Modeling of Surface Conductance over Sunn Hemp by Artificial Neural Network

IF 1.6 4区农林科学 Q2 AGRONOMY

Italian Journal of Agrometeorology-Rivista Italiana Di Agrometeorologia Pub Date : 2019-12-28 DOI:10.13128/IJAM-589

L. Şaylan, R. Kimura, Nilcan Altınbaş, B. Çaldağ, F. Bakanoğullari

{"title":"Modeling of Surface Conductance over Sunn Hemp by Artificial Neural Network","authors":"L. Şaylan, R. Kimura, Nilcan Altınbaş, B. Çaldağ, F. Bakanoğullari","doi":"10.13128/IJAM-589","DOIUrl":null,"url":null,"abstract":"Performances of an Artificial Neural Network (ANN), a multiple linear regression (MLR) and the Jarvis type model were compared to estimate the surface conductance of the sunn hemp crop, which is a driving factor affecting evapotranspiration. It was modeled by ANN and MLR using various parameters including global solar radiation, temperature, soil water content, relative humidity, precipitation and irrigation, vapor pressure deficit, wind speed and leaf area index (LAI). The measurements were carried out during the growing season of sunn hemp in 2004. The best correlation (r2=0.73) between the surface conductance and all variables was estimated by the ANN, whereas r2 was 0.91 in the training period. The average absolute relative error was 26.54% for the ANN (r2=0.80); 51.07% for the MLR (r2=0.53) and 58.30% for Jarvis model (r2=0.26), when the vapor pressure deficit, temperature, soil water content, global solar radiation and leaf area index were considered to model. Comparisons showed that the ANN approach had a better modeling potential of the surface conductance compared to the MLR and Jarvis model. \n \nKeywords: Agriculture, Air-water interaction, Evapotranspiration, Network analysis","PeriodicalId":54371,"journal":{"name":"Italian Journal of Agrometeorology-Rivista Italiana Di Agrometeorologia","volume":"82 1","pages":"37-48"},"PeriodicalIF":1.6000,"publicationDate":"2019-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Italian Journal of Agrometeorology-Rivista Italiana Di Agrometeorologia","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.13128/IJAM-589","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AGRONOMY","Score":null,"Total":0}

引用次数: 2

Abstract

Performances of an Artificial Neural Network (ANN), a multiple linear regression (MLR) and the Jarvis type model were compared to estimate the surface conductance of the sunn hemp crop, which is a driving factor affecting evapotranspiration. It was modeled by ANN and MLR using various parameters including global solar radiation, temperature, soil water content, relative humidity, precipitation and irrigation, vapor pressure deficit, wind speed and leaf area index (LAI). The measurements were carried out during the growing season of sunn hemp in 2004. The best correlation (r2=0.73) between the surface conductance and all variables was estimated by the ANN, whereas r2 was 0.91 in the training period. The average absolute relative error was 26.54% for the ANN (r2=0.80); 51.07% for the MLR (r2=0.53) and 58.30% for Jarvis model (r2=0.26), when the vapor pressure deficit, temperature, soil water content, global solar radiation and leaf area index were considered to model. Comparisons showed that the ANN approach had a better modeling potential of the surface conductance compared to the MLR and Jarvis model. Keywords: Agriculture, Air-water interaction, Evapotranspiration, Network analysis

查看原文本刊更多论文

太阳麻表面电导率的人工神经网络建模

比较了人工神经网络(ANN)、多元线性回归(MLR)和Jarvis型模型在估算太阳麻作物表面电导方面的性能，这是影响蒸发蒸腾的驱动因素。利用全球太阳辐射、温度、土壤含水量、相对湿度、降水和灌溉、蒸汽压亏缺、风速和叶面积指数(LAI)等参数，采用人工神经网络(ANN)和MLR进行了模拟。测量是在2004年大麻生长季节进行的。人工神经网络估计表面电导与各变量之间的最佳相关系数(r2=0.73)，而训练期间的r2为0.91。人工神经网络的平均绝对相对误差为26.54% (r2=0.80);考虑水汽压亏缺、温度、土壤含水量、太阳总辐射和叶面积指数时，MLR模型的拟合系数为51.07% (r2=0.53)， Jarvis模型的拟合系数为58.30% (r2=0.26)。对比表明，与MLR和Jarvis模型相比，人工神经网络方法具有更好的表面电导建模潜力。关键词:农业，空气-水相互作用，蒸散，网络分析

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分钟内获得全文求助全文

来源期刊

Italian Journal of Agrometeorology-Rivista Italiana Di Agrometeorologia AGRONOMY-ENVIRONMENTAL SCIENCES

CiteScore

2.10

自引率

8.30%

发文量

期刊介绍： Among the areas of specific interest of the journal there are: ecophysiology; phenology; plant growth, quality and quantity of production; plant pathology; entomology; welfare conditions of livestocks; soil physics and hydrology; micrometeorology; modeling, simulation and forecasting; remote sensing; territorial planning; geographical information systems and spatialization techniques; instrumentation to measure physical and biological quantities; data validation techniques, agroclimatology; agriculture scientific dissemination; support services for farmers.