Remote Sensing Big Data (Springer Remote Sensing/Photogrammetry)

✍ Scribed by Liping Di, Eugene Yu

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 298
• Category: Library

✦ Synopsis

This monograph provides comprehensive coverage of the collection, management, and use of big data obtained from remote sensing. The book begins with an introduction to the basics of big data and remote sensing, laying the groundwork for the more specialized information to follow. The volume then goes on to address a wide variety of topics related to the use and management of remote sensing big data, including hot topics such as analysis through machine learning, cyberinfrastructure, and modeling. Examples on how to use the results of big data analysis of remotely sensed data for concrete decision-making are offered as well. The closing chapters discuss geospatial big data initiatives throughout the world and future challenges and opportunities for remote sensing big data applications.

The audience for this book includes researchers at the intersection of geoscience and data science, senior undergraduate and graduate students, and anyone else interested in how large datasets obtained through remote sensing can be best utilized. The book presents a culmination of 30 years of research from renowned spatial scientists Drs. Liping Di and Eugene Yu.

✦ Table of Contents

Contents
About the Authors
Chapter 1: Introduction
1.1 Concepts of Big Data
1.2 Features of Big Data
1.2.1 Big Data Volume
1.2.2 Big Data Velocity
1.2.3 Big Data Variety
1.2.4 Big Data Veracity
1.2.5 Big Data Value
1.3 Big Data Method and Technology
1.4 Remote Sensing Big Data
References
Chapter 2: Remote Sensing
2.1 Concepts
2.2 Sensors
2.2.1 Sensors by Radiometric Spectrums
2.2.1.1 Multi- and Hyperspectral Remote Sensing
2.2.1.2 Active Microwave Remote Sensing
2.2.1.3 Passive Microwave Remote Sensing
2.2.1.4 Active Optical Remote Sensing
2.2.1.5 GPS Remote Sensing
2.2.1.6 Imaging Sonar
2.2.2 Sensors by Work Mode
2.2.2.1 Frame
2.2.2.2 Whiskbroom
2.2.2.3 Pushbroom
2.2.2.4 Side Scanning
2.2.2.5 Conical Scanning
2.3 Platforms
2.3.1 Satellites
2.3.2 Airborne
2.3.3 In Situ
2.3.4 Shipborne
References
Chapter 3: Special Features of Remote Sensing Big Data
3.1 Volume of Remote Sensing Big Data
3.2 Variety of Remote Sensing Big Data
3.3 Velocity of Remote Sensing Big Data
3.4 Veracity of Remote Sensing Big Data
3.5 Value of Remote Sensing Big Data
References
Chapter 4: Remote Sensing Big Data Collection Challenges and Cyberinfrastructure and Sensor Web Solutions
4.1 Remote Sensing Big Data Collection Challenges
4.2 Remote Sensing Big Data Collection Cyberinfrastructure
4.2.1 Global Earth Observation System of Systems (GEOSS)
4.2.2 NASA Earth Observing System (EOS) Data and Information System (EOSDIS)
4.2.3 ESA Federated Earth Observation (FedEO)
4.3 Sensor Web
4.4 Applications
4.4.1 Climate
4.4.2 Weather
4.4.3 Disasters
4.4.4 Agriculture
References
Chapter 5: Remote Sensing Big Data Computing
5.1 Computing Power to Handle Big Data: Distributed and Parallel Computing
5.2 Evolution of Geospatial Computing Platform
5.2.1 Stand-Alone Software System Architecture
5.2.2 Client-Server Software System Architecture
5.2.3 Distributed Computing
5.3 Service-Oriented Architecture (SOA)
5.3.1 Service Roles
5.3.2 Service Operations
5.3.3 Service Chaining
5.3.4 Web Services
5.3.5 Common Technology Stack for Web Services
5.3.5.1 Web Services Description Language (WSDL)
5.3.5.2 Universal Description, Discovery, and Integration (UDDI)
5.3.5.3 The Simple Object Access Protocol (SOAP)
5.3.5.4 Business Process Execution Language (BPEL)
5.3.6 Web Service Applications
5.3.7 Web Service Standards
5.3.8 OGC Web Services
5.3.8.1 Operation Components
5.3.8.1.1 Client Services
5.3.8.1.2 Catalog and Registry Services
5.3.8.1.3 Data Services
5.3.8.1.4 Application Services
5.3.8.2 Data Components
5.3.8.2.1 Geospatial Data
5.3.8.2.2 Geospatial Metadata
5.3.8.2.3 Names
5.3.8.2.4 Relationship
5.3.8.2.5 Containers
5.4 High-Throughput Computing Infrastructure
5.4.1 Super Computing
5.4.2 Cluster Computer
5.4.3 Grid Computing
5.4.4 Cloud Computing
5.4.4.1 What Does the Cloud Provide?
5.4.4.2 What Make Cloud Possible?
5.4.4.3 Characteristics of Cloud Computing
5.4.4.4 Comparing Cloud Computing with Grid Computing
5.4.4.5 Software Platforms for Distributed Processing of Big Data in Cloud Computing
5.4.4.5.1 MapReduce with Hadoop
5.4.4.5.2 Spark
5.4.4.5.3 SCALE
5.4.4.5.4 Other Platforms
References
Chapter 6: Remote Sensing Big Data Management
6.1 Remote Sensing Big Data Governance
6.1.1 Strategy
6.1.2 Organizational Structure/Communications
6.1.3 Data Policy
6.1.4 Measurements
6.1.5 Technology
6.2 Remote Sensing Big Data Curation
6.2.1 Remote Sensing Big Data Organization
6.2.1.1 Data Format
6.2.1.2 Metadata
6.2.1.3 Map Projection
6.2.2 Remote Sensing Big Data Archiving
6.2.3 Remote Sensing Big Data Cataloging
6.2.4 Remote Sensing Big Data Quality Assessment
6.2.5 Remote Sensing Big Data Usability
6.2.6 Remote Sensing Big Data Version Control
6.3 Remote Sensing Big Data Dissemination Services
6.3.1 Data Discovery
6.3.2 Data Access
References
Chapter 7: Standards for Big Data Management
7.1 Standards for Remote Sensing Data Archiving
7.2 Standards for Remote Sensing Big Data Metadata
7.2.1 What Is Metadata?
7.2.2 The FGDC Content Standard for Digital Geospatial Metadata
7.2.3 The FGDC Remote Sensing Metadata Extensions
7.2.4 ISO 19115 Geographic Information—Metadata
7.2.4.1 ISO 19115-2
7.2.4.2 ISO 19115-1
7.2.5 ISO Standards for Data Quality
7.3 Standards for Remote Sensing Big Data Format
7.4 Standards for Remote Sensing Big Data Discovery
7.4.1 OGC Catalog Service for Web (CSW)
7.4.2 OpenSearch
7.5 Standards for Remote Sensing Big Data Access
7.5.1 OGC Web Coverage Service (WCS)
7.5.2 OGC Web Feature Service (WFS)
7.5.3 OGC Web Map Service (WMS)
7.5.4 OGC Sensor Observation Service (SOS)
7.5.5 OpenDAP
References
Chapter 8: Implementation Examples of Big Data Management Systems for Remote Sensing
8.1 CWIC
8.1.1 Introduction
8.1.2 CEOS WGISS
8.1.3 CWIC Architecture Design
8.1.4 CWIC System Implementation
8.1.5 Results and Conclusion
8.1.6 Future Work
8.2 The Registry in GEOSS GCI
8.2.1 Background
8.2.1.1 GEO
8.2.1.2 The Role of the Registry
8.2.2 The GEOSS Component and Service Registry
8.2.2.1 Functionalities
8.2.2.2 Concept
8.2.2.3 System Design
8.2.3 System Implementation
8.2.3.1 Logical Design and Main Functionalities
8.2.3.2 Registry Pages
8.2.3.3 The Registry
References
Chapter 9: Big Data Analytics for Remote Sensing: Concepts and Standards
9.1 Big Data Analytics Concepts
9.1.1 What Is Big Data Analytics?
9.1.2 Categories of Big Data Analytics
9.1.3 Big Data Analytics Use Cases
9.2 Remote Sensing Big Data Analytics Concepts
9.2.1 Remote Sensing Big Data Challenges
9.2.2 Categories of Remote Sensing Big Data Analytics
9.2.3 Processes of Remote Sensing Big Data Analytics
9.2.4 Objectives of Remote Sensing Big Data Analytics
9.3 Big Data Analytics Standards
9.3.1 IEEE Big Data Analytics Standards
9.3.2 ISO Big Data Working Group: ISO/IEC JTC 1/SC 42/WG 2
References
Chapter 10: Big Data Analytic Platforms
10.1 Big Data Analytic Platforms
10.2 Data Storage Strategy in Big Data Analytic Platforms
10.3 Data-Processing Strategy in Big Data Analytic Platforms
10.4 Tools in Big Data Analytic Platforms
10.5 Data Visualization in Big Data Analytic Platforms
10.6 Remote Sensing Big Data Analytic Platforms
10.6.1 GeoMesa
10.6.2 GeoTrellis
10.6.3 RasterFrames
10.7 Remote Sensing Big Data Analytic Services
10.7.1 Google Earth Engine
10.7.2 EarthServer—an Open Data Cube
10.7.3 NASA Earth Exchange
10.7.4 NASA Giovanni
10.7.5 Others
References
Chapter 11: Algorithmic Design Considerations of Big Data Analytics
11.1 Complexity of Remote Sensing Big Data Analytic Algorithms
11.2 Challenges and Algorithm Design Considerations from Volume
11.3 Challenges and Algorithm Design Considerations from Velocity
11.4 Challenges and Algorithm Design Considerations from Variety
11.5 Challenges and Algorithm Design Considerations from Veracity
11.6 Challenges and Algorithm Design Considerations from Value
References
Chapter 12: Machine Learning and Data Mining Algorithms for Geospatial Big Data
12.1 Distributed and Parallel Learning
12.2 Data Reduction and Approximate Computing
12.2.1 Sampling
12.2.2 Approximate Computing
12.3 Feature Selection and Feature Extraction
12.4 Incremental Learning
12.5 Deep Learning
12.6 Ensemble Analysis
12.7 Granular Computing
12.8 Stochastic Algorithms
12.9 Transfer Learning
12.10 Active Learning
References
Chapter 13: Modeling, Prediction, and Decision Making Based on Remote Sensing Big Data
13.1 A General Framework
13.2 Modeling
13.2.1 Data Models and Structures
13.2.2 Modeling with Remote Sensing Big Data
13.2.3 Validation with Remote Sensing Big Data
13.3 Decision Making
References
Chapter 14: Examples of Remote Sensing Applications of Big Data Analytics—Fusion of Diverse Earth Observation Data
14.1 The Concept of Data Fusion
14.1.1 Definitions
14.1.2 Classification of Data Fusion
14.2 Data Fusion Architectures
14.3 Fusion of MODIS and Landsat with Deep Learning
14.3.1 The Problem
14.3.2 Data Fusion Methods
References
Chapter 15: Examples of Remote Sensing Applications of Big Data Analytics—Agricultural Drought Monitoring and Forecasting
15.1 Agricultural Drought
15.2 Remote Sensing Big Data for Agricultural Drought
15.3 Geospatial Data Analysis Infrastructure GeoBrain
15.4 The Global Agricultural Drought Monitoring and Forecasting System Portal
References
Chapter 16: Examples of Remote Sensing Applications of Big Data Analytics—Land Cover Time Series Creation
16.1 Remote Sensing Big Data for Land Cover Classification
16.2 Land Cover Classification Methodology
16.3 Results and Discussions
References
Chapter 17: Geospatial Big Data Initiatives in the World
17.1 US Federal Government Big Data Initiative
17.1.1 Big Earth Data Initiative
17.1.2 NSF EarthCube
17.2 Big Data Initiative in China
17.3 Big Data Initiatives in Europe
17.4 Big Data Initiatives in Australia
17.5 Other Big Data Initiatives
References
Chapter 18: Challenges and Opportunities in the Remote Sensing Big Data
18.1 Challenges
18.2 Opportunities
References
Index