Multi-Source Remote Sensing and Foundation Models for Advanced Vegetation Mapping and Ecosystem Service Assessment

Dear Colleagues,

Vegetation plays a central role in regulating ecosystem functions and climate while maintaining biodiversity. It is therefore key to facilitate, implement, and support sustainable land management. Accurately characterizing vegetation patterns and quantifying associated ecosystem services are therefore vital for understanding landscape processes and informing environmental decision-making. 

In recent years, rapid progress in remote sensing technologies—from high-resolution optical and SAR satellite missions to UAV platforms, LiDAR systems, and next-generation multispectral and hyperspectral sensors—has expanded the capacity for detailed observation of vegetation structure, composition, and dynamics. These diverse data sources provide complementary information, enabling the capture of vegetation traits and diversity heterogeneity across spatial, temporal, and spectral dimensions.

The integration of multi-source remote sensing has become increasingly indispensable for enhancing vegetation mapping and ecosystem service assessment, particularly under the accelerating pressures of climate change, land-use intensification, and ecological degradation. By combining the strengths of different sensors, it is possible for researchers to improve classification accuracy, better represent fine-scale vegetation traits, and quantify ecosystem services with greater precision and consistency. Foundation models, multi-sensor fusion and cross-scale analysis also facilitate more robust monitoring frameworks capable of supporting ecological modeling, carbon accounting, habitat assessment, and nature-based solutions.

Despite these advances, significant challenges remain. Effective fusion of multi-platform datasets requires improved algorithms for harmonization and interoperability, especially when incorporating disparate spatial resolutions, spectral characteristics, and temporal frequencies. Cross-scale modeling and upscaling strategies still face limitations in generalization and transferability across diverse ecosystems. Foundation models, on the other hand, need to balance spectral, temporal, spatial and contextual dimensions, while avoiding bias towards particular ecosystems. Additionally, the increasing volume and complexity of remote sensing data introduce computational barriers that necessitate new approaches in big data processing, machine learning, and cloud-based geospatial analytics.

Addressing these challenges is crucial for advancing both methodological innovation and applied understanding of vegetation and ecosystem service dynamics.

This Special Issue, “Multi-Source Remote Sensing and Foundation Models for Advanced Vegetation Mapping and Ecosystem Service Assessment,” aims to showcase innovative research that integrates diverse remote sensing platforms—including optical, SAR, LiDAR, UAV, multispectral, and hyperspectral systems—to advance the characterization of vegetation structure, bio-chemical traits, function, and dynamics. A central goal is to promote methodological breakthroughs in multi-sensor data fusion, cross-scale analysis, and machine-learning-based modeling including self-supervised learning approaches that enhance the accuracy, robustness, and transferability of vegetation mapping approaches, and ecosystem service assessments and monitoring approaches.

By bridging technological and methodological development with ecological applications, this Special Issue seeks to stimulate interdisciplinary collaboration and foster new insights into how multi-source remote sensing can support the monitoring of landscape change, biodiversity patterns, and ecosystem functionality under global environmental pressures. Contributions emphasizing novel algorithms, fusion strategies, ecological modeling, uncertainty analysis, or applications in diverse biomes are particularly encouraged.

The aims of this Special Issue align closely with the scope of Remote Sensing, which emphasizes cutting-edge sensor technologies, data-processing methodologies, and geospatial applications for understanding Earth system processes. By highlighting research that advances both the science and operational use of multi-source remote sensing and foundation models for vegetation and ecosystem services, the Special Issue reinforces the journal’s mission to promote innovative, high-impact remote sensing solutions for global environmental monitoring and sustainable land management.

This Special Issue welcomes a wide range of contributions that advance the use of multi-source remote sensing and novel foundation models for vegetation characterization and ecosystem service assessments. Suggested themes include, but are not limited to, the following:

(1) Self-supervised learning approaches for data integration into foundation models.

(2) Multi-sensor fusion approaches for vegetation classification, biomass estimation, and structural/bio-chemical characterization.

(3) Integration of optical, SAR, and LiDAR datasets to capture vegetation heterogeneity and improve retrieval of biophysical and functional traits.

(4) Ecosystem service mapping and modeling, including carbon storage, habitat quality, soil conservation, hydrological regulation, and nature-based solutions.

(5) Shallow to deep machine learning methods designed for multi-source data harmonization, feature extraction, predictive modeling and development of foundation models.

(6) Time-series and phenology-driven analysis for monitoring vegetation dynamics, land surface phenology, disturbance regimes, and long-term ecological change.

(7) UAV-based vegetation surveys and their fusion with satellite or airborne datasets for augmenting available training data and for fine-scale mapping and validation.

(8) Trait-based, functional, or biodiversity-oriented mapping using multispectral, hyperspectral, or LiDAR data.

(9) Cross-scale integration, upscaling methodologies, and uncertainty analysis to improve the robustness and transferability of remote sensing applications across regions and ecosystems.

(10) Methodological, algorithmic, or technological innovations that enhance the efficiency, precision, or interpretability of multi-source remote sensing workflows.

We encourage the submission of original research articles, methodological or technical papers, and comprehensive review articles that synthesize emerging trends, challenges, and future directions in this rapidly evolving field.

Dr. Jianhong Liu
Prof. Dr. Clement Atzberger
Dr. Peijun Sun
Prof. Dr. Xianfeng Liu
Dr. Donghai Zhang
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-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.

• multi-source remote sensing
• foundation model
• vegetation mapping and monitoring
• sensor fusion
• lidar–optical–sar integration
• ecosystem service assessment
• shallow to deep machine learning
• time-series analysis
• multi-sensor uav-based vegetation monitoring
• land surface phenology and phenology-driven mapping
• cross-scale modeling and uncertainty assessment