A Short-Term Rainfall Prediction Model Using Multi-task Convolutional Neural Networks
Authors:
- Minghui QiuMQMinghui Qiu
- Peilin ZhaoPZPeilin Zhao
- Ke ZhangKZKe Zhang
- Jun HuangJHJun Huang
- Xing ShiXSXing Shi
- Xiaoguang WangXWXiaoguang Wang
- Wei ChuWCWei Chu
- 1 November 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 395-404
Abstract
Precipitation prediction, such as short-term rainfall prediction, is a very important problem in the field of meteorological service. In practice, most of recent studies focus on leveraging radar data or satellite images to make predictions. However, there is another scenario where a set of weather features are collected by various sensors at multiple observation sites. The observations of a site are sometimes incomplete but provide important clues for weather prediction at nearby sites, which are not fully exploited in existing work yet. To solve this problem, we propose a multi-task convolutional neural network model to automatically extract features from the time series measured at observation sites and leverage the correlation between the multiple sites for weather prediction via multi-tasking. To the best of our knowledge, this is the first attempt to use multi-task learning and deep learning techniques to predict short-term rainfall amount based on multi-site features. Specifically, we formulate the learning task as an end-to-end multi-site neural network model which allows to leverage the learned knowledge from one site to other correlated sites, and model the correlations between different sites. Extensive experiments show that the learned site correlations are insightful and the proposed model significantly outperforms a broad set of baseline models including the European Centre for Medium-range Weather Forecasts system (ECMWF).Keywords
This publication has 16 references indexed in Scilit:
- On the performance of the new NWP nowcasting system at the Danish Meteorological Institute during a heavy rain periodMeteorology and Atmospheric Physics, 2015
- Use of NWP for Nowcasting Convective Precipitation: Recent Progress and ChallengesBulletin of the American Meteorological Society, 2014
- An Observation Operator for Radar Refractivity Change: Comparison of Observations and Convective-Scale SimulationsBoundary-Layer Meteorology, 2013
- Links Between Weather Phenomena and Characteristics of Refractivity Measured by Precipitation RadarBoundary-Layer Meteorology, 2011
- Flash flood forecasting: What are the limits of predictability?Quarterly Journal of the Royal Meteorological Society, 2007
- Spatial-temporal rainfall fields: modelling and statistical aspectsHydrology and Earth System Sciences, 2000
- Efficient BackProp1998
- Long Short-Term MemoryNeural Computation, 1997
- A simple spatial-temporal model of rainfallProceedings of the Royal Society of London. A. Mathematical and Physical Sciences, 1988
- Learning representations by back-propagating errorsNature, 1986