Muutke küpsiste eelistusi

Artificial Intelligence in Earth Science: Best Practices and Fundamental Challenges [Pehme köide]

Edited by (Principal Investigator, Center for Spatial Information Science and Systems, George Mason University, USA), Edited by (Assistant Professor of), Edited by (Research scientist, Department of Civil and Environmental Engineering, University of Washington, USA)
  • Formaat: Paperback / softback, 430 pages, kõrgus x laius: 235x191 mm, kaal: 1000 g
  • Ilmumisaeg: 26-Apr-2023
  • Kirjastus: Elsevier - Health Sciences Division
  • ISBN-10: 0323917372
  • ISBN-13: 9780323917377
Teised raamatud teemal:
Artificial Intelligence in Earth Science: Best Practices and Fundamental ChallengesSuurem pilt
  • Formaat: Paperback / softback, 430 pages, kõrgus x laius: 235x191 mm, kaal: 1000 g
  • Ilmumisaeg: 26-Apr-2023
  • Kirjastus: Elsevier - Health Sciences Division
  • ISBN-10: 0323917372
  • ISBN-13: 9780323917377
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780323917377.html
Märksõnad:
Artificial Intelligence in Earth Science: Best Practices and Fundamental Challenges provides a comprehensive, step-by-step guide to AI workflows for solving problems in Earth Science. The book focuses on the most challenging problems in applying AI in Earth system sciences, such as training data preparation, model selection, hyperparameter tuning, model structure optimization, spatiotemporal generalization, transforming model results into products, and explaining trained models. In addition, it provides full-stack workflow tutorials to help walk readers through the whole process, regardless of previous AI experience.

The book tackles the complexity of Earth system problems in AI engineering, fully guiding geoscientists who are planning to implement AI in their daily work.
  • Provides practical, step-by-step guides for Earth Scientists who are interested in implementing AI techniques in their work
  • Features case studies to show real-world examples of techniques described in the book
  • Includes additional elements to help readers who are new to AI, including end-of-chapter, key concept bulleted lists that concisely cover key concepts in the chapter
Contributors ix
1 Introduction of artificial intelligence in Earth sciences
1(16)
Ziheng Sun
Nicoteta Cristea
1 Background and motivation
1(3)
2 AI evolution in Earth sciences
4(2)
3 Latest developments and challenges
6(2)
4 Short-term and long-term expectations for AI
8(1)
5 Future developments and how to adapt
9(1)
6 Practical AI: From prototype to operation
9(2)
7 Why do we write this book?
11(1)
8 Learning goals and tasks
12(2)
9 Assignments & open questions
14(1)
References
14(3)
2 Machine learning for snow cover mapping
17(24)
Kehan Yang
Aji John
Ziheng Sun
Nicoleta Cristea
1 Introduction
17(1)
2 Machine learning tools and model
18(1)
3 Data preparation
19(2)
4 Model parameter tuning
21(7)
5 Model training
28(4)
6 Model performance evaluation
32(6)
7 Conclusion
38(1)
8 Assignment
39(1)
9 Open questions
39(1)
References
39(2)
3 AI for sea ice forecasting
41(18)
Sahara Ali
Yiyi Huang
Jianwu Wang
1 Introduction
41(1)
2 Sea ice seasonal forecast
42(2)
3 Sea ice data exploration
44(1)
4 ML approaches for sea ice forecasting
45(10)
5 Results and analysis
55(1)
6 Discussion
56(1)
7 Open questions
57(1)
8 Assignments
57(1)
References
57(2)
4 Deep learning for ocean mesoscale eddy detection
59(42)
Edwin Goh
Annie Didier
Jinbo Wang
1 Introduction
59(1)
2
Chapter layout
60(1)
3 Data preparation
61(14)
4 Training and evaluating an eddy detection model
75(19)
5 Discussion
94(3)
6 Summary
97(1)
7 Assignments
97(1)
8 Open questions
98(1)
Acknowledgments
99(1)
References
99(2)
5 Artificial intelligence for plant disease recognition
101(18)
Jayme Garcia Amal Barbedo
1 Introduction
101(2)
2 Data retrieval and preparation
103(2)
3 Step-by-step implementation
105(6)
4 Experimental results and how to select a model
111(2)
5 Discussion
113(2)
6 Conclusion
115(1)
7 Assignment
115(1)
8 Open questions
115(1)
References
116(3)
6 Spatiotemporal attention ConvLSTM networks for predicting and physically interpreting wildfire spread
119(38)
Arif Masrur
Manzhu Yu
1 Introduction
119(2)
2 Methodology
121(2)
3 Earth AI workflow
123(25)
4 Results
148(6)
5 Conclusions
154(1)
6 Assignment
155(1)
7 Open questions
155(1)
References
155(2)
7 AI for physics-inspired hydrology modeling
157(48)
Andrew Bennett
1 Introduction and background
157(3)
2 PyTorch and autodifferentiation
160(9)
3 Extremely brief background on numerical optimization
169(8)
4 Bringing things together: Solving ODEs inside of neural networks
177(9)
5 Scaling up to a conceptual hydrologic model
186(15)
6 Conclusions
201(1)
References
202(1)
Further reading
203(2)
8 Theory of spatiotemporal deep analogs and their application to solar forecasting
205(42)
Weiming Hu
Guido Cervone
George Young
1 Introduction
206(2)
2 Research data
208(3)
3 Methodology
211(7)
4 Results and discussion
218(16)
5 Final remarks
234(1)
6 Assignment
235(1)
7 Open questions
236(1)
Appendix A Deep learning layers and operators
236(2)
Appendix B Verification of extended analog search with GFS
238(2)
Appendix C Weather analog identification under a high irradiance regime
240(2)
Appendix D Model attribution
242(2)
References
244(3)
9 AI for improving ozone forecasting
247(24)
Ahmed Alnuaim
Ziheng Sun
Didarul Islam
1 Introduction
247(2)
2 Background
249(2)
3 Data collection
251(3)
4 Dataset preparation
254(1)
5 Machine learning
255(9)
6 ML workflow management
264(1)
7 Discussion
265(1)
8 Conclusion
266(1)
9 Assignment
267(1)
10 Open questions
267(1)
11 Lessons learned
267(1)
References
268(3)
10 AI for monitoring power plant emissions from space
271(24)
Ahmed Alnuaim
Ziheng Sun
1 Introduction
271(3)
2 Background
274(1)
3 Data collection
275(6)
4 Preprocessing
281(4)
5 Machine learning
285(5)
6 Managing emission AI workflow in Geoweaver
290(1)
7 Discussion
291(1)
8 Summary
292(1)
9 Assignment
292(1)
10 Open questions
293(1)
11 Lessons learned
293(1)
References
294(1)
11 AI for shrubland identification and mapping
295(22)
Michael J. Mahoney
Lucas K. Johnson
Colin M. Beier
1 Introduction
295(1)
2 What you'll learn
296(1)
3 Background
296(1)
4 Prerequisites
297(2)
5 Model building
299(13)
6 Discussion
312(3)
7 Summary
315(1)
8 Assignment
315(1)
9 Open questions
315(1)
References
316(1)
12 Explainable AI for understanding ML-derived vegetation products
317(20)
Geetha Satya Mounika Ganji
Wai Hang Chow Lin
1 Introduction
317(1)
2 Background
318(2)
3 Prerequisites
320(1)
4 Method & technique
320(2)
5 Experiment & results
322(11)
6 Summary
333(1)
7 Assignment
334(1)
8 Open questions
334(1)
9 Lessons learned
334(1)
Acknowledgments
335(1)
References
335(1)
Further reading
335(2)
13 Satellite image classification using quantum machine learning
337(20)
Olawale Ayoade
Pablo Rivas
Javier Orduz
Nurul Rafi
1 Introduction
337(3)
2 Data
340(2)
3 Applying QML on MODIS hyperspectral images
342(11)
4 Conclusions
353(1)
5 Assignments
354(1)
6 Open questions
354(1)
Acknowledgment
354(1)
References
354(3)
14 Provenance in earth AI
357(22)
Amruta Kale
Xiaogang Ma
1 Introduction
357(2)
2 Overview of relevant concepts in provenance, XAI, and TAI
359(4)
3 Need for provenance in earth AI
363(2)
4 Technical approaches
365(7)
5 Discussion
372(2)
6 Conclusions
374(1)
7 Assignment
374(1)
8 Open questions
374(1)
Acknowledgments
375(1)
References
375(4)
15 AI ethics for earth sciences
379(18)
Pablo Rivas
Christopher Thompson
Brenda Tafur
Bikram Khanal
Olawale Ayoade
Tonni Das Jui
Korn Sooksatra
Javier Orduz
Gissella Bejarano
1 Introduction
379(1)
2 Prior work
380(1)
3 Addressing ethical concerns during system design
380(2)
4 Considerating algorithmic bias
382(2)
5 Designing ethically driven automated systems
384(2)
6 Assessing the impact of autonomous and intelligent systems on human well-being
386(1)
7 Developing AI literacy, skills, and readiness
387(1)
8 On documenting datasets for AI
388(2)
9 On documenting AI models
390(1)
10 Carbon emissions of earth AI models
391(2)
11 Conclusions
393(1)
12 Assignments
393(1)
13 Open questions
394(1)
References
394(3)
Index 397
Ziheng Sun is a Principal Investigator at the Center for Spatial Information Science and Systems, and a research assistant professor the Department of Geography and Geoinformation Science at George Mason University. He is a practitioner of using the latest technologies such as artificial intelligence and high-performance computing, to seek for answers to the questions in geoscience. He invented RSSI, a novel index for artificial object recognition from high resolution aerial images, and proposed parameterless automatic classification solution for reducing the parameter-tuning burden on scientists. Prof Sun has published over 50 papers in renowned journals in geoscience and has worked on several federal-funded projects to build geospatial cyberinfrastructure systems for better disseminating, processing, visualizing, and understanding spatial big data. Nicoleta Cristea is a research scientist in the Department of Civil and Environmental Engineering at the University of Washington (UW), a research scientist with the UW Freshwater Initiative, and a data science fellow at the UW eScience Institute. Her current research focus is on modeling snow surface temperature and evaluating spatially distributed hydrologic models. Nicoleta is currently leading an NSF-funded project on mapping snow covered areas from Cubesat imagery using deep learning techniques. Pablo Rivas is assistant professor of computer science at Baylor University where he teaches courses related to machine learning, deep learning, data mining, and theory. His research areas include deep machine learning and large-scale data mining in big data analytics, large-scale multidimensional multispectral signal analysis, statistical pattern recognition methods, image restoration, image analysis, intelligent software systems, and health-care imaging. Other research areas include applied mathematics, numerical optimization, swarm intelligence optimization, evolutionary algorithms, soft computing, fuzzy logic, neural networks, and neuro-fuzzy systems.