• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.53 no.3
• /
• pp.297-302
• /
• 2008

Application of genotype by environment ($G\;{\times}\;E$) interaction would be used for identifying optimum test condition of the varietal adaptation in the establishment of breeding purpose. Yield and yield components were used to perform additive main effect and multiplicative interaction (AMMI) analysis. Significant difference for $G\;{\times}\;E$ interaction were observed for all variable examined. For yield, 0.18 of total sum of squares corresponded to $G\;{\times}\;E$ interaction. Correlation analysis was carried out between genotypic scores of the first interaction principal component axis (IPCA 1) for agronomic characters. Significant correlations were observed between IPCA 1 for yield and capsule bearing stem length (CBSL), number of capsule per plant (NOC). The biplot of grain yield means for IPCA1 which accounted for 34% of the variation in total treatment sums of squares showed different reaction according to $G\;{\times}\;E$ interaction, genotypes and environments. Taegu showed relatively lower positive IPCA1 scores, and it also showed smaller coefficient variation of yield mean where it is recommendable as a optimal site for the sesame cultivar adaptation and evaluation trial. In case of variables, Yangbaek and M1 showed relatively lower IPCA1 scores, but the score direction showed opposite each other on the graph. Ansan, Miryang1, Miryang4, and Miryang6 seemed to be similar group in view of yield response against IPCA1 scores. These results will be helpful to select experimental site for sesame in Korea to minimize $G\;{\times}\;E$ interaction for the selection of promising genotype with higher stability.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.88-88
• /
• 2022

Detection of stress responses in crops is important to diagnose crop growth and evaluate yield. Also, the multi-spectral sensor is effectively known to evaluate stress caused by nutrient and moisture in crops or biological agents such as weeds or diseases. Therefore, in this experiment, multispectral images were taken by an unmanned aerial vehicle(UAV) under field condition. The experiment was conducted in the long-term fertilizer field in the National Institute of Crop Science, and experiment area was divided into different status of NPK(Control, N-deficiency, P-deficiency, K-deficiency, Non-fertilizer). Total 11 vegetation indices were created with RGB and NIR reflectance values using python. Variations in nutrient content in plants affect the amount of light reflected or absorbed for each wavelength band. Therefore, the objective of this experiment was to evaluate vegetation indices derived from multispectral reflectance data as input into machine learning algorithm for the classification of nutritional deficiency in rice. RandomForest model was used as a representative ensemble model, and parameters were adjusted through hyperparameter tuning such as RandomSearchCV. As a result, training accuracy was 0.95 and test accuracy was 0.80, and IPCA, NDRE, and EVI were included in the top three indices for feature importance. Also, precision, recall, and f1-score, which are indicators for evaluating the performance of the classification model, showed a distribution of 0.7-0.9 for each class.