A Mechanism-Coupled Split Window Network for Medium- to High-Resolution Land Surface Temperature Retrieval
arXiv:2509.04991v2 Announce Type: replace-cross Abstract: Land surface temperature (LST) is a fundamental physical variable in land-atmosphere interactions, surface energy budgets, and climate processes. LST derived from medium- to high-resolution thermal infrared (TIR) observations effectively reveals thermal environmental disparities across distinct landscape units. However, achieving accurate, robust, and globally generalizable LST retrieval remains challenging under complex atmospheric conditions and diverse land cover types. Traditional split window (SW) algorithms heavily rely on empiric
Advances in AI and remote sensing technology, coupled with increasing climate concerns, enable more sophisticated environmental monitoring capabilities.
Accurate land surface temperature data is critical for understanding climate change, managing natural resources, and predicting extreme weather events, impacting economic stability and public safety.
Improved LST retrieval models can provide more precise and reliable data for environmental policy-making and agricultural planning, enhancing predictive capabilities.
- · Climate scientists
- · Agricultural sector
- · Environmental monitoring agencies
- · AI/ML developers
- · Sectors reliant on outdated climate models
- · Regions unprepared for climate-related shifts
More precise LST data becomes available for research and operational applications.
Enhanced climate models and predictive capabilities lead to better resource allocation and disaster preparedness.
Improved environmental intelligence informs global policy and investment, potentially accelerating climate adaptation and mitigation efforts.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG