Atnaujinkite slapukų nuostatas

El. knyga: Multisensor Data Fusion and Machine Learning for Environmental Remote Sensing

4.50/5 (4 ratings by Goodreads)
(University of Central Florida, Orlando, USA), (University of Central Florida, Orlando, USA)
  • Formatas: 528 pages
  • Išleidimo metai: 21-Feb-2018
  • Leidėjas: CRC Press Inc
  • Kalba: eng
  • ISBN-13: 9781498774345
Kitos knygos pagal šią temą:
Multisensor Data Fusion and Machine Learning for Environmental Remote SensingDidesnis paveikslėlis
  • Formatas: 528 pages
  • Išleidimo metai: 21-Feb-2018
  • Leidėjas: CRC Press Inc
  • Kalba: eng
  • ISBN-13: 9781498774345
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

In the last few years the scientific community has realized that obtaining a better understanding of interactions between natural systems and the man-made environment across different scales demands more research efforts in remote sensing. An integrated Earth system observatory that merges surface-based, air-borne, space-borne, and even underground sensors with comprehensive and predictive capabilities indicates promise for revolutionizing the study of global water, energy, and carbon cycles as well as land use and land cover changes.

The aim of this book is to present a suite of relevant concepts, tools, and methods of integrated multisensor data fusion and machine learning technologies to promote environmental sustainability. The process of machine learning for intelligent feature extraction consists of regular, deep, and fast learning algorithms. The niche for integrating data fusion and machine learning for remote sensing rests upon the creation of a new scientific architecture in remote sensing science that is designed to support numerical as well as symbolic feature extraction managed by several cognitively oriented machine learning tasks at finer scales. By grouping a suite of satellites with similar nature in platform design, data merging may come to help for cloudy pixel reconstruction over the space domain or concatenation of time series images over the time domain, or even both simultaneously.

Organized in 5 parts, from Fundamental Principles of Remote Sensing; Feature Extraction for Remote Sensing; Image and Data Fusion for Remote Sensing; Integrated Data Merging, Data Reconstruction, Data Fusion, and Machine Learning; to Remote Sensing for Environmental Decision Analysis, the book will be a useful reference for graduate students, academic scholars, and working professionals who are involved in the study of Earth systems and the environment for a sustainable future. The new knowledge in this book can be applied successfully in many areas of environmental science and engineering.
Preface xv
Acknowledgments xvii
Authors xix
Chapter 1 Introduction
1(10)
1.1 Background
1(2)
1.2 Objectives and Definitions
3(2)
1.3 Featured Areas of the Book
5(2)
References
7(4)
Part I Fundamental Principles of Remote Sensing
Chapter 2 Electromagnetic Radiation and Remote Sensing
11(12)
2.1 Introduction
11(1)
2.2 Properties of Electromagnetic Radiation
12(1)
2.3 Solar Radiation
12(1)
2.4 Atmospheric Radiative Transfer
13(3)
2.4.1 Principles of Radiative Transfer
13(2)
2.4.2 Reflection
15(1)
2.4.3 Refraction
15(1)
2.5 Remote Sensing Data Collection
16(3)
2.5.1 Atmospheric Windows for Remote Sensing
16(2)
2.5.2 Specific Spectral Region for Remote Sensing
18(1)
2.5.3 Band Distribution for Remote Sensing
18(1)
2.6 Rationale of Thermal Remote Sensing
19(2)
2.6.1 Thermal Radiation
19(1)
2.6.2 Energy Budget and Earth's Net Radiation
20(1)
2.7 Basic Terminologies of Remote Sensing
21(1)
2.8 Summary
22(1)
References
22(1)
Chapter 3 Remote Sensing Sensors and Platforms
23(24)
3.1 Introduction
23(1)
3.2 Remote Sensing Platforms
24(2)
3.2.1 Space-Borne Platforms
24(2)
3.2.2 Air-Borne Platforms
26(1)
3.2.3 Ground- or Sea-Based Platforms
26(1)
3.3 Remote Sensing Sensors
26(4)
3.3.1 Passive Sensors
28(1)
3.3.2 Active Sensors
29(1)
3.4 Real-World Remote Sensing Systems
30(5)
3.5 Current, Historical, and Future Important Missions
35(5)
3.5.1 Current Important Missions
35(1)
3.5.2 Historic Important Missions
36(2)
3.5.3 Future Important Missions
38(2)
3.6 System Planning of Remote Sensing Applications
40(4)
3.7 Summary
44(1)
References
44(3)
Chapter 4 Image Processing Techniques in Remote Sensing
47(22)
4.1 Introduction
47(1)
4.2 Image Processing Techniques
47(10)
4.2.1 Pre-Processing Techniques
48(6)
4.2.1.1 Atmospheric Correction
48(1)
4.2.1.2 Radiometric Correction
49(1)
4.2.1.3 Geometric Correction
50(1)
4.2.1.4 Geometric Transformation
51(1)
4.2.1.5 Resampling
52(1)
4.2.1.6 Mosaicking
53(1)
4.2.1.7 Gap Filling
53(1)
4.2.2 Advanced Processing Techniques
54(3)
4.2.2.1 Image Enhancement
54(1)
4.2.2.2 Image Restoration
55(1)
4.2.2.3 Image Transformation
55(1)
4.2.2.4 Image Segmentation
56(1)
4.3 Common Software for Image Processing
57(4)
4.3.1 ENVI
58(1)
4.3.2 ERDAS IMAGINE
58(1)
4.3.3 PCI Geomatica
59(1)
4.3.4 ArcGIS
59(1)
4.3.5 MATLAB®
60(1)
4.3.6 IDL
61(1)
4.4 Summary
61(1)
References
61(8)
Part II Feature Extraction for Remote Sensing
Chapter 5 Feature Extraction and Classification for Environmental Remote Sensing
69(26)
5.1 Introduction
69(2)
5.2 Feature Extraction Concepts and Fundamentals
71(6)
5.2.1 Definition of Feature Extraction
71(1)
5.2.2 Feature and Feature Class
72(2)
5.2.3 Fundamentals of Feature Extraction
74(3)
5.3 Feature Extraction Techniques
77(4)
5.3.1 Spectral-Based Feature Extraction
77(3)
5.3.2 Spatial-Based Feature Extraction
80(1)
5.4 Supervised Feature Extraction
81(3)
5.5 Unsupervised Feature Extraction
84(1)
5.6 Semi-supervised Feature Extraction
84(1)
5.7 Image Classification Techniques with Learning Algorithms
85(2)
5.8 Performance Evaluation Metric
87(2)
5.9 Summary
89(1)
References
89(6)
Chapter 6 Feature Extraction with Statistics and Decision Science Algorithms
95(32)
6.1 Introduction
95(1)
6.2 Statistics and Decision Science-Based Feature Extraction Techniques
96(24)
6.2.1 Filtering Operation
96(3)
6.2.2 Mathematical Morphology
99(3)
6.2.3 Decision Tree Learning
102(3)
6.2.3.1 Decision Tree Classifier
102(2)
6.2.3.2 RF Classifier
104(1)
6.2.4 Cluster Analysis
105(3)
6.2.4.1 Connectivity-Based Clustering
105(1)
6.2.4.2 Centroid-Based Clustering
106(1)
6.2.4.3 Density-Based Clustering
106(1)
6.2.4.4 Distribution-Based Clustering
107(1)
6.2.5 Regression and Statistical Modeling
108(5)
6.2.5.1 Linear Extrapolation and Multivariate Regression
108(1)
6.2.5.2 Logistic Regression
109(4)
6.2.6 Linear Transformation
113(4)
6.2.6.1 Principal Component Analysis (PCA)
113(2)
6.2.6.2 Linear Discriminant Analysis (LDA)
115(1)
6.2.6.3 Wavelet Transform
116(1)
6.2.7 Probabilistic Techniques
117(13)
6.2.7.1 Maximum Likelihood Classifier (MLC)
117(1)
6.2.7.2 Naive Bayes Classifier
118(2)
6.3 Summary
120(1)
References
120(7)
Chapter 7 Feature Extraction with Machine Learning and Data Mining Algorithms
127(40)
7.1 Introduction
127(3)
7.2 Genetic Programming
130(7)
7.2.1 Modeling Principles and Structures
130(2)
7.2.2 Illustrative Example
132(5)
7.3 Artificial Neural Networks
137(7)
7.3.1 Single-Layer Feedforward Neural Networks and Extreme Learning Machine
138(4)
7.3.2 Radial Basis Function Neural Network
142(2)
7.4 Deep Learning Algorithms
144(9)
7.4.1 Deep Learning Machine
144(2)
7.4.2 Bayesian Networks
146(4)
7.4.3 Illustrative Example
150(3)
7.5 Support Vector Machine
153(5)
7.5.1 Classification Based on SVM
153(3)
7.5.2 Multi-Class Problem
156(1)
7.5.3 Illustrative Example
156(2)
7.6 Particle Swarm Optimization Models
158(2)
7.7 Summary
160(1)
References
161(6)
Part III Image and Data Fusion for Remote Sensing
Chapter 8 Principles and Practices of Data Fusion in Multisensor Remote Sensing for Environmental Monitoring
167(28)
8.1 Introduction
167(1)
8.2 Concepts and Basics of Image and Data Fusion
168(3)
8.2.1 Pixel-Level Fusion
169(1)
8.2.2 Feature-Level Fusion
170(1)
8.2.3 Decision-Level Fusion
170(1)
8.3 Image and Data Fusion Technology Hubs
171(14)
8.3.1 Multispectral Remote Sensing-Based Fusion Techniques
171(5)
8.3.1.1 Image and Data Fusion with the Aid of Pre-Processors
171(2)
8.3.1.2 Image and Data Fusion with the Aid of Feature Extractors
173(1)
8.3.1.3 Uncertainty-Based Approaches for Multi-Resolution Fusion
173(1)
8.3.1.4 Matrix Factorization Approaches across Spatiotemporal and Spectral Domains
174(1)
8.3.1.5 Hybrid Approaches
174(1)
8.3.1.6 Environmental Applications
175(1)
8.3.2 Hyperspectral Remote Sensing-Based Fusion Techniques
176(4)
8.3.2.1 Data Fusion between Hyperspectral and Multispectral Images
178(1)
8.3.2.2 Data Fusion between Hyperspectral Images and LiDAR Data
179(1)
8.3.2.3 Hybrid Approach
179(1)
8.3.2.4 Environmental Applications
180(1)
8.3.3 Microwave Remote Sensing-Based Fusion Techniques
180(16)
8.3.3.1 Data Fusion between SAR and the Optical Imageries
182(1)
8.3.3.2 Data Fusion between SAR and LiDAR or Laser Altimeter
183(1)
8.3.3.3 Data Fusion between SAR, Polarimetric, and Interferometric SAR or Others
184(1)
8.3.3.4 Environmental Applications
184(1)
8.4 Summary
185(2)
References
187(8)
Chapter 9 Major Techniques and Algorithms for Multisensor Data Fusion
195(34)
9.1 Introduction
195(1)
9.2 Data Fusion Techniques and Algorithms
196(22)
9.2.1 Pan-Sharpening
197(5)
9.2.1.1 Component Substitution
198(2)
9.2.1.2 Relative Spectral Contribution
200(1)
9.2.1.3 High Frequency Injection
200(1)
9.2.1.4 Multi-Resolution Transformation
201(1)
9.2.1.5 Statistical and Probabilistic Methods
201(1)
9.2.2 Statistical Fusion Methods
202(4)
9.2.2.1 Regression-Based Techniques
202(1)
9.2.2.2 Geostatistical Approaches
202(1)
9.2.2.3 Spatiotemporal Modeling Algorithms
203(3)
9.2.3 Unmixing-Based Fusion Methods
206(3)
9.2.4 Probabilistic Fusion Methods
209(3)
9.2.5 Neural Network-Based Fusion Methods
212(3)
9.2.6 Fuzzy Set Theory-Based Fusion Methods
215(1)
9.2.7 Support Vector Machine-Based Fusion Methods
215(1)
9.2.8 Evolutionary Algorithms
215(2)
9.2.9 Hybrid Methods
217(1)
9.3 Summary
218(1)
References
219(10)
Chapter 10 System Design of Data Fusion and the Relevant Performance Evaluation Metrics
229(18)
10.1 Introduction
229(1)
10.2 System Design of Suitable Data Fusion Frameworks
230(4)
10.2.1 System Design for Data Fusion-Case 1
230(2)
10.2.2 System Design for Data Fusion-Case 2
232(2)
10.2.3 The Philosophy for System Design of Data Fusion
234(1)
10.3 Performance Evaluation Metrics for Data Fusion
234(7)
10.3.1 Qualitative Analysis
235(1)
10.3.2 Quantitative Analysis
235(12)
10.3.2.1 Without Reference Image
235(2)
10.3.2.2 With Reference Image
237(4)
10.4 Summary
241(1)
References
241(6)
Part IV Integrated Data Merging, Data Reconstruction, Data Fusion, and Machine Learning
Chapter 11 Cross-Mission Data Merging Methods and Algorithms
247(30)
11.1 Introduction
247(3)
11.1.1 Data Merging with Bio-Optical or Geophysical Models
248(1)
11.1.2 Data Merging with Machine Learning Techniques
248(1)
11.1.3 Data Merging with Statistical Techniques
249(1)
11.1.4 Data Merging with Integrated Statistical and Machine Learning Techniques
249(1)
11.2 The SIASS Algorithm
250(12)
11.2.1 Data Merging via SIASS
250(12)
11.2.1.1 SVD
255(1)
11.2.1.2 Q-Q adjustment
255(3)
11.2.1.3 EMD
258(1)
11.2.1.4 ELM
259(3)
11.2.1.5 Performance Evaluation
262(1)
11.3 Illustrative Example for Demonstration
262(11)
11.3.1 Study Area
262(1)
11.3.2 Baseline Sensor Selection
263(3)
11.3.3 Systematic Bias Correction
266(3)
11.3.4 Location-Dependent Bias Correction
269(1)
11.3.5 Spectral Information Synthesis
269(4)
11.4 Summary
273(1)
References
274(3)
Chapter 12 Cloudy Pixel Removal and Image Reconstruction
277(24)
12.1 Introduction
277(6)
12.2 Basics of Cloud Removal for Optical Remote Sensing Images
283(2)
12.2.1 Substitution Approaches
283(1)
12.2.2 Interpolation Approaches
284(1)
12.3 Cloud Removal with Machine Learning Techniques
285(11)
12.4 Summary
296(1)
References
296(5)
Chapter 13 Integrated Data Fusion and Machine Learning for Intelligent Feature Extraction
301(22)
13.1 Introduction
301(3)
13.1.1 Background
301(1)
13.1.2 The Pathway of Data Fusion
302(2)
13.2 Integrated Data Fusion and Machine Learning Approach
304(13)
13.2.1 Step 1-Data Acquisition
305(1)
13.2.2 Step 2-Image Processing and Preparation
306(1)
13.2.3 Step 3-Data Fusion
307(1)
13.2.4 Step 4-Machine Learning for Intelligent Feature Extraction
308(4)
13.2.5 Step 5-Water Quality Mapping
312(5)
13.3 Summary
317(1)
Appendix 1: Ground-Truth Data
318(1)
Appendix 2
319(1)
References
319(4)
Chapter 14 Integrated Cross-Mission Data Merging, Fusion, and Machine Learning Algorithms Toward Better Environmental Surveillance
323(22)
14.1 Introduction
323(2)
14.2 Architecture of CDIRM
325(11)
14.2.1 Image Pre-Processing
327(1)
14.2.2 Data Merging via SIASS
328(2)
14.2.3 Data Reconstruction via SMIR
330(4)
14.2.4 Feature Extraction and Content-Based Mapping
334(2)
14.3 Summary
336(3)
Appendix: Field Data Collection for Ground Truthing
339(2)
References
341(4)
Part V Remote Sensing for Environmental Decision Analysis
Chapter 15 Data Merging for Creating Long-Term Coherent Multisensor Total Ozone Record
345(30)
15.1 Introduction
345(3)
15.2 Data Collection and Analysis
348(3)
15.2.1 OMPS TCO Data
348(1)
15.2.2 OMI TCO Data
349(1)
15.2.3 WOUDC TCO Data
350(1)
15.2.4 Comparative Analysis of TCO Data
351(1)
15.3 Statistical Bias Correction Scheme
351(9)
15.3.1 Basics of the Q-Q Adjustment Method in This Study
355(4)
15.3.1.1 Traditional Bias Correction Method
355(2)
15.3.1.2 Modified Bias Correction Method
357(2)
15.3.2 Overall Inconsistency Index for Performance Evaluation
359(1)
15.4 Performance of Modified Bias Correction Method
360(5)
15.5 Detection of Ozone Recovery Based on the Merged TCO Data
365(2)
15.6 Calibration of the Merged TCO Record with Ground-Based Measurements
367(3)
15.7 Summary
370(1)
References
370(5)
Chapter 16 Water Quality Monitoring in a Lake for Improving a Drinking Water Treatment Process
375(22)
16.1 Introduction
375(3)
16.2 Study Region
378(1)
16.3 Study Framework
379(5)
16.4 TOC Mapping in Lake Harsha Using IDFM
384(10)
16.4.1 Field Campaign
384(2)
16.4.2 Impact of Data Fusion
386(2)
16.4.3 Impact of Feature Extraction Algorithms
388(3)
16.4.4 Spatiotemporal TOC Mapping for Daily Monitoring
391(3)
16.5 Summary
394(1)
References
395(2)
Chapter 17 Monitoring Ecosystem Toxins in a Water Body for Sustainable Development of a Lake Watershed
397(24)
17.1 Introduction
397(4)
17.2 Study Region and Pollution Episodes
401(2)
17.3 Space-borne and in situ Data Collection
403(1)
17.4 Study Framework
404(5)
17.4.1 Data Acquisition
407(1)
17.4.2 Image Processing
407(1)
17.4.3 Data Fusion
408(1)
17.4.4 Machine Learning or Data Mining
408(1)
17.4.5 Concentration Map Generation
409(1)
17.5 Model Comparison for Feature Extraction
409(7)
17.5.1 Reliability Analysis
409(4)
17.5.2 Prediction Accuracy over Different Models
413(10)
17.5.2.1 Comparison between Bio-Optical Model and Machine Learning Model for Feature Extraction
413(1)
17.5.2.2 Impact of Data Fusion on Final Feature Extraction
414(1)
17.5.2.3 Influences of Special Bands on Model Development
414(2)
17.6 Mapping for Microcystin Concentrations
416(2)
17.7 Summary
418(1)
References
419(2)
Chapter 18 Environmental Reconstruction of Watershed Vegetation Cover to Reflect the Impact of a Hurricane Event
421(30)
18.1 Introduction
421(2)
18.2 Study Regions and Environmental Events
423(3)
18.2.1 The Hackensack and Pascack Watershed
423(1)
18.2.2 The Impact of Hurricane Sandy
424(2)
18.3 Unsupervised Multitemporal Change Detection
426(4)
18.3.1 Data Fusion
426(2)
18.3.2 NDVI Mapping Based on the Fused Images
428(1)
18.3.3 Performance Evaluation of Data Fusion
428(1)
18.3.4 Tasseled Cap Transformation for Hurricane Sandy Event
428(2)
18.4 Entropy Analysis of Data Fusion
430(2)
18.5 Comparison of the Hurricane Sandy Impact on the Selected Coastal Watershed
432(8)
18.5.1 NDVI Maps
432(1)
18.5.2 Tasseled Cap Transformation Plots
432(8)
18.6 Multitemporal Change Detection
440(3)
18.7 Dispersion Analysis of TCT versus NDVI
443(4)
18.8 Summary
447(1)
References
448(3)
Chapter 19 Multisensor Data Merging and Reconstruction for Estimating PM25 Concentrations in a Metropolitan Region
451(30)
19.1 Introduction
451(3)
19.2 AOD Products and Retrieval Algorithms
454(3)
19.2.1 AOD Products
454(2)
19.2.2 AOD Retrieval Algorithms
456(1)
19.3 Challenges in Merging of AOD Products
457(1)
19.4 Study Framework and Methodology
458(5)
19.4.1 Study Area
458(1)
19.4.2 Data Sources
458(2)
19.4.3 Methodology
460(3)
19.4.4 Performance Evaluation
463(1)
19.5 Results
463(11)
19.5.1 Variability of PM2.5 Concentrations
463(1)
19.5.2 Data Merging of AOD Products
464(2)
19.5.3 PM2 5 Concentration Modeling and Mapping
466(5)
19.5.4 Gap Filling Using SMIR Method
471(3)
19.6 Application Potential for Public Health Studies
474(1)
19.7 Summary
475(1)
References
475(6)
Chapter 20 Conclusions
481(8)
20.1 Introduction
481(1)
20.2 Challenges
481(4)
20.2.1 Data Science and Big Data Analytics
481(2)
20.2.2 Environmental Sensing
483(1)
20.2.3 Environmental Modeling
484(1)
20.3 Future Perspectives and Actualization
485(2)
20.3.1 Contemporary Research Topics
485(1)
20.3.2 Remote Sensing Education
485(2)
20.4 Summary
487(1)
References
487(2)
Index 489
Ni-Bin Chang is currently a professor with the Civil, Environmental, and Construction Engineering Department at the University of Central Florida. He has authored and coauthored over 230 peer-reviewed journal articles, seven books and 220 conference papers. He is a Fellow of the Royal Society of Chemistry (F.RSC) in the United Kingdom (July, 2015), the International Society of Optics and Photonics (F.SPIE) (Dec., 2014), the American Association for the Advancement of Science (F.AAAS) (Feb., 2012), the American Society of Civil Engineers (F.ASCE) (April, 2009), and a Foreign Member of the European Academy of Sciences (M.EAS) (Nov., 2008). He is also a senior member of Institute of Electrical and Electronics Engineers (IEEE) (since 2012). During Aug. 2012 and Aug. 2014, Prof. Chang has served on a number of professional and government positions including the program director of the Hydrologic Sciences Program and Cyber-innovation Sustainability Science and Engineering Program at the National Science Foundation in the US. He is currently an editor-in-chief, associate editor, or editorial board member of over 30 professional
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97814987743452e.html
Raktažodžiai: