Short-term precipitation forecasting remains challenging due to the difficulty in capturing long-term spatiotemporal dependencies. Current deep learning methods fall short in establishing effective dependencies between conditions and forecast results, while also lacking interpretability. To address this issue, we propose a Precipitation Nowcasting Using Diffusion Transformer with Causal Attention model. Our model leverages Transformer and combines causal attention mechanisms to establish spatiotemporal queries between conditional information (causes) and forecast results (results). This design enables the model to effectively capture long-term dependencies, allowing forecast results to maintain strong causal relationships with input conditions over a wide range of time and space. We explore four variants of spatiotemporal information interactions for DTCA, demonstrating that global spatiotemporal labeling interactions yield the best performance. In addition, we introduce a Channel-To-Batch shift operation to further enhance the model’s ability to represent complex rainfall dynamics. We conducted experiments on two datasets. Compared to state-of-the-art U-Net-based methods, our approach improved the CSI (Critical Success Index) for predicting heavy precipitation by approximately 15% and 8% respectively, achieving state-of-the-art performance. Our project is open source and available on GitHub at: https://github.com/ybu-lxd/DTCA.
15 February 2013 in IEEE Signal Processing Letters
A Copula-based joint statistical model is proposed for texture representation on the domain of quaternion wavelet transform (QWT). Both the magnitude and the three phases of QWT are used as the discriminative information for constructing a 2-level Copula model, which consists of inner and outer Copulas. The inner Copula is applied to the intra-scale dependence while the outer Copula to capture the magnitude-phase dependence. Texture retrieval experiments based on Bayesian framework are carried out to evaluate our model. Experimental results show that, based on the multilevel Copula model, the performance of texture representation is improved by taking into account both the magnitude-phase dependence and the intra-scale dependence.
The growing volume of meteorological data and advancements in computing performance have made the application of deep learning technology in short-term rainfall prediction crucial. However, existing learning approaches struggle to accurately predict detailed spatial location information, particularly obvious in predicting extreme rainfall events, leading to inadequate prediction accuracy and subpar performance in meteorological assessment indicators, limiting the effectiveness and applicability of deep learning models in rainfall prediction. To address these challenges, we propose a spacetime separable latent diffusion model with intensity structure information (SSLDM-ISI) to capture spatial and temporal information more efficiently. SSLDM-ISI incorporates two key strategies to solve the spatiotemporal information issue. First, a spatiotemporal conversion block (STC Block) within the backbone network effectively extracts and integrates spatiotemporal information. Second, our proposed latent space coding technique based on rainfall intensity structural information enhances the information representation ability of extreme rainfall. In addition, an examination of the impact of various conditions is conducted on the prediction results to enhance the model’s prediction accuracy and stability. Through comparative analysis of meteorological evaluation and image quality evaluation indicators on two datasets, our proposed approach outperforms existing advanced technologies in short-term rainfall prediction, achieving current state-of-the-art results. Our project is open source and available on GitHub at: https://github.com/ybu-lxd/SISLDM-ISI
27 March 2024 in IEEE Geoscience and Remote Sensing Letters
Deep neural networks have made great achievements in rainfall prediction.However, the current forecasting methods have certain limitations, such as with blurry generated images and incorrect spatial positions. To overcome these challenges, we propose a Two-stage Rainfall-Forecasting Diffusion Model (TRDM) aimed at improving the accuracy of long-term rainfall forecasts and addressing the imbalance in performance between temporal and spatial modeling. TRDM is a two-stage method for rainfall prediction tasks. The task of the first stage is to capture robust temporal information while preserving spatial information under low-resolution conditions. The task of the second stage is to reconstruct the low-resolution images generated in the first stage into high-resolution images. We demonstrate state-of-the-art results on the MRMS and Swedish radar datasets. On the Swedish dataset, our proposed method achieves a 5-10 percentage-point improvement in CSI compared to the other baseline methods for the 60-80 minute prediction range. Our project is open source and available on GitHub at: https://github.com/clearlyzerolxd/TRDM.