Advances in GeoAI with Remote Sensing Imagery for Urban Green Space Mapping and Monitoring

Dear Colleagues,

(1) An introduction highlighting the scientific background and importance of this research area.

Urban green spaces (UGSs), including parks, gardens, street trees, and lawns, are essential elements of sustainable and livable cities. They provide crucial ecosystem services, alleviate urban heat island effects, enhance biodiversity, and improve residents’ physical and mental health. Against the backdrop of rapid urbanization and climate change, accurate, efficient, and dynamic UGS monitoring has become increasingly important for urban planning, environmental management, and policy-making.

Remote sensing technology, with its unique capability for synoptic and repeated Earth observation, serves as a primary means for UGS mapping. The availability of high-resolution (HR) and very-high-resolution (VHR) imagery allows for the detailed delineation of UGS. However, conventional methods such as pixel-based and object-oriented image analysis often face difficulties in handling the spectral diversity and complex spatial structures typical of urban settings, resulting in limitations in terms of accuracy and automation.

The emerging field of geospatial artificial intelligence (GeoAI) is transforming UGS monitoring. By integrating advanced artificial intelligence, particularly deep learning, with geospatial science, GeoAI provides effective solutions to these challenges. Convolutional neural networks (CNNs) have shown strong performance in feature extraction, while more recent Transformer-based models, with their self-attention mechanisms, further advance the field by capturing long-range contextual information. These capabilities enable the precise segmentation of complex UGS boundaries, differentiation between tree species, and detection of small or hidden vegetation in densely built environments.

(2) Aims of the Special Issue and how its subject relates to the journal’s scope.

This Special Issue aims to compile cutting-edge research that leverages the synergy between advanced remote sensing technologies and breakthroughs in GeoAI to advance the state of the art in UGS extraction and monitoring. We seek the submission of contributions that explore novel methodologies, address key challenges, and demonstrate practical applications that move beyond conventional approaches.

(3) Suggested themes and article types for submission.

We invite the submission of high-quality original research articles and comprehensive review papers that address, but are not limited to, the following topics:

1. Novel GeoAI and Deep Learning Architectures for UGS Analysis;
2. Multi-Source and Multi-Modal Data Fusion in UGS Mapping;
3. Dynamic Monitoring and Time-Series Analysis of UGS Changes;
4. UGS Applications for Urban Sustainability and Environmental Justice;
5. Explainable AI (XAI) and Uncertainty Quantification in UGS Extraction;
6. Cloud-Based Computing and Automated Workflows for Large-Scale UGS Monitoring;
7. From Pixels to People: Integrating Remote Sensing with Social Perception and Public Health.

Dr. Zhoupeng Ren
Prof. Dr. Yong Ge
Dr. Junfu Fan
Prof. Dr. Feng Ling
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. 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.

• urban green space
• GeoAI
• remote sensing
• deep learning
• data fusion
• environmental justice
• dynamic monitoring
• explainable AI
• image segmentation