scholarly journals A time-dependent parameter estimation framework for crop modeling

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Faezeh Akhavizadegan ◽  
Javad Ansarifar ◽  
Lizhi Wang ◽  
Isaiah Huber ◽  
Sotirios V. Archontoulis
Keyword(s):  
Machine Learning ◽  
Parameter Estimation ◽  
Estimation Method ◽  
Time Dependent ◽  
Bayesian Optimization ◽  
Parameter Estimates ◽  
Crop Modeling ◽  
Bayesian Optimization Algorithm ◽  
Crop Models ◽  
Dependent Parameter

AbstractThe performance of crop models in simulating various aspects of the cropping system is sensitive to parameter calibration. Parameter estimation is challenging, especially for time-dependent parameters such as cultivar parameters with 2–3 years of lifespan. Manual calibration of the parameters is time-consuming, requires expertise, and is prone to error. This research develops a new automated framework to estimate time-dependent parameters for crop models using a parallel Bayesian optimization algorithm. This approach integrates the power of optimization and machine learning with prior agronomic knowledge. To test the proposed time-dependent parameter estimation method, we simulated historical yield increase (from 1985 to 2018) in 25 environments in the US Corn Belt with APSIM. Then we compared yield simulation results and nine parameter estimates from our proposed parallel Bayesian framework, with Bayesian optimization and manual calibration. Results indicated that parameters calibrated using the proposed framework achieved an 11.6% reduction in the prediction error over Bayesian optimization and a 52.1% reduction over manual calibration. We also trained nine machine learning models for yield prediction and found that none of them was able to outperform the proposed method in terms of root mean square error and R2. The most significant contribution of the new automated framework for time-dependent parameter estimation is its capability to find close-to-optimal parameters for the crop model. The proposed approach also produced explainable insight into cultivar traits’ trends over 34 years (1985–2018).

A Time-Dependent Reliability Estimation Method Based on Gaussian Process Regression

2018 ◽  
Author(s):  
Wang Han ◽  
Xiaoling Zhang ◽  
Xiesi Huang ◽  
Haiqing Li
Keyword(s):  
Machine Learning ◽  
Mechanical System ◽  
Physical Modeling ◽  
Learning Algorithm ◽  
Estimation Method ◽  
Gaussian Process Regression ◽  
Reliability Estimation ◽  
Time Dependent ◽  
Physics Of Failure ◽  
Gear Transmission System

This paper presents a time-dependent reliability estimation method for engineering system based on machine learning and simulation method. Due to the stochastic nature of the environmental loads and internal incentive, the physics of failure for mechanical system is complex, and it is challenging to include uncertainties for the physical modeling of failure in the engineered system’s life cycle. In this paper, an efficient time-dependent reliability assessment framework for mechanical system is proposed using a machine learning algorithm considering stochastic dynamic loads in the mechanical system. Firstly, stochastic external loads of mechanical system are analyzed, and the finite element model is established. Secondly, the physics of failure mode of mechanical system at a time location is analyzed, and the distribution of time realization under each load condition is calculated. Then, the distribution of fatigue life can be obtained based on high-cycle fatigue theory. To reduce the calculation cost, a machine learning algorithm is utilized for physical modeling of failure by integrating uniform design and Gaussian process regression. The probabilistic fatigue life of gear transmission system under different load conditions can be calculated, and the time-varying reliability of mechanical system is further evaluated. Finally, numerical examples and the fatigue reliability estimation of gear transmission system is presented to demonstrate the effectiveness of the proposed method.

scholarly journals A QUASI-LIKELIHOOD APPROACH TO PARAMETER ESTIMATION FOR SIMULATABLE STATISTICAL MODELS

2014 ◽  
Vol 33 (2) ◽  
pp. 107 ◽  
Author(s):  
Markus Baaske ◽  
Felix Ballani ◽  
Karl Gerald Van den Boogaart
Keyword(s):  
Parameter Estimation ◽  
Statistical Models ◽  
Estimation Method ◽  
Score Function ◽  
Boolean Model ◽  
Parameter Estimates ◽  
Random Errors ◽  
Likelihood Functions ◽  
Simulation Based ◽  
Likelihood Approach

This paper introduces a parameter estimation method for a general class of statistical models. The method exclusively relies on the possibility to conduct simulations for the construction of interpolation-based metamodels of informative empirical characteristics and some subjectively chosen correlation structure of the underlying spatial random process. In the absence of likelihood functions for such statistical models, which is often the case in stochastic geometric modelling, the idea is to follow a quasi-likelihood (QL) approach to construct an optimal estimating function surrogate based on a set of interpolated summary statistics. Solving these estimating equations one can account for both the random errors due to simulations and the uncertainty about the meta-models. Thus, putting the QL approach to parameter estimation into a stochastic simulation setting the proposed method essentially consists of finding roots to a sequence of approximating quasiscore functions. As a simple demonstrating example, the proposed method is applied to a special parameter estimation problem of a planar Boolean model with discs. Here, the quasi-score function has a half-analytical, numerically tractable representation and allows for the comparison of the model parameter estimates found by the simulation-based method and obtained from solving the exact quasi-score equations.

Application of the Weighted Least Squares Parameter Estimation Method to the Robot Calibration

1994 ◽  
Vol 116 (3) ◽  
pp. 890-893 ◽  
Author(s):  
G. Zak ◽  
B. Benhabib ◽  
R. G. Fenton ◽  
I. Saban
Keyword(s):  
Parameter Estimation ◽  
Least Squares ◽  
Weighted Least Squares ◽  
Kinematic Model ◽  
Measurement Data ◽  
Estimation Method ◽  
Kinematic Parameter ◽  
Measuring System ◽  
Parameter Estimates ◽  
Robot Calibration

Significant attention has been paid recently to the topic of robot calibration. To improve the robot’s accuracy, various approaches to the measurement of the robot’s position and orientation (pose) and correction of its kinematic model have been proposed. Little attention, however, has been given to the method of estimation of the kinematic parameters from the measurement data. Typically, a least-squares solution method is used to estimate the corrections to the parameters of the model. In this paper, a method of kinematic parameter estimation is proposed where a standard least-squares estimation procedure is replaced by weighted least-squares. The weighting factors are calculated based on all the a priori available statistical information about the robot and the pose-measuring system. By giving greater weight to the measurements made where the standard deviation of the noise in the data is expected to be lower, a significant reduction in the error of the kinematic parameter estimates is made possible. The improvement in the calibration results was verified using a calibration simulation algorithm.

scholarly journals Hyperparameter Importance Analysis based on N-RReliefF Algorithm

2019 ◽  
Vol 14 (4) ◽  
pp. 557-573 ◽  
Author(s):  
Yunlei Sun ◽  
Huiquan Gong ◽  
Yucong Li ◽  
Dalin Zhang
Keyword(s):  
Machine Learning ◽  
Bayesian Optimization ◽  
Great Success ◽  
Random Forest Algorithm ◽  
Bayesian Optimization Algorithm ◽  
Svm Algorithm ◽  
Importance Analysis ◽  
Hyperparameter Selection ◽  
And Performance ◽  
Influence Degree

Hyperparameter selection has always been the key to machine learning. The Bayesian optimization algorithm has recently achieved great success, but it has certain constraints and limitations in selecting hyperparameters. In response to these constraints and limitations, this paper proposed the N-RReliefF algorithm, which can evaluate the importance of hyperparameters and the importance weights between hyperparameters. The N-RReliefF algorithm estimates the contribution of a single hyperparameter to the performance according to the influence degree of each hyperparameter on the performance and calculates the weight of importance between the hyperparameters according to the improved normalization formula. The N-RReliefF algorithm analyses the hyperparameter configuration and performance set generated by Bayesian optimization, and obtains the important hyperparameters in random forest algorithm and SVM algorithm. The experimental results verify the effectiveness of the N-RReliefF algorithm.

Estimating taxonomic durations and preservation probability

Paleobiology ◽  
1997 ◽  
Vol 23 (3) ◽  
pp. 278-300 ◽  
Author(s):  
Mike Foote
Keyword(s):  
Parameter Estimation ◽  
Estimation Method ◽  
Parameter Estimates ◽  
Extinction Rate ◽  
Mammal Species ◽  
The Face ◽  
Stratigraphic Ranges ◽  
Binned Data ◽  
Preservation Rate ◽  
Discrete Time Models

Paleontological completeness and stratigraphic ranges depend on extinction rate, origination rate, preservation rate, and the length of the interval of time over which observations can be made. I derive expressions for completeness and the distribution of durations and ranges as functions of these parameters, considering both continuous- and discrete-time models.Previous work has shown that, if stratigraphic ranges can be followed indefinitely forward, and if extinction and preservation occur at stochastically constant rates, then extinction rate and preservability can be estimated from (1) discrete (binned) stratigraphic ranges even if data on occurrences within ranges are unknown, and (2) continuous ranges if the number of occurrences within each range is known. I show that, regardless of whether the window of observation is finite or infinite, extinction and preservation rates can also be estimated from (3) continuous ranges when the number of occurrences is not known, and (4) discrete ranges when the number of occurrences is not known. One previous estimation method for binned data involves a sample-size bias. This is circumvented by using maximum likelihood parameter estimation. It is worth exploiting data on occurrences within ranges when these are available, since they allow preservation rate to be estimated with less variance. The various methods yield comparable parameter estimates when applied to Cambro-Ordovician trilobite species and Cenozoic mammal species.Stratigraphic gaps and variable preservation affect stratigraphic ranges predictably. In many cases, accurate parameter estimation is possible even in the face of these complications. The distribution of stratigraphic ranges can be used to estimate the sizes of gaps if their existence is known.

scholarly journals Prediction of tubular solar still performance by machine learning integrated with Bayesian optimization algorithm

2020 ◽  
pp. 116233
Author(s):  
Yunpeng Wang ◽  
A.W. Kandeal ◽  
Ahmed Swidan ◽  
Swellam W. Sharshir ◽  
Gamal B. Abdelaziz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Optimization Algorithm ◽  
Bayesian Optimization ◽  
Solar Still ◽  
Bayesian Optimization Algorithm

scholarly journals Global synthesis of sea turtle von Bertalanffy growth parameters through Bayesian hierarchical modeling

2021 ◽  
Vol 657 ◽  
pp. 191-207
Author(s):  
MD Ramirez ◽  
T Popovska ◽  
EA Babcock
Keyword(s):  
Population Dynamics ◽  
Parameter Estimation ◽  
Body Size ◽  
Sea Turtles ◽  
Estimation Method ◽  
Growth Parameter ◽  
Sea Turtle ◽  
Parameter Estimates ◽  
Von Bertalanffy ◽  
Bayesian Hierarchical

Knowledge of sea turtle demographic rates is central to modeling their population dynamics, but few studies have quantitatively synthesized existing data globally. Here, we used a Bayesian hierarchical model to conduct a meta-analysis of published von Bertalanffy growth curve parameters (growth coefficient, K; asymptotic length, L∞) for chelonid sea turtles. We identified 34 studies for 5 of 6 extant chelonids that met minimum selection criteria. We implemented a suite of models that included a multivariate normal likelihood on the log-transformed values of the 2 parameters to evaluate the influence of species, population (regional management unit, RMU), parameter estimation method (mark-recapture, skeletochronology, length-frequency analysis), latitude, and sampled body size range (all sizes, no large, no small, no large or small) on growth parameter estimates. According to information criteria, the best model included a random effect of species. The second best model also included latitude as a fixed effect, but RMU, parameter estimation method, latitude, and sampled body size ultimately did not strongly influence the means or variances of K and L∞ among studies. The apparent lack of RMU effect on parameter estimates within species may be an artifact of the small number of RMUs with published growth parameter estimates. The species-specific, and in some cases RMU-specific, posterior means and standard deviations of K and L∞ from this study would be appropriate priors for future studies of growth in chelonid sea turtles or for models of population dynamics. We highlight the need for expanded study and synthesis of sea turtle somatic growth rates.

scholarly journals Parameter estimation in quantum sensing based on deep reinforcement learning

2022 ◽  
Vol 8 (1) ◽  
Author(s):  
Tailong Xiao ◽  
Jianping Fan ◽  
Guihua Zeng
Keyword(s):  
Parameter Estimation ◽  
Reinforcement Learning ◽  
Quantum Control ◽  
Linear Time ◽  
Time Dependent ◽  
Global Optimality ◽  
True Parameter ◽  
Reward Function ◽  
Quantum Sensing ◽  
Dependent Parameter

AbstractParameter estimation is a pivotal task, where quantum technologies can enhance precision greatly. We investigate the time-dependent parameter estimation based on deep reinforcement learning, where the noise-free and noisy bounds of parameter estimation are derived from a geometrical perspective. We propose a physical-inspired linear time-correlated control ansatz and a general well-defined reward function integrated with the derived bounds to accelerate the network training for fast generating quantum control signals. In the light of the proposed scheme, we validate the performance of time-dependent and time-independent parameter estimation under noise-free and noisy dynamics. In particular, we evaluate the transferability of the scheme when the parameter has a shift from the true parameter. The simulation showcases the robustness and sample efficiency of the scheme and achieves the state-of-the-art performance. Our work highlights the universality and global optimality of deep reinforcement learning over conventional methods in practical parameter estimation of quantum sensing.

scholarly journals Temperature Dependent Parameter Estimation of Electrical Vehicle Batteries

Energies ◽  
2019 ◽  
Vol 12 (19) ◽  
pp. 3755
Author(s):  
Anna I. Pózna ◽  
Katalin M. Hangos ◽  
Attila Magyar
Keyword(s):  
Parameter Estimation ◽  
Thermal Behavior ◽  
Temperature Effect ◽  
Estimation Method ◽  
Temperature Dependent ◽  
Simulation Experiments ◽  
Temperature Coefficients ◽  
Battery Model ◽  
Electrical Vehicle ◽  
Dependent Parameter

Parameter estimation of electrical vehicle batteries in the presence of temperature effect is addressed in this work. A simple parametric temperature dependent battery model is used for this purpose where the temperature dependence is described by static relationships. A two-stepmethod is used that includes a parameter estimation step of the key parameters at differenttemperatures followed by a static optimization step that determines the temperature coefficients of thecorresponding parameters. It was found that the temperature dependent parameter characteristicscan be reliably estimated from charging profiles only. The proposed method can be used as acomputationally effective way of determining the key battery parameters at a given temperature fromtheir actual estimated values and from their previously determined static temperature dependence.The proposed parameter estimation method was verified by simulation experiments on a morecomplex battery model that also describes the detailed dynamic thermal behavior of the battery.

Sign in / Sign up

Export Citation Format

Share Document