Groundwater is important for managing the water supply in agricultural countries like Bangladesh. Therefore, the ability to predict the changes of groundwater level is necessary for jointly planning the uses of ground...Groundwater is important for managing the water supply in agricultural countries like Bangladesh. Therefore, the ability to predict the changes of groundwater level is necessary for jointly planning the uses of groundwater resources. In this study, a new nonlinear autoregressive with exogenous inputs(NARX) network has been applied to simulate monthly groundwater levels in a well of Sylhet Sadar at a local scale. The Levenberg-Marquardt(LM) and Bayesian Regularization(BR) algorithms were used to train the NARX network, and the results were compared to determine the best architecture for predicting monthly groundwater levels over time. The comparison between LM and BR showed that NARX-BR has advantages over predicting monthly levels based on the Mean Squared Error(MSE), coefficient of determination(R^2), and Nash-Sutcliffe coefficient of efficiency(NSE). The results show that BR is the most accurate method for predicting groundwater levels with an error of ± 0.35 m. This method is applied to the management of irrigation water source, which provides important information for the prediction of local groundwater fluctuation at local level during a short period.展开更多
基于台架采集数据,采用外部输入非线性自回归(nonlinear autoregressive model with exogenous input,NARX)神经网络建立了具备瞬态特性的柴油机排气温度计算模型作为虚拟传感器,并采用并发式训练方法对模型进行训练。将结果与前馈神经...基于台架采集数据,采用外部输入非线性自回归(nonlinear autoregressive model with exogenous input,NARX)神经网络建立了具备瞬态特性的柴油机排气温度计算模型作为虚拟传感器,并采用并发式训练方法对模型进行训练。将结果与前馈神经网络、长短期记忆网络(long short term memory,LSTM)神经网络及量产发动机的排温传感器采集结果进行对比。经验证,稳态工况下,两种神经网络均能达到较高精度;欧洲瞬态循环(European transient cycle,ETC)工况下,NARX神经网络计算温度的最大偏差为6.6℃,量产发动机排温传感器测得温度最大偏差为45.9℃。NARX神经网络所需的计算时间约为现有电控单元排温模型的2.5倍。展开更多
In Saharan climates,greenhouses face extreme diurnal temperature fluctuations that generate thermal stress,reduce crop productivity,and hinder sustainable agricultural practices.Passive thermal storage using Phase Cha...In Saharan climates,greenhouses face extreme diurnal temperature fluctuations that generate thermal stress,reduce crop productivity,and hinder sustainable agricultural practices.Passive thermal storage using Phase Change Materials(PCM)is a promising solution to stabilize microclimatic conditions.This study aims to evaluate experimentally and numerically the effectiveness of PCM integration for moderating greenhouse temperature fluctuations under Saharan climatic conditions.Two identical greenhouse prototypes were constructed in Ghardaia,Algeria:a reference greenhouse and a PCM-integrated greenhouse using calcium chloride hexahydrate(CaCl_(2)⋅6H_(2)O).Thermal performance was assessed during a five-day experimental period(7–11May 2025)under severe ambient conditions.To complement this,a Nonlinear Auto-Regressive with eXogenous inputs(NARX)neural network model was developed and trained using a larger dataset(7–25 May 2025)to predict greenhouse thermal dynamics.The PCM greenhouse reduced peak daytime air temperature by an average of 8.14℃and decreased the diurnal temperature amplitude by 53.6%compared to the reference greenhouse.The NARX model achieved high predictive accuracy(R^(2)=0.990,RMSE=0.425℃,MAE=0.223℃,MBE=0.008℃),capturing both sensible and latent heat transfer mechanisms,including PCM melting and solidification.The combined experimental and predictive modeling results confirm the potential of PCM integration as an effective passive thermal regulation strategy for greenhouses in arid regions.This approach enhances microclimatic stability,improves energy efficiency,and supports the sustainability of protected agriculture under extreme climatic conditions.展开更多
文摘Groundwater is important for managing the water supply in agricultural countries like Bangladesh. Therefore, the ability to predict the changes of groundwater level is necessary for jointly planning the uses of groundwater resources. In this study, a new nonlinear autoregressive with exogenous inputs(NARX) network has been applied to simulate monthly groundwater levels in a well of Sylhet Sadar at a local scale. The Levenberg-Marquardt(LM) and Bayesian Regularization(BR) algorithms were used to train the NARX network, and the results were compared to determine the best architecture for predicting monthly groundwater levels over time. The comparison between LM and BR showed that NARX-BR has advantages over predicting monthly levels based on the Mean Squared Error(MSE), coefficient of determination(R^2), and Nash-Sutcliffe coefficient of efficiency(NSE). The results show that BR is the most accurate method for predicting groundwater levels with an error of ± 0.35 m. This method is applied to the management of irrigation water source, which provides important information for the prediction of local groundwater fluctuation at local level during a short period.
文摘基于台架采集数据,采用外部输入非线性自回归(nonlinear autoregressive model with exogenous input,NARX)神经网络建立了具备瞬态特性的柴油机排气温度计算模型作为虚拟传感器,并采用并发式训练方法对模型进行训练。将结果与前馈神经网络、长短期记忆网络(long short term memory,LSTM)神经网络及量产发动机的排温传感器采集结果进行对比。经验证,稳态工况下,两种神经网络均能达到较高精度;欧洲瞬态循环(European transient cycle,ETC)工况下,NARX神经网络计算温度的最大偏差为6.6℃,量产发动机排温传感器测得温度最大偏差为45.9℃。NARX神经网络所需的计算时间约为现有电控单元排温模型的2.5倍。
文摘In Saharan climates,greenhouses face extreme diurnal temperature fluctuations that generate thermal stress,reduce crop productivity,and hinder sustainable agricultural practices.Passive thermal storage using Phase Change Materials(PCM)is a promising solution to stabilize microclimatic conditions.This study aims to evaluate experimentally and numerically the effectiveness of PCM integration for moderating greenhouse temperature fluctuations under Saharan climatic conditions.Two identical greenhouse prototypes were constructed in Ghardaia,Algeria:a reference greenhouse and a PCM-integrated greenhouse using calcium chloride hexahydrate(CaCl_(2)⋅6H_(2)O).Thermal performance was assessed during a five-day experimental period(7–11May 2025)under severe ambient conditions.To complement this,a Nonlinear Auto-Regressive with eXogenous inputs(NARX)neural network model was developed and trained using a larger dataset(7–25 May 2025)to predict greenhouse thermal dynamics.The PCM greenhouse reduced peak daytime air temperature by an average of 8.14℃and decreased the diurnal temperature amplitude by 53.6%compared to the reference greenhouse.The NARX model achieved high predictive accuracy(R^(2)=0.990,RMSE=0.425℃,MAE=0.223℃,MBE=0.008℃),capturing both sensible and latent heat transfer mechanisms,including PCM melting and solidification.The combined experimental and predictive modeling results confirm the potential of PCM integration as an effective passive thermal regulation strategy for greenhouses in arid regions.This approach enhances microclimatic stability,improves energy efficiency,and supports the sustainability of protected agriculture under extreme climatic conditions.
