MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature

TL;DR

This paper introduces MoCoLSK, a novel deep learning architecture for high-resolution Land Surface Temperature downscaling that dynamically fuses multi-modal data, outperforming existing methods and supported by an open-source ecosystem.

Contribution

The paper presents MoCoLSK, a new modality-conditioned network for LST downscaling, and establishes the GrokLST open-source ecosystem with datasets and tools.

Findings

MoCoLSK outperforms existing methods in LST downscaling accuracy.

The approach effectively captures complex dependencies in multispectral data.

Open-source toolkit facilitates further research and application.

Abstract

Land Surface Temperature (LST) is a critical parameter for environmental studies, but directly obtaining high spatial resolution LST data remains challenging due to the spatio-temporal trade-off in satellite remote sensing. Guided LST downscaling has emerged as an alternative solution to overcome these limitations, but current methods often neglect spatial non-stationarity, and there is a lack of an open-source ecosystem for deep learning methods. In this paper, we propose the Modality-Conditional Large Selective Kernel (MoCoLSK) Network, a novel architecture that dynamically fuses multi-modal data through modality-conditioned projections. MoCoLSK achieves a confluence of dynamic receptive field adjustment and multi-modal feature fusion, leading to enhanced LST prediction accuracy. Furthermore, we establish the GrokLST project, a comprehensive open-source ecosystem featuring the GrokLST dataset, a high-resolution benchmark, and the GrokLST toolkit, an open-source PyTorch-based toolkit encapsulating MoCoLSK alongside 40+ state-of-the-art approaches. Extensive experimental results validate MoCoLSK's effectiveness in capturing complex dependencies and subtle variations within multispectral data, outperforming existing methods in LST downscaling. Our code, dataset, and toolkit are available at https://github.com/GrokCV/GrokLST.