• EI 工程索引(美)
  • CSCD 中国科学引文数据库来源期刊
  • 中文核心期刊
  • Caj-cd规范获奖期刊
高级搜索

基于机器学习算法构建新疆积雪覆盖率预测模型

邓文彬, 侯雪晴

邓文彬, 侯雪晴. 基于机器学习算法构建新疆积雪覆盖率预测模型[J]. 应用基础与工程科学学报, 2024, 32(6): 1664-1677. DOI: 10.16058/j.issn.1005-0930.2024.06.010
引用本文: 邓文彬, 侯雪晴. 基于机器学习算法构建新疆积雪覆盖率预测模型[J]. 应用基础与工程科学学报, 2024, 32(6): 1664-1677. DOI: 10.16058/j.issn.1005-0930.2024.06.010
DENG Wenbin, HOU Xueqing. Construction of a Snow Cover Prediction Model in Xinjiang Based on Machine Learning Algorithm[J]. Journal of Basic Science and Engineering, 2024, 32(6): 1664-1677. DOI: 10.16058/j.issn.1005-0930.2024.06.010
Citation: DENG Wenbin, HOU Xueqing. Construction of a Snow Cover Prediction Model in Xinjiang Based on Machine Learning Algorithm[J]. Journal of Basic Science and Engineering, 2024, 32(6): 1664-1677. DOI: 10.16058/j.issn.1005-0930.2024.06.010

基于机器学习算法构建新疆积雪覆盖率预测模型

基金项目: 

新疆维吾尔自治区自然科学基金项目(2022D01C55)

详细信息
    作者简介:

    邓文彬(1977-),男,博士,教授.E-mail:125864110@qq.com

    通讯作者:

    侯雪晴(1998-),女,硕士.E-mail:houxueqing1210@163.com

  • 中图分类号: P468.0+25

Construction of a Snow Cover Prediction Model in Xinjiang Based on Machine Learning Algorithm

  • 摘要: 积雪作为宝贵的淡水资源,其覆盖率的变动对农牧业经济的发展具有深远影响.当前对积雪覆盖率的预测研究较少,为提升积雪覆盖率预测的准确性,基于机器学习算法,构建支持向量回归(SVR)、粒子群(PSO)优化SVR、随机森林(RF)、XGBoost及优化后的XGBoost预测模型对新疆积雪覆盖率进行预测研究,并对模型预测精度进行对比分析.研究结果表明:RF和优化后的XGBoost模型的R2均大于0.9;传统SVR模型的R2均小于0.8,而PSO算法优化后的SVR模型的R2均大于0.8,部分大于0.9;XGBoost模型的R2均低于0.4.说明RF、优化后的XGBoost及PSO-SVR模型在积雪覆盖率预测研究中呈现出较高精度,XGBoost模型的预测结果最差,且利用不同算法对传统模型进行优化在研究中十分必要.
    Abstract: Snow cover is a kind of valuable freshwater resources,and the change of snow coverage rate has a profound impact on the development of agriculture and animal husbandry.There has been little research on the prediction of such coverage rates so far.In order to improve the accuracy of such prediction,this study uses machine learning algorithms to construct Support Vector Regression (SVR),PSO-optimized SVR,Random Forest (RF),XGBoost and optimized XGBoost prediction models,which are utilized to predict snow cover in Xinjiang,while comparing and analyzing the prediction accuracy of the models.The results show that the R2 values of both RF and optimized XGBoost models are greater than 0.9;the R2 values of all traditional SVR models is less than 0.8;the R2 values of all PSO-optimized SVR models are greater than 0.8,with some greater than 0.9;and the R2 values of all XGBoost models are lower than 0.4.These data indicate that the RF,optimized XGBoost and PSO-SVR models can deliver high prediction accuracy for snow cove;the XGBoost models have the poorest prediction results;and it is necessary to optimize traditional models with different algorithms.
  • [1] 肉克亚木·艾克木, 玉素甫江·如素力.伊犁河谷流域积雪分布及其变化分析[J].测绘科学, 2020, 45(6):157-164

    Meokyamu Aikmu, Yusufujiang Rusuli.Analysis of snowpack distribution and its changes in the Ili River Valley Basin[J].Science of Surveying and Mapping, 2020, 45(6):157-164

    [2] 刘 怡.新疆地区积雪、融雪型洪水与雪灾的时空变化特征研究[D].杨凌:西北农林科技大学, 2020 Liu Yi.A study on the spatial and temporal variation characteristics of snowpack, snowmelt-type flooding and snowstorms in Xinjiang[D].Yangling:Northwest A&F University, 2020
    [3] 张庆杰, 陶 辉, 苏布达, 等.基于CMIP6气候模式的新疆积雪深度时空格局研究[J].冰川冻土, 2021, 43(5):1435-1445

    Zhang Qingjie, Tao Hui, Su Buda, et al.Spatial and temporal pattern of snow depth in Xinjiang based on CMIP6 climate model[J].Journal of Glaciology and Geocryology.2021, 43(5):1435-1445

    [4] 时兴合, 李 林, 陈晓光, 等.青海南部牧区前冬积雪变化及其预测的关系模型研究[J].中国沙漠, 2012, 32(4):1062-1070

    Shi Xinghe, Li Lin, Chen Xiaoguang, et al.A relational modelling study on the change of pre-winter snowpack and its prediction in the pastoral areas of southern Qinghai[J].Journal of Desert Research, 2012, 32(4):1062-1070

    [5] 成 菲, 李巧萍, 沈新勇, 等.BCC-CSM1.1m对欧亚积雪覆盖的预测评估[J].应用气象学报, 2021, 32(5):553-566

    Cheng Fei, Li Qiaoping, Shen Xinyong, et al.Evaluation of BCC-CSM1.1m prediction of Eurasian snow cover[J].Journal of Applied Meteorological Science, 2021, 32(5):553-566

    [6] 郝靖宇.新疆天山山区积雪时空变化及预测分析[D].乌鲁木齐:新疆大学, 2020

    Hao Jingyu.Spatial and temporal variations of snow accumulation in the Tianshan Mountains of Xinjiang and analysis of forecasts[D].Urumqi:Xinjiang University, 2020

    [7]

    Meng Q, Ma X, Zhou Y.Forecasting of coal seam gas content by using support vector regression based on particle swarm optimization[J].Journal of Natural Gas Science and Engineering, 2014, 21:71-78

    [8] 王龙龙, 余威龙, 章玉容.基于支持向量机回归的粉煤灰混凝土氯离子质量分数预测[J].浙江建筑, 2024, 41(3):79-83

    Wang Longlong, Yu Weilong, Zhang Yurong.Prediction of chloride ion mass fraction in fly ash concrete based on support vector machine regression[J].Zhejiang Construction, 2024, 41(3):79-83

    [9] 张永奎.支持向量机回归算法的唐山市降水量空间插值研究[J].吉林水利, 2024, (2):23-25+78

    Zhang Yongkui.Support vector machine regression algorithm for spatial interpolation of precipitation in Tangshan City[J].Jilin Water Resources, 2024, (2):23-25+78

    [10] 陈家豪, 郑倩茹, 金立兵, 等.基于PSO-SVR模型预测粮食孔隙率[J].粮食与油脂, 2024, 37(6):55-59

    Chen Jiahao, Zheng Qianru, Jin Libing, et al.Prediction of grain porosity based on PSO-SVR model[J].Cereals&Oils, 2024, 37(6):55-59

    [11] 任远芳, 牛 坤, 丁 静, 等.基于改进PSO算法优化SVR的信息安全风险评估研究[J].贵州大学学报(自然科学版), 2024, 41(1):103-109

    Ren Yuanfang, Niu Kun, Ding Jing, et al.Research on information security risk assessment based on improved PSO algorithm foroptimising SVR[J].Journal of Guizhou University (Natural Science), 2024, 41(1):103-109

    [12] 刘 源, 王 宇.基于随机森林的森林生态系统物候模拟研究[J].农业与技术, 2024, 44(11):59-62

    Liu Yuan, Wang Yu.Forest ecosystem climate simulation based on random forest[J].Agriculture and Technology, 2024, 44(11):59-62

    [13] 孙胜难, 袁铸钢, 刘 钊, 等.基于随机森林回归算法的水泥立式磨磨内压差预测[J].洛阳理工学院学报(自然科学版), 2024, 34(2):44-50

    Sun Shengnan, Yuan Zhugang, Liu Zhao, et al.Prediction of differential pressure in cement vertical mill based on random forest regression algorithm[J].Journal of Luoyang Institute of Technology (Natural Science Edition), 2024, 34(2):44-50

    [14] 马赛赛, 张瑞新.基于随机森林算法的露天矿抛掷爆破影响因素分析[J].露天采矿技术, 2024, 39(3):11-14

    Ma Saisai, Zhang Ruixin.Analysis of the influence factors of cast blasting in open pit mines based on random forest algorithm[J].Opencast Mining Technology, 2024, 39(3):11-14

    [15] 李光环, 杨小天, 刘训钊.XGBoost与GRU模型在发电功率预测中的应用[J].福建电脑, 2024, 40(6):21-26

    Li Guanghuan, Yang Xiaotian, Liu Xunzhao.Application of XGBoost and GRU models in power generation prediction[J].Journal of Fujian Computer, 2024, 40(6):21-26

    [16] 曹 放, 李培骏, 詹同安, 等.基于XGBoost的崩塌落石风险预测模型及在复杂山区公路工程中的应用[J].交通科技与管理, 2024, 5(12):1-4

    Cao Fang, Li Peijun, Zhan Tongan, et al.XGBoost-based rockfall risk prediction model and its application in complex mountain highwayprojects[J].The Technology and Management of Transportation System, 2024, 5(12):1-4

    [17] 任 伟, 蒋兴浩, 孙锬锋.基于RBF神经网络的网络安全态势预测方法[J].计算机工程与应用, 2006, (31):136-138+144

    Ren Wei, Jiang Xinghao, Sun Pangfeng.A network security posture prediction method based on RBF neural network[J].Journal of Computer Research and Development, 2006, (31):136-138+144

    [18]

    Cortes C, Vapnik V.Suppor-vector networks[J].Machine Learning, 1995, 20(3):273-297

    [19] 杨绪兵, 陈松灿.基于原型超平面的多类最接近支持向量机[J].计算机研究与发展, 2006, 43(10):1700-1705

    Yang Xubing, Chen Songcan.Multi-class closest support vector machine based on prototype hyperplane[J].Journal of Computer Research and Development, 2006, 43(10):1700-1705

    [20] 刘 安.基于PCA-SVM模型的煤炭行业上市公司财务风险预警研究[D].宜昌:三峡大学, 2021 Liu An.Research on financial risk early warning of listed companies in coal industry based on PCA-SVM model[D].Yuchang:China Three Gorges University, 2021
    [21] 张 驰, 孙佳龙, 秦江涛, 等.基于支持向量回归的海洋次表层温度异常预测[J].江苏海洋大学学报(自然科学版), 2020, 29(2):50-57

    Zhang Chi, Sun Jialong, Qin Jiangtao, et al.Prediction of oceanic subsurface temperature anomalies based on support vectorregression[J].Journal of Jiangsu Ocean University (Natural Science Edition), 2020, 29(2):50-57

    [22] 周裕群, 张德生, 张 晓.一种改进的鲁棒模糊孪生支持向量机算法[J].计算机工程与应用, 2023, 59(1):140-148

    Zhou Yuqun, Zhang Desheng, Zhang Xiao.An improved robust fuzzy twin support vector machine algorithm[J].Journal of Computer Research and Development, 2023, 59(1):140-148

    [23]

    Smola A J, Schölkopf B.A tutorial on support vector regression[J].Statistics and Computing, 2004, 14:199-222

    [24] 孙玉婷, 王映龙, 杨红云, 等.基于支持向量机回归预测水稻叶片SPAD值[J].科技通报, 2018, 34(9):55-59

    Sun Yuting, Wang Yinglong, Yang Hongyun, et al.Predicting SPAD values of rice leaves based on support vector machine regression[J].Bulletin of Science and Technology, 2018, 34(9):55-59

    [25]

    Cherkassky V, Ma Y.Practical selection of SVM parameters and noise estimation for SVM regression[J].Neural Networks, 2004, 17(1):113-126

    [26] 杨 栩, 尤学一, 季 民.天津城市绿地土壤水分特征曲线模型及参数确定[J].干旱区资源与环境, 2013, 27(8):115-119

    Yang Xu, You Xueyi, Ji Min.Modelling and parameter determination of soil moisture profile in urban green areas of Tianjin[J].Journal of Arid Land Resources and Environment, 2013, 27(8):115-119

    [27]

    Maihemuti S, Wang W, Wang H, et al.Voltage security operation region calculation based on improved particle swarm optimization and recursive least square hybrid algorithm[J].Journal of Modern Power Systems and Clean Energy, 2020, 9(1):138-147

    [28] 秦文静, 樊贵盛.基于粒子群优化算法-支持向量机的原状黄土Van Genuchten模型参数土壤传输函数[J].干旱区资源与环境, 2020, 34(11):132-137

    Qin Wenjing, Fan Guisheng.Parameter soil transfer function of Van Genuchten model for primary loess based on particle swarm optimisation algorithm-support vector machine[J].Journal of Arid Land Resources and Environment, 2020, 34(11):132-137

    [29] 高佳南, 吴奉亮, 马 砺, 等.矿井淋水井筒风温PSO-SVR预测方法[J].西安科技大学学报, 2022, 42(3):476-483

    Gao Jianan, Wu Fengliang, Ma Li, et al.PSO-SVR prediction method of wind temperature in mine drench shaft[J].Journal of Xi’an University of Science and Technology, 2022, 42(3):476-483

    [30] 张范平, 唐德善, 戴会超, 等.基于CPSO参数辨识的支持向量机增泄水量计算模型研究[J].干旱区资源与环境, 2014, 28(12):117-121

    Zhang Fanping, Tang Deshan, Dai Huichao, et al.Research on support vector machine computational model for water augmentation and discharge based on CPSO parameter identification[J].Journal of Arid Land Resources and Environment, 2014, 28(12):117-121

    [31]

    Breiman L.Random forests[J].Machine Learning, 2001, 45:5-32

    [32] 赵华生, 金 龙, 黄小燕, 等.基于CNN和RF算法的ECMWF降水分级订正预报方法[J].气象科技, 2021, 49(3):419-426

    Zhao Huasheng, Jin Long, Huang Xiaoyan, et al.A hierarchical revised forecast method for ECMWF precipitation based on CNN and RF algorithms[J].Meteorological Science and Technology, 2021, 49(3):419-426

    [33] 许垚涛, 李 鹏, 马方铭, 等.不同机器学习模型在流域输沙模拟中的应用与解释[J/OL].应用基础与工程科学学报, 1-14[2024-10-12]

    Xu Yaotao, Li Peng, Ma Fangming, et al.Application and interpretation of different machine learning models in watershed sand transport simulation[J/OL].Journal of Basic Science and Engineering, 1-14[2024-10-12]

    [34]

    Chen T, Guestrin C.Xgboost:A scalable tree boosting system[C].Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016:785-794

    [35] 王迎超, 郭 崟, 姜 雯, 等.基于XGBoost算法的公路隧道失稳风险评估模型及系统开发[J].应用基础与工程科学学报, 2024, 32(4):957-971

    Wang Yingchao, Guo Yin, Jiang Wen, et al.Risk assessment model and system development of road tunnel instability based on XGBoost algorithm[J].Journal of Basic Science and Engineering, 2024, 32(4):957-971

    [36] 薛 强, 吕继强, 罗平平, 等.和田河流域山区积雪覆盖时空变化规律研究[J].中国农村水利水电, 2020, (1):88-96

    Xue Qiang, Lü Jiqiang, Luo Pingping, et al.Study on spatial and temporal variation rules of snow cover in mountainous areas of Hotan River Basin[J].China Rural Water and Hydropower, 2020, (1):88-96

    [37] 叶聪霄.青藏高原积雪深度时空变化及其影响因素分析[D].南京:南京信息工程大学, 2023

    Ye Congxiao.Analysis of spatial and temporal variations of snow depth and its influencing factors on the Tibetan Plateau[D].Nanjing:Nanjing University of Information Science & Technology, 2023

    [38]

    Leathers D J, Robinson D A.Abrupt changes in the seasonal cycle of north American snow cover[J].Journal of Climate, 1997, 10(10):2569-2585

    [39] 王计平, 蔚奴平, 丁 易, 等.森林植被对积雪分配及其消融影响研究综述[J].自然资源学报, 2013, 28(10):1808-1816

    Wang Jiping, Wei Nuping, Ding Yi, et al.A review on the effects of forest vegetation on snow distribution and its ablation[J].Journal of Natural Resources, 2013, 28(10):1808-1816

    [40] 李 虹, 李忠勤, 陈普晨, 等.近20a新疆阿尔泰山积雪时空变化及其影响因素[J].干旱区研究, 2023, 40(7):1040-1051

    Li Hong, Li Zhongqin, Chen Puchen, et al.Spatial and temporal variations of snowpack in the Altai Mountains of Xinjiang in the last 20a and their influencing factors[J].Arid Zone Research, 2023, 40(7):1040-1051

计量
  • 文章访问数:  29
  • HTML全文浏览量:  6
  • PDF下载量:  15
  • 被引次数: 0
出版历程
  • 收稿日期:  2024-06-30
  • 修回日期:  2024-10-14

目录

    /

    返回文章
    返回