DIGITAL LIBRARY
GOOGLE EARTH ENGINE AS CLOUD COMPUTING PLATFORM IN REMOTE SENSING POSTGRADUATE STUDIES
University of València (SPAIN)
About this paper:
Appears in: INTED2020 Proceedings
Publication year: 2020
Pages: 4839-4842
ISBN: 978-84-09-17939-8
ISSN: 2340-1079
doi: 10.21125/inted.2020.1328
Conference name: 14th International Technology, Education and Development Conference
Dates: 2-4 March, 2020
Location: Valencia, Spain
Abstract:
The University of Valencia (Spain) offers an accredited university Master’s Degree in Remote Sensing, providing students with its technological and scientific basis. This degree allows acquiring competencies in satellite image processing, field instrumentation and geographical information techniques. It enables students to familiarize with the most relevant databases of remote sensing imagery. In addition, students receive training in tools and software for processing and analyzing geospatial imagery including Environment for Visualizing Images (ENVI), MATrix LABoratory (MATLAB), and the Sentinel Application Platform (SNAP). The use of these software in the classroom implies the students to have downloaded the input (e.g., a satellite image) locally in their computers for further processing it and/or executing algorithms, which is a limitation for time series analysis at planetary scale.

Recently, Google developed a planetary-scale platform for Earth science data and analysis called Google Earth Engine (GEE). GEE combines a multi-petabyte catalog of satellite imagery and geospatial datasets at global scale and makes it available for academic, non-profit, business and government users. Besides the access to this huge amount of data, GEE offers the capability of cloud computing.

In this work, we describe the use of GEE in the Master’s Degree in Remote Sensing. The platform enables students to run algorithms in parallel in the cloud, thus exploiting the computational power of thousands of computers in Google's data centers. This reduces the computing time dramatically, making it affordable to process time series of medium and coarse resolution data at planetary scale in a few seconds. Just a Google account and an Internet connection are needed for data accessing and programming in this web platform. These features make GEE a well-suited tool for educational purposes in remote sensing, also allowing the possibility of online training.
Keywords:
Remote Sensing, Master Studies, Cloud Computing, Google Earth Engine.