The Experts below are selected from a list of 504516 Experts worldwide ranked by ideXlab platform
Unal Eler - One of the best experts on this subject based on the ideXlab platform.
-
estimating crimean juniper tree height using nonlinear regression and artificial neural network models
Forest Ecology and Management, 2013Co-Authors: Ramazan Ozcelik, Maria J Diamantopoulou, Felipe Crecentecampo, Unal ElerAbstract:Abstract Artificial neural network models offer a number of advantages including the ability to implicitly detect complex nonlinear relationships between input and output variables, which are very helpful in tree height modeling. Back-propagation artificial neural network models were produced for individual-tree height estimation and the results were compared with the most used tree height estimation methods. Height diameter ( h – d ) measurements of 1163 Crimean juniper trees in 63 sample plots from southwestern region of Turkey were used. A calibrated basic h – d mixed model, a generalized h – d model and back-propagation artificial neural network h – d models were constructed and compared. When the variability of the h – d relationship from stand to stand can be incorporated into the model, then both mixed-effects nonlinear regression and back-propagation neural network modeling approaches can produce accurate results, reducing the root mean squared Error by more than 20% as compared to a basic nonlinear regression model. The use of a generalized h – d model also showed reliable results (reduction of 13% in root mean squared Error as compared to a nonlinear regression model). The back-propagation artificial neural network model seems a reliable alternative to the other methods examined possessing the best generalization ability. Further, from a practical point of view it has the advantage that no height measurements are needed for its implementation. On the contrary prior information is required for the mixed-effects model calibration which is a limiting factor according to its use.
Quaife Tristan - One of the best experts on this subject based on the ideXlab platform.
-
Improving soil moisture prediction of a high-resolution land surface model by parameterising pedotransfer functions through assimilation of SMAP satellite data
'Copernicus GmbH', 2021Co-Authors: Pinnington Ewan, Amezcua Javier, Cooper Elizabeth, Dadson Simon, Ellis Rich, Peng Jian, Robinson Emma, Morrison Ross, Osborne Simon, Quaife TristanAbstract:Pedotransfer functions are used to relate gridded databases of soil texture information to the soil hydraulic and thermal parameters of land surface models. The parameters within these pedotransfer functions are uncertain and calibrated through analyses of point soil samples. How these calibrations relate to the soil parameters at the spatial scale of modern land surface models is unclear because gridded databases of soil texture represent an area average. We present a novel approach for calibrating such pedotransfer functions to improve land surface model soil moisture prediction by using observations from the Soil Moisture Active Passive (SMAP) satellite mission within a data assimilation framework. Unlike traditional calibration procedures, data assimilation always takes into account the relative uncertainties given to both model and observed estimates to find a maximum likelihood estimate. After performing the calibration procedure, we find improved estimates of soil moisture and heat flux for the Joint UK Land Environment Simulator (JULES) land surface model (run at a 1 km resolution) when compared to estimates from a cosmic-ray soil moisture monitoring network (COSMOS-UK) and three flux tower sites. The spatial resolution of the COSMOS probes is much more representative of the 1 km model grid than traditional point-based soil moisture sensors. For 11 cosmic-ray neutron soil moisture probes located across the modelled domain, we find an average 22 % reduction in root mean squared Error, a 16 % reduction in unbiased root mean squared Error and a 16 % increase in correlation after using data assimilation techniques to retrieve new pedotransfer function parameters
-
Improving soil moisture prediction of a high-resolution land surface model by parameterising pedotransfer functions through assimilation of SMAP satellite data
'Copernicus GmbH', 2020Co-Authors: Pinnington Ewan, Amezcua Javier, Cooper Elizabeth, Dadson Simon, Ellis Rich, Peng Jian, Robinson Emma, Quaife TristanAbstract:Pedotransfer functions are used to relate gridded databases of soil texture information to the soil hydraulic and thermal parameters of land surface models. The parameters within these pedotransfer functions are uncertain and calibrated through analyses of point soil samples. How these calibrations relate to the soil parameters at the spatial scale of modern land surface models is unclear, because gridded databases of soil texture represent an area average. We present a novel approach for calibrating such pedotransfer functions to improve land surface model soil moisture prediction by using observations from the Soil Moisture Active Passive (SMAP) satellite mission within a data assimilation framework. Unlike traditional calibration procedures data assimilation always takes into account the relative uncertainties given to both model and observed estimates to find a maximum likelihood estimate. After performing the calibration procedure we find improved estimates of soil moisture for the JULES land surface model (run at a 1 km resolution) when compared to estimates from a cosmic-ray soil moisture monitoring network (COSMOS-UK). The spatial resolution of these COSMOS probes is much more representative of the 1 km model grid than traditional point based soil moisture sensors. For 11 cosmic-ray neutron soil moisture probes located across the modelled domain we find an average 22 % reduction in root-mean squared Error, a 16 % reduction in unbiased root-mean squared Error and a 16 % increase in correlation after using data assimilation techniques to retrieve new pedotransfer function parameters
Kurt R Brorsen - One of the best experts on this subject based on the ideXlab platform.
-
reproducing global potential energy surfaces with continuous filter convolutional neural networks
Journal of Chemical Physics, 2019Co-Authors: Kurt R BrorsenAbstract:Neural networks fit to reproduce the potential energy surfaces of quantum chemistry methods offer a realization of analytic potential energy surfaces with the accuracy of ab initio methods at a computational cost similar to classical force field methods. One promising class of neural networks for this task is the SchNet architecture, which is based on the use of continuous-filter convolutional neural networks. Previous work has shown the ability of the SchNet architecture to reproduce density functional theory energies and forces for molecular configurations sampled during equilibrated molecular dynamics simulations. Due to the large change in energy when bonds are broken and formed, the fitting of global potential energy surfaces is normally a more difficult task than fitting the potential energy surface in the region of configurational space sampled during equilibrated molecular dynamics simulations. Herein, we demonstrate the ability of the SchNet architecture to reproduce the energies and forces of the potential energy surfaces of the H + H2 and Cl + H2 reactions and the OCHCO+ and H2CO/cis-HCOH/trans-HCOH systems. The SchNet models reproduce the potential energy surface of the reactions well with the best performing SchNet model having a test set Root-Mean-Squared Error of 0.52 meV and 2.01 meV for the energies of the H + H2 and Cl + H2 reactions, respectively, and a test set mean absolute Error for the force of 0.44 meV/bohr for the H + H2 reaction. For the OCHCO+ and H2CO/cis-HCOH/trans-HCOH systems, the best performing SchNet model has a test set Root-Mean-Squared Error of 2.92 meV and 13.55 meV, respectively.
Yuan Zong - One of the best experts on this subject based on the ideXlab platform.
-
automatic anterior chamber angle measurement for ultrasound biomicroscopy using deep learning
Journal of Glaucoma, 2020Co-Authors: Qian Chen, Zhenying Jiang, Guohua Deng, Yuan ZongAbstract:Purpose To develop a software package for automated measuring of the trabecular-iris angle (TIA) using ultrasound biomicroscopy. Methods Ultrasound biomicroscopy images were collected and the TIA was manually measured by specialists. Different models were used as the convolutional neural network for the automatic TIA measurement. The Root-Mean-Squared Error, explained variance, and mean absolute percentage Error were used to evaluate the performance of these models. The interobserver reproducibility, coefficient of variation, and intraclass correlation coefficient were calculated to evaluate the consistency between the manual measured and the model predicted values. Results ResNet-18 had the best performance in Root-Mean-Squared Error, explained variance, and mean absolute percentage Error among all 5 models. The average difference between the angles measured manually and by the model is -0.46±3.97 degrees for all eyes, -1.67±5.19 degrees for open angles, and 0.75±1.43 degrees for narrow angles. The coefficient of variation, intraclass correlation coefficient, and reproducibility of the total TIA measurements are 6.8%, 0.95, and 6.1 degrees for all angles; 6.4%, 0.99, and 7.7 degrees for open angles; and 8.8%, 0.93, and 4 degrees for narrow angles, respectively. Conclusions Preliminary results show that this fully automated anterior chamber angle measurement method can achieve high accuracy and have good consistency with the manual measurement results, this has great significance for future clinical practice.
Ramazan Ozcelik - One of the best experts on this subject based on the ideXlab platform.
-
estimating crimean juniper tree height using nonlinear regression and artificial neural network models
Forest Ecology and Management, 2013Co-Authors: Ramazan Ozcelik, Maria J Diamantopoulou, Felipe Crecentecampo, Unal ElerAbstract:Abstract Artificial neural network models offer a number of advantages including the ability to implicitly detect complex nonlinear relationships between input and output variables, which are very helpful in tree height modeling. Back-propagation artificial neural network models were produced for individual-tree height estimation and the results were compared with the most used tree height estimation methods. Height diameter ( h – d ) measurements of 1163 Crimean juniper trees in 63 sample plots from southwestern region of Turkey were used. A calibrated basic h – d mixed model, a generalized h – d model and back-propagation artificial neural network h – d models were constructed and compared. When the variability of the h – d relationship from stand to stand can be incorporated into the model, then both mixed-effects nonlinear regression and back-propagation neural network modeling approaches can produce accurate results, reducing the root mean squared Error by more than 20% as compared to a basic nonlinear regression model. The use of a generalized h – d model also showed reliable results (reduction of 13% in root mean squared Error as compared to a nonlinear regression model). The back-propagation artificial neural network model seems a reliable alternative to the other methods examined possessing the best generalization ability. Further, from a practical point of view it has the advantage that no height measurements are needed for its implementation. On the contrary prior information is required for the mixed-effects model calibration which is a limiting factor according to its use.
