• Journal of Bio-Environment Control
• /
• v.28 no.4
• /
• pp.420-428
• /
• 2019

This study is the heating energy saving test of the high-bed strawberry crown heating system. The system consists of electric hot water boiler, thermal storage tank, circulation pump, crown heating pipe(white low density polyethylene, diameter 16mm) and a temperature control panel. For crown heating, the hot water pipe was installed as close as possible to the crown part after planting the seedlings and the pipe position was fixed with a horticultural fixing pin. In the local heating type, hot water at $20{\sim}23^{\circ}C$ is stored in the themal tank by using an electric hot water boiler, and crown spot is partially heated at the setting temperature of $13{\sim}15^{\circ}C$ by turning on/off the circulation pump using a temperature sensor for controlling the hot water circulation pump which was installed at the very close to crown of strawberry. The treatment of test zone consisted of space heating $4^{\circ}C$ + crown heating(treatment 1), space heating $8^{\circ}C$(control), space heating $6^{\circ}C$ + crown heating(treatment 2). And strawberries were planted in the number of 980 for each treatment. The heating energy consumption was compared between November 8, 2017 and March 30, 2018. Accumulated power consumption is converted to integrated kerosene consumption. The converted kerosene consumption is 1,320L(100%) for space $8^{\circ}C$ heating, 928L(70.3%) for space $4^{\circ}C$ + crown heating, 1,161L($88^{\circ}C$) for space $6^{\circ}C$ + crown heating). It was analyzed that space $4^{\circ}C$ + pipe heating and space $6^{\circ}C$ + crown heating save heating energy of 29.7% and 12% respectively compared to $8^{\circ}C$ space heating(control).

• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.697-723
• /
• 2022

Data-driven models to predict groundwater levels 30 days in advance were developed for 12 groundwater monitoring stations in the middle-Jeju watershed, Jeju Island. Stacked long short-term memory (stacked-LSTM), a deep learning technique suitable for time series forecasting, was used for model development. Daily time series data from 2001 to 2022 for precipitation, groundwater usage amount, and groundwater level were considered. Various models were proposed that used different combinations of the input data types and varying lengths of previous time series data for each input variable. A general procedure for deep-learning-based model development is suggested based on consideration of the comparative validation results of the tested models. A model using precipitation, groundwater usage amount, and previous groundwater level data as input variables outperformed any model neglecting one or more of these data categories. Using extended sequences of these past data improved the predictions, possibly owing to the long delay time between precipitation and groundwater recharge, which results from the deep groundwater level in Jeju Island. However, limiting the range of considered groundwater usage data that significantly affected the groundwater level fluctuation (rather than using all the groundwater usage data) improved the performance of the predictive model. The developed models can predict the future groundwater level based on the current amount of precipitation and groundwater use. Therefore, the models provide information on the soundness of the aquifer system, which will help to prepare management plans to maintain appropriate groundwater quantities.