A Climate Downscaling Deep Learning Model considering the Multiscale Spatial Correlations and Chaos of Meteorological Events

Abstract

Climate downscaling is a way to provide finer resolution data at local scales, which has been widely used in meteorological research. The two main approaches for climate downscaling are dynamical and statistical. The traditional dynamical downscaling methods are quite time- and resource-consuming based on general circulation models (GCMs). Recently, more and more researchers construct a statistical deep learning model for climate downscaling motivated by the single-image superresolution (SISR) process in computer vision (CV). This is an approach that uses historical climate observations to learn a low-resolution to high-resolution mapping and produces great enhancements in terms of efficiency and effectiveness. Therefore, it has provided an appreciable new insight and successful downscaling solution to multiple climate phenomena. However, most existing models only make a simple analogy between climate downscaling and SISR and ignore the underlying dynamical mechanisms, which leads to the overaveraged downscaling results lacking crucial physical details. In this paper, we incorporate the a priori meteorological knowledge into a deep learning formalization for climate downscaling. More specifically, we consider the multiscale spatial correlations and the chaos in multiple climate events. Depending on two characteristics, we build up a two-stage deep learning model containing a stepwise reconstruction process and ensemble inference, which is named climate downscaling network (CDN). It can extract more local/remote spatial dependencies and provide more comprehensive captures of extreme conditions. We evaluate our model based on two datasets: climate science dataset (CSD) and benchmark image dataset (BID). The results demonstrate that our model shows the effectiveness and superiority in downscaling daily precipitation data from 2.5 degrees to 0.5 degrees over Asia and Europe. In addition, our model exhibits better performance than the other traditional approaches and state-of-the-art deep learning models.

Multivariate deep learning for reconstruction of spatial missing climate data

“…Climate events can be treated as very complicated hydrodynamic phenomena [13]. The various meteorological variables do not exist independently, and there are complex physical connections between them.…”

“…With the development of deep learning, innovative ideas and methods have been brought to the meteorological field [13]. In optimizing deep learning algorithms and improving computer hardware performance, the scale and ability of deep learning models have been explosively improved.…”

spateGAN: Spatio‐Temporal Downscaling of Rainfall Fields Using a cGAN Approach

“…Recent studies have extended the spatial super‐resolution approach to the temporal domain and generated a single image with a fourfold higher spatio‐temporal resolution applied to rainfall and temperature data (Serifi et al., 2021). CNNs have also shown their potential in downscaling low‐resolution climate model outputs while outperforming other statistical approaches (Baño‐Medina et al., 2020; Mu et al., 2020; Sun & Tang, 2020; Vaughan et al., 2022).…”

Investigating transformer‐based models for spatial downscaling and correcting biases of near‐surface temperature and wind‐speed forecasts

“…It has the advantage of being computationally efficient and able to correct model biases. However, due to its simplified mathematics formalization and assumption of statistical stationarity (Mu et al ., 2020), statistical downscaling can be degraded and even generates unreasonable results (Vandal et al ., 2017).…”