• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.449-456
• /
• 2022

This study proposes a deep learning algorithm to predict crop yield using GIS (Geographic Information System) to extract soil properties from Soilgrids and soil suitability class maps. The proposed model modified the structure of a published CNN-RNN (Convolutional Neural Network-Recurrent Neural Network) based crop yield prediction model suitable for the domestic crop environment. The existing model has two characteristics. The first is that it replaces the original yield with the average yield of the year, and the second is that it trains the data of the predicted year. The new model uses the original field value to ensure accuracy, and the network structure has been improved so that it can train only with data prior to the year to be predicted. The proposed model predicted the yield per unit area of autumn cabbage for kimchi by region based on weather, soil, soil suitability classes, and yield data from 1980 to 2020. As a result of computing and predicting data for each of the four years from 2018 to 2021, the error amount for the test data set was about 10%, enabling accurate yield prediction, especially in regions with a large proportion of total yield. In addition, both the proposed model and the existing model show that the error gradually decreases as the number of years of training data increases, resulting in improved general-purpose performance as the number of training data increases.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.2
• /
• pp.132-139
• /
• 2009

Yield is a very important measure that can expresses simply for productivity and performance of company. So, yield is used widely in many industries nowadays. With the development of the information technology and online based real-time process monitoring technology, many industries operate the production lines that are developed into automation system. In these production lines, the product structures are very complexity and variety. So, there are many multi-variate processes that need to be monitored with many quality characteristics and associated process variables at the same time. These situations have made it possible to obtain super-large manufacturing process data sets. However, there are many difficulties with finding the cause of process variation or useful information in the high capacity database. In order to solve this problem, neural networks technique is a favorite technique that predicts the yield of process for process control. This paper uses a neural networks technique for improvement and maintenance of yield in manufacturing process. The purpose of this paper is to model the prediction of a sub process that has much effect to improve yields in total manufacturing process and the prediction of adjustment values of this sub process. These informations feedback into the process and the process is adjusted. Also, we show that the proposed model is useful to the manufacturing process through the case study.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.647-659
• /
• 2017

Garlic and onion are grown in major cultivation regions that depend on the crop condition and the meteorology of the production area. Therefore, when yields are to be predicted, it is reasonable to use a statistical model in which both the crop and the meteorological elements are considered. In this paper, using a multiple linear regression model, we predicted garlic and onion yields in major cultivation regions. We used the MODIS NDVI that reflects the crop conditions, and six meteorological elements for 7 major cultivation regions from 2006 to 2015. The multiple linear regression models were suggested by using stepwise regression in the extraction of independent variables. As a result, the MODIS NDVI in February was chosen the significant independent variable of the garlic and onion yield prediction model. In the case of meteorological elements, the garlic yield prediction model were the mean temperature (March), the rainfall (November, March), the relative humidity (April), and the duration time of sunshine (April, May). Also, the rainfall (November), the duration time of sunshine (January), the relative humidity (April), and the minimum temperature (June) were chosen among the variables as the significant meteorological elements of the onion yield prediction model. MODIS NDVI and meteorological elements in the model explain 84.4%, 75.9% of the garlic and onion with a root mean square error (RMSE) of 42.57 kg/10a, 340.29 kg/10a. These lead to the result that the characteristics of variations in garlic and onion growth according to MODIS NDVI and other meteorological elements were well reflected in the model.

• Journal of Korean Society of Forest Science
• /
• v.112 no.2
• /
• pp.209-216
• /
• 2023

This study aimed to use national forest inventory data to develop a forest productivity index and yield prediction model of a Tilia amurensis stand. The site index displaying the forest productivity of the Tilia amurensis stand was developed as a Schumacher model, and the site index classification curve was generated from the model results; its distribution growth in Korea ranged from 8-16. The growth model using age as an independent variable for breast height and height diameter estimation was derived from the Chapman-Richards and Weibull model. The Fitness Indices of the estimation models were 0.32 and 0.11, respectively, which were generally low values, but the estimation-equation residuals were evenly distributed around 0, so we judged that there would be no issue in applying the equation. The stand basal area and site index of the Tilia amurensis stand had the greatest effect on the stand-volume change. These two factors were used to derive the Tilia amurensis stand yield model, and the model's determination coefficient was approximately 94%. After verifying the residual normality of the equation and autocorrelation of the growth factors in the yield model, no particular problems were observed. Finally, the growth and yield models of the Tilia amurensis stand were used to produce the makeshift stand yield table. According to this table, when the Tilia amurensis stand is 70 years old, the estimated stand-volume per hectare would be approximately 208 m³ . It is expected that these study results will be helpful for decision-making of Tilia amurensis stands management, which have high value as a forest resource for honey and timber.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.7
• /
• pp.83-93
• /
• 2003

This research compared the observed and model predicted results that include; runoff, sediment yield, and nutrient losses from a 2.71 ha cattle grazing pasture field in North Alabama. Application of water quality computer simulation models can inexpensively and quickly assess the impact of pasture management practices on water quality. AGNPS single storm based model was applied to the three pasture species; Bermudagrass, fescue, and Ryegrass. While comparing model predicted results with observed data, it showed that model can reasonably predict the runoff, sediment yield and nutrient losses from the watershed. Over-prediction and under-prediction by the model occurred during very high and low rainfall events, respectively. The study concluded that AGNPS model can be reasonably applied to assess the impacts of pasture management practices and chicken litter application on water quality.

• Animal Bioscience
• /
• v.34 no.4
• /
• pp.770-782
• /
• 2021

Objective: The aim of the present study was to compare the effectiveness of three approaches (the seasonal auto-regressive integrated moving average [SARIMA] model, the nonlinear autoregressive exogenous [NARX] artificial neural networks and Wood's model) to the prediction of milk yield during lactation. Methods: The dataset comprised monthly test-day records from 965 Polish Holstein-Friesian Black-and-White primiparous cows. The milk yields from cows in their first lactation (from 5 to 305 days in milk) were used. Each lactation was divided into ten lactation stages of approximately 30 days. Two age groups and four calving seasons were distinguished. The records collected between 2009 and 2015 were used for model fitting and those from 2016 for the verification of predictive performance. Results: No significant differences between the predicted and the real values were found. The predictions generated by SARIMA were slightly more accurate, although they did not differ significantly from those produced by the NARX and Wood's models. SARIMA had a slightly better performance, especially in the initial periods, whereas the NARX and Wood's models in the later ones. Conclusion: The use of SARIMA was more time-consuming than that of NARX and Wood's model. The application of the SARIMA, NARX and Wood's models (after their implementation in a user-friendly software) may allow farmers to estimate milk yield of cows that begin production for the first time.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.82-89
• /
• 2023

Various machine-learning models may yield high predictive power for massive time series for time series prediction. However, these models are prone to instability in terms of computational cost because of the high dimensionality of the feature space and nonoptimized hyperparameter settings. Considering the potential risk that model training with a high-dimensional feature set can be time-consuming, we evaluate a feature-importance-based feature selection method to derive a tradeoff between predictive power and computational cost for time series prediction. We used two machine learning techniques for performance evaluation to generate prediction models from a retail sales dataset. First, we ranked the features using impurity- and Local Interpretable Model-agnostic Explanations (LIME) -based feature importance measures in the prediction models. Then, the recursive feature elimination method was applied to eliminate unimportant features sequentially. Consequently, we obtained a subset of features that could lead to reduced model training time while preserving acceptable model performance.

• Journal of Biosystems Engineering
• /
• v.23 no.3
• /
• pp.253-258
• /
• 1998

The part I was for developing regression models to predict the moisture content, protein content and viscosity of brown and milled rice using Near Infrared(NIR) Reflectance analyzer. The purpose of this study(part II) is to measure fundamental data required for the prediction of rice quality, and to develop regression models to predict the protein content of brown and milled rice, brown rice yield from undried paddy powder by using Near Infrared(NIR) Reflectance analyzer. The results of this study were summarized as follows : The predicted values of protein contents obtained from the undried paddy powder were well correlated to the measured values from brown and milled rice. The predicted yields of brown rice from undried paddy powder were not well correlated to the lab measured values from dried paddy. Continuous study in wavelength selection and of constituent relationship is necessary for practical application.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1998.06b
• /
• pp.171-177
• /
• 1998

The part Ⅰ was for developing regression models to predict the moisture content, protein content and viscosity of brown and milled rice using Near Unfrared (NIR) Reflectance analyzer. The purpose of this study(part Ⅱ) is to measure fundamental data required for the prediction of rice quality , and to develop regression models to predict the protein content of brown and milled rice, brown rice yield from undreid paddy powder by using Near Infrared (NIR) Reflectance analyzer. The results of this study were summarized as follows . The predicted values of protein contents obtained from the undried paddy powder were will correlated to the measured values from brown and milled rice. The predicted yields of brown rice from undried paddy powder were not well correlated to be lab measured values from dried paddy. Continuous study in wavelength selection and of constituent relationship is necessary for practical application.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.11
• /
• pp.98-105
• /
• 1999

As the IC(Integrated Circuit) has been densified and complicated, it is required to thorough process control to improve yield. Experts, for this purpose, focused on the process analysis automation, which is came from the strict data management in semiconductor manufacturing. In this paper, we presents the process analysis system that can analyze causes, for a output after processes. Also, the plasma etching process that highly affects yield among semiconductor process is modeled to predict a output before the process. To approach this problem, we use adaptively trained neural networks that exhibit superior accuracy over statistical techniques. And in comparison with methods in other paper, a method that history of trend for input data is considered is shown to offer advantage in both learning and prediction capability. This research regards CD(Critical Dimension) that is considerable in high integrated circuit as output variable of the prediction model.