricultural applications
  • 10.6 Disaster management and earth sciences
  • 11. Challenges and future trends
  • 11.1 Data quality and accuracy
  • 11.2 Data availability and accessibility
  • 11.3 Data analysis and interpretation
  • 11.4 Data management and security
  • 12. Conclusion
  • References
  • 5
  • Cloud computing platforms-based remote sensing big data applications
  • 1. Introduction
  • 2. GEE overview
  • 2.1 Earth engine dataset
  • 2.2 Functions and operations
  • 2.3 Applications
  • 2.3.1 Vegetation
  • 2.3.2 Agriculture
  • 2.3.3 Natural disaster
  • 2.3.4 Image processing
  • 2.3.5 Climate change studies
  • 2.3.6 Others
  • 3. Conclusion
  • References
  • 6
  • Role of various machine and deep learning classification algorithms in Google Earth Engine: A comparative analysis
  • 1. Introduction
  • 1.1 Background
  • 1.2 Significance of comparing different classification algorithms
  • 2. ML and DL approaches
  • 2.1 Supervised learning
  • 2.2 Semisupervised learning
  • 2.3 Unsupervised learning
  • 2.4 Reinforcement learning
  • 3. Machine learning classification algorithms in GEE
  • 3.1 Logistic regression (LR)
  • 3.2 Decision trees (DT)
  • 3.3 Random forest (RF)
  • 3.4 Support vector machine (SVM)
  • 3.5 k-nearest neighbors (KNN)
  • 4. Deep learning classification algorithms in GEE
  • 4.1 Artificial neural networks (ANN)
  • 4.2 Convolutional neural networks (CNN)
  • 4.3 Long short-term memory (LSTM) networks
  • 4.4 Gradient boosting decision trees (GBDT) (e.g., XGBoost, LightGBM)
  • 5. GEE integrating with AI: The state of the ART
  • 6. Performance metrics
  • 6.1 Precision
  • 6.2 Accuracy
  • 6.3 Recall
  • 6.4 F1 score
  • 7. Conclusion
  • Declaration of funding
  • Acknowledgment
  • References
  • 7
  • Google Earth Engine and artificial intelligence for SDGs
  • 1. Introduction
  • 2. Methodology
  • 3. Applications of GEE and AI for SDGs.
  • 3.1 SDG 11
  • GEE and AI for sustainable cities
  • 3.2 SDG 3 and 6
  • GEE and AI for health and water
  • 3.3 SDG 7 and 13
  • GEE and AI for energy and climate action
  • 3.4 SDG 15
  • GEE and AI for life on land
  • 4. Challenges, opportunities and future outlook of GEE and AI for SDGs
  • 5. Conclusion
  • Acknowledgments
  • Funding
  • References
  • Further reading
  • B
  • Emerging applications of GEE in earth observation
  • 8
  • Machine learning algorithms for air quality and air pollution monitoring using GEE
  • 1. Introduction
  • 1.1 Effects of air pollution on human health
  • 1.1.1 Particulate matter
  • 1.1.2 Nitrogen dioxide
  • 1.1.3 Ozone
  • 1.1.4 Carbon monoxide
  • 1.1.5 Sulfur dioxide
  • 1.2 Effects of air pollution on environment
  • 1.2.1 Climate change
  • 1.2.2 Floods
  • 1.2.3 Harmful effects on crops
  • 1.2.4 Soil acidification
  • 1.2.5 Wildlife
  • 1.2.6 Eutrophication
  • 1.2.7 Acid rain
  • 1.2.8 Wildfires
  • 1.3 Anthropogenic sources of air pollution
  • 1.3.1 Industries
  • 1.3.2 Vehicular exhaust
  • 1.3.3 Thermal power plants
  • 1.3.4 Waste burning
  • 1.3.5 Crop residue burning
  • 1.3.6 Brick kilns
  • 1.3.7 Residential biofuel burning
  • 1.4 Air quality index
  • 2. Study area
  • 3. Dataset used
  • 3.1 Copernicus DEM GLO-30: Global 30 m digital elevation model
  • 3.2 CPCB CAAQMS data
  • 3.3 Dynamic world V1
  • 3.4 ERA5-land daily
  • 3.5 GHSL: Global population surfaces 1975-2030
  • 3.6 MODIS aerosol optical depth daily L2G
  • 3.7 MODIS NDVI
  • 3.8 Sentinel- 5P TROPOMI
  • 3.9 VIIRS daily gridded day night band 500m
  • 4. Methods
  • 4.1 Machine learning regression
  • 4.2 R2 and root mean square error
  • 5. Methodology
  • 6. Results and discussions
  • 6.1 Satellite maps for seasonal variation of pollutants
  • 6.2 Retrieval of air pollutants through random forest regression
  • 6.3 Air quality index maps
  • 7. Conclusion
  • References
  • Further reading.
  • 9
  • Investigation of surface water dynamics from the Landsat series using Google Earth Engine: A case study of Lake ...
  • 1. Introduction
  • 2. Study area
  • 3. Material and method
  • 3.1 Google Earth Engine platform
  • 3.2 Used data
  • 3.3 Water surface detection and accuracy assessment
  • 4. Results
  • 4.1 Accuracy assessment in detecting water surface dynamics
  • 4.2 Dynamics of surface water in terms of area and spatial distribution
  • 5. Discussion
  • 6. Conclusion
  • Funding
  • References
  • 10
  • Monitoring of land cover changes and dust events over the last 2decades using Google Earth Engine: Hamoun wetl ...
  • 1. Introduction
  • 2. Materials and method
  • 2.1 Case study
  • 2.2 Methodology
  • 2.2.1 Aerosol Optical Depth
  • 2.2.2 Normalized Difference Vegetation Index
  • 2.2.3 Normalized Difference Water Index
  • 3. Results and discussion
  • 4. Conclusions
  • References
  • 11
  • Leveraging Google Earth Engine for improved groundwater management and sustainability
  • 1. Introduction
  • 2. Methodology
  • 2.1 Data collection and processing
  • 2.2 Terrestrial and groundwater storage
  • 2.3 Linear regression
  • 3. Results and discussion
  • 4. Conclusion
  • Data availability
  • References
  • 12
  • Customized spatial data cube of urban environs using Google Earth Engine (GEE)
  • 1. Introduction
  • 2. Customized spatial data cube of urban environs
  • 2.1 Generation of data science products
  • 2.1.1 Temporal land cover datasets
  • 2.1.2 Temporal land surface temperature (LST) datasets
  • 2.1.3 Urban growth modeling
  • 2.1.4 Multisensor data normalization for nigh time light data analysis
  • 2.2 Creation of Web Application using GEE platform to access and analyze the data science products
  • 3. Web user interfaces to access the customized data cube
  • 3.1 User interface for temporal urban growth and LST analysis.