Precipitation Nowcasting with Satellite Imagery

Лебедев, В. В.; Ivashkin, Vladimir; Rudenko, Irina; Ganshin, A.; Молчанов, А. А.; Ovcharenko, Sergei; Grokhovetskiy, Ruslan; Бушмаринов, Иван С.; Solomentsev, Dmitry

doi:10.1145/3292500.3330762

Cited by 62 publications

(50 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Today a neural network approach is being successfully applied by the combined data from radars, satellites and computational forecast models [10]. However, such systems are efficient only for the territory where such system has been previously trained and, in most cases, where ground radar data are available [2]. The present paper describes the process of developing a precipitation nowcasting model for the Far East region of Russia providing no radar data are available.…”

Section: Nowcasting Methodsmentioning

confidence: 99%

“…The increased interest to nowcasting from the scientific community is facilitated by the continuously improving quality and growing amount of data obtained due to the commissioning of new satellites and ground meteorological radars as well as the development of computational forecasting methods. At the same time the major part of the current research largely uses radar data for nowcasting as being the most plausible [1][2][3][4] in comparison with the data generated by the computational forecast models and geostationary satellites. Despite the fact that over the last decades the model forecasts precision has considerably increased, it requires a lot of computational and time resources to conduct computations with a high spatiotemporal resolution comparable with the radar data resolution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of precipitation nowcasting method using geostationary satellite data

Andreev¹,

Pererva²,

Kuchma³

2020

Sovr. Probl. DZZ Kosm.

View full text Add to dashboard Cite

Section: Nowcasting Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development of precipitation nowcasting method using geostationary satellite data

Andreev¹,

Pererva²,

Kuchma³

2020

Sovr. Probl. DZZ Kosm.

View full text Add to dashboard Cite

“…The precipitation estimation task aims at estimating per-pixel precipitation rate values, which is usually formulated as a segmentation-like problem [39,40]. In this paper, we take U-Net [41], which is a widely used model in image segmentation based on fully convolutional network (FCN) [42], as our baseline network.…”

Section: Baseline Networkmentioning

confidence: 99%

Multi-Task Collaboration Deep Learning Framework for Infrared Precipitation Estimation

et al. 2021

View full text Add to dashboard Cite

Infrared observation is an all-weather, real-time, large-scale precipitation observation method with high spatio-temporal resolution. A high-precision deep learning algorithm of infrared precipitation estimation can provide powerful data support for precipitation nowcasting and other hydrological studies with high timeliness requirements. The “classification-estimation” two-stage framework is widely used for balancing the data distribution in precipitation estimation algorithms, but still has the error accumulation issue due to its simple series-wound combination mode. In this paper, we propose a multi-task collaboration framework (MTCF), i.e., a novel combination mode of the classification and estimation model, which alleviates the error accumulation and retains the ability to improve the data balance. Specifically, we design a novel positive information feedback loop composed of a consistency constraint mechanism, which largely improves the information abundance and the prediction accuracy of the classification branch, and a cross-branch interaction module (CBIM), which realizes the soft feature transformation between branches via the soft spatial attention mechanism. In addition, we also model and analyze the importance of the input infrared bands, which lay a foundation for further optimizing the input and improving the generalization of the model on other infrared data. Extensive experiments based on Himawari-8 demonstrate that compared with the baseline model, our MTCF obtains a significant improvement by 3.2%, 3.71%, 5.13%, 4.04% in F1-score when the precipitation intensity is 0.5, 2, 5, 10 mm/h, respectively. Moreover, it also has a satisfactory performance in identifying precipitation spatial distribution details and small-scale precipitation, and strong stability to the extreme-precipitation of typhoons.

show abstract

“…Over the past few years, machine learning proved to be able to address rain nowcasting and was applied in several regions [8][9][10][11][12][13]. More recently, new neural network architectures were used: in [14], a PredNet [15] is adapted to predict rain in the region of Kyoto.…”

Section: Introductionmentioning

confidence: 99%

Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting

Bouget

Béréziat

Brajard³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Short- or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risk monitoring. Existing data-driven approaches, especially deep learning models, have shown significant skill at this task, using only rainfall radar images as inputs. In order to determine whether using other meteorological parameters such as wind would improve forecasts, we trained a deep learning model on a fusion of rainfall radar images and wind velocity produced by a weather forecast model. The network was compared to a similar architecture trained only on radar data, to a basic persistence model and to an approach based on optical flow. Our network outperforms by 8% the F1-score calculated for the optical flow on moderate and higher rain events for forecasts at a horizon time of 30 min. Furthermore, it outperforms by 7% the same architecture trained using only rainfall radar images. Merging rain and wind data has also proven to stabilize the training process and enabled significant improvement especially on the difficult-to-predict high precipitation rainfalls.

show abstract

Precipitation Nowcasting with Satellite Imagery

Cited by 62 publications

References 24 publications

Development of precipitation nowcasting method using geostationary satellite data

Development of precipitation nowcasting method using geostationary satellite data

Multi-Task Collaboration Deep Learning Framework for Infrared Precipitation Estimation

Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting

Contact Info

Product

Resources

About