Lighting the Night with Generative Artificial Intelligence

TL;DR

This paper introduces RefDiff, a generative diffusion model that produces high-precision visible light reflectance data at night from infrared satellite data, enhancing continuous weather observation capabilities.

Contribution

The study pioneers the use of diffusion models for nighttime visible light reflectance generation, significantly improving accuracy and uncertainty estimation over classical models.

Findings

RefDiff achieves SSIM of 0.90 in reflectance generation.

Model performs well in complex cloud regions.

Nighttime reflectance generation is validated against VIIRS data.

Abstract

The visible light reflectance data from geostationary satellites is crucial for meteorological observations and plays an important role in weather monitoring and forecasting. However, due to the lack of visible light at night, it is impossible to conduct continuous all-day weather observations using visible light reflectance data. This study pioneers the use of generative diffusion models to address this limitation. Based on the multi-band thermal infrared brightness temperature data from the Advanced Geostationary Radiation Imager (AGRI) onboard the Fengyun-4B (FY4B) geostationary satellite, we developed a high-precision visible light reflectance generative model, called Reflectance Diffusion (RefDiff), which enables 0.47~\mu\mathrm{m}, 0.65~\mu\mathrm{m}, and 0.825~\mu\mathrm{m} bands visible light reflectance generation at night. Compared to the classical models, RefDiff not only significantly improves accuracy through ensemble averaging but also provides uncertainty estimation. Specifically, the SSIM index of RefDiff can reach 0.90, with particularly significant improvements in areas with complex cloud structures and thick clouds. The model's nighttime generation capability was validated using VIIRS nighttime product, demonstrating comparable performance to its daytime counterpart. In summary, this research has made substantial progress in the ability to generate visible light reflectance at night, with the potential to expand the application of nighttime visible light data.