A linear regression machine learning model to estimate the baseline evapotranspiration based on temperature data for South Korea is developed in this study. FAO56 Penman–Monteith (FAO56 P–M) reference evapotranspiration calculated with meteorological data (1981–2021) obtained from sixty-two meteorological stations nationwide is used as the label. All study datasets provide daily, monthly, or annual values based on the average temperature, daily temperature difference, and extraterrestrial radiation. Multiple linear regression (MLR) and polynomial regression (PR) are applied as machine learning algorithms, and twelve models are tested using the training data. The results of the performance evaluation of the period from 2017 to 2021 show that the polynomial regression algorithm that learns the amount of extraterrestrial radiation achieves the best performance (the minimum root-mean-square errors of 0.72 mm/day, 11.3 mm/month, and 40.5 mm/year for daily, monthly, and annual scale, respectively). Compared to temperature-based empirical equations, such as Hargreaves, Blaney–Criddle, and Thornthwaite, the model trained using the polynomial regression algorithm achieves the highest coefficient of determination and lowest error with the reference evapotranspiration of the FAO56 Penman–Monteith equation when using all meteorological data. Thus, the proposed method is more effective than the empirical equations under the condition of insufficient meteorological data when estimating reference evapotranspiration.
This study was conducted to investigate awareness and needs for care farming in South Korea. A questionnaire that includes 20 questions was developed for this study. The survey was answered by the 1,302 respondents who lived in the six cities such as Seoul, Incheon, Daejeon, Daegu, Ulsan, and Gwangju in the period of October 2016. The respondents who were aged over 20 years were recruited by a convenience sampling method. As the results, 50.4% and 40.1% of the respondents reported 'Know nothing' and 'Know of care farming', respectively. The experience for participating in care farming was low (29.0%). The purposes of participating in care farming reported as experience (31.4%), leisure (25.0%), and education (21.0%). Frequency of visiting for care farming complex was daily (44.3%) and 1 night 2days-3nights 4days (32.9%). Moreover, 67.7% of potential consumers had intention of paying the care farming fee. The acceptable fee reported as an average 11,339 won per day. In addition, needs for care farming complex was very high in the respondents with or without disease. The present study is anticipated to support the needs for care farming complex and provides reference data for administers in care farming.
The purpose of this study is to analyze the possible relationship between industrial structure and economic development in rural areas in South Korea. Accordingly, this study uses the Herfindahl–Hirschman Index and a two-step cluster analysis method to conduct an empirical analysis of the rural areas of Chungcheongbuk-do as the research object. The results show that among the 11 regions with concentrated industrial structures, the cluster results of 2 regions changed from the decentralized low employment cluster in 2010 to a concentrated high employment cluster in 2015, while the cluster results of other regions remained unchanged. Among the 18 regions with decentralized industrial structure, the cluster results of 5 regions changed from the concentrated high employment cluster in 2010 to the decentralized low employment cluster. Meanwhile, the cluster results of three regions changed from the decentralized low employment cluster in 2010 to the concentrated high employment cluster in 2015, while the cluster results of other regions remained unchanged. Based on this, it can be concluded that, for general rural areas, a low level of industrial diversification, that is, a concentrated industrial structure, is more conducive to promoting the economic development of rural areas. However, there is a special case, namely that rural areas with certain specific advantages, a high level of industrial diversification, or a decentralized industrial structure are more conducive to the development of the regional economy.
Storage rate forecasting for the agricultural reservoir is helpful for preemptive responses to disasters such as agricultural drought and planning so as to maintain a stable agricultural water supply. In this study, SVM, RF, and ANN machine learning algorithms were tested to forecast the monthly storage rate of agricultural reservoirs. The storage rate observed over 30 years (1991–2022) was set as a label, and nine datasets for a one- to three-month storage rate forecast were constructed using precipitation and evapotranspiration as features. In all, 70% of the total data was used for training and validation, and the remaining 30% was used as a test. The one-month storage rate forecasting showed that all SVM, RF, and ANN algorithms were highly reliable, with R2 values ≥ 0.8. As a result of the storage rate forecast for two and three months, the ANN and SVM algorithms showed relatively reasonable explanatory power with an average R2 of 0.64 to 0.69, but the RF algorithm showed a large generalization error. The results of comparing the learning time showed that the learning speed was the fastest in the order of SVM, RF, and ANN algorithms in all of the one to three months. Overall, the learning performance of SVM and ANN algorithms was better than RF. The SVM algorithm is the most credible, with the lowest error rates and the shortest training time. The results of this study are expected to provide the scientific information necessary for the decision-making regarding on-site water managers, which is expected to be possible through the connection with weather forecast data.