Fire in the current prediction methods, based on traditional statistical forecasting methods fire prediction errors exist, and based on neural network prediction methods exist smart "over-fit" and the promotion of capacity is not strong, such as disadvantage.
在目前火灾预测方法中,基于统计学的传统火灾预测方法存在预测误差较大,而基于神经网络的智能预测方法又存在“过拟合”和推广能力不强等缺点。
参考来源 - 基于支持向量机的火灾预测系统研究Fire in the current prediction methods, based on traditional statistical forecasting methods fire prediction errors exist, and based on neural network prediction methods exist smart "over-fit" and the promotion of capacity is not strong, such as disadvantage.
在目前火灾预测方法中,基于统计学的传统火灾预测方法存在预测误差较大,而基于神经网络的智能预测方法又存在“过拟合”和推广能力不强等缺点。
参考来源 - 基于支持向量机的火灾预测系统研究·2,447,543篇论文数据，部分数据来源于NoteExpress
虽然不同的模型预测不同的方面细节，他们都表明约四分之一的地表火灾风险会变化。
Although the different models predict different details, they agree that the fire risk will change for about a quarter of the land surface.
据某些全球环流模型预测，21世纪的亚马逊地区可能更干燥。这种概率的上升有可能促使亚马逊成为火灾多发区。
The higher probability of a drier Amazon in the 21st Century predicted by some global circulation models... may push Amazonia towards an amplified fire-prone system.
尽管那些投保火灾险和偷窃险的投机商们能根据几十年的经验来投保，但是金融市场却向来难以预测。
Those who insure against fire and theft can set premiums on the basis of decades of experience; financial markets are inherently less predictable.
应用推荐