기상 및 환경 센서 데이터 기반 생육 환경 최적화 연구
Optimization of Growth Environments Based on Meteorological and Environmental Sensor Data
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study aimed to analyze the environmental factors affecting tomato growth by examining the correlation between weather andgrowth environment sensor data from P Smart Farm located in Gwangseok-myeon, Nonsan-si, Chungcheongnam-do. Key environmentalvariables such as the temperature, humidity, sunlight hours, solar radiation, and daily light integral (DLI) significantly affecttomato growth. The optimal temperature and DLI conditions play crucial roles in enhancing tomato growth and the photosynthetic efficiency. In this study, we developed a model to correct and predict the time-series variations in internal environmental sensor data usingexternal weather sensor data. A linear regression analysis model was employed to estimate the external temperature variations and internalDLI values of P Smart Farm. Then, regression equations were derived based on these data. The analysis verified that the estimatedvariations in external temperature and internal DLI are explained effectively by the regression models. In this research, we analyzed andmonitored smart-farm growth environment data based on weather sensor data. Thereby, we obtained an optimized model for the temperatureand light conditions crucial for tomato growth. Additionally, the study emphasizes the importance of sensor-based data analysisin dynamically adjusting the tomato growth environment according to the variations in weather and growth conditions. The observationsof this study indicate that analytical solutions using public weather data can provide data-driven operational experiences and productivityimprovements for small- and medium-sized facility farms that cannot afford expensive sensors.
Abstract
This study aimed to analyze the environmental factors affecting tomato growth by examining the correlation between weather andgrowth environment sensor data from P Smart Farm located in Gwangseok-myeon, Nonsan-si, Chungcheongnam-do. Key environmentalvariables such as the temperature, humidity, sunlight hours, solar radiation, and daily light integral (DLI) significantly affecttomato growth. The optimal temperature and DLI conditions play crucial roles in enhancing tomato growth and the photosynthetic efficiency. In this study, we developed a model to correct and predict the time-series variations in internal environmental sensor data usingexternal weather sensor data. A linear regression analysis model was employed to estimate the external temperature variations and internalDLI values of P Smart Farm. Then, regression equations were derived based on these data. The analysis verified that the estimatedvariations in external temperature and internal DLI are explained effectively by the regression models. In this research, we analyzed andmonitored smart-farm growth environment data based on weather sensor data. Thereby, we obtained an optimized model for the temperatureand light conditions crucial for tomato growth. Additionally, the study emphasizes the importance of sensor-based data analysisin dynamically adjusting the tomato growth environment according to the variations in weather and growth conditions. The observationsof this study indicate that analytical solutions using public weather data can provide data-driven operational experiences and productivityimprovements for small- and medium-sized facility farms that cannot afford expensive sensors.
참고문헌 (14)
- G. van Straten, "Optimal Control of Greenhouse Cultivation", pp.1~87 (2011), CRC Press
- J. H. Min, "The optimal control technology on complex environment in horticulture based on artificial intelligence", Proc. of 2017 KIICE Conf., pp.756~759 (2017)
- J. Park, "Controlling photo-environment of Ginseng cultivation using agricultural weather Sensor Data", J. Sens. Sci. Technol, 31(3), pp.180~186 (2022)
- Rural Development Administration (RDA), "Smart green-house environment guidelines (2018)", RDA, ~ (2018)
- M. S. Farooq, "Role of IoT technology in agriculture : A systematic literature review", Electronics, 9(319), pp.319(1)~319(41) (2020)
- M. S. Kabir, "Environmental sensing and remote communication for smart farming : a review", Precis. Agric. Sci. Technol., 4(2), pp.81~96 (2022)
- O. Körner, "Design for an improved greenhouse climate control system in semi-arid regions", Comput. Electron. Agric., 84(1), pp.91~106 (2003)
- S. Ko, "A study on system design for tracking the optimal light compensation point of plants", J. Korean Inst. Illum. Electr. Install. Eng, 36(2), pp.1~7 (2022)
- T. Higashide, "Review of dry matter production and growth modelling to improve the yield of greenhouse tomatoes", Hort. J., 91(3), pp.247~266 (2022)
- Climate change 2021: The physical science basis. Summary for policymakers, "Working Group I", Intergovernmental Panel on Climate Change (IPCC), ~ (2021)
- X. Fan, "Response of Flavor Substances in Tomato Fruit to Light Spectrum and Daily Light Integral", Plants, 12(15), pp.2832(1)~2832(16) (2023)
- Y. -H. Kim, "Comparison of Growth and fruiting characteristics between cultivars for the selection of appropriate domestic cultivars when cultivating paprika in high-temperature periods", Hortic. Sci. Technol, 41(6), pp.674~685 (2023)
- Y. Niu, "Decision method for greenhouse tomato light regulation based on the concavity of photosynthesis response", Comput. Electron. Agric., 222, pp.109088~ (2024)