Deep Precipitation Downscaling

Yu, Tingzhao; Kuang, Qiuming; Zheng, Jiangping; Hu, Junnan

doi:10.1109/lgrs.2021.3049673

Cited by 10 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 unequivocally highlights the superiority of DPDM in downscaling results compared to other statistical methods. This includes deterministic models such as Enhanced Deep Residual Networks for Super-Resolution with Generative Adversarial framework (EDSR-GAN), known for their superiority over traditional statistical techniques [40][41][42][43] , as well as the widely-used linear interpolation methods (Lerp) in meteorology 44,45 (PSNR), Structure Similarity Index Measure (SSIM), and Root Mean Square Error (RMSE). It is worth mentioning that this superiority is particularly evident in the case of precipitation and temperature downscaling, which are very important for social life in a warming climate.…”

Section: Resultsmentioning

confidence: 99%

Diffusion model-based probabilistic downscaling for 180-year East Asian climate reconstruction

Ling,

Lu,

Luo

et al. 2024

npj Clim Atmos Sci

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Diffusion model-based probabilistic downscaling for 180-year East Asian climate reconstruction

Ling,

Lu,

Luo

et al. 2024

npj Clim Atmos Sci

View full text Add to dashboard Cite

show abstract

“…Results show that it is superior to pure numerical weather prediction. For getting precise and accurate prediction, Yu et al [19] proposes an auxiliary guided spatial distortion network. However, few existing methods take both a deep learning architecture design and meteorological theory into account, which might be a possible avenue for future research.…”

Section: Deep Learningmentioning

confidence: 99%

Deep Quantified Visibility Estimation for Traffic Image

Zhang

et al. 2022

Atmosphere

View full text Add to dashboard Cite

Image-based quantified visibility estimation is an important task for both atmospheric science and computer vision. Traditional methods rely largely on meteorological observation or manual camera calibration, which restricts its performance and generality. In this paper, we propose a new end-to-end pipeline for single image-based quantified visibility estimation by an elaborate integration between meteorological physical constraint and deep learning architecture design. Specifically, the proposed Deep Quantified Visibility Estimation Network (abbreviated as DQVENet) consists of three modules, i.e., the Transmission Estimation Module (TEM), the Depth Estimation Module (DEM), and the Extinction coEfficient Estimation Module (E3M). Casting on these modules, the meteorological prior constraint can be combined with deep learning. To validate the performance of DQVENet, this paper also constructs a traffic image dataset (named QVEData) with accurate visibility calibration. Experimental results compared with many state-of-the-art methods on QVEData demonstrate the effectiveness and superiority of DQVENet.

show abstract

“…Short-term extreme heavy rainfall is a major weather disaster affecting human lives and socio-economics. Analyzing the features of weather radar echoes and performing the extrapolation based on these features are commonly used for nowcasting [1][2][3]. Currently, the predominant radar extrapolation methods in operations are based on algorithms such as cross-correlation, centroid tracking and optical-flow analysis [4,5].…”

Section: Introductionmentioning

confidence: 99%

DiffREE: Feature-Conditioned Diffusion Model for Radar Echo Extrapolation

Qi-liang,

Xing,

Tong

et al. 2024

Preprint

View full text Add to dashboard Cite

Deep learning techniques for radar echo extrapolation and prediction have become crucial for short-term precipitation forecasts in recent years. As the extrapolation leading time extends, radar echo intensity attenuates increasingly, and the forecast performance on strong echoes declines rapidly. These are two typical characteristics contributing to the current inaccurate results of radar extrapolation. To this end, we propose a novel diffusion radar echo extrapolation (DiffREE) algorithm driven by echo frames in this study. This algorithm deeply integrates the spatio-temporal information of radar echo frames through a conditional encoding module, and then it utilizes a Transformer encoder to automatically extract the spatio-temporal features of echoes. These features serve as inputs to the conditional diffusion model, driving the model to reconstruct the current radar echo frame. Moreover, a validation experiment demonstrates that the proposed method can generate high-precision and high-quality forecast images of radar echoes. To further substantiate the model performance, the DiffREE algorithm is compared with the other four models by using public datasets. In the radar echo extrapolation task, the DiffREE demonstrates a remarkable improvement in the evaluation metrics of critical success index, equitable threat score, Heidke skill score and probability of detection by 21.5%, 27.6%, 25.8%, and 21.8%, respectively, displaying notable superiority.

show abstract

Deep Precipitation Downscaling

Cited by 10 publications

References 24 publications

Diffusion model-based probabilistic downscaling for 180-year East Asian climate reconstruction

Diffusion model-based probabilistic downscaling for 180-year East Asian climate reconstruction

Deep Quantified Visibility Estimation for Traffic Image

DiffREE: Feature-Conditioned Diffusion Model for Radar Echo Extrapolation

Contact Info

Product

Resources

About