Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS
Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS
复制标题
DOI：
10.1016/j.eswa.2014.02.047
复制
发表时间：
2014-09-01
影响因子：
8.5
通讯作者：
Pandey, Ashish
中科院分区：
文献类型：
--
作者：
Goyal, Manish Kumar;Bharti, Birendra;Pandey, Ashish
本文研究了人工神经网络（ANN）、最小二乘-支持向量回归（LS-SVR）、模糊逻辑和自适应神经模糊推理系统（ANFIS）技术在提高亚热带气候下蒸发皿日蒸发估计精度方面的能力。利用印度Karso流域2000 - 2010年3801个日记录的气象数据，开发并验证了日蒸发皿蒸发量估算模型。测量的气象变量包括每日观测的降雨量、最低和最高气温、最低和最高湿度以及日照时数。在模型开发之前，使用Gamma检验（GT）来得出每个输入输出集的噪声方差估计，以便确定在本研究中使用的机器学习方法中使用的最有用的预测因子。人工神经网络模型由贝叶斯正则化（BR）的前馈反向传播（FFBP）模型和LevenbergMarquardt （LM）算法组成。比较了人工神经网络、LSSVR、模糊逻辑和ANFIS模型提供的估计。还考虑了经验Hargreaves and Samani方法（HGS）以及Stephens-Stewart方法（SS），以便与较新的机器学习方法进行比较。均方根误差（RMSE）和相关系数（CORR）是用来评价各种模型准确性的统计性能指标。通过比较发现，模糊逻辑和LS-SVR方法可以成功地利用现有的气候资料对日蒸发过程进行建模。此外，结果表明，机器学习模型优于传统的HGS和SS经验方法。(C) 2014 Elsevier Ltd.版权所有。
This paper investigates the abilities of Artificial Neural Networks (ANN), Least Squares - Support Vector Regression (LS-SVR), Fuzzy Logic, and Adaptive Neuro-Fuzzy Inference System (ANFIS) techniques to improve the accuracy of daily pan evaporation estimation in sub-tropical climates. Meteorological data from the Karso watershed in India (consisting of 3801 daily records from the year 2000 to 2010) were used to develop and test the models for daily pan evaporation estimation. The measured meteorological variables include daily observations of rainfall, minimum and maximum air temperatures, minimum and maximum humidity, and sunshine hours. Prior to model development, the Gamma Test (GT) was used to derive estimates of the noise variance for each input-output set in order to identify the most useful predictors for use in the machine learning approaches used in this study. The ANN models consisted of feed forward backpropagation (FFBP) models with Bayesian Regularization (BR), along with the LevenbergMarquardt (LM) algorithm. A comparison was made between the estimates provided by the ANN, LSSVR, Fuzzy Logic, and ANFIS models. The empirical Hargreaves and Samani method (HGS), as well as the Stephens-Stewart (SS) method, were also considered for comparison with the newer machine learning methods. The Root Mean Square Error (RMSE) and Correlation Coefficient (CORR) were the statistical performance indices that were used to evaluate the accuracy of the various models. Based on the comparison, it was found that the Fuzzy Logic and LS-SVR approaches can be employed successfully in modeling the daily evaporation process from the available climatic data. In addition, results showed that the machine learning models outperform the traditional HGS and SS empirical methods. (C) 2014 Elsevier Ltd. All rights reserved.