Geospatial Artificial Intelligence (AI) in Earth Observation, Remote Sensing and GIScience

Dear Colleagues,

Geospatial Artificial Intelligence (Geospatial AI) approaches have had a transformative influence on Earth observation and remote sensing fields such as nature language processing and computer vision. With the progression in deep learning algorithms, software and hardware technologies, scalable computation platforms, and the availability of high-resolution geospatial data are empowering the fast-growing field of Geospatial AI. These state-of-the-art methods have enabled a next generation of Earth observation and remote sensing and provided new means for researching Earth’s surface at a variety of scales from land use changes to other geographic forms and processes in general. Moreover, in the past few decades, to capture the dynamic process of space change, which is often driven by the combination of synergetic spatial and aspatial factors and their interactions, researchers have made great efforts to unravel the mechanism behind it. The great strides in complex analysis and Geospatial AI in spatial analysis have fundamentally changed traditional methodologies and have provided deeper theoretical insight into the dynamics of space change.

Geospatial AI emphasizes the cognition of the geographical environment and enriches GIScience by integrating multi-angle, multi-spectrum, multi-platform, multi-scale data. Meanwhile, although the multi-modal remote sensing data fusion can break through the limitation of single-modal data, eliminate redundancy, and achieve the effective combination and utilization of complementary information, multi-modal AI structures come at an enormous computational cost. Thus, simulating reality with data-driven machine learning within a relatively simple framework is desired. To a large extent, modern Geospatial AI systems do not only establish assumptions and structured concepts about the operating principles of the world but also tend to minimize the structure of algorithms to preserve the simplicity of the algorithm and explain complex scenes on Earth’s surface. Further studies require the combination of macroscopic geographic zoning deconstruction and microscopic visual cognition to develop complexity metrics and form multi-scale adaptive schemes. More practices are needed to reveal the application fields of different AI algorithms.

In this Special Issue, we will try to inspire the growth and distribution of open Geospatial AI tools that can be re-processed for GIScience research and education. Submissions demonstrating the added value of taking a Geospatial AI approach over existing approaches would be preferred. Papers should ideally also allow for insights into the mechanistic underpinnings of the system being investigated. New theories and methods of AI applications in spatially explicit AI models, spatial prediction and interpolation, earth observation, social sensing, and geospatial semantics are all welcomed in this Special Issue. Potential topics in this collection include, but are not limited to, the following:

• Geospatial AI for object detection, localization, and classification.
• Geospatial AI for agent-based modeling and cellular automata.
• Geospatial AI for object segmentation, reconstruction, and registration.
• Geospatial AI for anomaly/novelty detection and visual search.
• Geospatial AI for using light detection and range (LiDAR) data.
• Geospatial AI for developing early warning systems.
• Geospatial AI for climate trace.
• Geospatial AI for environmental watch projects such as biomass watch, fishing watch, forest watch, and beyond.
• Geospatial AI for generating new geo-spatial datasets in Earth’s domain.
• Geospatial AI for smart conveyance and autonomous cars.
• Geospatial AI for all other earth observation applications.
• Geospatial AI for modeling land use and land cover changes.
• Geospatial AI for social sensing.
• Geospatial AI for urban visual intelligence.
• Geospatial AI for seismic analysis and prediction.
• Geospatial AI for city understanding and analysis.
• Geospatial AI for social intelligence.

Dr. Shan Liu
Prof. Dr. Xuan Liu
Dr. Kenan Li
Dr. Zhengtong Yin
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 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-anonymized 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.