A theoretical and real world evaluation of two Bayesian techniques for the calibration of variety parameters in a sugarcane crop model

Sexton, Justin; Everingham, Yvette; Inman-Bamber, N. G.

doi:10.1016/j.envsoft.2016.05.014

Cited by 47 publications

(27 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Description (Sexton et al ): leaf_size = size of each leaf serving as inflection points for leaf size curve, leaf_size_no = leaf number from top leaf (leaf number 1), cane_fraction = fraction of accumulated biomass partitioned to cane, sucrose_fraction_stalk = fraction accumulated biomass partitioned to sucrose, stress_factor_stalk = stress factor for sucrose accumulation, tt_emerg_to_begcane = degree‐days required from emergence to start stalk growth, tt_begcane_to_flowering = degree‐days required from start of stalk growth to start of flowering, tt_flowering_to_crop_end = degree‐days from flowering to crop death/end, green_leaf_no = green leaf number, tillerf_leaf_size = expansion factor applied to leaf size due to tillering, tillerf_leaf_size_no = leaf number from top leaf (leaf number 1).…”

Section: Methodsmentioning

confidence: 99%

Drying‐Off Periods for Irrigated Sugarcane to Maximize Sucrose Yields Under Brazilian Conditions

Dias

Sentelhas

2018

Irrigation and Drainage

View full text Add to dashboard Cite

The natural ripening process in sugarcane plants is influenced by several factors, including water stress. In irrigated sugarcane areas, water application is often withheld prior to harvest, a process called drying-off, which is done to increase the sucrose content and yield, and to provide suitable conditions of soil moisture for mechanical harvesting. Based on this, the objective of this study was to determine the drying-off periods for irrigated sugarcane in different Brazilian regions to maximize sucrose yields. The APSIM-Sugarcane model was used to simulate 12-month plant cane in 12 Brazilian sites for a long-term period. Three soil types with different water-holding capacities (low, medium and high) were adopted. The drying-off periods were determined based on the relationship between relative stalk dry mass yield (dried-off and fully irrigated) and days in which water was withheld prior to harvest, considering yield reduction up to 4% as a target. As expected, the drying-off periods varied considerably according to locations, soil types and harvest dates, with the median ranging from 15 to 115 days. In general, more drying-off days are required at the beginning and end of the harvesting season, when higher interannual variability is also observed. The results obtained are useful for planning and decision-making in irrigated sugarcane areas, since they allow evaluation of the best strategy to maximize sucrose yield. RÉSUMÉLe processus naturel de maturation de la canne à sucre est influencé par plusieurs facteurs, dont le stress hydrique. Dans les zones de production de canne à sucre irriguée, l'application de l'eau est normalement suspendue avant la récolte, un processus nommée séchage, lequel est réalisé pour augmenter le contenu et rendement de saccharose, et pour assurer des conditions adéquates d'humidité du sol pour la récolte mécanique. Basée sur cela, l'objectif de cette étude a été de déterminer les périodes de séchage pour des cannes à sucre irriguées dans différentes régions du Brésil pour maximiser le rendement de saccharose. Le model APSIM-Sugarcane a été utilisé pour simuler, à long terme, la canne de 12 mois dans 12 sites brésiliens. Trois types de sol avec différentes capacités de rétention (faible, moyenne et forte) ont été adoptés. Les périodes de séchage ont été déterminées par la relation entre la productivité relative (sèche et irriguée) et le nombre de jours pendant lesquels l'eau a été suspendue avant la récolte, compte tenu de l'objectif de réduction de 4% de la productivité. Comme prévu, les périodes de séchage ont varié considérablement selon les localités, types de sol et dates de récolte, dont la médiane a varié de 15 à 115 jours. En général, plus de jours de séchages sont nécessaires au commencement et à la fin de saison de récolte, quand une haute variabilité interannuelle est observée. Les résultats obtenus sont utiles pour les processus de planification et de prise de décision dans les zones de canne à sucre irriguée, puisque cela permet d'évaluer la meilleure stratégie pour m...

show abstract

Section: Methodsmentioning

confidence: 99%

Drying‐Off Periods for Irrigated Sugarcane to Maximize Sucrose Yields Under Brazilian Conditions

Dias

Sentelhas

2018

Irrigation and Drainage

View full text Add to dashboard Cite

show abstract

“…Fitting complex biological models to data remains a challenging problem, and a number of optimization strategies have been employed to obtain parameter estimates for crop growth models or their phenology models (Archontoulis et al, 2014;He et al, 2010;Lamsal et al, 2017;Messina et al, 2018;Sexton et al, 2016;Wallach et al, 2001). The approach used here assumes that there may be more than one equivalently good solution given the data (sometimes referred to as equifinality) and employs a highly-parallelized, multi-modal optimization strategy (Wong, 2015).…”

Section: ) Training Component Models: Fitting Knowledge-based Phenolmentioning

confidence: 99%

“…Like many biological models, these models are overparameterized, and they are unidentifiable given only the observations of calendar dates to developmental stages that are typically measured in applied field settings. This problem of fitting unidentifiable models with non-convex cost landscapes and limited data is not unique to the life sciences; while strategies exist to reparameterize the complex model to assist model fitting, crop growth modelers have generally employed various optimization approaches to regularize and fit the complex crop growth model (Archontoulis et al, 2014;He et al, 2010;Lamsal et al, 2017;Messina et al, 2018;Sexton et al, 2016;Wallach et al, 2001). The best optimization strategy will vary with the size and composition of the training dataset, sensitivity of the output to the selected set of input parameters, choice of priors and regularization schemes, and model runtime.…”

Section: Introductionmentioning

confidence: 99%

Intercontinental prediction of soybean phenology via hybrid ensemble of knowledge-based and data-driven models

McCormick

Truong

Rotundo

et al. 2020

Preprint

View full text Add to dashboard Cite

The timing of crop development has significant impacts on management decisions and subsequent yield formation. A large intercontinental dataset recording the timing of soybean developmental stages was used to establish ensembling approaches that leverage both discrete-time dynamical system models of soybean phenology and data-driven, machine-learned models to achieve accurate and interpretable predictions. We demonstrate that the knowledge-based, dynamical models can improve machine learning by generating expert-engineered features. Combining the predictions of the diverse component models via super learning resulted in a mean absolute error of 4.12 and 4.55 days to flowering (R1) and physiological maturity (R7), providing an improvement relative to the best benchmark model error of 6.90 and 15.47 days, respectively. The hybrid intercontinental model applies to a much wider range of management and temperature conditions than previous mechanistic models, enabling improved decision support as alternative cropping systems arise, farm sizes increase, and changes in the global climate continue to accelerate.

show abstract

“…One type of study is model specific; it identifies the most important parameters in that model, and explains how they can be estimated from data . Other studies have focused on the implementation of a Bayesian approach or on the comparison of frequentist and Bayesian approaches (Gao et al, 2020;Jansen and Hagenaars, 2004;Sexton et al, 2016), on numerical methods of seeking best parameter values (Bhar et al, 2020), on the choice of parameters to estimate (Angulo et al, 2013), or on the observed data to use for calibration (Guillaume et al, 2011;Hoogenboom et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

The chaos in calibrating crop models

Wallach

Palosuo

Thorburn

et al. 2020

Preprint

View full text Add to dashboard Cite

Calibration, that is the estimation of model parameters based on fitting the model to experimental data, is among the first steps in essentially every application of crop models and process models in other fields and has an important impact on simulated values. The goal of this study is to develop a comprehensive list of the decisions involved in calibration and to identify the range of choices made in practice, as groundwork for developing guidelines for crop model calibration starting with phenology. Three groups of decisions are identified; the criterion for choosing the parameter values, the choice of parameters to estimate and numerical aspects of parameter estimation. It is found that in practice there is a large diversity of choices for every decision, even among modeling groups using the same model structure. These findings are relevant to process models in other fields.

show abstract

A theoretical and real world evaluation of two Bayesian techniques for the calibration of variety parameters in a sugarcane crop model

Cited by 47 publications

References 49 publications

Drying‐Off Periods for Irrigated Sugarcane to Maximize Sucrose Yields Under Brazilian Conditions

Drying‐Off Periods for Irrigated Sugarcane to Maximize Sucrose Yields Under Brazilian Conditions

Intercontinental prediction of soybean phenology via hybrid ensemble of knowledge-based and data-driven models

The chaos in calibrating crop models

Contact Info

Product

Resources

About