Diffusion Model-based Probabilistic Downscaling for 180-year East Asian Climate Reconstruction
This provides a more detailed perspective on regional climate change in East Asia, addressing the need for localized insights in the context of global warming, but it is incremental as it adapts diffusion models to a specific domain.
The paper tackles the problem of downscaling climate data from coarse to fine resolution by introducing a diffusion probabilistic downscaling model (DPDM) that transforms data from 1° to 0.1° resolution, achieving more accurate local details and generating ensemble members to evaluate uncertainty, and applies it to create a 180-year dataset for East Asia.
As our planet is entering into the "global boiling" era, understanding regional climate change becomes imperative. Effective downscaling methods that provide localized insights are crucial for this target. Traditional approaches, including computationally-demanding regional dynamical models or statistical downscaling frameworks, are often susceptible to the influence of downscaling uncertainty. Here, we address these limitations by introducing a diffusion probabilistic downscaling model (DPDM) into the meteorological field. This model can efficiently transform data from 1° to 0.1° resolution. Compared with deterministic downscaling schemes, it not only has more accurate local details, but also can generate a large number of ensemble members based on probability distribution sampling to evaluate the uncertainty of downscaling. Additionally, we apply the model to generate a 180-year dataset of monthly surface variables in East Asia, offering a more detailed perspective for understanding local scale climate change over the past centuries.