• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.66 no.2
• /
• pp.105-111
• /
• 2021

Rice lodging is an annual occurrence caused by typhoons accompanied by strong winds and strong rainfall, resulting in damage relating to pre-harvest sprouting during the ripening period. Thus, rapid estimations of the area of lodged rice are necessary to enable timely responses to damage. To this end, we obtained images related to rice lodging using a drone in Gimje, Buan, and Gunsan, which were converted to 128 × 128 pixels images. A convolutional neural network (CNN) model, a deep learning model based on these images, was used to predict rice lodging, which was classified into two types (lodging and non-lodging), and the images were divided in a 8:2 ratio into a training set and a validation set. The CNN model was layered and trained using three optimizers (Adam, Rmsprop, and SGD). The area of rice lodging was evaluated for the three fields using the obtained data, with the exception of the training set and validation set. The images were combined to give composites images of the entire fields using Metashape, and these images were divided into 128 × 128 pixels. Lodging in the divided images was predicted using the trained CNN model, and the extent of lodging was calculated by multiplying the ratio of the total number of field images by the number of lodging images by the area of the entire field. The results for the training and validation sets showed that accuracy increased with a progression in learning and eventually reached a level greater than 0.919. The results obtained for each of the three fields showed high accuracy with respect to all optimizers, among which, Adam showed the highest accuracy (normalized root mean square error: 2.73%). On the basis of the findings of this study, it is anticipated that the area of lodged rice can be rapidly predicted using deep learning.

• Journal of the Korea Institute of Building Construction
• /
• v.20 no.1
• /
• pp.83-91
• /
• 2020

The recent bridge construction projects is demanded more sophisticated risk management measures and loss forecasts to brace for risk losses from an increase in the trend of bridge construction. This study aims to analyze the risk factors that caused the loss of material in actual bridge construction and to develop a quantified predictive loss model, based on the past record of insurance payment by major domestic insurance companies for bridge construction projects. For the development of quantitative bridge construction loss model, the dependent variable was selected as the loss ratio, i.e., the ratio of insurance payout divided by the total project cost, while the independent variable adopted 1) Technical factors: superstructure type, foundation type, construction method, and bridge length 2) Natural hazards: typhoon and flood 3) Project information: construction period and total project cost. Among the selected independent variables, superstructure type, construction method, and project period were shown to affect the ratio of bridge construction losses. The results of this study can provide government agencies, bridge construction design and construction and insurance companies with the quantitative damage prediction and risk assessment services, using risk indicators and loss prediction functions derived from the findings of this study and can be used as a guideline for future basic bridge risk assessment development research.