Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting

Precipitation nowcasting by radar echo extrapolation using machine learning algorithms is a field worthy of further study, since rainfall prediction is essential in work and life. Current methods of predicting the radar echo images need further improvement in prediction accuracy as well as in presen...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dan Niu, Junhao Huang, Zengliang Zang, Liujia Xu, Hongshu Che, Yuanqing Tang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	precipitation nowcasting RNN spatiotemporal prediction refinement network Science Q
Acceso en línea:	https://doaj.org/article/91fc300347da4d7ead39ef8829b57cc5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:91fc300347da4d7ead39ef8829b57cc5
record_format	dspace
spelling	oai:doaj.org-article:91fc300347da4d7ead39ef8829b57cc52021-11-11T18:52:58ZTwo-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting10.3390/rs132142852072-4292https://doaj.org/article/91fc300347da4d7ead39ef8829b57cc52021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4285https://doaj.org/toc/2072-4292Precipitation nowcasting by radar echo extrapolation using machine learning algorithms is a field worthy of further study, since rainfall prediction is essential in work and life. Current methods of predicting the radar echo images need further improvement in prediction accuracy as well as in presenting the predicted details of the radar echo images. In this paper, we propose a two-stage spatiotemporal context refinement network (2S-STRef) to predict future pixel-level radar echo maps (deterministic output) more accurately and with more distinct details. The first stage is an efficient and concise spatiotemporal prediction network, which uses the spatiotemporal RNN module embedded in an encoder and decoder structure to give a first-stage prediction. The second stage is a proposed detail refinement net, which can preserve the high-frequency detailed feature of the radar echo images by using the multi-scale feature extraction and fusion residual block. We used a real-world radar echo map dataset of South China to evaluate the proposed 2S-STRef model. The experiments showed that compared with the PredRNN++ and ConvLSTM method, our 2S-STRef model performs better on the precipitation nowcasting, as well as at the image quality evaluating index and the forecasting indices. At a given 45 dBZ echo threshold (heavy precipitation) and with a 2 h lead time, the widely used CSI, HSS, and SSIM indices of the proposed 2S-STRef model are found equal to 0.195, 0.312, and 0.665, respectively. In this case, the proposed model outperforms the OpticalFlow method and PredRNN++ model.Dan NiuJunhao HuangZengliang ZangLiujia XuHongshu CheYuanqing TangMDPI AGarticleprecipitation nowcastingRNNspatiotemporal predictionrefinement networkScienceQENRemote Sensing, Vol 13, Iss 4285, p 4285 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	precipitation nowcasting RNN spatiotemporal prediction refinement network Science Q
spellingShingle	precipitation nowcasting RNN spatiotemporal prediction refinement network Science Q Dan Niu Junhao Huang Zengliang Zang Liujia Xu Hongshu Che Yuanqing Tang Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting
description	Precipitation nowcasting by radar echo extrapolation using machine learning algorithms is a field worthy of further study, since rainfall prediction is essential in work and life. Current methods of predicting the radar echo images need further improvement in prediction accuracy as well as in presenting the predicted details of the radar echo images. In this paper, we propose a two-stage spatiotemporal context refinement network (2S-STRef) to predict future pixel-level radar echo maps (deterministic output) more accurately and with more distinct details. The first stage is an efficient and concise spatiotemporal prediction network, which uses the spatiotemporal RNN module embedded in an encoder and decoder structure to give a first-stage prediction. The second stage is a proposed detail refinement net, which can preserve the high-frequency detailed feature of the radar echo images by using the multi-scale feature extraction and fusion residual block. We used a real-world radar echo map dataset of South China to evaluate the proposed 2S-STRef model. The experiments showed that compared with the PredRNN++ and ConvLSTM method, our 2S-STRef model performs better on the precipitation nowcasting, as well as at the image quality evaluating index and the forecasting indices. At a given 45 dBZ echo threshold (heavy precipitation) and with a 2 h lead time, the widely used CSI, HSS, and SSIM indices of the proposed 2S-STRef model are found equal to 0.195, 0.312, and 0.665, respectively. In this case, the proposed model outperforms the OpticalFlow method and PredRNN++ model.
format	article
author	Dan Niu Junhao Huang Zengliang Zang Liujia Xu Hongshu Che Yuanqing Tang
author_facet	Dan Niu Junhao Huang Zengliang Zang Liujia Xu Hongshu Che Yuanqing Tang
author_sort	Dan Niu
title	Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting
title_short	Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting
title_full	Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting
title_fullStr	Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting
title_full_unstemmed	Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting
title_sort	two-stage spatiotemporal context refinement network for precipitation nowcasting
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/91fc300347da4d7ead39ef8829b57cc5
work_keys_str_mv	AT danniu twostagespatiotemporalcontextrefinementnetworkforprecipitationnowcasting AT junhaohuang twostagespatiotemporalcontextrefinementnetworkforprecipitationnowcasting AT zengliangzang twostagespatiotemporalcontextrefinementnetworkforprecipitationnowcasting AT liujiaxu twostagespatiotemporalcontextrefinementnetworkforprecipitationnowcasting AT hongshuche twostagespatiotemporalcontextrefinementnetworkforprecipitationnowcasting AT yuanqingtang twostagespatiotemporalcontextrefinementnetworkforprecipitationnowcasting
_version_	1718431714218344448

Two-Stage Spatiotemporal Context Refinement Network for Precipitation Nowcasting

Ejemplares similares