DiffREE: Feature-Conditioned Diffusion Model for Radar Echo
Extrapolation
Author:
Qi-liang WU1, Xing WANG1, Tong ZHANG1, Zi-shu MIAO2, Wei-liang YE1, Hao LI1
Affiliation:
1. Nanjing University of Information Science and Technology 2. Baotou Meteorological Bureau
Abstract
Abstract
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.
Publisher
Research Square Platform LLC
Reference68 articles.
1. Le, Xuan-Hien and Lee, Giha and Jung, Kwansue and An, Hyun-uk and Lee, Seungsoo and Jung, Younghun Application of Convolutional Neural Network for Spatiotemporal Bias Correction of Daily Satellite-Based Precipitation. 12(17): 2731 https://doi.org/10.3390/rs12172731, Full Text PDF:C\:\\Users\\wswql\\Zotero\\storage\\KLQUFJT5\\Le 等 。 - 2020 - Application of Convolutional Neural Network for Sp.pdf:application/pdf;Snapshot:C\:\\Users\\wswql\\Zotero\\storage\\9VDVIU9H\\2731.html:text/html, {APHRODITE}, convolutional autoencoder ({ConvAE}), convolutional neural network ({CNN}), Mekong River basin, {PERSIANN}-{CDR}, precipitation bias correction, Number: 17 Publisher: Multidisciplinary Digital Publishing Institute, english, 2020-01, 2022-11-05, Remote Sensing, Spatiotemporal precipitation data is one of the essential components in modeling hydrological problems. Although the estimation of these data has achieved remarkable accuracy owning to the recent advances in remote-sensing technology, gaps remain between satellite-based precipitation and observed data due to the dependence of precipitation on the spatiotemporal distribution and the specific characteristics of the area. This paper presents an efficient approach based on a combination of the convolutional neural network and the autoencoder architecture, called the convolutional autoencoder ({ConvAE}) neural network, to correct the pixel-by-pixel bias for satellite-based products. The two daily gridded precipitation datasets with a spatial resolution of 0.25 ° employed are Asian Precipitation-Highly Resolved Observational Data Integration towards Evaluation ({APHRODITE}) as the observed data and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Climate Data Record ({PERSIANN}-{CDR}) as the satellite-based data. Furthermore, the Mekong River basin was selected as a case study, because it is one of the largest river basins, spanning six countries, most of which are developing countries. In addition to the {ConvAE} model, another bias correction method based on the standard deviation method was also introduced. The performance of the bias correction methods was evaluated in terms of the probability distribution, temporal correlation, and spatial correlation of precipitation. Compared with the standard deviation method, the {ConvAE} model demonstrated superior and stable performance in most comparisons conducted. Additionally, the {ConvAE} model also exhibited impressive performance in capturing extreme rainfall events, distribution trends, and described spatial relationships between adjacent grid cells well. The findings of this study highlight the potential of the {ConvAE} model to resolve the precipitation bias correction problem. Thus, the {ConvAE} model could be applied to other satellite-based products, higher-resolution precipitation data, or other issues related to gridded data., https://www.mdpi.com/2072-4292/12/17/2731, 2072-4292, http://creativecommons.org/licenses/by/3.0/ 2. Trebing, Kevin and Stanczyk, Tomasz and Mehrkanoon, Siamak {SmaAt}-{UNet}: Precipitation nowcasting using a small attention-{UNet} architecture. 145: 178--186 https://doi.org/10.1016/j.patrec.2021.01.036, 全 文:C\:\\Users\\wswql\\Zotero\\storage\\P2GZJVHQ\\Trebing 等 。 - 2021 - SmaAt-UNet Precipitation nowcasting using a small.pdf:application/pdf;ScienceDirect Snapshot:C\:\\Users\\wswql\\Zotero\\storage\\SXWENMSF\\S0167865521000556.html:text/html, Neural networks, Coupling regularization, Domain adaptation, Kernel methods, english, 2021-05-01, 2022-11-05, Pattern Recognition Letters, Pattern Recognition Letters, Weather forecasting is dominated by numerical weather prediction that tries to model accurately the physical properties of the atmosphere. A downside of numerical weather prediction is that it is lacking the ability for short-term forecasts using the latest available information. By using a data-driven neural network approach we show that it is possible to produce an accurate precipitation nowcast. To this end, we propose {SmaAt}-{UNet}, an efficient convolutional neural networks-based on the well known {UNet} architecture equipped with attention modules and depthwise-separable convolutions. We evaluate our approaches on a real-life datasets using precipitation maps from the region of the Netherlands and binary images of cloud coverage of France. The experimental results show that in terms of prediction performance, the proposed model is comparable to other examined models while only using a quarter of the trainable parameters., {SmaAt}-{UNet}, https://www.sciencedirect.com/science/article/pii/S0167865521000556, 0167-8655 3. Song, Kuan and Yang, Guowei and Wang, Qixun and Xu, Chunmeng and Liu, Jianzhong and Liu, Wenjun and Shi, Chen and Wang, Ying and Zhang, Gong and Yu, Xiaochen and Gu, Zhu and Zhang, Wenpeng Deep Learning Prediction of Incoming Rainfalls: An Operational Service for the City of Beijing China. IEEE Xplore Abstract Record:C\:\\Users\\wswql\\Zotero\\storage\\GVREGEUW\\8955589.html:text/html, Deep learning, Meteorological radar, {AI} as a Service, Deep Learning, {FCN}, Radar imaging, Rain, Weather Forecast, Weather forecasting, Weather Radar, {ISSN}: 2375-9259, 2019-11, 2019 International Conference on Data Mining Workshops ({ICDMW}), 180--185, 2019 International Conference on Data Mining Workshops ({ICDMW}), We developed a deep learning prototype for the purpose of rainfall prediction for the city of Beijing China. It predicts rainfall dynamics in the next two hours with spatial reso-lution of 1km and temporal resolution of 6 minutes. That is a magnitude better than traditional weather forecasting. The computation time is less than 10 seconds, several magnitudes of less computation time than traditional forecasting. This deep learning network combines the strengths of known structures such as U-Net, {ResNet}, Sqeeze-and-Excitation, and the spatial Attention mod-ule. We rely solely on full convolutional layers instead of {RNN} layers as used in other weather prediction ef-forts. Meteorologically assessment metrics suggest better performance by the {FCN} approach. The prototype is now up and running in anticipation for the summer rain season of 2019. This might be the first such service employed by a capital weather service., Deep Learning Prediction of Incoming Rainfalls, 10.1109/ICDMW.2019.00036 4. Qiu, XueXing and Zhang, FuQing (2016) Prediction and predictability of a catastrophic local extreme precipitation event through cloud-resolving ensemble analysis and forecasting with Doppler radar observations. Science China Earth Sciences 59: 518--532 Springer 5. Bai, Cong and Sun, Feng and Zhang, Jinglin and Song, Yi and Chen, Shengyong Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting. 19: 1--5 https://doi.org/10.1109/LGRS.2022.3162882, IEEE Xplore Abstract Record:C\:\\Users\\wswql\\Zotero\\storage\\H8AE32DK\\9743916.html:text/html, Data mining, Decoding, Feature extraction, Feature fusion, Fuses, global feature, high-intensity rainfall, local feature, Logic gates, Merging, Meteorological radar, precipitation nowcasting, Conference Name: {IEEE} Geoscience and Remote Sensing Letters, 2022, {IEEE} Geoscience and Remote Sensing Letters, Precipitation nowcasting is one of the fundamental challenges in natural hazard research. High-intensity rainfall, especially the rainstorm, will lead to the enormous loss of people ’s property. Existing methods usually utilize convolution operation to extract rainfall features and increase the network depth to expand the receptive field to obtain fake global features. Although this scheme is simple, only local rainfall features can be extracted leading to insensitivity to high-intensity rainfall. This letter proposes a novel precipitation nowcasting framework named Rainformer, in which, two practical components are proposed: the global features extraction unit and the gate fusion unit ({GFU}). The former provides robust global features learning ability depending on the window-based multi-head self-attention (W-{MSA}) mechanism, while the latter provides a balanced fusion of local and global features. Rainformer has a simple yet efficient architecture and significantly improves the accuracy of rainfall prediction, especially on high-intensity rainfall. It offers a potential solution for real-world applications. The experimental results show that Rainformer outperforms seven state of the arts methods on the benchmark database and provides more insights into the high-intensity rainfall prediction task., Rainformer, 1558-0571
|
|