Extreme Precipitation Nowcasting using Multi-Task Latent Diffusion Models

• URL: http://arxiv.org/abs/2410.14103v2
• Date: Sat, 26 Oct 2024 06:46:26 GMT
• Title: Extreme Precipitation Nowcasting using Multi-Task Latent Diffusion Models
• Authors: Li Chaorong, Ling Xudong, Yang Qiang, Qin Fengqing, Huang Yuanyuan,
• Abstract summary: We introduce the multi-task latent diffusion model(MTLDM), a novel approach for precipitation prediction. We decompose the radar image using decomposition technology and then predict the sub-images separately. This method enables consistent prediction of real-world precipitation areas up to 5-80 min in advance.
• Score: 0.0
• License:
• Abstract: Deep learning models have made remarkable strides in precipitation prediction, yet they continue to struggle with capturing the spatial details of the features of radar images, particularly over high precipitation intensity areas. This shortcoming is evident in the form of low forecast accuracy in the spatial positioning of radar echo images across varying precipitation intensity regions. To address this challenge, we introduce the multi-task latent diffusion model(MTLDM), a novel approach for precipitation prediction. The basic concept of the MTLDM is based on the understanding that the radar image representing precipitation is the result of multiple factors. Therefore, we adopt a divide-and-conquer approach, that is, we decompose the radar image using decomposition technology and then predict the decomposed sub-images separately. We conceptualize the precipitation image as a composition of various components corresponding to different precipitation intensities. The MTLDM decomposes the precipitation image into these distinct components and employs a dedicated task to predict each one. This method enables spatiotemporally consistent prediction of real-world precipitation areas up to 5-80 min in advance, outperforming existing state-of-the-art techniques across multiple evaluation metrics.

Related papers

• PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling [85.56969895866243]
  We propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth. A zero-shot blur kernel estimation mechanism and an auto-scale denoise guidance strategy are introduced to adapt the unconditional correlations to any blurriness modes.
  arXiv  Detail & Related papers  (2024-10-08T08:38:23Z)
• Two-stage Rainfall-Forecasting Diffusion Model [1.6005657281443229]
  TRDM is a two-stage method for rainfall prediction tasks. The first stage is to capture robust temporal information while preserving spatial information under low-resolution conditions. The second stage is to reconstruct the low-resolution images generated in the first stage into high-resolution images.
  arXiv  Detail & Related papers  (2024-02-20T07:37:32Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• Contrastive Learning Based Recursive Dynamic Multi-Scale Network for Image Deraining [47.764883957379745]
  Rain streaks significantly decrease the visibility of captured images. Existing deep learning-based image deraining methods employ manually crafted networks and learn a straightforward projection from rainy images to clear images. We propose a contrastive learning-based image deraining method that investigates the correlation between rainy and clear images.
  arXiv  Detail & Related papers  (2023-05-29T13:51:41Z)
• Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification [1.7718093866806544]
  We introduce a latent diffusion model (LDM) for precipitation nowcasting - short-term forecasting based on the latest observational data. We benchmark it against the GAN-based Deep Generative Models of Rainfall (DGMR) and a statistical model, PySTEPS. The clearest advantage of the LDM is that it generates more diverse predictions than DGMR or PySTEPS.
  arXiv  Detail & Related papers  (2023-04-25T15:03:15Z)
• Diffusion Probabilistic Model Made Slim [128.2227518929644]
  We introduce a customized design for slim diffusion probabilistic models (DPM) for light-weight image synthesis. We achieve 8-18x computational complexity reduction as compared to the latent diffusion models on a series of conditional and unconditional image generation tasks.
  arXiv  Detail & Related papers  (2022-11-27T16:27:28Z)
• Deep-Learning-Based Precipitation Nowcasting with Ground Weather Station Data and Radar Data [14.672132394870445]
  We propose ASOC, a novel attentive method for effectively exploiting ground-based meteorological observations from multiple weather stations. ASOC is designed to capture temporal dynamics of the observations and also contextual relationships between them. We show that such a combination improves the average critical success index (CSI) of predicting heavy (at least 10 mm/hr) and light (at least 1 mm/hr) rainfall events at 1-6 hr lead times by 5.7%.
  arXiv  Detail & Related papers  (2022-10-20T14:59:58Z)
• Cloud removal Using Atmosphere Model [7.259230333873744]
  Cloud removal is an essential task in remote sensing data analysis. We propose to use scattering model for temporal sequence of images of any scene in the framework of low rank and sparse models. We develop a semi-realistic simulation method to produce cloud cover so that various methods can be quantitatively analysed.
  arXiv  Detail & Related papers  (2022-10-05T01:29:19Z)
• TRU-NET: A Deep Learning Approach to High Resolution Prediction of Rainfall [21.399707529966474]
  We present TRU-NET, an encoder-decoder model featuring a novel 2D cross attention mechanism between contiguous convolutional-recurrent layers. We use a conditional-continuous loss function to capture the zero-skewed %extreme event patterns of rainfall. Experiments show that our model consistently attains lower RMSE and MAE scores than a DL model prevalent in short term precipitation prediction.
  arXiv  Detail & Related papers  (2020-08-20T17:27:59Z)
• From Rain Generation to Rain Removal [67.71728610434698]
  We build a full Bayesian generative model for rainy image where the rain layer is parameterized as a generator. We employ the variational inference framework to approximate the expected statistical distribution of rainy image. Comprehensive experiments substantiate that the proposed model can faithfully extract the complex rain distribution.
  arXiv  Detail & Related papers  (2020-08-08T18:56:51Z)
• Multi-Scale Progressive Fusion Network for Single Image Deraining [84.0466298828417]
  Rain streaks in the air appear in various blurring degrees and resolutions due to different distances from their positions to the camera. Similar rain patterns are visible in a rain image as well as its multi-scale (or multi-resolution) versions. In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features.
  arXiv  Detail & Related papers  (2020-03-24T17:22:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.