Applications of Deep and Machine Learning in Remote Sensing

Remote sensing is a flourishing engineering discipline involving a variety of techniques. In a literal sense, remote sensing simply means sensing the object of the observation remotely; that is, without 'touching' it. Let us summarize some features of remote sensing when applied to Earth observations. A remote Earth observation is performed with sensors that measure electromagnetic fields after their interaction with the Earth. These sensors (e.g., radars, lidars, optical cameras, infrared cameras, etc.) are operated through platforms (e.g., satellites, planes, unmanned aerial vehicles (UAVs), given fixed locations, etc.) and collect data. The data collected must be organized and interpreted. A very promising way of organizing remotely sensed data is the use of Geographical Information Systems (GISs). Roughly speaking, given a location in space and time, the GIS makes the corresponding remotely sensed data available. The traditional methods of interpreting the remotely sensed data derived from engineering (i.e., signal processing) and applied mathematics (i.e., inverse problems, mathematical physics). Needless to say, the volume of remotely sensed data available to the public is huge. This makes remote sensing a natural candidate for the application of the new techniques emerging in the scientific and technical literature widely known under the names of Data Science, Artificial Intelligence (AI), and Machine Learning (ML). In particular, remotely sensed images can be interpreted using techniques taken from artificial vision and robotics such as Deep Learning (DL), including special kinds of neural networks such as Convolutional Neural Networks (CNNs). Moreover, hybrid methods that combine AI and non-AI methods can be developed to interpret remotely sensed data.

The practical questions that can be answered using remotely sensed data are countless; for example, weather, forestry, agriculture, oceanography, ecology, navigation, infrastructure surveillance, etc.

This Special Issue welcomes the submission of papers concerned with, but not limited to, theory and applications in the subjects mentioned above. For example, quantum sensing, autonomous vehicles, and high-performance computing can be regarded as research fields that are related to remote sensing or that can provide methods and ideas to remote sensing. Of course, papers addressing new challenging problems in remote sensing are welcome to be submitted.

Prof. Francesco Zirilli
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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Applied Sciences 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 2400 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.

• Earth observation
• remote sensing
• artificial intelligence
• machine learning
• deep learning