Topic
Nowcasting
About: Nowcasting is a research topic. Over the lifetime, 1965 publications have been published within this topic receiving 34075 citations.
Papers published on a yearly basis
Papers
More filters
•
TL;DR: This paper proposes the convolutional LSTM (ConvLSTM) and uses it to build an end-to-end trainable model for the precipitation nowcasting problem and shows that it captures spatiotemporal correlations better and consistently outperforms FC-L STM and the state-of-the-art operational ROVER algorithm.
Abstract: The goal of precipitation nowcasting is to predict the future rainfall intensity in a local region over a relatively short period of time. Very few previous studies have examined this crucial and challenging weather forecasting problem from the machine learning perspective. In this paper, we formulate precipitation nowcasting as a spatiotemporal sequence forecasting problem in which both the input and the prediction target are spatiotemporal sequences. By extending the fully connected LSTM (FC-LSTM) to have convolutional structures in both the input-to-state and state-to-state transitions, we propose the convolutional LSTM (ConvLSTM) and use it to build an end-to-end trainable model for the precipitation nowcasting problem. Experiments show that our ConvLSTM network captures spatiotemporal correlations better and consistently outperforms FC-LSTM and the state-of-the-art operational ROVER algorithm for precipitation nowcasting.
4,487 citations
•
07 Dec 2015TL;DR: In this article, a convolutional LSTM (ConvLSTM) was proposed to capture spatiotemporal correlations better and consistently outperforms FC-LSTMs.
Abstract: The goal of precipitation nowcasting is to predict the future rainfall intensity in a local region over a relatively short period of time. Very few previous studies have examined this crucial and challenging weather forecasting problem from the machine learning perspective. In this paper, we formulate precipitation nowcasting as a spatiotemporal sequence forecasting problem in which both the input and the prediction target are spatiotemporal sequences. By extending the fully connected LSTM (FC-LSTM) to have convolutional structures in both the input-to-state and state-to-state transitions, we propose the convolutional LSTM (ConvLSTM) and use it to build an end-to-end trainable model for the precipitation nowcasting problem. Experiments show that our ConvLSTM network captures spatiotemporal correlations better and consistently outperforms FC-LSTM and the state-of-the-art operational ROVER algorithm for precipitation nowcasting.
2,474 citations
••
TL;DR: In this paper, a real-time automated identification, tracking, and short-term forecasting of thunderstorms based on volume-scan weather radar data is presented, with the emphasis on the concepts upon which the methodology is based.
Abstract: A methodology is presented for the real-time automated identification, tracking, and short-term forecasting of thunderstorms based on volume-scan weather radar data. The emphasis is on the concepts upon which the methodology is based. A “storm” is defined as a contiguous region exceeding thresholds for reflectivity and size. Storms defined in this way are identified at discrete time intervals. An optimization scheme is employed to match the storms at one time with those at the following time, with some geometric logic to deal with mergers and splits. The short-term forecast of both position and size is based on a weighted linear fit to the storm track history data. The performance of the detection and forecast were evaluated for the summer 1991 season, and the results are presented.
851 citations
•
792 citations
••
TL;DR: A neural network is developed to forecast rainfall intensity fields in space and time using a three-layer learning network with input, hidden, and output layers and is shown to perform well when a relatively large number of hidden nodes are utilized.
675 citations