摘要
为了得到更精准的短时降雨预测结果,提出了一个基于神经网络的预测模型,可通过多普勒雷达图像序列预测某区域36min内的降雨概率。通过对神经网络和传统光流法的对比分析,还提出了一种结合了两种方法各自优点的集成预测模型。集成模型学习到了更丰富的降雨带变化模式。在一个包含多地、多月真实雷达数据的大规模数据集上的实验表明,神经网络模型实现了具有较高精度的短时降雨预测,且集成模型在整体的预测性能上有明显改进。
In order to obtain higher accurate in short-term rainfall prediction, a neural network-based prediction model is proposed. It can predict the rainfall probability in 36 minutes using Doppler radar image sequence. By comparatively analyzing the neural network-based method and the traditional optical flow-based method, an ensemble prediction model, which combines the advantages of both methods, is also developed. The ensemble model learns more diverse rainfall changing patterns. The methods are evaluated on a large dataset that contains real radar data spanning across multiple radar stations and for months.Experimental results show that the neural network model achieves prediction with high accuracy and that the ensemble model obtains obvious improvement in overall prediction performances.
作者
郭尚瓒
肖达
袁行远
Guo Shangzan;Xiao Da;Yuan Xingyuan(School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876;Beijing Colorful Clouds Technology Co.Ltd, Beijing, 100083)
出处
《气象科技进展》
2017年第1期107-113,共7页
Advances in Meteorological Science and Technology
基金
国家自然科学基金(61202082)
国家"二四二"信息安全计划基金项目(2014A120
2015A071)
关键词
短时降雨预测
神经网络
多层感知器
光流
雷达图像
short-term rainfall prediction
neural network
multilayer perceptron
optical flow
radar image
