Deep Domain Adaptation Applied to Remote Sensing Data Analysis

Deep learning has transformed remote sensing, driving state-of-the-art results in land use and land cover classification, object detection, change detection, and ecological assessment. Yet a core challenge remains: models trained on data from one domain — defined by sensor type, geographic region, acquisition date, or atmospheric conditions — often degrade sharply when applied to another, even for the same task. Generating sufficient labelled reference data to retrain for each new domain is costly and time-consuming.

Domain adaptation addresses this gap by enabling models to transfer knowledge across spatial, temporal, and sensor domains, with or without target-domain labels. Recent advances in foundation models and vision-language models (VLMs) are opening new frontiers in this space: large-scale pre-trained models offer rich, generalizable representations that can dramatically reduce the labelled data burden, while VLMs introduce the possibility of language-guided adaptation and zero-shot transfer to unseen remote sensing domains.

This Research Topic welcomes contributions on the methodological development, evaluation, and application of deep domain adaptation for remote sensing, including:

Land use and land cover mapping through domain-invariant representations
Cross-sensor and cross-regional adaptation for improved classification accuracy
Semi-supervised and unsupervised deep adaptation techniques
Foundation model fine-tuning and prompting strategies for remote sensing domains
Vision-language models for zero-shot and few-shot domain transfer
Benchmark datasets and evaluation protocols for domain adaptation
Transfer learning and continual learning for dynamic remote sensing data
Applications in environmental monitoring, agriculture, urban analysis, and disaster response

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Data Report
• Editorial
• FAIR² Data
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Policy and Practice Reviews
• Policy Brief
• Review
• Systematic Review
• Technology and Code

Keywords: domain adaptation, artificial intelligence, deep learning, remote sensing, image classification, semantic segmentation, regression models

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.