Estimation of soil temperature using gene expression programming and artificial neural networks in a semiarid region
Estimation of soil temperature using gene expression programming and artificial neural networks in a semiarid region
复制标题
DOI：
10.1007/s12665-017-6395-1
复制
发表时间：
2017-01
影响因子：
2.8
通讯作者：
J. Behmanesh;S. Mehdizadeh
中科院分区：
文献类型：
--
作者：
J. Behmanesh;S. Mehdizadeh
土壤温度是影响土壤理化性质的重要参数之一。在本研究中，两个生物启发的人工智能方法，包括基因表达编程（GEP）和人工神经网络（ANN），以及多元线性回归（MLR）被用来估计土壤温度在六个不同的深度（5，10，20，30，50和100厘米）的Sanandaj天气站在伊朗西部的半干旱地区。使用最低和最高气温、相对湿度、风速、日照时数和外星辐射等十二种气象参数组合作为输入变量。包含土壤温度和大气参数的完整数据集跨越1997年至2008年，分为训练数据集（1997-2004年）和测试数据集（2005-2008年）。为了评价模型的准确性，计算决定系数（R2）和均方根误差（RMSE）。结果表明，GEP、ANN和MLR都能模拟不同深度的T_2。然而，ANN方法的性能是最好的。
Soil temperature (Ts) is one of the most important parameters which affect physical and chemical properties of soil. In the present study, two biologically inspired approaches for artificial intelligence including gene expression programming (GEP) and artificial neural networks (ANN), as well as multiple linear regression (MLR) were used to estimate the soil temperature at six different depths (5, 10, 20, 30, 50 and 100 cm) for the Sanandaj synoptic station in a semiarid region in western Iran. Twelve combinations of meteorological parameters, such as minimum and maximum air temperatures, relative humidity, wind speed, sunshine hours and extraterrestrial radiation, were used as input variables. The full data set containing soil temperature and atmospheric parameters, which spans the time period from 1997 to 2008, was divided into training (1997–2004) and testing (2005–2008) data sets. To evaluate the accuracy of the models, determination coefficient (R2) and root mean square error (RMSE) were calculated. The results showed that the GEP, ANN and MLR were able to modelTsat different depths. However, the performance of the ANN approach was the best.