Parameter estimation for crop growth model using evolutionary and bio-inspired algorithms

Zúñiga, Elmer César Trejo; Cruz, Irineo Lorenzo López; Garcia, Agustin Ruiz

doi:10.1016/j.asoc.2014.06.023

Cited by 23 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To efficiently solve this calibration problem, many research efforts have focused on developing metaheuristic methods that are capable of finding good solutions in reasonable computation times (Balsa-Canto, Banga, Egea, Fernandez-Villaverde, & de Hijas-Liste, 2012;Banga & Balsa-Canto, 2008;Gábor & Banga, 2015;Sun, Garibaldi, & Hodgman, 2012). Many examples using various metaheuristics can be found in the literature, such as simulating annealing (Perkins, Jaeger, Reinitz, & Glass, 2006), evolutionary strategies (Ji & Xu, 2006;Jostins & Jaeger, 2010), differential evolution (Da Ros et al, 2013;Villaverde & Banga, 2014;Zúñiga, Cruz, & García, 2014), scatter search (Egea, Balsa-Canto, García, & Banga, 2009;Egea, Martí, & Banga, 2010), particle swarm optimization (Palafox, Noman, & Iba, 2012;Tang, Chai, Wang, & Cao, 2020), among others. Also, many proposals exploit different parallelization strategies and infrastructures to solve these problems in competitive execution times (Adams et al, 2013;González et al, 2017;Lee, Hsiao, & Hwang, 2014;Penas, González, Egea, Banga and Doallo, 2015;Teijeiro et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

Parallel ant colony optimization for the training of cell signaling networks

González

Gábor²,

Sáez-Rodríguez³

et al. 2022

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Parallel ant colony optimization for the training of cell signaling networks

González

Gábor²,

Sáez-Rodríguez³

et al. 2022

Expert Systems with Applications

View full text Add to dashboard Cite

“…Although the EGA was successfully applied for calibrating the parameters of AquaCrop and achieved satisfactory calibration and validation performance in this study, the use of EGA in crop models still has some problems that require further study. Avoiding being stuck in a local optimal solution is a common problem when using the search algorithm to find the global optimal solution (Trejo Zuniga et al, 2014), which still needs attention. The main advantage of the automatic calibration using a standard algorithm such as EGA is that the calibration is transparent and much less subject to non-documented decisions by the model user.…”

Section: Perspectives On Automatic Calibrationmentioning

confidence: 99%

“…used in crop yield forecasting, irrigation and field management decisions, and impact assessment of climate change on agriculture (Confalonieri et al, 2016). Crop models simulate many processes related to plant physiology and soil water and nutrient flows and transformations, which result in complex model structures, a large number of parameters, and nonlinear responses (Trejo Zuniga et al, 2014, Xi, Lu, Gui, Qi, & Zhang, 2017. These characteristics of crop models greatly affect the accuracy and efficiency of the model calibration.…”

mentioning

confidence: 99%

Calibrating AquaCrop model using genetic algorithm with multi‐objective functions applying different weight factors

et al. 2021

View full text Add to dashboard Cite

Fast and efficient calibration is essential for the effective application of crop models. However, many formulas, parameters, and nonlinear responses in crop models make calibration difficult and time consuming. Using an intelligent optimization algorithm to calibrate the model has advantages in global search ability, optimization speed, and automatic calibration compared to the manual trial and error method, although performance may depend strongly on the objective function used. This study evaluated the use of an improved genetic algorithm, namely elite genetic algorithm (EGA), for calibration of a water-driven crop model (AquaCrop) using three different objective functions separately, which comprise observed variables from harvest and in-season data and differ in calculating the weight factors of these variables. Observations of maize (Zea mays L.) and wheat (Triticum aestivum L.) under different irrigation treatments were used for model calibration and validation. The results showed satisfactory calibration performances for the EGA applying the three objective functions, that is, the coefficient of determination and index of agreement were all >0.97 for canopy cover (CC) and biomass of both maize and wheat, and also showed good agreement between simulated and observed soil water storage. The three objective functions differed in calibration speed and performance, since they differ in error source and calculation, moreover, they performed similar or better than manual calibration. The validation results showed that the AquaCrop model calibrated by the EGA can predict CC, biomass, yield, and soil water storage of maize and wheat. In general, calibration of the AquaCrop model using EGA greatly improves the model application efficiency for irrigation management. INTRODUCTIONCrop models are important tools for designing and assessing agricultural production systems, and they have been widely

show abstract

“…Additionally, crop growth models can provide detailed estimations of crop status, including phenological status, leaf area index ( LAI ), and yield of specific crop types 3 . Furthermore, these models can predict crop yields as a function of soil conditions, weather, and management practices 4 . Therefore, crop growth models have become important tools for quantitatively evaluating the relationships among soil, weather, and vegetation, and for facilitating the timely regulation of crop growth, which has attracted widespread attention.…”

Section: Introductionmentioning

confidence: 99%

A new regional cotton growth model based on reference crop evapotranspiration for predicting growth processes

Lin

Deng

Wei

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Meteorological conditions and irrigation amounts are key factors that affect crop growth processes. Typically, crop growth and development are modeled as a function of time or growing degree days (GDD). Although the most important component of GDD is temperature, it can vary significantly year to year while also gradually shifting due to climate changes. However, cotton is highly sensitive to various meteorological factors, and reference crop evapotranspiration (ETO) integrates the primary meteorological factors responsible for global dryland extension and aridity changes. This paper constructs a cotton growth model using ETO, which improves the accuracy of crop growth simulation. Two cotton growth models based on the logistic model established using GDD or ETO as independent factors are evaluated in this paper. Additionally, this paper examines mathematical models that relate irrigation amount and irrigation water utilization efficiency (IWUE) to the maximum leaf area index (LAImax) and cotton yield, revealing some key findings. First, the model using cumulative reference crop evapotranspiration (CETO) as the independent variable is more accurate than the one using cumulative growing degree days. To better reflect the effects of meteorological conditions on cotton growth, this paper recommends using CETO as the independent variable to establish cotton growth models. Secondly, the maximum cotton yield is 7171.7 kg/ha when LAImax is 6.043 cm2/cm2, the corresponding required irrigation amount is 518.793 mm, and IWUE is 21.153 kg/(ha·mm). Future studies should consider multiple associated meteorological factors and use ETO crop growth models to simulate and predict crop growth and yield.

show abstract

Parameter estimation for crop growth model using evolutionary and bio-inspired algorithms

Cited by 23 publications

References 23 publications

Parallel ant colony optimization for the training of cell signaling networks

Parallel ant colony optimization for the training of cell signaling networks

Calibrating AquaCrop model using genetic algorithm with multi‐objective functions applying different weight factors

A new regional cotton growth model based on reference crop evapotranspiration for predicting growth processes

Contact Info

Product

Resources

About