Big Earth Observation Data: From Cloud Technologies to Insights and Foresight

Dear Colleagues,

Among the many areas where big data have made their entrance, Earth Observation has been one of the most impacted. The pace at which the number of sensors, either ground-, air- or space-borne, is increasing is unprecedented. In addition, images are now acquired at a finer spatial resolution than ever before, with more frequent revisit times. Meanwhile, many archives are adopting a policy of free, full, and open data access. For instance, the data streams generated by the Sentinel satellites from the European Union Copernicus Programme are delivering more than 20 TB per day. All these data can be freely downloaded for scientific, commercial, or any other use. However, although the data are free, full, and open, computing resources and data communication are not. Bandwidth has increased as technology has improved, but not at the same pace as the data volume is growing. It is therefore a limiting factor that has paved the way for a paradigm shift from bringing data to the user to bringing the user to the data. Downloads are then reserved for transferring information-rich but low-volume data. The high volumes of data can be processed in parallel with high throughput computing (HTC) clusters with thousands of cores that have fast access to the data. Complex processing algorithms benefit from high performance computing (HPC). Machine learning for deep neural networks runs much faster on dedicated hardware, such as graphical processing units (GPU). Few organizations have the means to buy, set up, and maintain these highly specialized environments. They therefore move to cloud computing, where resources can be shared and scaled depending on the user needs.

In addition to the technical aspects with respect to cloud-based infrastructures, contributions regarding the analysis of big Earth Observation data on these infrastructures are welcome.

This Special Issue is linked to the Big Data from Space conference (https://www.bigdatafromspace2021.org/). The emphasis of the 2021 edition of this conference is “From Insights to Foresight”. In particular, this special issue aims for contributions dealing with applications whereby insights extracted from big Earth observation data are used as a basis for foresight of interest to societal challenges, such as the Sustainable Development Goals and climate change. Models integrating Earth Observation time series linked with other relevant data sources in support to policy and decision making are indeed most relevant within the context of our rapidly changing world.

Dr. Pieter Kempeneers
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.