Atnaujinkite slapukų nuostatas

El. knyga: Deep Learning for the Earth Sciences: A Comprehensive Approach to Remote Sensing, Climate Science and Geosciences

Edited by , Edited by , Edited by (University of Valencia, Spain), Edited by
  • Formatas: PDF+DRM
  • Išleidimo metai: 16-Aug-2021
  • Leidėjas: John Wiley & Sons Inc
  • Kalba: eng
  • ISBN-13: 9781119646150
Kitos knygos pagal šią temą:
Deep Learning for the Earth Sciences: A Comprehensive Approach to Remote Sensing, Climate Science and GeosciencesDidesnis paveikslėlis
  • Formatas: PDF+DRM
  • Išleidimo metai: 16-Aug-2021
  • Leidėjas: John Wiley & Sons Inc
  • Kalba: eng
  • ISBN-13: 9781119646150
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“.

"The research in deep learning for the geosciences and Earth observation is growing fast and goes beyond the mere application of algorithms to new data. This is a huge interdisciplinary field. Applying new algorithms to the data deluge is a hot topic in all these cross-sectorial fields. Academic research on this area is strongly involved, and many specialized conferences and special issues in journals are arising each year. The book will provide the reader with the landscape, skills, and principles to quickly become familiar with both fields? needs and applications and will give a principled status of where are we now. The practitioner will be ready to use the technology and principles in his/her own research field in a short period of time. The highlights on future research at the end of each chapter will provide new ideas, particularly for those people involved in advanced research education, who will find these highlights of special interest for PhD Thesis orientations"--

Explore this insightful treatment of deep learning in the field of earth sciences, from four leading voices in the field

Deep learning is a fundamental technique in modern artificial intelligence and is being applied to disciplines across the scientific spectrum. Earth science is no exception. Yet, the link between deep learning and Earth sciences has only recently entered academic curricula and thus has not yet proliferate broad spread. Deep Learning for the Earth Sciences delivers a perspective and unique treatment of the concepts, skills, and practices necessary to quickly become familiar with the application of deep learning techniques to the Earth sciences. The book prepares readers to be ready to use the technologies and principles described within in their own research.

The distinguished editors have also included resources that explain and provide new ideas and recommendations for new research especially useful to those involved in advanced research education or those seeking PhD thesis orientations. Readers will also benefit from the inclusion of:

  • An introduction to deep learning for classification purposes, including advances in image segmentation and encoding priors, anomaly detection and target detection, and domain adaptation
  • An exploration of learning representations and unsupervised deep learning, including deep learning image fusion, image retrieval, and matching and co-registration
  • Practical discussions of regression, fitting, parameter retrieval, forecasting and interpolation
  • An examination of physics-aware deep learning models, including emulation of complex codes and model parametrizations

    Perfect for PhD students and researchers in the fields of geosciences, image processing, remote sensing, electrical engineering and computer science, and machine learning, Deep Learning for the Earth Sciences will also earn a place in the libraries of machine learning and pattern recognition researchers, engineers, and scientists.

    • Foreword xvi
    Vipin Kumar
    Acknowledgments xvii
    List of Contributors
    		xviii
    List of Acronyms
    		xxiv
    1 Introduction
    		1(12)
    Gustau Camps-Vails
    Xiao Xiang Zhu
    Devis Tuia
    Markus Reichstein
    1.1 A Taxonomy of Deep Learning Approaches
    		2(1)
    1.2 Deep Learning in Remote Sensing
    		3(4)
    1.3 Deep Learning in Geosciences and Climate
    		7(2)
    1.4 Book Structure and Roadmap
    		9(4)
    Part I Deep Learning to Extract Information from Remote Sensing Images
    		13(148)
    2 Learning Unsupervised Feature Representations of Remote Sensing Data with Sparse Convolutional Networks
    		15(9)
    Jose E. Adsuara
    Manuel Campos-Taberner
    Javier Garaa-Haro
    Carlo Gatta
    Adriana Romero
    Gustau Camps-Vails
    2.1 Introduction
    		15(2)
    2.2 Sparse Unsupervised Convolutional Networks
    		17(2)
    2.2.1 Sparsity as the Guiding Criterion
    		17(1)
    2.2.2 The EPLS Algorithm
    		18(1)
    2.2.3 Remarks
    		18(1)
    2.3 Applications
    		19(3)
    2.3.1 Hyperspectral Image Classification
    		19(2)
    2.3.2 Multisensor Image Fusion
    		21(1)
    2.4 Conclusions
    		22(2)
    3 Generative Adversarial Networks in the Geosciences
    		24(13)
    Gonzalo Mateo-Garda
    Valero Laparra
    Christian Requena-Mesa
    Luis Gomez-Chow
    3.1 Introduction
    		24(1)
    3.2 Generative Adversarial Networks
    		25(3)
    3.2.1 Unsupervised GANs
    		25(1)
    3.2.2 Conditional GANs
    		26(1)
    3.2.3 Cycle-consistent GANs
    		27(1)
    3.3 GANs in Remote Sensing and Geosciences
    		28(3)
    3.3.1 GANs in Earth Observation
    		28(2)
    3.3.2 Conditional GANs in Earth Observation
    		30(1)
    3.3.3 CycleGANs in Earth Observation
    		30(1)
    3.4 Applications of GANs in Earth Observation
    		31(5)
    3.4.1 Domain Adaptation Across Satellites
    		31(2)
    3.4.2 Learning to Emulate Earth Systems from Observations
    		33(3)
    3.5 Conclusions and Perspectives
    		36(1)
    4 Deep Self-taught Learning in Remote Sensing
    		37(9)
    Ribana Roscher
    4.1 Introduction
    		37(1)
    4.2 Sparse Representation
    		38(2)
    4.2.1 Dictionary Learning
    		39(1)
    4.2.2 Self-taught Learning
    		40(1)
    4.3 Deep Self-taught Learning
    		40(5)
    4.3.1 Application Example
    		43(1)
    4.3.2 Relation to Deep Neural Networks
    		44(1)
    4.4 Conclusion
    		45(1)
    5 Deep Learning-based Semantic Segmentation in Remote Sensing
    		46(21)
    Dew's Tula
    Diego Marcos
    Konrad Schindler
    Bertrand Le Saux
    5.1 Introduction
    		46(1)
    5.2 Literature Review
    		47(2)
    5.3 Basics on Deep Semantic Segmentation: Computer Vision Models
    		49(6)
    5.3.1 Architectures for Image Data
    		49(3)
    5.3.2 Architectures for Point-clouds
    		52(3)
    5.4 Selected Examples
    		55(11)
    5.4.1 Encoding Invariances to Train Smaller Models: The example of Rotation
    		55(4)
    5.4.2 Processing 3D Point Clouds as a Bundle of Images: SnapNet
    		59(3)
    5.4.3 Lake Ice Detection from Earth and from Space
    		62(4)
    5.5 Concluding Remarks
    		66(1)
    6 Object Detection in Remote Sensing
    		67(23)
    Jian Ding
    Jinwang Wang
    Wen Yang
    Gui-Song Xia
    6.1 Introduction
    		67(5)
    6.1.1 Problem Description
    		67(2)
    6.1.2 Problem Settings of Object Detection
    		69(1)
    6.1.3 Object Representation in Remote Sensing
    		69(1)
    6.1.4 Evaluation Metrics
    		69(1)
    6.1.4.1 Precision-Recall Curve
    		70(1)
    6.1.4.2 Average Precision and Mean Average Precision
    		71(1)
    6.1.5 Applications
    		71(1)
    6.2 Preliminaries on Object Detection with Deep Models
    		72(3)
    6.2.1 Two-stage Algorithms
    		72(1)
    6.2.1.1 R-CNNs
    		72(1)
    6.2.1.2 R-FCN
    		73(1)
    6.2.2 One-stage Algorithms
    		73(1)
    6.2.2.1 YOLO
    		73(1)
    6.2.2.2 SSD
    		73(2)
    6.3 Object Detection in Optical RS Images
    		75(11)
    6.3.1 Related Works
    		75(1)
    6.3.1.1 Scale Variance
    		75(1)
    6.3.1.2 Orientation Variance
    		75(1)
    6.3.1.3 Oriented Object Detection
    		75(1)
    6.3.1.4 Detecting in Large-size Images
    		76(1)
    6.3.2 Datasets and Benchmark
    		77(1)
    6.3.2.1 DOTA
    		77(1)
    6.3.2.2 VisDrone
    		77(1)
    6.3.2.3 DIOR
    		77(1)
    6.3.2.4 X View
    		77(1)
    6.3.3 Two Representative Object Detectors in Optical RS Images
    		78(1)
    6.3.3.1 Mask OBB
    		78(4)
    6.3.3.2 Rol Transformer
    		82(4)
    6.4 Object Detection in SAR Images
    		86(3)
    6.4.1 Challenges of Detection in SAR Images
    		86(1)
    6.4.2 Related Works
    		86(2)
    6.4.3 Datasets and Benchmarks
    		88(1)
    6.5 Conclusion
    		89(1)
    7 Deep Domain Adaptation in Earth Observation
    		90(615)
    Benjamin Keilenberger
    Onur Tasar
    Bharath Bhushan Damodaran
    Nicolas Courty
    Devis Tuia
    7.1 Introduction
    		90(1)
    7.2 Families of Methodologies
    		91(2)
    7.3 Selected Examples
    		93(11)
    7.3.1 Adapting the Inner Representation
    		93(4)
    7.3.2 Adapting the Inputs Distribution
    		97(3)
    7.3.3 Using (few, well chosen) Labels from the Target Domain
    		100(4)
    7.4 Concluding remarks
    		104(1)
    8 Recurrent Neural Networks and the Temporal Component
    		105(1)
    Marco Korner
    Marc Rujiwurm
    8.1 Recurrent Neural Networks
    		106(5)
    8.1.1 Training RNNs
    		107(1)
    8.1.1.1 Exploding and Vanishing Gradients
    		107(2)
    8.1.1.2 Circumventing Exploding and Vanishing Gradients
    		109(2)
    8.2 Gated Variants of RNNs
    		111(3)
    8.2.1 Long Short-term Memory Networks
    		111(1)
    8.2.1.1 The Cell State ct and the Hidden State h1
    		112(1)
    8.2.1.2 The Forget Gate ft
    		112(1)
    8.2.1.3 The Modulation Gate v1 and the Input Gate i1
    		112(1)
    8.2.1.4 The Output Gate o1
    		112(1)
    8.2.1.5 Training LSTM Networks
    		113(1)
    8.2.2 Other Gated Variants
    		113(1)
    8.3 Representative Capabilities of Recurrent Networks
    		114(3)
    8.3.1 Recurrent Neural Network Topologies
    		114(1)
    8.3.2 Experiments
    		115(2)
    8.4 Application in Earth Sciences
    		117(1)
    8.5 Conclusion
    		118(2)
    9 Deep Learning for Image Matching and Co-registration
    		120(16)
    Maria Vakaiopoulou
    Stergios Christodoutidis
    Mihir Sahasrabudhe
    Nikos Paragios
    9.1 Introduction
    		120(3)
    9.2 Literature Review
    		123(3)
    9.2.1 Classical Approaches
    		123(1)
    9.2.2 Deep Learning Techniques for Image Matching
    		124(1)
    9.2.3 Deep Learning Techniques for Image Registration
    		125(1)
    9.3 Image Registration with Deep Learning
    		126(8)
    9.3.1 2D Linear and Deformable Transformer
    		126(1)
    9.3.2 Network Architectures
    		127(1)
    9.3.3 Optimization Strategy
    		128(1)
    9.3.4 Dataset and Implementation Details
    		129(1)
    9.3.5 Experimental Results
    		129(5)
    9.4 Conclusion and Future Research
    		134(2)
    9.4.1 Challenges and Opportunities
    		134(1)
    9.4.1.1 Dataset with Annotations
    		134(1)
    9.4.1.2 Dimensionality of Data
    		135(1)
    9.4.1.3 Multitemporal Datasets
    		135(1)
    9.4.1.4 Robustness to Changed Areas
    		135(1)
    10 Multisource Remote Sensing Image Fusion
    		136(14)
    Wei He
    Danfeng Hong
    Giuseppe Scarpa
    Tatsumi Uezato
    Naoto Yokoya
    10.1 Introduction
    		136(1)
    10.2 Pansharpening
    		137(6)
    10.2.1 Survey of Pansharpening Methods Employing Deep Learning
    		137(3)
    10.2.2 Experimental Results
    		140(1)
    10.2.2.1 Experimental Design
    		140(1)
    10.2.2.2 Visual and Quantitative Comparison in Pansharpening
    		140(3)
    10.3 Multiband Image Fusion
    		143(5)
    10.3.1 Supervised Deep Learning-based Approaches
    		143(2)
    10.3.2 Unsupervised Deep Learning-based Approaches
    		145(1)
    10.3.3 Experimental Results
    		146(1)
    10.3.3.1 Comparison Methods and Evaluation Measures
    		146(1)
    10.3.3.2 Dataset and Experimental Setting
    		146(1)
    10.3.3.3 Quantitative Comparison and Visual Results
    		147(1)
    10.4 Conclusion and Outlook
    		148(2)
    11 Deep Learning for Image Search and Retrieval in Large Remote Sensing Archives
    		150(11)
    Gencer Sumbul
    Jian Kang
    Begum Demir
    11.1 Introduction
    		150(2)
    11.2 Deep Learning for RS CBIR
    		152(4)
    11.3 Scalable RS CBIR Based on Deep Hashing
    		156(3)
    11.4 Discussion and Conclusion
    		159(2)
    Acknowledgement
    		160(1)
    Part II Making a Difference in the Geosciences With Deep Learning
    		161(122)
    12 Deep Learning for Detecting Extreme Weather Patterns
    		163(23)
    Mayur Mudigonda
    Prabhat Ram
    Karthik Kashinath
    Evan Racah
    Ankur Mahesh
    Yunjie Liu
    Christopher Beckham
    Jim Biard
    Thorsten Kurth
    Sookyung Kim
    Samira Kahou
    Tegan Maharaj
    Burlen Loring
    Christopher Pal
    Travis O'Brien
    Kenneth E. Kunkel
    Michael F. Wehner
    William D. Collins
    12.1 Scientific Motivation
    		163(3)
    12.2 Tropical Cyclone and Atmospheric River Classification
    		166(4)
    12.2.1 Methods
    		166(1)
    12.2.2 Network Architecture
    		167(2)
    12.2.3 Results
    		169(1)
    12.3 Detection of Fronts
    		170(5)
    12.3.1 Analytical Approach
    		170(1)
    12.3.2 Dataset
    		171(1)
    12.3.3 Results
    		172(2)
    12.3.4 Limitations
    		174(1)
    12.4 Semi-supervised Classification and Localization of Extreme Events
    		175(4)
    12.4.1 Applications of Semi-supervised Learning in Climate Modeling
    		175(1)
    12.4.1.1 Supervised Architecture
    		176(1)
    12.4.1.2 Semi-supervised Architecture
    		176(1)
    12.4.2 Results
    		176(1)
    12.4.2.1 Frame-wise Reconstruction
    		176(2)
    12.4.2.2 Results and Discussion
    		178(1)
    12.5 Detecting Atmospheric Rivers and Tropical Cyclones Through Segmentation Methods
    		179(5)
    12.5.1 Modeling Approach
    		179(1)
    12.5.1.1 Segmentation Architecture
    		180(1)
    12.5.1.2 Climate Dataset and Labels
    		181(1)
    12.5.2 Architecture Innovations: Weighted Loss and Modified Network
    		181(2)
    12.5.3 Results
    		183(1)
    12.6 Challenges and Implications for the Future
    		184(1)
    12.7 Conclusions
    		185(1)
    13 Spatio-temporal Autoencoders in Weather and Climate Research
    		186(18)
    Xavier-Andoni Tibau
    Christian Reimers
    Christian Requena-Mesa
    Jakob Runge
    13.1 Introduction
    		186(1)
    13.2 Autoencoders
    		187(6)
    13.2.1 A Brief History of Autoencoders
    		188(1)
    13.2.2 Archetypes of Autoencoders
    		189(2)
    13.2.3 Variational Autoencoders (VAE)
    		191(1)
    13.2.4 Comparison Between Autoencoders and Classical Methods
    		192(1)
    13.3 Applications
    		193(10)
    13.3.1 Use of the Latent Space
    		193(2)
    13.3.1.1 Reduction of Dimensionality for the Understanding of the System Dynamics and its Interactions
    		195(4)
    13.3.1.2 Dimensionality Reduction for Feature Extraction and Prediction
    		199(1)
    13.3.2 Use of the Decoder
    		199(2)
    13.3.2.1 As a Random Sample Generator
    		201(1)
    13.3.2.2 Anomaly Detection
    		201(1)
    13.3.2.3 Use of a Denoising Autoencoder (DAE) Decoder
    		202(1)
    13.4 Conclusions and Outlook
    		203(1)
    14 Deep Learning to Improve Weather Predictions
    		204(14)
    Peter D. Dueben
    Peter Bauer
    Samantha Adams
    14.1 Numerical Weather Prediction
    		204(3)
    14.2 How Will Machine Learning Enhance Weather Predictions?
    		207(1)
    14.3 Machine Learning Across the Workflow of Weather Prediction
    		208(5)
    14.4 Challenges for the Application of ML in Weather Forecasts
    		213(3)
    14.5 The Way Forward
    		216(2)
    15 Deep Learning and the Weather Forecasting Problem: Precipitation Nowcasting
    		218(22)
    Zhihan Gao
    Xingjian Shi
    Hao Wang
    Dit-Yan Yeung
    Wang-chun Woo
    Wai-Kin Wong
    15.1 Introduction
    		218(2)
    15.2 Formulation
    		220(1)
    15.3 Learning Strategies
    		221(2)
    15.4 Models
    		223(10)
    15.4.1 FNN-based Odels
    		223(2)
    15.4.2 RNN-based Models
    		225(1)
    15.4.3 Encoder-forecaster Structure
    		226(1)
    15.4.4 Convolutional LSTM
    		226(1)
    15.4.5 ConvLSTM with Star-shaped Bridge
    		227(1)
    15.4.6 Predictive RNN
    		228(1)
    15.4.7 Memory in Memory Network
    		229(2)
    15.4.8 Trajectory GRU
    		231(2)
    15.5 Benchmark
    		233(3)
    15.5.1 HKO-7 Dataset
    		234(1)
    15.5.2 Evaluation Methodology
    		234(1)
    15.5.3 Evaluated Algorithms
    		235(1)
    15.5.4 Evaluation Results
    		236(1)
    15.6 Discussion
    		236(4)
    Appendix
    		238(1)
    Acknowledgement
    		239(1)
    16 Deep Learning for High-dimensional Parameter Retrieval
    		240(18)
    David Malmgren-Hansen
    16.1 Introduction
    		240(2)
    16.2 Deep Learning Parameter Retrieval Literature
    		242(2)
    16.2.1 Land
    		242(1)
    16.2.2 Ocean
    		243(1)
    16.2.3 Cryosphere
    		244(1)
    16.2.4 Global Weather Models
    		244(1)
    16.3 The Challenge of High-dimensional Problems
    		244(6)
    16.3.1 Computational Load of CNNs
    		247(2)
    16.3.2 Mean Square Error or Cross-entropy Optimization?
    		249(1)
    16.4 Applications and Examples
    		250(7)
    16.4.1 Utilizing High-Dimensional Spatio-spectral Information with CNNs
    		250(3)
    16.4.2 The Effect of Loss Functions in Retrieval of Sea Ice Concentrations
    		253(4)
    16.5 Conclusion
    		257(1)
    17 A Review of Deep Learning for Cryospheric Studies
    		258(11)
    Lin Liu
    17.1 Introduction
    		258(2)
    17.2 Deep-learning-based Remote Sensing Studies of the Cryosphere
    		260(5)
    17.2.1 Glaciers
    		260(1)
    17.2.2 Ice Sheet
    		261(1)
    17.2.3 Snow
    		262(1)
    17.2.4 Permafrost
    		263(1)
    17.2.5 Sea Ice
    		264(1)
    17.2.6 River Ice
    		265(1)
    17.3 Deep-learning-based Modeling of the Cryosphere
    		265(1)
    17.4 A Summary and Prospect
    		266(3)
    Appendix: List of Data and Codes
    		267(2)
    18 Emulating Ecological Memory with Recurrent Neural Networks
    		269(14)
    Basil Kraft
    Simon Besnard
    Sujan Koirala
    18.1 Ecological Memory Effects: Concepts and Relevance
    		269(1)
    18.2 Data-driven Approaches for Ecological memory Effects
    		270(2)
    18.2.1 A Brief Overview of Memory Effects
    		270(1)
    18.2.2 Data-driven Methods for Memory Effects
    		271(1)
    18.3 Case Study: Emulating a Physical Model Using Recurrent Neural Networks
    		272(4)
    18.3.1 Physical Model Simulation Data
    		272(1)
    18.3.2 Experimental Design
    		273(1)
    18.3.3 RNN Setup and Training
    		274(2)
    18.4 Results and Discussion
    		276(5)
    18.4.1 The Predictive Capability Across Scales
    		276(3)
    18.4.2 Prediction of Seasonal Dynamics
    		279(2)
    18.5 Conclusions
    		281(2)
    Part III Linking Physics and Deep Learning Models
    		283(48)
    19 Applications of Deep Learning in Hydrology
    		285(13)
    Chaopeng Shen
    Kathryn Lawson
    19.1 Introduction
    		285(1)
    19.2 Deep Learning Applications in Hydrology
    		286(10)
    19.2.1 Dynamical System Modeling
    		286(1)
    19.2.1.1 Large-scale Hydrologic Modeling with Big Data
    		286(4)
    19.2.1.2 Data-limited LSTM Applications
    		290(2)
    19.2.2 Physics-constrained Hydrologic Machine Learning
    		292(1)
    19.2.3 Information Retrieval for Hydrology
    		293(1)
    19.2.4 Physically-informed Machine Learning for Subsurface Flow and Reactive Transport Modeling
    		294(2)
    19.2.5 Additional Observations
    		296(1)
    19.3 Current Limitations and Outlook
    		296(2)
    20 Deep Learning of Unresolved Turbulent Ocean Processes in Climate Models
    		298(9)
    Laure Zanna
    Thomas Bolton
    20.1 Introduction
    		298(1)
    20.2 The Parameterization Problem
    		299(1)
    20.3 Deep Learning Parameterizations of Subgrid Ocean Processes
    		300(1)
    20.3.1 Why DL for Subgrid Parameterizations?
    		300(1)
    20.3.2 Recent Advances in DL for Subgrid Parameterizations
    		300(1)
    20.4 Physics-aware Deep Learning
    		301(2)
    20.5 Further Challenges ahead for Deep Learning Parameterizations
    		303(4)
    21 Deep Learning for the Parametrization of Subgrid Processes in Climate Models
    		307(8)
    Pierre Gentine
    Veronika Eyring
    Tom Beuder
    21.1 Introduction
    		307(2)
    21.2 Deep Neural Networks for Moist Convection (Deep Clouds) Parametrization
    		309(3)
    21.3 Physical Constraints and Generalization
    		312(2)
    21.4 Future Challenges
    		314(1)
    22 Using Deep Learning to Correct Theoretically-derived Models
    		315(13)
    Peter A. G. Watson
    22.1 Experiments with the Lorenz '96 System
    		317(7)
    22.1.1 The Lorenz '96 Equations and Coarse-scale Models
    		318(1)
    22.1.1.1 Theoretically-derived Coarse-scale Model
    		318(1)
    22.1.1.2 Models with ANNs
    		319(1)
    22.1.2 Results
    		320(1)
    22.1.2.1 Single-timestep Tendency Prediction Errors
    		320(1)
    22.1.2.2 Forecast and Climate Prediction Skill
    		321(3)
    22.1.3 Testing Seamless Prediction
    		324(1)
    22.2 Discussion and Outlook
    		324(3)
    22.2.1 Towards Earth System Modeling
    		325(1)
    22.2.2 Application to Climate Change Studies
    		326(1)
    22.3 Conclusion
    		327(1)
    23 Outlook
    		328(3)
    Markus Reichstein
    Gustau Camps-Vails
    Devis Tuia
    Xiao Xiang Zhu
    Bibliography 331(70)
    Index 401
    Gustau Camps-Valls is Professor of Electrical Engineering and Lead Researcher in the Image Processing Laboratory (IPL) at the Universitat de Valčncia. His interests include development of statistical learning, mainly kernel machines and neural networks, for Earth sciences, from remote sensing to geoscience data analysis. Models efficiency and accuracy but also interpretability, consistency and causal discovery are driving his agenda on AI for Earth and climate.

    Devis Tuia, PhD, is Associate Professor at the Ecole Polytechnique Fédérale de Lausanne (EPFL). He leads the Environmental Computational Science and Earth Observation laboratory, which focuses on the processing of Earth observation data with computational methods to advance Environmental science.



    Xiao Xiang Zhu is Professor of Data Science in Earth Observation and Director of the Munich AI Future Lab AI4EO at the Technical University of Munich and heads the Department EO Data Science at the German Aerospace Center. Her lab develops innovative machine learning methods and big data analytics solutions to extract large scale geo-information from big Earth observation data, aiming at tackling societal grand challenges, e.g. Urbanization, UNs SDGs and Climate Change.

    Markus Reichstein is Director of the Biogeochemical Integration Department at the Max-Planck- Institute for Biogeochemistry and Professor for Global Geoecology at the University of Jena. His main research interests include the response and feedback of ecosystems (vegetation and soils) to climatic variability with an Earth system perspective, considering coupled carbon, water and nutrient cycles. He has been tackling these topics with applied statistical learning for more than 15 years.
    Daugiau apie elektronines knygas Daugiau apie elektronines knygas
    Pastovi nuoroda: https://www.kriso.lt/db/97811196461502e.html
    Raktažodžiai: