• Journal of Digital Convergence
• /
• v.18 no.4
• /
• pp.243-250
• /
• 2020

Systematic farming can be planned and managed if long-term agricultural weather information of the plantation is available. Because the greatest risk factor for crop cultivation is the weather. In this study, a method for long-term predicting of agricultural weather using the GloSea5 and machine learning is presented for the cultivation of Chinese cabbage. The GloSea5 is a long-term weather forecast that is available up to 240 days. The deep neural networks and the spatial randomforest were considered as the method of machine learning. The longterm prediction performance of the deep neural networks was slightly better than the spatial randomforest in the sense of root mean squared error and mean absolute error. However, the spatial randomforest has the advantage of predicting temperatures with a global model, which reduces the computation time.

• Journal of the Korean Society of Systems Engineering
• /
• v.16 no.1
• /
• pp.58-67
• /
• 2020

A big data processing method to predict solar power generation using systems engineering approach is developed in this work. For developing analytical method, linear model (LM), support vector machine (SVN), and artificial neural network (ANN) technique are chosen. As evaluation indices, the cross-correlation and the mean square root of prediction error (RMSEP) are used. From multi-variable comparison test, it was found that ANN methodology provides the highest correlation and the lowest RMSEP.

• 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.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.2
• /
• pp.53-69
• /
• 2020

The increase of the impermeable area due to industrialization and urban development distorts the hydrological circulation system and cause serious stream drying phenomena. In order to manage this, it is necessary to develop a technology for impact assessment of stream drying phenomena, which enables quantitative evaluation and prediction. In this study, the cause of streamflow reduction was assessed for dam and weir watersheds in the five major river basins of South Korea by using distributed hydrological model DrySAT-WFT (Drying Stream Assessment Tool and Water Flow Tracking) and GIS time series data. For the modeling, the 5 influencing factors of stream drying phenomena (soil erosion, forest growth, road-river disconnection, groundwater use, urban development) were selected and prepared as GIS-based time series spatial data from 1976 to 2015. The DrySAT-WFT was calibrated and validated from 2005 to 2015 at 8 multipurpose dam watershed (Chungju, Soyang, Andong, Imha, Hapcheon, Seomjin river, Juam, and Yongdam) and 4 gauging stations (Osucheon, Mihocheon, Maruek, and Chogang) respectively. The calibration results showed that the coefficient of determination (R²) was 0.76 in average (0.66 to 0.84) and the Nash-Sutcliffe model efficiency was 0.62 in average (0.52 to 0.72). Based on the 2010s (2006~2015) weather condition for the whole period, the streamflow impact was estimated by applying GIS data for each decade (1980s: 1976~1985, 1990s: 1986~1995, 2000s: 1996~2005, 2010s: 2006~2015). The results showed that the 2010s averaged-wet streamflow (Q95) showed decrease of 4.1~6.3%, the 2010s averaged-normal streamflow (Q185) showed decreased of 6.7~9.1% and the 2010s averaged-drought streamflow (Q355) showed decrease of 8.4~10.4% compared to 1980s streamflows respectively on the whole. During 1975~2015, the increase of groundwater use covered 40.5% contribution and the next was forest growth with 29.0% contribution among the 5 influencing factors.

• Korean Journal of Soil Science and Fertilizer
• /
• v.25 no.3
• /
• pp.231-241
• /
• 1992

To study the relationships between major micrometeorological elements and their influences on evapotranspiration(ET) in the canopy of two rice cultivars, Daecheongbyo and Samgangbyo, synoptic meteorological factors, micrometeorological elements and ET from the canopy and biomass production were observed at various growth stages in the paddy field of Suwon Weather Forcast Office in 1989. ET from the rice community was highly correlated with the following factors in order of pan evaporation>air temperature>leaf temperature>solar radiation>sunshine duration>difference in vapor pressure depicit(VPD)>water temperature. ET observed showed higher correlation with the evaporation from small pan than that from Class A pan. Varietal difference would be noted in the relationships between ET in Samgangbyo canopy and the evaporations observed from the pans, with which closer a correlation was found in Samgangbyo than in Daecheongbyo. The ratio of canopy ET to the evaporation from Class A pan was maintained over 1.0 through the growth stages with the maximum of 1.9 at the late August. The evaporation observed from Class A pan was amounted to 71.9% of that from small pan. ET was better correlated with solar radiation than with net radiation which reached about 66% of solar radiation. Maximum temperature showed higher correlation with ET than mean air temperature, and also wind speed of 1m above ground revealed positive correlation. The relative humidity, however, had no correlation with the exception of ET in rainy days. A regression model developed to estimate ET as a function of meteorological elements being described with $R^2$ of 0.607 as : $ET=-5.3594+0.7005Pan\;A+0.1926T_{mean}+0.0878_{sol}+0.025RH$.