Deep Learning and Computer Vision for GeoInformation Sciences

Dear Colleagues,

In recent years, significant progress has been made in the combined fields of deep learning (DL) and computer vision (CV), with applications ranging from driverless cars to facial recognition to robotics. There is a natural synergy between the geoinformation sciences and DL and CV due to the vast quantities of geolocated and time-stamped data being generated from various sources, including satellite imagery, street-level images, and video and airborne and unmanned aerial system (UAS) imagery, as well as social media data, text data, and other data streams. In the field of remote sensing, in particular, significant progress has already been made in object detection, image classification and scene classification, amongst others. More recently, DL architectures have been applied to heterogeneous geospatial data types, such as networks, broadening their applicability across a range of spatial processes.

This Special Issue aims to collate the state of the art in deep learning and computer vision for the geoinformation sciences, from the application of existing DL and CV algorithms in diverse contexts to the development of novel techniques. Submissions are invited across a range of topics related to DL and CV, including but not limited to:

Theory and algorithms: Development of novel theory and algorithms specific to the geoinformation sciences, including methods for modelling heterogeneous spatio-temporal data types.
Integration of DL and CV into traditional modelling frameworks: Using DL and CV to augment traditional modelling techniques, e.g. through data creation, fusion or integrated algorithmic design.
Deep reinforcement learning: Application of deep reinforcement learning to spatial processes.
Geocomputation for DL and CV: Improving the performance and scalability of DL and CV using geocomputational techniques.
Incorporating DL and CV in Geoinformation Science Curricula: Meeting demands in education for incorporating artificial intelligence into educational curricula, particularly geolocational aspects of DL and CV in GIScience programs as well as other disciplines of DL/CV development (e.g., engineering, computer science) and application areas (listed below).
Applications: Open scope within the geoinformation sciences (e.g., transport and mobility, smart cities, agriculture, marine science, ecology, geology, forestry, public health, urban/rural planning, infrastructure, disaster management, social networks, local/global modelling, climate and atmosphere, etc.).

Dr. James Haworth
Dr. Suzana Dragicevic
Dr. Marguerite Madden
Dr. Mingshu Wang
Dr. Haosheng Huang
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. ISPRS International Journal of Geo-Information is an international peer-reviewed open access monthly 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 1900 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.