当前位置: X-MOL 学术Comput. Electron. Agric. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-step ahead forecasting of daily reference evapotranspiration using deep learning
Computers and Electronics in Agriculture ( IF 7.7 ) Pub Date : 2020-11-01 , DOI: 10.1016/j.compag.2020.105728
Lucas Borges Ferreira , Fernando França da Cunha

Abstract Daily reference evapotranspiration (ETo) forecasts can help farmers in irrigation planning. Therefore, this study assesses the potential of deep learning (long short-term memory (LSTM), one-dimensional convolutional neural network (1D CNN) and a combination of the two previous models (CNN-LSTM)) and traditional machine learning models (artificial neural network (ANN) and random forest (RF)), in regional and local scenarios, to forecast multi-step ahead daily ETo (seven days) using iterated, direct and multiple input multiple output (MIMO) forecasting strategies. Three input data combinations were assessed: (1) only lagged ETo; (2) lagged ETo + day of the year of each step of the time lag considered; and (3) the same of input combination 2 + lagged meteorological variables. Data from 53 weather stations located in Minas Gerais, Brazil, were used. Four stations were used as test stations. Two baselines were also employed: (B1), all the forecasting horizon is considered equal to the mean ETo measured during the last seven days; and (B2), ahead ETo values are considered equal to their respective historical monthly means. In general, MIMO was the best forecasting strategy, offering good performance and lower computational cost. The deep learning models performed slightly better than the machine learning models, and both were better than the best baseline (B2), mainly on the first and second forecasting days. Among the deep learning models, CNN-LSTM2 (i.e., CNN-LSTM with input combination 2) performed the best in local scenario (mean RMSE over the prediction horizon and stations equal to 0.87), and CNN-LSTM3 performed the best in regional scenario (mean RMSE equal to 0.88). The regional models are recommended instead of the local models since they exhibited similar performances and have higher generalization capacity. Finally, although the models developed have not exhibited high accuracies, they can be useful tools in places where historical monthly mean ETo is used to forecast ETo.

中文翻译:

使用深度学习对每日参考蒸发量进行多步提前预测

摘要 每日参考蒸发量 (ETo) 预测可以帮助农民进行灌溉规划。因此,本研究评估了深度学习(长短期记忆(LSTM)、一维卷积神经网络(1D CNN)和之前两种模型的组合(CNN-LSTM))和传统机器学习模型(人工神经网络 (ANN) 和随机森林 (RF)),在区域和局部场景中,使用迭代、直接和多输入多输出 (MIMO) 预测策略预测多步每日 ETo(7 天)。评估了三种输入数据组合:(1) 仅滞后 ETo;(2) 滞后 ETo + 考虑的时间滞后的每一步的年份中的第几天;(3)输入组合2+滞后气象变量相同。来自巴西米纳斯吉拉斯州 53 个气象站的数据,被使用。四个站用作测试站。还使用了两个基线:(B1),所有预测范围都被认为等于过去 7 天内测量的平均 ETo;和 (B2),提前 ETo 值被认为等于它们各自的历史月均值。总的来说,MIMO 是最好的预测策略,具有良好的性能和较低的计算成本。深度学习模型的表现略好于机器学习模型,并且都优于最佳基线 (B2),主要是在第一和第二个预测日。在深度学习模型中,CNN-LSTM2(即输入组合为 2 的 CNN-LSTM)在局部场景中表现最好(预测范围内的平均 RMSE 和站点等于 0.87),CNN-LSTM3 在区域场景中表现最好(平均 RMSE 等于 0.88)。推荐使用区域模型而不是局部模型,因为它们表现出相似的性能并且具有更高的泛化能力。最后,虽然开发的模型没有表现出很高的准确度,但在使用历史月平均 ETo 预测 ETo 的地方,它们可以成为有用的工具。
更新日期:2020-11-01
down
wechat
bug