Usage of SUBSTOR model in potato yield prediction

Šťastná, Milada; Toman, František; Dufková, Jana Kozlovský

doi:10.1016/j.agwat.2009.09.015

Cited by 33 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, the amount of empirical data included in the modeling remains a controversial issue. In many works, the authors of the models use a lot of independent variables [3,12,44,45] or use classical prognostic models developed exclusively for potato: SUBSTOR-Potato [46,47], LINTUL-Potato-DSS Model [48], etc. In that situation, when the model tries to estimate too many unknowns for the number of observations made, the model's ability to detect real relationships is severely limited [49].…”

Section: Discussionmentioning

confidence: 99%

The Application of Multiple Linear Regression and Artificial Neural Network Models for Yield Prediction of Very Early Potato Cultivars before Harvest

et al. 2021

View full text Add to dashboard Cite

Yield forecasting is a rational and scientific way of predicting future occurrences in agriculture—the level of production effects. Its main purpose is reducing the risk in the decision-making process affecting the yield in terms of quantity and quality. The aim of the following study was to generate a linear and non-linear model to forecast the tuber yield of three very early potato cultivars: Arielle, Riviera, and Viviana. In order to achieve the set goal of the study, data from the period 2010–2017 were collected, coming from official varietal experiments carried out in northern and northwestern Poland. The linear model has been created based on multiple linear regression analysis (MLR), while the non-linear model has been built using artificial neural networks (ANN). The created models can predict the yield of very early potato varieties on 20th June. Agronomic, phytophenological, and meteorological data were used to prepare the models, and the correctness of their operation was verified on the basis of separate sets of data not participating in the construction of the models. For the proper validation of the model, six forecast error metrics were used: i.e., global relative approximation error (RAE), root mean square error (RMS), mean absolute error (MAE), and mean absolute percentage error (MAPE). As a result of the conducted analyses, the forecast error results for most models did not exceed 15% of MAPE. The predictive neural model NY1 was characterized by better values of quality measures and ex post forecast errors than the regression model RY1.

show abstract

Section: Discussionmentioning

confidence: 99%

The Application of Multiple Linear Regression and Artificial Neural Network Models for Yield Prediction of Very Early Potato Cultivars before Harvest

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A flow diagram of the application and processes for DSSAT can be found in Jones et al [ 25 ]. The model took into account several processes simultaneously and each simulation run consisted of calculations of the phenological development, formation of leaf, stem and root biomass and its partitioning, available soil water and its utilization by the crop, and the N balance and its distribution to crop organs [ 43 ].…”

Section: Methodsmentioning

confidence: 99%

Estimation of Nitrogen Pools in Irrigated Potato Production on Sandy Soil Using the Model SUBSTOR

2015

View full text Add to dashboard Cite

Recent increases in nitrate concentrations in the Suwannee River and associated springs in northern Florida have raised concerns over the contributions of non-point sources. The Middle Suwannee River Basin (MSRB) is of special concern because of prevalent karst topography, unconfined aquifers and sandy soils which increase vulnerability of the ground water contamination from agricultural operations- a billion dollar industry in this region. Potato (Solanum tuberosum L.) production poses a challenge in the area due to the shallow root system of potato plants, and low water and nutrient holding capacity of the sandy soils. A four-year monitoring study for potato production on sandy soil was conducted on a commercial farm located in the MSRB to identify major nitrogen (N) loss pathways and determine their contribution to the total environmental N load, using a partial N budget approach and the potato model SUBSTOR. Model simulated environmental N loading rates were found to lie within one standard deviation of the observed values and identified leaching loss of N as the major sink representing 25 to 38% (or 85 to 138 kg ha-1 N) of the total input N (310 to 349 kg ha-1 N). The crop residues left in the field after tuber harvest represented a significant amount of N (64 to 110 kg ha-1N) and posed potential for indirect leaching loss of N upon their mineralization and the absence of subsequent cover crops. Typically, two months of fallow period exits between harvest of tubers and planting of the fall row crop (silage corn). The fallow period is characterized by summer rains which pose a threat to N released from rapidly mineralizing potato vines. Strategies to reduce N loading into the groundwater from potato production must focus on development and adoption of best management practices aimed on reducing direct as well as indirect N leaching losses.

show abstract

“…Most of these studies showed that this model was suitable for simulation of potato growth (mainly for potato yield) but was less accurate for other crop growth variables (Raymundo et al, 2017) and extreme weather conditions (i.e. low amount of precipitation and its disordered distribution during the growing season) (Šťastná et al, 2010); or high mean air temperatures (Šťastná et al, 2010;Raymundo et al, 2017). Camargo et al (2015aCamargo et al ( , 2015bCamargo et al ( , 2016 reported a field data set with potato (phenological stages, crop growth evolution, growth indices, light interception, and relationships of quality and quantity of the potato crop with several irrigation depths) which may be suitable for evaluating the SUBSTOR-Potato model as well as to optimize the management of irrigation water in the area.…”

Section: Introductionmentioning

confidence: 99%

“…Decision support systems (DSSs) – such as crop simulation models – are tools that allow this challenge to be achieved under different management conditions (Boote et al ., 2010). The SUBSTOR-Potato model (Griffin et al ., 1993) has been widely used for simulating potato growth under different irrigation and nitrogen (N) management conditions (Mahdian and Gallichand, 1995; Travasso et al ., 1996; Snapp and Fortuna, 2003; Šťastná et al ., 2010; Arora et al ., 2013; Woli et al ., 2016; Raymundo et al ., 2017). Most of these studies showed that this model was suitable for simulation of potato growth (mainly for potato yield) but was less accurate for other crop growth variables (Raymundo et al ., 2017) and extreme weather conditions (i.e.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of deficit irrigation strategies by using SUBSTOR-Potato model in a semi-arid area

et al. 2019

View full text Add to dashboard Cite

In areas where water is scarce, the use of regulated deficit irrigation, combined with decision support system tools, may decrease the impact of agriculture on natural water resources, as well as on energy consumption, thereby improving the profitability of farms. With this aim, the SUBSTOR-Potato model (incorporated in the DSSAT Program) was evaluated with a 2-year field test (2011 and 2012) conducted in a semi-arid area (Albacete, Spain) applying four irrigation levels (120, 100, 80 and 60% of irrigation requirements). Subsequently, the model was used for simulating the potato yield under several deficit irrigation strategies (ISs) during 30 years of a semi-arid climate (1988–2017) and determining the most profitable option. The considered ISs were deemed those most suitable from the yield and water productivity point of view by some authors. The model performance for tuber yield was satisfactory with an index of agreement >0.91 and errors between 0.71 and 3.06 × 103 kg/ha. The ISs simulated with SUBSTOR-Potato showed that slight deficit irrigation (5–10%) may increase the water productivity and profitability of the farms. Moreover, tuber formation (from onset of tuber initiation to harvest) was shown to be the most sensitive stage, therefore it is highly recommended to avoid deficit during this stage, which would cause a large reduction in yield (around 8 t/ha, depending on the level of deficit suffered by the crop).

show abstract

Usage of SUBSTOR model in potato yield prediction

Cited by 33 publications

References 9 publications

The Application of Multiple Linear Regression and Artificial Neural Network Models for Yield Prediction of Very Early Potato Cultivars before Harvest

The Application of Multiple Linear Regression and Artificial Neural Network Models for Yield Prediction of Very Early Potato Cultivars before Harvest

Estimation of Nitrogen Pools in Irrigated Potato Production on Sandy Soil Using the Model SUBSTOR

Analysis of deficit irrigation strategies by using SUBSTOR-Potato model in a semi-arid area

Contact Info

Product

Resources

About