小波包遗传规划:一种新的气象干旱预报模型

IF 0.8 4区 工程技术 Q4 ENGINEERING, CIVIL Teknik Dergi Pub Date : 2021-07-01 DOI:10.18400/tekderg.605453
A. D. Mehr, M. Safari, Vahid Nourani
{"title":"小波包遗传规划:一种新的气象干旱预报模型","authors":"A. D. Mehr, M. Safari, Vahid Nourani","doi":"10.18400/tekderg.605453","DOIUrl":null,"url":null,"abstract":"This study presents developing procedures and verification of a new hybrid model, namely wavelet packet-genetic programming (WPGP) for short-term meteorological drought forecast. To this end, the multi-temporal standardized precipitation evapotranspiration index (SPEI) has been used as the drought quantifying parameter at two meteorological stations at Ankara province, Turkey. The new WPGP model comprises two main steps.  In the first step, the wavelet packet, which is a generalization of the well-known wavelet transform, is used to decompose the SPEI series into deterministic and stochastic sub-signals. Then, classic genetic programming (GP) is applied to formulate the deterministic sub-signal considering its effective lags. To characterize the stochastic component, different theoretical probability distribution functions were assessed, and the best one was selected to integrate with the GP-evolved function. The efficiency of the new model was cross-validated with the first order autoregressive (AR1), GP, and random forest (RF) models developed as the benchmarks in the present study. The results showed that the WPGP is a robust model, superior to AR1 and RF, and significantly increases the predictive accuracy of the standalone GP model.","PeriodicalId":49442,"journal":{"name":"Teknik Dergi","volume":null,"pages":null},"PeriodicalIF":0.8000,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"17","resultStr":"{\"title\":\"Wavelet Packet-Genetic Programming: A New Model for Meteorological Drought Hindcasting\",\"authors\":\"A. D. Mehr, M. Safari, Vahid Nourani\",\"doi\":\"10.18400/tekderg.605453\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study presents developing procedures and verification of a new hybrid model, namely wavelet packet-genetic programming (WPGP) for short-term meteorological drought forecast. To this end, the multi-temporal standardized precipitation evapotranspiration index (SPEI) has been used as the drought quantifying parameter at two meteorological stations at Ankara province, Turkey. The new WPGP model comprises two main steps.  In the first step, the wavelet packet, which is a generalization of the well-known wavelet transform, is used to decompose the SPEI series into deterministic and stochastic sub-signals. Then, classic genetic programming (GP) is applied to formulate the deterministic sub-signal considering its effective lags. To characterize the stochastic component, different theoretical probability distribution functions were assessed, and the best one was selected to integrate with the GP-evolved function. The efficiency of the new model was cross-validated with the first order autoregressive (AR1), GP, and random forest (RF) models developed as the benchmarks in the present study. The results showed that the WPGP is a robust model, superior to AR1 and RF, and significantly increases the predictive accuracy of the standalone GP model.\",\"PeriodicalId\":49442,\"journal\":{\"name\":\"Teknik Dergi\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.8000,\"publicationDate\":\"2021-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"17\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Teknik Dergi\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.18400/tekderg.605453\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Teknik Dergi","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.18400/tekderg.605453","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 17

摘要

本文介绍了一种新的短期气象干旱预测混合模型——小波包遗传规划(WPGP)的开发过程和验证。为此,在土耳其安卡拉省的两个气象站使用多时相标准化降水蒸散指数(SPEI)作为干旱量化参数。新的WPGP模型包括两个主要步骤。在第一步中,小波包是众所周知的小波变换的推广,用于将SPEI序列分解为确定性和随机性子信号。然后,将经典遗传规划(GP)应用于考虑有效滞后的确定子信号的公式化。为了表征随机分量,评估了不同的理论概率分布函数,并选择了最好的概率分布函数与GP进化函数相结合。新模型的效率与作为本研究基准开发的一阶自回归(AR1)、GP和随机森林(RF)模型进行了交叉验证。结果表明,WPGP是一个稳健的模型,优于AR1和RF,并显著提高了独立GP模型的预测精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Wavelet Packet-Genetic Programming: A New Model for Meteorological Drought Hindcasting
This study presents developing procedures and verification of a new hybrid model, namely wavelet packet-genetic programming (WPGP) for short-term meteorological drought forecast. To this end, the multi-temporal standardized precipitation evapotranspiration index (SPEI) has been used as the drought quantifying parameter at two meteorological stations at Ankara province, Turkey. The new WPGP model comprises two main steps.  In the first step, the wavelet packet, which is a generalization of the well-known wavelet transform, is used to decompose the SPEI series into deterministic and stochastic sub-signals. Then, classic genetic programming (GP) is applied to formulate the deterministic sub-signal considering its effective lags. To characterize the stochastic component, different theoretical probability distribution functions were assessed, and the best one was selected to integrate with the GP-evolved function. The efficiency of the new model was cross-validated with the first order autoregressive (AR1), GP, and random forest (RF) models developed as the benchmarks in the present study. The results showed that the WPGP is a robust model, superior to AR1 and RF, and significantly increases the predictive accuracy of the standalone GP model.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Teknik Dergi
Teknik Dergi 工程技术-工程:土木
自引率
30.80%
发文量
65
审稿时长
>12 weeks
期刊介绍: The scope of Teknik Dergi is naturally confined with the subjects falling in the area of civil engineering. However, the area of civil engineering has recently been significantly enlarged, even the definition of civil engineering has somewhat changed. Half a century ago, engineering was simply defined as “the art of using and converting the natural resources for the benefit of the mankind”. Today, the same objective is expected to be realised (i) by complying with the desire and expectations of the people concerned and (ii) without wasting the resources and within the sustainability principles. This change has required an interaction between engineering and social and administrative sciences. Some subjects at the borderline between civil engineering and social and administrative sciences have consequently been included in the area of civil engineering. Teknik Dergi defines its scope in line with this understanding. However, it requires the papers falling in the borderline to have a significant component of civil engineering.
期刊最新文献
Scheduling, Management and Optimization of Construction Process A Downscaling Application for Local Meteorological Variables of Eastern Black Sea Basin and Scenario Based Predictions Developing a Performance-Based Payment Model in Urban Public Transport Systems Evaluation of Occupational Safety in the Operation and Maintenance Activities of Dams Determination of Finite Element Modelling Errors for Box Culverts Using Field Load Tests
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1