Abstract
The 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).
Highlights
The performance of crop models in simulating various aspects of the cropping system is sensitive to parameter calibration
Several global sensitivity analysis methods have been proposed to calibrate the parameters in crop models, including Fourier amplitude sensitivity test (FAST)[23], extended FAST24, multi-normal approximations[25], simulated a nnealing[26], shuffled complex evolution method[27], least squares[28], regression-based model[29], interaction-based model[30], nonparametric smoothing[31], Markov chain Monte Carlo parameter estimation[20,32,33,34,35], generalized likelihood uncertainty estimation[32], multi-model e nsembles[36], maximal conditional posterior d istribution[37], hybrid metropolis Hastings Gibbs algorithm[38], differential evolution adaptative metropolis algorithm[39,40], Bayesian model[33,35,41,42,43,44], Bayesian optimization (BO)[45], and Bayesian-based multilevel factorial analysis[46]
The result shows that the proposed framework with the parallel Bayesian optimization (PBO) algorithm outperformed the BO and the manual approaches in terms of yield simulation from 1985 to 2018 (Table 2)
Summary
The performance of crop models in simulating various aspects of the cropping system is sensitive to parameter calibration. Several global sensitivity analysis methods have been proposed to calibrate the parameters in crop models, including Fourier amplitude sensitivity test (FAST)[23], extended FAST24, multi-normal approximations[25], simulated a nnealing[26], shuffled complex evolution method[27], least squares[28], regression-based model[29], interaction-based model[30], nonparametric smoothing[31], Markov chain Monte Carlo parameter estimation[20,32,33,34,35], generalized likelihood uncertainty estimation[32], multi-model e nsembles[36], maximal conditional posterior d istribution[37], hybrid metropolis Hastings Gibbs algorithm[38], differential evolution adaptative metropolis algorithm[39,40], Bayesian model[33,35,41,42,43,44], Bayesian optimization (BO)[45], and Bayesian-based multilevel factorial analysis[46]. Monte Carlo-based methods are computationally intensive and fail to provide adequate sample density from solution space when the number of parameters increases[50]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.