首页|机器学习在人工增雨效果统计检验中的应用

机器学习在人工增雨效果统计检验中的应用

Application of Machine Learning to Statistical Evaluation of Artificial Rainfall Enhancement

扫码查看
原文链接
  • NETL
  • NSTL
  • 维普
  • 万方数据
利用福建省古田人工增雨试验基地2014年1月-2023年1月小时自然降水数据,结合线性拟合、多项式回归和样条回归等多种数学统计方法,开展决策树、支持向量机(SVM)和卷积神经网络(CNN)3种机器学习方法在估测目标区自然降水中的应用研究.目标区和对比区自然雨量关系模型对比结果表明:以区域平均面雨量为统计变量时,CNN和四项式回归效果相对较好,其中CNN的确定系数为0.516,均方根误差为1.097 mm;对平均面雨量进行六次方根变换后,各模型的精准度大幅提升,CNN表现最优,确定系数为0.658,其次为SVM;为克服目标区和对比区雨量时间序列效应及空间分布不均等问题,以面雨量空间格点数据作为研究对象,采用CNN 3种优化器(自适应矩估计、均方根传递和梯度随机下降)算法进行对比,发现基于自适应矩估计优化器建立目标区和对比区雨量关系模型最优,其降水估测值与实测值更接近,均方根误差最小,为0.61 mm.因此,利用CNN方法能够进一步优化目标区和对比区雨量关系模型,可为定量评估人工增雨效果提供参考.
As an important part of weather modification operation,the scientific effectiveness evaluation of artifi-cial rainfall enhancement has gradually attracted attentions of government and public.In order to evaluate effects of artificial rainfall enhancement objectively and quantitatively,combing linear fitting,polynomial regression,spline regression and 3 other machine learning methods including decision tree,support vector machine and neural network,the relationship model between the rainfall in the target area and the contrast area is established based on rainfall data and operation information of recent 10 years in Fujian.Different historical regression statistical test schemes of rainfall enhancement effects are compared and analyzed,ai-ming to further optimize the best natural rainfall estimation algorithm based on alterable contrast area with statistical method,which can provide reference for the assessment of artificial rainfall enhancement effects.Results show that historical rainfall data samples are mainly concentrated in the weak rainfall grade.Using multiple regression methods(linear regression,polynomial regression and spline regres-sion),the piecewise statistics of rainfall data does not significantly improve the linear regression model be-tween two regions,and its root mean square error(RMSE)is generally higher than the statistical results.By comparing various machine learning and linear regression models,it is found that CNN and quomial re-gression perform relatively well when the regional average surface rainfall is taken as the statistical varia-ble,with the determination coefficient of CNN being 0.516 and RMSE being 1.097 mm.Each statistical model is greatly improved after six root square transformations of rainfall data.The performance of the model established by CNN method is relatively optimal,with determination coefficient R2 up to 0.658 and RMSE only 0.2 mm1/6,followed by SVM statistical model based on sixth-order root square transform data,with R2 being 0.41 and RMSE being 0.203 mm1/6.In order to further overcome the time asynchronization and uneven spatial distribution of rainfall in the two regions,the convolutional neural network CNN opti-mizers(RMSP,ADAM and SGD)are used to establish the contrast-target region rainfall relationship model based on the grid data of natural rainfall plane.Comparison results show that the ADAM optimizer model is the best with the RMSE of 0.61 mm,and its ability to estimate natural rainfall in the affected ar-ea is enhanced,by which method the disturbance of the heavy rainfall center will be reduced.

artificial rainfall effect evaluationregional historical regressionmachine learningstatistical test

李丹、林文、刘群、冯宏芳、胡淑萍、汪智海

展开 >

福建省气象科学研究所,福州 350001

福建省灾害天气重点实验室,福州 350001

中国气象局海峡灾害天气重点开放实验室,福州 350001

闽南师范大学数学与统计学院,漳州 363000

福建省宁德市古田县气象局,宁德 352000

展开 >

人工增雨效果评估 区域历史回归 机器学习 统计检验

国家重点研发计划中国气象局人工影响天气中心效果评估方法研发与应用创新团队国家自然科学基金面上项目中央引导性地方科技发展专项

2019YFC1510303WMC2023IT03420750882021L3019

2024

10.11898/1001-7313.20240110

应用气象学报
中国气象科学研究院 国家气象中心 国家卫星气象中心 国家气候中心　国家气象信息中心　中国气象局气象探测中心

应用气象学报

CSTPCD北大核心
影响因子：1.459
ISSN：1001-7313
年,卷(期)：2024.35(1)
  • 33