Emulation and Surrogate Modeling in Remote Sensing: Advances, Challenges and Applications

Dear Colleagues,

Remote sensing increasingly depends on complex radiative transfer models, large-scale numerical simulations, and computationally intensive inversion workflows. As satellite missions grow in spectral, spatial, and temporal complexity, conventional modeling and retrieval approaches are reaching their computational limits. Emulation and surrogate modeling—often built on advanced machine learning algorithms, efficient sampling strategies, and dimensionality reduction techniques—have emerged as powerful solutions to these challenges, offering fast, scalable, and flexible alternatives to expensive physical models and data-processing pipelines. Surrogates can be derived from physically based radiative transfer simulations, empirically from observational data, or through hybrid approaches that integrate physics and machine learning. Together, they enable real-time applications, facilitate uncertainty quantification, and support operational processing for current and upcoming missions.

This Special Issue aims to bring together advances in emulation and surrogate modeling across the full remote sensing domain—from vegetation, soil, and hydrology to cryosphere, atmosphere, and coastal applications. We welcome the submission of contributions that focus on the development of new emulators; design and comparison of machine learning architectures, sampling schemes (e.g., active learning, optimal experimental design), and dimensionality reduction methods (e.g., PCA, autoencoders, manifold learning); evaluation of performance and scalability; integration of uncertainty estimation; or demonstrate applications in retrievals, data assimilation, or mission preparation (e.g., FLEX, CHIME, CO₂M). Submissions covering cloud-native and high-performance implementations are especially encouraged.

Topics include, but are not limited to, the following:

• Surrogate modeling of radiative transfer or physical forward models.
• Data-driven and machine-learning emulators (e.g., GPR, deep learning, and hybrid models).
• Emulation for inversion, parameter retrieval, and data assimilation.
• Uncertainty-aware emulation and probabilistic surrogates.
• Sampling strategies and experimental design for training efficient emulators.
• Dimensionality reduction for emulation (e.g., PCA, latent-space methods, and spectral compression).
• Cloud-based and HPC implementations of emulators.
• Emulation for mission preparation, calibration/validation, and large-scale mapping.
• Applications across vegetation, hydrology, cryosphere, urban remote sensing, ocean color, and atmospheric sensing.

This Special Issue aims to establish a comprehensive overview of current advances and future directions in surrogate modeling—highlighting the role of modern machine learning, sampling strategies, and dimensionality reduction—to support more efficient, scalable, and uncertainty-aware remote sensing workflows.

Dr. Jochem Verrelst
Dr. Jorge Vicent
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.