Accuracy evaluation of the crop-weather yield predictive models of Italian ryegrass and forage rye using cross-validation

Peng, Jinglun; Kim, Moon‐Ju; Jo, Mu-Hwan; Deng, Min; Kim, Kyung-Dae; Lee, Bae-Hun; Kim, Byong-Wan; Sung, Kyung Il

doi:10.1007/s12892-017-0090-0

Cited by 17 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The R-squared and the normalized root-mean-square error (NRMSE) were utilized as accuracy indicators. The calculation equation of NRMSE and the judgement criteria followed the previous studies [34]. Microsoft Excel 2010 (Microsoft Corp, Redmond, WA, USA) was used to prepare the datasets, and SPSS 24.0 was adopted for the statistical analyses.…”

Section: Yield Modeling Methodsmentioning

confidence: 99%

Yield Prediction Modeling for Sorghum–Sudangrass Hybrid Based on Climatic, Soil, and Cultivar Data in the Republic of Korea

2020

View full text Add to dashboard Cite

The objective of this study was to construct a sorghum–sudangrass hybrid (SSH) yield prediction model based on climatic, soil, and cultivar information in the southern area of the Korean Peninsula. Besides, the effects of climatic factors on SSH yield were investigated simultaneously. The SSH dataset (n = 105), including Dry Matter Yield (DMY, kg/ha), Seeding-Harvest Accumulated Temperature (SHaAT, °C), Seeding–Harvest Accumulated Precipitation (SHAP, mm), Seeding–Harvest Sunshine Duration (SHSD, h), Soil Suitability Score (SSS), and cultivar maturity information, was developed for model construction. Subsequently, using general linear modeling method, the SSH yield prediction model was constructed as follows: DMY = 6.5SHaAT – 4.9SHAP + 13.8SHSD – 54.4SSS – 1036.4 + Maturity. The impacts of the accumulated thermal climatic variables and accumulated precipitation during crop growth on the variance of SSH yield in this region were confirmed. The summer-concentrated precipitation in the southern area of the Korean Peninsula exceeded the proper range of SSH water requirement and led to stresses to its yield production. Furthermore, to improve the data quality for high fitness model construction, the standard schedule for forage crop cultivation experiment in this region was recommended to be developed, especially under the data requirement in the context of the big data era.

show abstract

Section: Yield Modeling Methodsmentioning

confidence: 99%

Yield Prediction Modeling for Sorghum–Sudangrass Hybrid Based on Climatic, Soil, and Cultivar Data in the Republic of Korea

2020

View full text Add to dashboard Cite

show abstract

“…In addition, 10‐fold cross‐validation was performed to evaluate the predictive accuracy of the model referring to the method reported by Peng et al (Peng, Kim, Jo et al, ). R 2 and the normalized root‐mean‐square error (NRMSE) were calculated to measure the accurate predictive ability of the model.…”

Section: Methodsmentioning

confidence: 99%

“…Kim, Jeon, Sung, and Kim () examined the path relationship between whole ‐ crop barley yield and climate factors such as temperature, precipitation and sunshine duration using a Bayesian approach of structural equation model and found that the yield of whole ‐ crop barley was affected by spring temperature directly and affected by spring rainfall indirectly. Furthermore, Peng et al, (); Peng, Kim, Kim et al, (); Peng, Kim, Jo et al, () reported several studies using general linear model to construct the yield predictive models of Italian ryegrass and forage rye. However, few studies were reported on crop ‐ weather models for whole‐crop barley in South Korea.…”

Section: Introductionmentioning

confidence: 99%

Yield modeling for prediction of regional whole‐crop barley productivity

et al. 2019

View full text Add to dashboard Cite

Rice production has surpassed market demand in South Korea, and it is necessary to diversify the inputs of available agricultural resources from rice production to forage or other more demanded grains. This research was conducted to develop a yield predictive model of whole‐crop barley (Hordeum vulgare L.) based on climatic data in South Korea. A data set (n = 290) containing dry matter yield (DMY), cultivated locations and climatic variables was developed based on collected research reports. With DMY as the response variable, three optimal climatic variables including spring accumulated temperature (SAT), period to accumulated temperature 150°C (PAT150) and spring duration of sunshine (SDS) were selected through the stepwise approach of multiple regression analysis. Subsequently, through the general linear model, the yield predictive model including the three climatic variables and cultivated locations was constructed. The adjusted R2 of the model was 51.6%. Meanwhile, the model was tested through residual diagnostics and cross‐validation. The selection of SAT, PAT150 and SDS confirmed that the growth and development of autumn‐seeded whole‐crop barley were active in the next spring in South Korea, while the coefficient of determination of the model was lower than anticipated since only considering climatic variables. In the future research, a new model with higher interpretability might be developed via increasing data size, adopting more environmental variables or constructing the models for each location individually instead of pooling their data together.

show abstract

“…Training and testing to apply K-Fold Cross-Validation for data sharing. 10 Folds are used because this value has been widely used in previous research and produces the most accurate validation (Peng et al, 2017).…”

Section: Figure 1 Research Algorithmmentioning

confidence: 99%

Smoothing in Neural Network for Univariat Time Series Data Forecasting

Syamsiah

Purwandani

2020

jri

View full text Add to dashboard Cite

Time series data is interesting research material for many people. Not a few models have been produced, but very optimal accuracy has not been obtained. Neural network is one that is widely used because of its ability to understand non-linear relationships between data. This study will combine a neural network with exponential smoothing to produce higher accuracy. Exponential smoothing is one of the best linear methods is used for data set transformation and thereafter the new data set will be used in training and testing the Neural Network model. The resulting model will be evaluated using the standard error measure Root Mean Square Error (RMSE). Each model was compared with its RMSE value and then performed a T-Test. The proposed ES-NN model proved to have better predictive results than using only one method.

show abstract

Accuracy evaluation of the crop-weather yield predictive models of Italian ryegrass and forage rye using cross-validation

Cited by 17 publications

References 23 publications

Yield Prediction Modeling for Sorghum–Sudangrass Hybrid Based on Climatic, Soil, and Cultivar Data in the Republic of Korea

Yield Prediction Modeling for Sorghum–Sudangrass Hybrid Based on Climatic, Soil, and Cultivar Data in the Republic of Korea

Yield modeling for prediction of regional whole‐crop barley productivity

Smoothing in Neural Network for Univariat Time Series Data Forecasting

Contact Info

Product

Resources

About