The slope (g(1)) of stomatal conductance to photosynthesis is an important parameter in the optimal stomatal behavior theory-based stomatal conductance model of Medlyn et al. (2011). Although studies have modelled the...
详细信息
The slope (g(1)) of stomatal conductance to photosynthesis is an important parameter in the optimal stomatal behavior theory-based stomatal conductance model of Medlyn et al. (2011). Although studies have modelled the spatial variations in g(1), disclosing its variations over environmental gradients and different plant functional types. However, the above methods are still not accurate enough on a global scale, as they do not consider the temporal variations in g(1). To address this issue we used the Ensemble Kalman Filter (EnKF) to assimilate tower-based gross primary productivity (GPP) and latent heat flux (LE) of 17 cropland flux sites into a remote sensing (RS)-based evapotranspiration-photosynthesis coupled model, termed SCOPES-Crop, to derive the temporal variations in g(1) for C-3 and C-4 crops. We also used the feedforward artificial neural network (FANN) along with RS variables to model g(1). Results showed g(1) to rise rapidly in spring and summer, and then decline in autumn. The value of g(1) reached the lowest value and remained stable in wintertime. FANN-based modeling of g(1) showed R (RMSE) = 0.81 (1.94 kPa(0.5)) and 0.90 (0.70 kPa(0.5)) for C-3 and C-4 Crops, respectively, for the testing dataset. The estimates of GPP and LE using FANN-derived g(1) at the 17 flux sites were improved as compared to that using fixed g(1). The mean values of site-level R(RMSE) for GPP and LE simulated using FANN-derived g(1) are 0.92 (1.8 gC m(-2) d(-2)) and 0.85 (22.5 W m(-2)), respectively. Our results revealed notable seasonal variations in g(1), indicating the importance of considering the temporal variations in g(1) in evapotranspiration-photosynthesis coupled model. The FANN along with RS variables showed great potential of representing the g(1) variations.
To be able to use finite element (FE) simulations in structural component development, experimental investigations for the characterization of the material properties are required to subsequently calibrate suitable ma...
详细信息
To be able to use finite element (FE) simulations in structural component development, experimental investigations for the characterization of the material properties are required to subsequently calibrate suitable material cards. In contrast to the commonly used computational and time-consuming method of parameter identification (PI) by using analytical and numerical optimizations with internal or commercial software, a more time-efficient method based on machine learning (ML) is presented. This method is applied to simulate the material behavior of additively manufactured specimens made of acrylonitrile butadiene styrene (ABS) under uniaxial stress in a structural simulation. By using feedforward artificial neural networks (FFANN) for the ML-based direct inverse PI process, various investigations were carried out on the influence of sampling strategies, data quantity and data preparation on the prediction accuracy of the NN. Furthermore, the results of hyperparameter (HP) search methods are presented and discussed and their influence on the prediction quality of the FFANN are critically evaluated. The investigations show that the NN-based method is applicable to the present use case and results in material parameters that lead to a lower error between experimental and calculated force-displacement curves than the commonly used optimization-based method.
In recent years, artificialneuralnetworks and their applications for large data sets have become a crucial part of scientific research. In this work, we implement the Multilayer Perceptron (MLP), which is a class of...
详细信息
In recent years, artificialneuralnetworks and their applications for large data sets have become a crucial part of scientific research. In this work, we implement the Multilayer Perceptron (MLP), which is a class of feedforward artificial neural network (ANN), to predict ground-state binding energies of atomic nuclei. Two different MLP architectures with three and four hidden layers are used to study their effects on the predictions. To train the MLP architectures, two different inputs are used along with the latest atomic mass table and changes in binding energy predictions are also analyzed in terms of the changes in the input channel. It is seen that using appropriate MLP architectures and putting more physical information in the input channels, MLP can make fast and reliable predictions for binding energies of atomic nuclei, which is also comparable to the microscopic energy density functionals.
This paper proposes a method for the real-time prediction of water quality index (WQI) by excluding the biological oxygen demand and chemical oxygen demand, which are not measured in real time, from the model inputs. ...
详细信息
This paper proposes a method for the real-time prediction of water quality index (WQI) by excluding the biological oxygen demand and chemical oxygen demand, which are not measured in real time, from the model inputs. In this study, feedforward artificial neural networks are used to model the WQI in Perak River basin Malaysia due to its capability in modelling nonlinear systems. The results show that the developed single feedforwardneuralnetwork model can predict WQI very well with the coefficient of determination R2 and mean squared error (MSE) of 0.9090 and 0.1740 on the unseen validation data, respectively. In addition to that, the aggregation of multiple neuralnetworks in predicting the WQI further improves the prediction performance on the unseen validation data. Forward selection and backward elimination selective combination methods are used to combine multiple neuralnetworks and both methods lead to 6 and 5 networks being combined with R2 and MSE of 0.9340, 0.9270 and 0.1156, 0.1256, respectively. It is clearly shown that combining multiple neuralnetworks does improve the performance for WQI prediction.
暂无评论