Remote Sensing Dense Prediction in the Era of Foundation Models and AI Agents
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "AI Remote Sensing".
Deadline for manuscript submissions: 31 March 2027 | Viewed by 57
Editors
Interests: GeoAI; AI4EO; multimodal remote sensing; change detection; disaster response; height estimation
Special Issues, Collections and Topics in MDPI journals
Interests: GeoAI; physical-based image synthesis; multimodal remote sensing; land cover mapping; height estimation; change detection
Interests: remote sensing; computer vision; UAV vision; lightweight models; image classification; object detection; segmentation; change detection; road segmentation; low level
Special Issues, Collections and Topics in MDPI journals
Interests: anomaly/disturbance detection; remote sensing foundation model; zero/few-shot learning
Special Issue Information
Dear Colleagues,
Dense prediction—semantic segmentation, change detection, height and depth estimation, and object extraction—lies at the heart of remote sensing image interpretation, underpinning applications from land-cover mapping and urban monitoring to precision agriculture and disaster response. Deep learning has brought remarkable progress in these tasks over the past decade. Nevertheless, prevailing models remain largely task-specific: they are trained on closed label sets, rely on costly pixel-level annotations, and often generalize poorly across sensors, resolutions, and geographic regions.
The emergence of foundation models and AI agents is reshaping this landscape. Vision foundation models pre-trained on massive Earth observation archives, promptable segmentation models, and vision–language models now enable open-vocabulary, zero-/few-shot, and interactive dense prediction. Meanwhile, multimodal large language models (MLLMs) and agentic frameworks are beginning to couple pixel-level perception with reasoning, tool use, and autonomous workflow planning, pointing toward generalist systems that can flexibly answer “where and what” questions about the Earth’s surface. This Special Issue aims to bring together the latest advances at this intersection, in close alignment with the scope of Remote Sensing and its AI Remote Sensing section.
Topics of interest include, but are not limited to, the following:
- Remote sensing foundation models and pre-training strategies for dense prediction;
- Promptable, interactive, and open-vocabulary segmentation of remote sensing imagery;
- Label-efficient learning: self-/semi-/weakly supervised learning, domain adaptation, and generalization;
- Multimodal and cross-modal dense prediction with optical, SAR, hyperspectral, and LiDAR data;
- Change detection and spatiotemporal dense prediction;
- Dense regression tasks such as height, depth, and biophysical parameter estimation;
- Multimodal large language models and AI agents for pixel-level geospatial analysis;
- Generative models and synthetic data for dense prediction;
- Benchmarks, datasets, and evaluation protocols;
- Applications in land-cover mapping, urban monitoring, agriculture, and disaster response.
Dr. Hongruixuan Chen
Dr. Jian Song
Dr. Wei Lu
Dr. Jingtao Li
Guest Editors
Dr. Kai Tang
Guest Editor Assistant
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. 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.
Keywords
- semantic segmentation
- dense prediction
- change detection
- foundation models
- vision–language models
- multimodal large language models
- AI agents
- label-efficient learning
- Earth observation
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
