Differential evolution based radial basis function neural network model for reference evapotranspiration estimation
Differential evolution based radial basis function neural network model for reference evapotranspiration estimation
复制标题
DOI：
10.1007/s42452-020-04069-z
复制
发表时间：
2021-01
影响因子：
2.6
通讯作者：
B. Majhi;D. Naidu
中科院分区：
文献类型：
--
作者：
B. Majhi;D. Naidu
本研究是一项努力，研究能力的差分进化为基础的径向基函数神经网络（RBFDE）模型每周参考蒸散量（ET0）作为一个函数的气候参数在不同的农业气候带（ACZ）在印度中东部潮湿的亚湿润地区。以FAO推荐的Penman-Monteith经验公式（FAO56-PM）计算的ET0作为目标变量进行研究。建议RBFDE模型的性能进行了比较粒子群优化的径向基函数（RBFPSO），径向基函数神经网络（RBFNN），多层人工神经网络（MLANN）模型和传统的经验方程的Hargreaves，Turc，Open-Pan，和Blaney-Criddle。每周ET0的估计，得到使用RBFDE，RBFPSO，RBFNN和MLANN观察到比等效的经验方法更一致。为了对模拟结果进行严格的分析，计算了平均绝对百分比误差（MAPE）、均方根误差（RMSE）、决定系数（R2）和Nash-Sutcliffe效率因子（NSE）。利用软计算模型得到的低MAPE和RMSE值沿着增加，R2和NSE接近1，表明软计算模型比经验方法产生更好的ET 0估计值。在软计算模型，RBFDE提供了改进的结果相比，RBFPSO，RBFNN，和MLANN模型。该方法可推广应用于其它ACZ的ET0估算。
The present study is an effort to examine the capability of a differential evolution based radial basis function neural network (RBFDE) to model weekly reference evapotranspiration (ET0) as a function of climatic parameters in different agro-climatic zones (ACZs) of a moist sub-humid region in East-Central India. The ET0computed using the empirical equation of Penman–Monteith suggested by the Food and Agricultural Organization (FAO56-PM) is considered as a target variable for investigation. The performance of the proposed RBFDE model is compared with particle swarm optimization based radial basis function (RBFPSO), radial basis function neural network (RBFNN), multilayer artificial neural network (MLANN) models and conventional empirical equations of Hargreaves, Turc, Open-Pan, and Blaney-Criddle. Weekly ET0estimates that are obtained using RBFDE, RBFPSO, and RBFNN and MLANN are observed to be more consistent than equivalent empirical methods. For a critical analysis of simulation results, mean absolute percentage error (MAPE), root means square error (RMSE), determination coefficient (R2) and Nash–Sutcliffe efficiency factor (NSE) is computed. Low MAPE and RMSE values along with higher R2and NSE close to 1, obtained with soft computing models exhibit that, soft computing models produce better estimates of ET0than empirical methods. Among the soft computing models, RBFDE provides improved results as compared to RBFPSO, RBFNN, and MLANN models. This method can be extended for ET0estimation in other ACZs.