• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.1
• /
• pp.21-29
• /
• 2021

The emerging smart world based on IoT requires deployment of a large number of diverse sensors to generate data pertaining to different applications. Recent years have witnessed a plethora of IoT solutions beneficial to various application domains, IoT techniques also help boost agricultural productivity by increasing crop yields and reducing losses. This paper presents a predictive IoT smart farm platform for forcast services. We built an online agricultural forecasting service that collects microclimate data from weather stations in real-time. To demonstrate effectiveness of our proposed system, we designed a frost and pest forecasting modes on the microclimate data collected from weather stations, notifies the possibilities of frost, and sends pest forecast messages to farmers using push services so that they can protect crops against damages. It is expected to provide effectively that more precise climate forecasts thus could potentially precision agricultural services to reduce crop damages and unnecessary costs, such as the use of non-essential pesticides.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.295-305
• /
• 2021

In this study, we constructed using Random Forest(RF) by selecting the meteorological factors related to the occurrence of frost. As a result, when constructing a classification model for frost occurrence, even if the amount of data set is large, the imbalance in the data set for development of model has been analyzed to have a bad effect on the predictive power of the model. It was found that building a single integrated model by grouping meteorological factors related to frost occurrence by region is more efficient than building each model reflecting high-importance meteorological factors. Based on our results, it is expected that a high-accuracy frost occurrence prediction model will be able to be constructed as further studies meteorological factors for frost prediction.

• Journal of Korea Water Resources Association
• /
• v.54 no.9
• /
• pp.667-680
• /
• 2021

We investigated changes in frost days and frost-free periods and to comparatively assess frost event prediction models developed using logistic regression (LR), random forest (RF), and long short-term memory (LSTM) networks. The meteorological variables for the model development were collected from the Suwon, Cheongju, and Gwangju stations for the period of 1973-2019 for spring (March - May) and fall (September - November). The developed models were then evaluated by Precision, Recall, and f-1 score and graphical evaluation methods such as AUC and reliability diagram. The results showed that significant decreases (significance level of 0.01) in the frequencies of frost days were at the three stations in both spring and fall. Overall, the evaluation metrics showed that the performance of RF was highest, while that of LSTM was lowest. Despite higher AUC values (above 0.9) were found at the three stations, reliability diagrams showed inconsistent reliability. A further study is suggested on the improvement of the predictability of both frost events and the first and last frost days by the frost event prediction models and reliability of the models. It would be beneficial to replicate this study at more stations in other regions.

• The Magazine of the Society of Air-Conditioning and Refrigerating Engineers of Korea
• /
• v.38 no.12
• /
• pp.51-60
• /
• 2009

본 연구에서는 착상 조건 하에서 열교환기 휜의 열전도를 고려하여 휜 표면에서의 착상 거동을 예측하기 위하여 수학적 모델을 제시한다. 이 때, 공기측은 착상 현상에 대한 3차원 유동 변화의 영향을 고려한다. 서리층 두께에 대한 해석 결과는 실험 결과를 최대 10% 오차 내에서 잘 예측한다. 유동에 수직한 방향(z-dir.)의 서리층 두께 성장은 휜의 열전도에 의해 휜 바탕 근처에서 활발하고, 휜 끝으로 갈수록 지수함수적으로 둔화된다. 휜의 열전도를 고려한 경우에 비해 휜의 표면온도가 일정한 조건에서 서리층 두께는 최대 2배, 열전달량은 평군 10% 정도 과대 예측한다. 따라서, 열교환기 휜에서의 착상 거동을 정확하게 예측하기 위해 착상 모델 해석 시 휜의 열전도를 고려해야 한다. 휜의 열전도 고려 유무에 따른 착상 거동의 차이를 보완하기 위해 열전달량에 대한 등가온도를 산출하며, 이를 근거로 무차원 등가 온도 상관식을 도출한다.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.26 no.1
• /
• pp.63-74
• /
• 2024

In agriculture, frost can be devastating, which is why observation and forecasting are so important. According to a recent report analyzing frost observation data from the Korea Meteorological Administration, despite global warming due to climate change, the late frost date in spring has not been accelerated, and the frequency of frost has not decreased. Therefore, it is important to automate and continuously operate frost observation in risk areas to prevent agricultural frost damage. In the existing frost observation using leaf wetness sensors, there is a problem that the reference voltage value fluctuates over a long period of time due to contamination of the observation sensor or changes in the humidity of the surrounding environment. In this study, a datalogger program was implemented to automatically solve these problems. The established frost observation system can stably and automatically accumulate time-resolved observation data over a long period of time. This data can be utilized in the future for the development of frost diagnosis models using machine learning methods and the production of frost occurrence prediction information for surrounding areas.

• Journal of the Korean earth science society
• /
• v.40 no.6
• /
• pp.606-612
• /
• 2019

In this study, to estimate the occurrence of frost that has a negative effect on th growth of crops, we constructed to the statistical model. We factored such various meteorological elements as the minimum temperature, temperature at 18:00, temperature at 21:00, temperature at 24:00, average wind speed, wind speed at 18:00, wind speed at 21:00, amount of cloud, amount of precipitation within 5 days, amount of precipitation within 3 days, relative humidity, dew point temperature, minimum grass temperature and ground temperature. Among the diverse variables, the several weather factors were selected for frost occurrence estimation model using statistical methods: T-test, Variable importance plot of Random Forest, Multicollinearity test, Akaike Informaiton Criteria, and Wilk's Lambda values. As a result, the selected meteorological factors were the amount of cloud, temperature at 24:00, dew point temperature, wind speed at 21:00. The accuracy of the frost occurrence estimation model using Random Forest was 70.6%. When it applied to the main production areas of vegetables, a estimation accuracy of the model was 65.2 and 78.6%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.10
• /
• pp.7138-7145
• /
• 2015

In this study, experiments were conducted to investigate the correspondence between the output voltage of the photoelectric sensor and the frost height under heating and defrosting capacity test condition (dry bulb temperature $2^{\circ}C$, wet bulb temperature $1^{\circ}C$) described at KS C 9306, where a real heat exchanger was used as a test rig instead of a large-scale model. A digital microscope and a photoelectric sensor unit consisting of an emitter and a transistor (receiver) were installed in the front of it. A linear correlation is proposed to predict the frost height based on 150 experimental data, approximately 54% of the measured data are consistent with the predicted frost heights within a relative deviation of ${\pm}10%$, it yields good agreement with 90% of the measured data when the frost height larger than 0.3mm with in a relative deviation of ${\pm}10%$. Compared with Xiao's correlation, the slope namely, the change of frost height in accordance with the change of output voltage is consistent within the error of 2.3%. But vertical intercept shows big difference with Xiao's correlation, because it was developed with a large scale model instead of a real heat exchanger.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.11 no.4
• /
• pp.135-142
• /
• 2009

In order to predict frostfall, nocturnal cooling rate and air temperature changes were analyzed on days with and without frost when the maximum temperature was lower than $20^{\circ}C$. In general, the nocturnal cooling rates on frosty days were higher than those on non-frosty days. The cooling rates averaged from 19:00 to 24:00 on frosty and non-frosty days were $1.7^{\circ}Ch^{-1}$ and $0.7^{\circ}Ch^{-1}$ respectively. As expected, the nocturnal temperature on frosty days was lower than that on non-frosty days. Especially, the midnight air temperature averaged about $3.9{\pm}1.5^{\circ}C$ on frosty days, which was lower than that on non-frosty days (i.e., $10.1{\pm}2.9^{\circ}C$). The discriminant analysis using three independent variables (i.e., total cloud amount, air temperature at 24:00, and 5-day rainfall amount) successfully classified the presence of frost with 87% accuracy.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.543-552
• /
• 2022

When frost occurs, crops are directly damaged. When crops come into contact with low temperatures, tissues freeze, which hardens and destroys the cell membranes or chloroplasts, or dry cells to death. In July 2020, a sudden sub-zero weather and frost hit the Minas Gerais state of Brazil, the world's largest coffee producer, damaging about 30% of local coffee trees. As a result, coffee prices have risen significantly due to the damage, and farmers with severe damage can produce coffee only after three years for crops to recover, which is expected to cause long-term damage. In this paper, we tried to predict frost using frost generation data and weather observation data provided by the Korea Meteorological Administration to prevent severe frost. A model was constructed by reflecting weather factors such as wind speed, temperature, humidity, precipitation, and cloudiness. Using XGB(eXtreme Gradient Boosting), SVM(Support Vector Machine), Random Forest, and MLP(Multi Layer perceptron) models, various hyper parameters were applied as training data to select the best model for each model. Finally, the results were evaluated as accuracy(acc) and CSI(Critical Success Index) in test data. XGB was the best model compared to other models with 90.4% ac and 64.4% CSI, followed by SVM with 89.7% ac and 61.2% CSI. Random Forest and MLP showed similar performance with about 89% ac and about 60% CSI.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.3
• /
• pp.226-235
• /
• 2023

This study aimed to supplement the shortcomings of the Multiple-sensor-based Frost Observation System (MFOS). The developed frost observation system is an improvement of the existing system. Based on the leaf wetness sensor (LWS), it not only detects frost but also functions to predict surface temperature, which is a major factor in frost occurrence. With the existing observation system, 1) it is difficult to observe ice (frost) formation on the surface when capturing an image of the LWS with an RGB camera because the surface of the sensor reflects most visible light, 2) images captured using the RGB camera before and after sunrise are dark, and 3) the thermal infrared camera only shows the relative high and low temperature. To identify the ice (frost) generated on the surface of the LWS, a LWS that was painted black and three sheets of glass at the same height to be used as an auxiliary tool to check the occurrence of ice (frost) were installed. For RGB camera shooting before and after sunrise, synchronous LED lighting was installed so the power turns on/off according to the camera shooting time. The existing thermal infrared camera, which could only assess the relative temperature (high or low), was improved to extract the temperature value per pixel, and a comparison with the surface temperature sensor installed by the National Institute of Meteorological Sciences (NIMS) was performed to verify its accuracy. As a result of installing and operating the MFOS v2, which reflects these improvements, the accuracy and efficiency of automatic frost observation were demonstrated to be improved, and the usefulness of the data as input data for the frost prediction model was enhanced.