LPT-QPN: A Lightweight Physics-Informed Transformer for Quantitative Precipitation Nowcasting

Li, Dawei; Deng, Kefeng; Zhang, Di; Liu, Yudi; Leng, Hongze; Yin, Fukang; Ren, Kaijun; Song, Junqiang

doi:10.1109/tgrs.2023.3328945

Cited by 5 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These observations offer a unique perspective for studying distinct precipitation processes within TC. AI methods based on DL technology have been employed to model these observations (Huang et al., 2022; C. Wang & Li, 2023; H. Wang & Li, 2024), improving the identification of complex nonlinear correlations between precipitation regions and intensity by learning potential precipitation distributions (Kim et al., 2022; D. Li et al., 2023; Ravuri et al., 2021; Yang et al., 2022). The technologies consider precipitation rates at each grid position in historical data as multiple video frames.…”

Section: Introductionmentioning

confidence: 99%

“…AI methods based on DL technology have been employed to model these observations (Huang et al, 2022;H. Wang & Li, 2024), improving the identification of complex nonlinear correlations between precipitation regions and intensity by learning potential precipitation distributions (Kim et al, 2022;D. Li et al, 2023;Ravuri et al, 2021;Yang et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Tropical Cyclone Precipitation Forecasting With Deep Learning and Satellite Image Sequencing

Yang,

Wang,

2024

Journal of Geophysical Research: Machine Learning and Computati

View full text Add to dashboard Cite

Precipitation forecasting in tropical cyclones (TC) is vital for warning systems and disaster management. Artificial intelligence (AI)‐based methods show promise in this domain. Here, we investigate two aspects of AI forecasting for TC precipitation: modeling satellite image sequencing and analyzing predictability. To the former, using the Global Precipitation Measurement, we establish a high‐accuracy regional and intensity forecasting method. Through an analysis of precipitation patterns and intensities, we have demonstrated the effectiveness, reliability, and robustness of forecasting TC precipitation. To the latter, we conduct predictability research, which covers different intensity categories and landfall versus non‐landfall TC precipitation. The conclusions are: (a) TC precipitation varies regionally with predictability differences among intensity categories; (b) Forecasting landfalling TC precipitation is less challenging than non‐landfalling, considering TC intensity and paths. The proposed method also demonstrates strong forecasting capabilities in handling extreme and accumulated precipitation within 0–120 min, achieving an accuracy rate of 87%.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Tropical Cyclone Precipitation Forecasting With Deep Learning and Satellite Image Sequencing

Yang,

Wang,

2024

Journal of Geophysical Research: Machine Learning and Computati

View full text Add to dashboard Cite

show abstract

DB-RNN: An RNN for Precipitation Nowcasting Deblurring

Ma,

Zhang,

Liu

2024

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

View full text Add to dashboard Cite

Precipitation nowcasting based on artificial intelligence has garnered widespread attention in the meteorological and computer communities in recent years. While new models are continuously proposed to refresh the forecasting performance, the problem of gradual blurring of forecast maps as the forecast period extends is still serious. Most models use the mean loss and the recursive prediction structure (such as MS-RNN). The mean loss always results in an average of future states, visually appearing as a blur. The recursive prediction method brings the accumulation of error (blur), causing the error (blur) of long-term predictions to increase exponentially. In this study, we add the adversarial loss and gradient loss to penalize the network to ease the blur caused by the averaging loss, and we introduce an additional deblurring network (composed of MS-RNN) behind the forecasting network (composed of MS-RNN) to alleviate the blur caused by the recursive structure, which reduces the blur of the current frame and then recursively and incrementally reduces the blur of subsequent frames. We name the proposed model DB-RNN, which can slow down the error accumulation and alleviate the blurring dilemma. Like MS-RNN, DB-RNN is compatible with multiple RNN models, such as ConvLSTM, TrajGRU, PredRNN, PredRNN++, MIM, MotionRNN, PrecipLSTM, etc. Experiments on two large radar datasets named HKO-7 and DWD-12 indicate that DB-RNN's predictions are more accurate and clear than those from MS-RNN.

show abstract

A Novel Generative Adversarial Network Based on Gaussian-Perceptual for Downscaling Precipitation

Su,

Shi,

Wang

et al. 2024

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

LPT-QPN: A Lightweight Physics-Informed Transformer for Quantitative Precipitation Nowcasting

Cited by 5 publications

References 34 publications

Improving Tropical Cyclone Precipitation Forecasting With Deep Learning and Satellite Image Sequencing

Improving Tropical Cyclone Precipitation Forecasting With Deep Learning and Satellite Image Sequencing

DB-RNN: An RNN for Precipitation Nowcasting Deblurring

A Novel Generative Adversarial Network Based on Gaussian-Perceptual for Downscaling Precipitation

Contact Info

Product

Resources

About