Multimodal Semisupervised Deep Graph Learning for Automatic Precipitation Nowcasting

Miao, Kaichao; Wang, Wei; Hu, Rui; Zhang, Lei; Zhang, Yali; Wang, Xiang; Nian, Fudong

doi:10.1155/2020/4018042

Cited by 7 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further improve the performance of nowcasting models, enhancing the prediction capabilities for isolated precipitation patterns is crucial. As indicated by previous studies (e.g., Miao et al, 2020;Choi et al, 2021), training the data from satellites and surface observations associated with the physical processes of clouds and precipitation would significantly enhance the performance.…”

Section: Modelmentioning

confidence: 96%

“…Furthermore, in recent studies, both radar and satellite data or surface observations have been used as training data for U-Net models. The incorporation of multiple observational data has shown promising results in improving model performance (e.g., Lebedev et al, 2019;Miao et al, 2020;Choi et al, 2021). These improvements suggest that if the blurry effects of U-Net models can be addressed, U-Net-based precipitation prediction models can be competitive.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Advancing very short-term rainfall prediction with blended U-Net and partial differential approaches

Ha,

Park

2024

Front. Earth Sci.

View full text Add to dashboard Cite

Accurate and timely prediction of short-term rainfall is crucial for reducing the damages caused by heavy rainfall events. Therefore, various precipitation nowcasting models have been proposed. However, the performance of these models still remains limited. In particular, the current operational precipitation nowcasting method, which is based on radar echo tracking, such as the McGill Algorithm for Precipitation Nowcasting by Lagrangian Extrapolation (MAPLE), has a critical drawback when predicting newly developed or decayed precipitation fields. Recently proposed deep learning models, such as the U-Net convolutional neural network outperform the models based on radar echo tracking. However, these models are unsuitable for operational precipitation nowcasting due to their blurry predictions over longer lead times. To address these blurry effects and enhance the performance of U-Net-based rainfall prediction, we propose a blended model that combines a partial differential equation (PDE) model based on fluid dynamics with the U-Net model. The evaluation of the forecast skill, based on both qualitative and quantitative methods for 0–3-h lead times, demonstrates that the blended model provides less blurry and more accurate rainfall predictions compared with the U-Net and partial differential equation models. This indicates the potential to enhance the field of very short-term rainfall prediction. Additionally, we also evaluated the monthly-averaged forecast skills for different seasons, and confirmed the operational feasibility of the blended model, which contributes to the performance enhancement of operational nowcasting.

show abstract

Section: Modelmentioning

confidence: 96%

mentioning

confidence: 99%

Advancing very short-term rainfall prediction with blended U-Net and partial differential approaches

Ha,

Park

2024

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

“…Using meteorological data, such as precipitation, along with non-meteorological but relevant data such as topography, Miao et al (2020) proposed a multimodal semi-supervised deep graph network that is able to infer spatiotemporal correlations for China. For Next Generation Radar (NEXRAD) data in Denver and Dallas Fort Worth, Kim and Chandrasekar (2021) explored ConvGRUs, residual CNNs, and residual GRUs.…”

Section: -Minutes -mentioning

confidence: 99%

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

Sit¹,

Demiray²,

Demir³

2022

Preprint

View full text Add to dashboard Cite

With technological enhancements, the volume, velocity, and variety (3Vs) of the raw digital Earth data have increased in recent years. Due to the increased availability of computer resources and the growing popularity of deep learning applications, this data has been a crucial source for data-driven studies that have transformed the fields of climate and earth science. One of the critical data sources is precipitation supporting climate and earth science studies on modeling, forecasting, and preparedness for extreme events (i.e., floods, droughts, pollution transport). In this study, we worked on an extensive review of manuscripts focusing on use of deep learning methods to tackle challenges either to improve the quality or extrapolate (forecast) rainfall datasets. The purpose of this study is to summarize the most recent developments in deep learning approaches for forecasting rainfall or improving rainfall datasets, as well as highlighting issues, shortcomings, and open questions with insightful recommendations for future directions.

show abstract

“…Chen et al (2020) use ConvLSTM for nowcasting and early warning of heavy rainfall. Ran et al (2021) use Faster-RCNN (Ren et al, 2016) to identify precipitation clouds for Doppler weather radar. The deep neural networks have also been applied to reduce the bias and false alarms of satellite-based precipitation products (Tao et al, 2016).…”

Section: Deep Learningmentioning

confidence: 99%

MSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data

Liu

Chen

2021

Geosci. Model Dev.

View full text Add to dashboard Cite

Abstract. Eastern China is one of the most economically developed and densely populated areas in the world. Due to its special geographical location and climate, eastern China is affected by different weather systems, such as monsoons, shear lines, typhoons, and extratropical cyclones. In the near future, the rainfall rate becomes difficult to predict precisely due to these systems. Traditional physics-based methods such as numerical weather prediction (NWP) tend to perform poorly on nowcasting problems due to the spin-up issue. Moreover, various meteorological stations are distributed in this region, generating a large amount of observation data every day, which have great potential for application to data-driven methods. Thus, it is important to train a data-driven model from scratch that is suitable for the specific weather situation of eastern China. However, due to the high degrees of freedom and nonlinearity of machine learning algorithms, it is difficult to add physical constraints. Therefore, with the intention of using various kinds of data as a proxy for physical constraints, we collected three kinds of data (radar, satellite, and precipitation data) in the flood season from 2017 to 2018 in this area and preprocessed them into tensors (256×256) that cover eastern China with a domain of 12.8×12.8∘. The developed multisource data model (MSDM) combines the optical flow, random forest, and convolutional neural network (CNN) algorithms. It treats the precipitation nowcasting task as an image-to-image problem, which takes radar and satellite data with an interval of 30 min as inputs and predicts radar echo intensity with a lead time of 30 min. To reduce the smoothing caused by convolutions, we use the optical flow algorithm to predict satellite data in the following 120 min. The predicted radar echoes from the MSDM together with satellite data from the optical flow algorithm are recursively implemented in the MSDM to achieve a 120 min lead time. The MSDM predictions are comparable to those of other baseline models with a high temporal resolution of 6 min. To solve blurry image problems, we applied a modified structural similarity (SSIM) index as a loss function. Furthermore, we use the random forest algorithm with predicted radar and satellite data to estimate the rainfall rate, and the results outperform those of the traditional, nonlinear radar reflectivity factor and rainfall rate (Z–R) relationships that use logarithmic functions. The experiments confirm that machine learning with multisource data provides more reasonable predictions and reveals a better nonlinear relationship between radar echo and precipitation rate. Apart from developing complicated machine learning algorithms, exploiting the potential of multisource data will yield more improvements.

show abstract

Multimodal Semisupervised Deep Graph Learning for Automatic Precipitation Nowcasting

Cited by 7 publications

References 18 publications

Advancing very short-term rainfall prediction with blended U-Net and partial differential approaches

Advancing very short-term rainfall prediction with blended U-Net and partial differential approaches

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

MSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data

Contact Info

Product

Resources

About