Prediction of reference evapotranspiration using artificial neural network
Prediction of reference evapotranspiration using artificial neural network
复制标题
使用人工神经网络预测参考蒸散量
DOI：
10.15740/has/ijae/8.1/1-8
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
A. N. Mankar
中科院分区：
文献类型：
--
作者：
R. Meshram;M. M. Deshmukh;S. Wadatkar;M. Kale;A. N. Mankar
这项研究的目的是利用人工神经网络 (ANN) 预测提前一个月的 ETo。收集了阿科拉站35年（1977-2011）的气候参数。 ETo 是通过使用标准 Penman-Monteith 方法估计的，由于无法获得 ETo 的观测数据，该方法进一步用于 ANN 模型的开发和验证。 ANN 模型是使用不同的输入组合开发的。该模型学会使用 Levenberg-Marquardt 学习方法预测 Akola 提前一个月的 ETo（即 ET o,t+1）。训练结果相互比较，并对未经训练的数据进行性能评估。根据获得的结果，具有 4-12-1 架构（输入层、隐藏层和输出层分别为 4 个、12 个和 1 个神经元）的 ANN 模型被发现是所有模型中最好的，其估计值的最小标准误差 (SE) 为 0.74 mm day -1，相关系数为 0.9260。研究得出的结论是，ANN4 模型具有更好的性能，平均绝对估计误差 (MAE) 和均方根误差 (RMSE) 分别为 0.20 和 0.27 mm day -1 ，平均绝对相对误差 (MARE) 为 5.7%，模型效率为 0.9745。
The study has been undertaken to predict one month ahead ETo using artificial neural networks (ANNs). Climatic parameters for 35 years (1977-2011) were collected for Akola station. The ETo was estimated by using standard Penman-Monteith method which was further used for development and validation of the ANN models as the observed data on ETo was not available. The ANN models were developed using different input combinations. The models learned to predict one month ahead ETo ( i.e. ET o,t+1 ) for Akola using Levenberg-Marquardt learning method. The training results were compared with each other, and performance evaluations were done for untrained data. Based on results obtained, the ANN model with architecture of 4-12-1 (four, twelve and one neuron(s) in the input, hidden, and output layers, respectively) was found to be the best amongst all the models with minimum standard error (SE) of estimates of 0.74 mm day -1 and correlation co-efficient of 0.9260. From the study it is concluded that ANN4 model had given better performance with mean absolute error of estimates (MAE) and root mean square error (RMSE) of 0.20 and 0.27 mm day -1 , respectively, mean absolute relative error (MARE) of 5.7 per cent and model efficiency of 0.9745.