Tremendous research has been done and is still in progress in the domain of earth science. With the advent of Big Data and availability of datasets on Earth science, the study of Earth sciences has reached new dimensions. The diversity and high dimensional remote sensing data have provided with complex data sets capable of giving insights and intelligence that was not possible in last decades. With Computing progress made in ingesting and inferring data from myriad of sources including high resolution cameras mounted on satellites and sensors giving access to unconventional Big Data and also with the GPU computing and Data science advances we are today able to leverage machine learning and deep learning in extensively complex datasets derived from remote sensing about Earth Sciences. Our focus is to analyze what exactly does big data mean in earth science applications and how can big data provide added value in this context. Furthermore, this chapter demonstrates various big data tools which can be mapped with various techniques to be used for experimenting earth science datasets, processed, and exploited for different earth science applications. In order to illustrate the aforementioned aspects, instances are presented in order to demonstrate the use of big data in remote sensing. Firstly, this chapter presents earth science studies, application areas/research fields and a brief insight on earth science data. Then various techniques implemented in this domain are elaborated viz. classification, clustering, regression, deep learning, pattern recognition, machine learning, earth data analysis and processing. Later this chapter introduces big data analytics and various tools/platforms in big data viz. BigInsights, GIS, Jupyter notebook, Matlab, Python. Finally, it is shown how these tools are mapped to Earth science datasets using ArcGIS to illustrate with experimental instances the inferences and patterns generated.
[1]
Alex A. Freitas,et al.
A survey of evolutionary algorithms for data mining and knowledge discovery
,
2003
.
[2]
Ali Asghar Torahi,et al.
Land Cover Classification and Forest Change Analysis, Using Satellite Imagery-A Case Study in Dehdez Area of Zagros Mountain in Iran
,
2011,
J. Geogr. Inf. Syst..
[3]
Imran Khan,et al.
Pattern Recognition: an Overview
,
2012
.
[4]
Sanjay Ghemawat,et al.
MapReduce: Simplified Data Processing on Large Clusters
,
2004,
OSDI.
[5]
Steve Kempler,et al.
Earth Science Data Analytics: Definitions, Techniques and Skills
,
2017
.
[6]
Nilanjan Dey,et al.
A MapReduce approach to diminish imbalance parameters for big deoxyribonucleic acid dataset
,
2016,
Comput. Methods Programs Biomed..
[7]
Chaowei Yang,et al.
Enabling Big Geoscience Data Analytics with a Cloud-Based, MapReduce-Enabled and Service-Oriented Workflow Framework
,
2015,
PloS one.
[8]
Johnny Wei-Bing Lin.
Why Python Is the Next Wave in Earth Sciences Computing
,
2012
.
[9]
Anuj Karpatne,et al.
A Guide to Earth Science Data: Summary and Research Challenges
,
2015,
Computing in Science & Engineering.
[10]
Paul W. J. Glover,et al.
The Application of Fuzzy Logic and Genetic Algorithms to Reservoir Characterization and Modeling
,
2002
.