Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting

Bai, Cong; Sun, Feng; Zhang, Jinglin; Song, Yi; Chen, Shengyong

doi:10.1109/lgrs.2022.3162882

Cited by 37 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatio-temporal prediction methods can be roughly divided into CNN-based (Oh et al 2015;Mathieu, Couprie, and LeCun 2015;Tulyakov et al 2018), RNN-based (Wang et al 2023b(Wang et al , 2022c, and other models including the combinations (Weissenborn, Täckström, and Uszkoreit 2019;Kumar et al 2019) and transformer based models (Dosovitskiy et al 2020;Bai et al 2022). While there are several existing models based on graph neural networks (GNNs), their primary focus is on handling graph data (Wang, Cao, and Philip 2020;Wang et al 2022b), which go out of the scope of our work.…”

Section: Related Workmentioning

confidence: 99%

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

Wu,

Liang,

Xiong

et al. 2024

AAAI

View full text Add to dashboard Cite

Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to designed models that are neither simple nor practical. To address this issue, this paper presents a systematic study on existing shortcomings faced by off-the-shelf models, including lack of local fidelity, poor prediction performance over long time-steps, low scalability, and inefficiency. To systematically address the aforementioned problems, we propose an EarthFarseer, a concise framework that combines parallel local convolutions and global Fourier-based transformer architectures, enabling dynamically capture the local-global spatial interactions and dependencies. EarthFarseer also incorporates a multi-scale fully convolutional and Fourier architectures to efficiently and effectively capture the temporal evolution. Our proposal demonstrates strong adaptability across various tasks and datasets, with fast convergence and better local fidelity in long time-steps predictions. Extensive experiments and visualizations over eight human society physical and natural physical datasets demonstrates the state-of-the-art performance of EarthFarseer. We release our code at https://github.com/easylearningscores/EarthFarseer.

show abstract

Section: Related Workmentioning

confidence: 99%

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

Wu,

Liang,

Xiong

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…For instance, Huang et al [15] proposed multimodal spatiotemporal networks for processing hyperspectral weather images and forecasted the trajectory and intensity of tropical cyclones. Bai et al [16] created a feature-extraction balanced network termed Rainformer to perform precipitation nowcasting. Hang et al [17] invented an unsupervised feature learning model which utilized multimodal data to extract features without any label information.…”

Section: Related Workmentioning

confidence: 99%

Faster and Lighter Meteorological Satellite Image Classification by a Lightweight Channel-Dilation-Concatenation Net

Shang

Zhang

Wang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

With the development of satellite photography, meteorologists are inclined to rely on methods for the automatic and efficient classification of weather images. However, many popular networks require numerous parameters and a lengthy inference time, making them unsuitable for real-time classification tasks. To solve these problems, a lightweight convolutional network termed the Channel-Dilation-Concatenation network (CDC-net) is constructed for meteorological satellite image classification. When extracting features, CDC-net utilizes depth-wise convolution rather than standard convolution. Additionally, a FeatureCopy operation was employed instead of a half-convolution operation. CDC-net extracts high-dimensional features and contains a local importance-based pooling layer, reducing the network's depth, the number of network parameters and inference time. Based on these techniques, the CDC-net achieves an accuracy of 93.56% on the Large-Scale Satellite Cloud Image Database for Meteorological Research, with a GPU inference time of 3.261 ms and 1.12 million parameters. Because many weather images reveal multiple weather patterns, multiple labels are necessary. Therefore, we propose a prediction method and conduct experiments on multi-label data. Experiments on single-label and multi-label meteorological satellite image datasets demonstrate the superiority of the CDC-net over other structures. Thus, the proposed CDC-net can provide a faster and lighter solution in meteorological satellite image classification.

show abstract

“…Deep learning-based strategies can primarily be categorized into two types: one is based on the Convolutional Neural Network (CNN), and the other is based on the Recurrent Neural Network (RNN) [9][10][11][12]. The former excels in modeling the spatial representation of radar echoes but has limited capability in modeling the temporal evolution [13]. The latter is adept at capturing the temporal correlations of radar echoes during motion processes but cannot analyze the spatial correlations between radar echo images.…”

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

Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting

Cited by 37 publications

References 13 publications

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

Faster and Lighter Meteorological Satellite Image Classification by a Lightweight Channel-Dilation-Concatenation Net

DiffREE: Feature-Conditioned Diffusion Model for Radar Echo Extrapolation

Contact Info

Product

Resources

About