• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2000.05a
• /
• pp.26-33
• /
• 2000

This study was conducted to investigate the relationships between yearly variations of elimatic elements and yearly variations of productivity in potato. In addition, correlation coefficients among yield and yield components were estimated. The data of yield and yield components were investigated for 9 years from 1987 to 1995. The meteorological data what gathered at the Goheung Weather Station for the same period of crop growing season were used to find out the relationships between climatic elements and crop productivity. Yearly variation of the daily minimum temperature in March and April were large with coefficients of variation (C.V.) of 126.0%, 368%, respectively, but the variation of the daily mean and maximum temperature in May and June were relative small. Stem length and number of stem show more C.V. of 9.3%, 14.3%, respectively, but the variation of the yield was relative small with 3.7%. Correlation coefficients between the amount of precipitation in April and yield, yield and daily mean temperature in June were negatively significant at the level of 5, 1 %, respectively. Correlation coefficients between the growth habits and yield are positively significant at the level of 5, 1 %, respectively. Simple linear regression equations by the least square method are estimated for stem length (Yl) and the precipitation in April(X) as Y,=82.47-0.11x (R2=0.3959), and for yield(Y2) and the precipitation in April(X) as Y,=2003.61-0.94X (R2=0.5418).

• 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.

• Proceedings of the KSME Conference
• /
• 2007.05b
• /
• pp.2333-2337
• /
• 2007

The practical studies on the method of particle contamination control for yield enhancement in the cleanroom were carried out. The method of the contamination control was considered, which is composed of data collection, data analysis, improvement action, verification, and implement control. The composition analysis for data collection and data analysis was used in the cellular phone module packaging lines. And this method was evaluated by the variation of yield loss between before and after improvement action. In case that the composition analysis was applied, the critical sources were selected and yield loss reduction through improvement actions was also investigated. From these results, it is concluded that the composition analysis is effective solutions for particle contamination control in the cleanroom.

• Proceedings of the KSME Conference
• /
• 2007.05b
• /
• pp.2338-2343
• /
• 2007

The practical studies on the method of particle contamination control for yield enhancement in the cleanroom were carried out. The method of the contamination control was proposed, which are composed of data collection, data analysis, improvement action, verification, and implement control. The partition check method for data collection and data analysis was used in the cellular phone module production lines. And this method was evaluated by the variation of yield loss between before and after improvement action. In case that the partition check method was applied, the critical process step was selected and yield loss reduction through improvement actions was observed. From these results, it is concluded that the partition check method is effective solution for particle contamination control in the cleanroom production lines.

• Plant Resources
• /
• v.6 no.3
• /
• pp.178-182
• /
• 2003

This study was conducted to investigate the relationship between yearly variations of climatic elements and yearly variations of productivity in perilla. In addition, correlation coefficients among yield and yield components were estimated. The data of yield and yield components were investigated for 10 years from 1991 to 2000. The meteorological data gathered at the Yeosu Weather Station for the same period were used to find out the relationships between climatic elements and productivity. Yearly variation of the amount of precipitation in September was large with coefficients of variation(c. v.) of 11.1%, but the coefficient of variance(c. v.) in July and August were relative small with 1.8, 2.1%, respectively. Number of cluster per hill and weight of 1,000 grains were greatly with c. v. of 76.1, 79.3%, respectively, but the coefficients of variance(c. v.) of plant height and seed yield were more less with 9.58, 10.60%, respectively. Correlation coefficients between precipitation of September and seed yield were positively significant correlation at the level of 5.1%, respectively, but the duration of sunshine in September and seed yield were negatively significant at the level of 5.1%, respectively. Correlation coefficients of these, the plant height, number of branches per plant, cluster length, number of cluster per hill, weight of 1,000 grains and seed yield were positively significant at the level of 5.1% respectively.

• Journal of the Korean Society of Tobacco Science
• /
• v.3 no.2
• /
• pp.115-122
• /
• 1981

Data for this study were obtained from Burley 21 (Nicotiana tabacum L.) grown under various densities on the field in 1978 and 1979 at the Jeonju Experiment Station, Korea Ginseng & Tobacco Research Institute. Interrelations between yield and its components were statistically studied by correlation, regression, and pathway analysis. Correlation of yield with plant population was significant and positive. Quadratic functions for yield vs. plant population and the length of the largest leaf were fitted to the data. Multiple recession equation between yield and its components (leaf number ($X_1$), a leaf area ($X_5$), weight per unit leaf area ($X_9$), plant population ($X_14$)), was significant at the 5% level. Measuring the relative importance of its components on yield, plant population was 49.5%, weight per unit leaf area 25.3%, a leaf 15.6%, and leaf number 9.8%.

• Journal of Biosystems Engineering
• /
• v.24 no.2
• /
• pp.135-144
• /
• 1999

An yield monitoring system plays a key role in precision farming. An yield monitoring system and a DGPS were implemented to a widely used domestic combine for yield mapping of a small sized paddy field, and yield mapping algorithms were investigated in this study. The yield variation in the 0.1ha rice paddy field was measured by installing a yield flow sensor and a grain moisture sensor at the end of the clean grain elevator discharging grains into a grain tank. Yield map of the test filed was drawn in a point map and a linear interpolated map based on the result of the field test. The size of a unit yield grid in yield mapping was determined based on the combine traveling speed, effective harvesting width and data storing period. It was possible to construct the yield map of a small sized paddy field.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.199-209
• /
• 2021

By removing the increasing trend that long-term time series average of rice yield due to technological advancement of rice variety and cultivation management, we tried to improve the rice yield estimation model which developed earlier using MODIS NDVI and meteorological data. A multiple linear regression analysis was carried out by using the NDVI derived from MYD13Q1 and weather data from 2002 to 2019. The model was improved by analyzing the increasing trend of rime-series rice yield and removing it. After detrending, the accuracy of the model was evaluated through the correlation analysis between the estimated rice yield and the yield statistics using the improved model. It was found that the rice yield predicted by the improved model from which the trend was removed showed good agreement with the annual change of yield statistics. Compared with the model before the trend removal, the correlation coefficient and the coefficient of determination were also higher. It was indicated that the trend removal method effectively corrects the rice yield estimation model.

• Advances in nano research
• /
• v.14 no.3
• /
• pp.225-234
• /
• 2023

In this study, we aim to use big data resources and statistical analysis to obtain a reliable instruction to reach high-quality and high yield agricultural yields. In this regard, soil type data, raining and temperature data as well as wheat production in each year are collected for a specific region. Using statistical methodology, the acquired data was cleaned to remove incomplete and defective data. Afterwards, using several classification methods in machine learning we tried to distinguish between different factors and their influence on the final crop yields. Comparing the proposed models' prediction using statistical quantities correlation factor and mean squared error between predicted values of the crop yield and actual values the efficacy of machine learning methods is discussed. The results of the analysis show high accuracy of machine learning methods in the prediction of the crop yields. Moreover, it is indicated that the random forest (RF) classification approach provides best results among other classification methods utilized in this study.

• Plant Resources
• /
• v.6 no.3
• /
• pp.159-164
• /
• 2003

This study was conducted to investigate the relationship between yearly variations of climatic elements and yearly variations of productivity in malting barley. In addition, correlation coefficients among yield and yield components were estimated. The data of yield and yield components were investigated for 10 years from 1991 to 2000. The meteorological data gathered at the Yeosu Weather Station for the same period were used to find out the relationships between climatic elements and productivity. Yearly varation of the amount of precipitation in December and January were large with coefficients of variation(c. v.) of 97.9, 51.3%, respectively, but the variation of the maximum temperature and minimum temperature in April were relative small. Yield, weight of 1,000 grains and culm length were greatly with c. v. of 37.3, 49.3 and 41.3%, respectively. spike length and number of spikes show more or less c. v. of 3.8, 24.7% respectively and number of grains per spike show still less variation with c. v. of 9.4%. Correlation coefficients between temperature of mean, maximum and minimum in February and seed yield and yield components were positively significant at level of 5.1%, respectively. Correlation coefficients between precipitation of April and seed yield were positively significant correlation at the level of 5.1 %, respectively, but the duration of sunshine in April and seed yield were negatively significant at the level of 5.1%, respectively. Correlation coefficients of those, yield components and yield, culm length, spike length, number of grains per spike, number of spikes per $m^2$, weight of 1,000 grains and seed yield were positively significant at the level of 5.1 % respectively.