Dear Colleagues,

Imagine, every point on Earth of 0,3 Ground Sampling Distance (GSD) is revisited 6-8 times per day, by commercial high resolution satellite imagery, complemented by other remote sensing satellites such as the EU Copernicus programme and local low-cost satellite imaging. Every single day, several Petabyte of geospatial data are collected and have to be stored for processing. This is an example of big geospatial data, and this is not yet considering other remote sensing technologies, such as laser scanning and photogrammetry.

The EU Copernicus programme is specifically designed for Earth Observation (EO), covering a broad range of applications supporting six thematic areas: Land, marine, atmosphere, climate change, emergency management and security. A new family of missions, called Sentinels, fulfill the needs of the operational aspects of the Copernicus programme.

The high resolution commercial satellite imagery, as delivered by the WorldView family, is superb for 3D and 4D reconstructions. Digital surface model reconstructions of WorldView-2 (WV2), WV3 and WV4 stereo scenes using Dense Image Matching may deliver precision values of less than 1m in height, providing basic data for 3D smart cities, landscape interpretations, and much more. In addition, oblique airborne photogrammetry and local UAV flights deliver images of superb quality, leading to cm-level in 3D reconstructions on ground. Today, aerial image blocks of 20,000 to 40,000 images can be processed without any problems. Besides passive image sensing LiDAR complements the basket of big geospatial data collections, delivering cm-level Digital Surface Models (DSMs) and Digital Elevation Models (DEMs).

It is out of question, that big geospatial data can only be fully explored using the latest computing and modeling technologies. Thus, data managements and reconstructions require for advanced and distributed data processing. The algorithms used become better and better, triggered by the progress in Machine Learning and Artificial Intelligence. It is interesting to observe the performance of Convolutional Neural Networks. It seems, that this kind of automatic processing may solve the data classification problem in remote sensing and delivers the semantic models we are looking for.

The data management in GIS environment will also change. All around the world 3D and 4D geo-databases will be established, for several reasons. On the one hand coastline protections are an issue because of climate change. The high resolution Digital Surface Models, delivered by Dense Image Matching of spaceborne, airborne and UAV photogrammetry, are merged with LiDAR DEMs to get the best information about critical height changes. Because of the high frequency of revisiting any point on Earth the spatio-temporal behavior is also to be modeled and stored in geo-databases. This allows also for disaster management, just in case some natural phenomenas would happen.

On the other hand, the combination of high resolution satellite imagery with airborne and UAV images delivers excellent streaming options, to come down to cm Ground Sampling Distance. The processing of these images, no matter of the singular sources or combined, delivers true orthophotos to be used for maintaining cadastral databases and topographic databases. Internet streaming of big geospatial data and its follow-up products onto nearly every office desk worldwide is another dimension in the management of GIS databases.

As big geospatial data and its processing are evolving, the field of Geographic Information Science is highly impacted by these developments. Thus, we kindly encourage all scientists and developers to submit latest research and developments dealing with big geospatial data, data mining by AI and ML, and advanced 3D and 4D modeling to this Special Issue. Please keep in mind, that we will accept only original research articles.

Prof. Dr. Dieter Fritsch
Prof. Martin Breunig
Guest Editors

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. 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 1700 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.

• High Resolution Satellite Imagery
• Oblique Images
• Cloud Storage
• Cloud Processing
• Point Cloud Processing
• 2,5D Modeling
• 3D Modeling
• 4D Modeling
• CSG Modeling
• Distributed data processing
• Machine Learning
• Deep Learning
• Convolutional Neural Networks (CNN)
• Semantic Modeling