Application of meta-heuristic hybrid models in estimating the average air temperature of Caspian sea coast of Iran

Q2 Environmental Science Environmental Challenges Pub Date : 2024-10-18 DOI:10.1016/j.envc.2024.101039
{"title":"Application of meta-heuristic hybrid models in estimating the average air temperature of Caspian sea coast of Iran","authors":"","doi":"10.1016/j.envc.2024.101039","DOIUrl":null,"url":null,"abstract":"<div><div>The rise of industrial societies leads to higher greenhouse gas emissions, profoundly affecting the climate in coastal regions. Consequently, air temperature readings from standard meteorological stations are key indicators of the Earth's environmental condition. Therefore, accurate estimation of daily temperature in each region is one of the important prerequisites for agricultural planning as well as water resources management and drought prevention, which can be done in different ways such as experimental, semi-experimental and intelligent models. In this research, WSVR, AIG-SVR, GWO-SVR and BAT-SVR hybrid models were investigated and evaluated in order to estimate the average daily air temperature on the shores of the Caspian Sea located in the north of Iran. For modeling, weather station data from Babolsar meteorological station located in Mazandaran province were used. During the water year from 2012 to 2022, daily parameters including relative humidity, maximum temperature, minimum temperature, wind speed, and evaporation were selected as network inputs, with the average daily air temperature as the network output. To assess and compare model performances, several criteria were employed including correlation coefficient, root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (NSE), and percentage bias. Comparative analysis revealed that the WSVR model surpassed other models, demonstrating the highest correlation coefficient (0.992), lowest RMSE (0.096), and lowest MAE (0.042). The highest Nash Sutcliffe criterion (0.996) and bias percentage (0.001) were prioritized in the validation stage.</div></div>","PeriodicalId":34794,"journal":{"name":"Environmental Challenges","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Challenges","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667010024002051","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Environmental Science","Score":null,"Total":0}
引用次数: 0

Abstract

The rise of industrial societies leads to higher greenhouse gas emissions, profoundly affecting the climate in coastal regions. Consequently, air temperature readings from standard meteorological stations are key indicators of the Earth's environmental condition. Therefore, accurate estimation of daily temperature in each region is one of the important prerequisites for agricultural planning as well as water resources management and drought prevention, which can be done in different ways such as experimental, semi-experimental and intelligent models. In this research, WSVR, AIG-SVR, GWO-SVR and BAT-SVR hybrid models were investigated and evaluated in order to estimate the average daily air temperature on the shores of the Caspian Sea located in the north of Iran. For modeling, weather station data from Babolsar meteorological station located in Mazandaran province were used. During the water year from 2012 to 2022, daily parameters including relative humidity, maximum temperature, minimum temperature, wind speed, and evaporation were selected as network inputs, with the average daily air temperature as the network output. To assess and compare model performances, several criteria were employed including correlation coefficient, root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (NSE), and percentage bias. Comparative analysis revealed that the WSVR model surpassed other models, demonstrating the highest correlation coefficient (0.992), lowest RMSE (0.096), and lowest MAE (0.042). The highest Nash Sutcliffe criterion (0.996) and bias percentage (0.001) were prioritized in the validation stage.
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
元启发式混合模型在估算伊朗里海沿岸平均气温中的应用
工业社会的兴起导致温室气体排放量增加,对沿海地区的气候产生了深远影响。因此,标准气象站的气温读数是地球环境状况的关键指标。因此,准确估算各地区的日气温是农业规划、水资源管理和干旱预防的重要前提条件之一。本研究对 WSVR、AIG-SVR、GWO-SVR 和 BAT-SVR 混合模型进行了研究和评估,以估算伊朗北部里海沿岸的日平均气温。建模时使用了马赞达兰省巴布萨尔气象站的气象站数据。在 2012 至 2022 水年期间,选择相对湿度、最高温度、最低温度、风速和蒸发量等日参数作为网络输入,并以日平均气温作为网络输出。为评估和比较模型性能,采用了多项标准,包括相关系数、均方根误差、平均绝对误差、纳什-苏特克利夫效率和偏差百分比。对比分析表明,WSVR 模型超越了其他模型,显示出最高的相关系数(0.992)、最低的均方根误差(0.096)和最低的平均绝对误差(0.042)。在验证阶段,最高的纳什-苏特克里夫标准(0.996)和偏差百分比(0.001)被优先考虑。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Environmental Challenges
Environmental Challenges Environmental Science-Environmental Engineering
CiteScore
8.00
自引率
0.00%
发文量
249
审稿时长
8 weeks
期刊最新文献
Long-term monitoring, predicting and connection between built-up land and urban heat island patterns based on remote sensing data Overcoming barriers to proactive plastic recycling toward a sustainable future Development of a brand value measurement model with a corporate social responsibility perspective. A comparative analysis of consumer perception of energy providers in Spain and Colombia Application of meta-heuristic hybrid models in estimating the average air temperature of Caspian sea coast of Iran Global change drives potential niche contraction and range shift of globally threatened African vulture
×
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