[1]成振华,周坤论,陶伟,等.基于三种机器学习算法的降水现象仪和雨量筒数据一致性检验[J].气象研究与应用,2022,43(03):115-119.[doi:10.19849/j.cnki.CN45-1356/P.2022.3.21]
 Cheng Zhenhua,Zhou Kunlun,Tao Wei,et al.Data consistency test of precipitation phenomenometer and rain gauge based on three machine learning algorithms[J].Journal of Meteorological Research and Application,2022,43(03):115-119.[doi:10.19849/j.cnki.CN45-1356/P.2022.3.21]
点击复制

基于三种机器学习算法的降水现象仪和雨量筒数据一致性检验()
分享到:

气象研究与应用[ISSN:1673-8411/CN:45-1356/P]

卷:
第43卷
期数:
2022年03期
页码:
115-119
栏目:
新技术应用
出版日期:
2022-09-15

文章信息/Info

Title:
Data consistency test of precipitation phenomenometer and rain gauge based on three machine learning algorithms
作者:
成振华 周坤论 陶伟 黄剑钊 王玮 景坤
广西壮族自治区气象技术装备中心, 南宁 530022
Author(s):
Cheng Zhenhua Zhou Kunlun Tao Wei Huang Jianzhao Wang Wei Jing Kun
Guangxi Meteorological Technology Equipment Center, Nanning 530022, China
关键词:
多元线性回归决策树回归最近邻回归降维算法气象数据质量
Keywords:
multiple linear regressiondecision tree regressionnearest neighbor regressiondimensionality reduction algorithmquality of meteorological data
分类号:
P412
DOI:
10.19849/j.cnki.CN45-1356/P.2022.3.21
摘要:
基于三种机器学习算法,对2018年南宁国家气象观测站雨量筒观测数据和降水现象仪的雨滴观测数据进行一致性检验试验。通过降维算法,对降水现象仪数据去除数据冗余,进一步分别采用多元线性回归、决策树回归、最近邻回归等3种机器学习算法验证与雨量筒数据的一致性情况。结果表明,综合性能中多元线性回归算法效果最好,在误差范围内的准确率达到85%以上;最近邻回归算法在小雨量中可以有较好的预测值,综合准确率达到75%,两种算法均优于决策树算法70%的准确率。
Abstract:
Based on three machine learning algorithms, a consistency test was conducted on the rain gauge observation data and the raindrop observation data of the precipitation phenomenon instrument of Nanning National Meteorological Observatory in 2018. Firstly, the dimensionality reduction algorithm is used to remove the data redundancy of the precipitation phenomenon meter data. Three machine learning algorithms including multiple linear regression, decision tree regression, and nearest neighbor regression are further used to verify the consistency with the rain gauge data. The results shows that the multiple linear regression algorithm has the best effect in the comprehensive performance, and its comprehensive accuracy rate is more than 85% within the error range, followed by the nearest neighbor regression algorithm with the accuracy rate reaching 75%, which has a better performance in predicting light rainfall. Both of the above algorithms outperformed the decision tree algorithm with 70% accuracy.

参考文献/References:

[1] 李力,姜有山,蔡凝昊,等.Parsivel降水粒子谱仪与观测站雨量计的对比分析[J].气象,2018,44(3):434-441.
[2] 周坤论,张哲睿,成振华,等.北海一次强降雨过程的雨滴谱特征分析[J].气象研究与应用,2022,43(2):16-22.
[3] 周坤论,黄剑钊,陶伟,等.降水类天气现象自动与人工观测质量对比分析[J].气象研究与应用,2022,43(1):112-117.
[4] 刘平,王磊,祁生秀,等.天气现象仪降水观测分析[J].成都信息工程大学学报,2020,35(1):104-110.
[5] 周冠博,钱奇峰,吕心艳,等.人工智能在台风监测和预报中的探索与展望[J].气象研究与应用,2022,43(2):1-8.
[6] 何慧,陆虹,覃卫坚,等.人工神经网络在月降水量预测业务中的研究和应用综述[J].气象研究与应用,2021,42(1):1-6.
[7] 覃卫坚,何莉阳,蔡悦幸.基于两种机器学习方法的广西后汛期降水预测模型[J].气象研究与应用,2022,43(1):8-13.
[8] 何清,李宁,罗文娟,等.大数据下的机器学习算法综述[J].模式识别与人工智能,2014,27(4):327-336.
[9] 李蝉娟. 高维数据降维处理关键技术研究[D].桂林:电子科技大学,2017.
[10] 吴玉霜,黄小燕,陈家正,等.机器学习在广西台风极大风速预报中的应用[J].气象研究与应用,2021,42(4):26-31.
[11] 陆虹,翟盘茂,覃卫坚,等.低温雨雪过程的粒子群-神经网络预报模型[J].应用气象学报,2015,26(5):513-524.
[12] 黄明明,林润生,黄帅,等.一种新的基于伪最近邻算法的降水预报方法[J].科学技术与工程,2018,18(17):222-228.

相似文献/References:

[1]潘静,陈峥蓉,黄燕波,等.基于MOS的广西北部湾沿海秋冬极大风速精细化预报[J].气象研究与应用,2022,43(01):26.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.05]
 Pan Jing,Chen Zhengrong,Huang Yanbo,et al.Refined prediction of maximum wind speed in autumn and winter along the coast of Guangxi Beibu Gulf based on MOS[J].Journal of Meteorological Research and Application,2022,43(03):26.[doi:10.19849/j.cnki.CN45-1356/P.2022.1.05]

备注/Memo

备注/Memo:
收稿日期:2022-04-12。
基金项目:降水天气现象仪探测数据订正模型本地化研究(桂气科2022QN09)
作者简介:成振华(1995-),男,山西临汾人,助理工程师,从事地面气象探测工作。E-mail:845869155@qq.com
更新日期/Last Update: 1900-01-01