Advancing Spatiotemporal Fusion for High-Resolution Multi-Modal Remote Sensing in Agriculture

The field of remote sensing in agriculture increasingly relies on high spatial resolution imagery to precisely monitor crop growth and agricultural landscapes. However, frequent cloud cover and long revisit periods pose significant challenges to capturing temporal heterogeneity—an aspect crucial for effective monitoring. Recent advancements in spatiotemporal fusion methods seek to address these obstacles by generating synthetic images that combine high spatial and temporal resolutions. Despite these innovations, the fusion of medium- and high-spatial-resolution images remains significantly underexplored. Cutting-edge models, such as dual-stream spatiotemporal decoupling fusion architectures, demonstrate the potential for deep learning to improve accuracy. Nonetheless, there is a pressing need for further exploration and refinement within this domain.

This Research Topic aims to advance the development of innovative models to overcome current limitations in agricultural remote sensing. It focuses on integrating diverse data sources while maintaining accuracy across various agricultural applications. By exploring new methodologies and models, the goal is to enhance the capacity for high-resolution spatiotemporal analysis and to address existing gaps in the field.

To gather further insights on enhancing agricultural remote sensing through spatiotemporal fusion, we welcome articles addressing, but not limited to, the following themes:

- Development and benchmarking of agricultural spatiotemporal fusion models (5–30 m, daily–biweekly)
- Integration of high-temporal-resolution data (e.g., Sentinel-2, MODIS) and high-spatial-resolution data (e.g., GaoFen, PlanetScope, WorldView)
- Uncertainty modeling and quality assessment in agricultural remote sensing
- Overcoming climatic and data collection challenges (e.g., cloud cover, seasonal variability, and incomplete time series) in remote sensing
- Case studies on agricultural applications

We welcome contributions that push the boundaries of current methodologies and propose novel solutions for overcoming limitations in agricultural remote sensing.

Keywords: spatiotemporal fusion, optical-sar integration, cloud removal, deep learning, agricultural monitoring, data reconstruction, remote sensing

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.