【摘要】 尝试利用人工神经网络的方法对南京地区的雷暴天气进行预报。南京站的探空资料(每天08时和20时各一次)可以反映雷暴发生前大气层结的初始状态,而江苏省闪电定位网资料则可以作为预报量加以使用。利用探空资料计算了一些与雷暴发生相关的预报因子,用以建立南京地区雷暴的神经网络预报模型,并应用独立样本进行了初步的模拟预报检验。初步结果表明,预报模型取得了较令人满意的效果,应用神经网络的方法预报雷暴的发生是可行的。更多还原

【Abstract】 A neural network-based scheme for a multivariate analysis of the occurrence of thunderstorm is presented. Many sounding-derived indices are combined together to make short-term forecasts of thunderstorm in the city of Nanjing. For thunderstorm forecasting, sounding and lightning strike data from June to September are used to train and validate the network. Output from the network show relatively satisfying performance with a forecast model in this preliminary study.更多还原