• Journal of Korean Society of Rural Planning
• /
• v.28 no.4
• /
• pp.105-117
• /
• 2022

This study tested SVM(support vector machine), RF(random forest), and ANN(artificial neural network) machine-learning models that can predict net irrigation water requirements in paddy fields. For the Jeonju and Jeongeup meteorological stations, the net irrigation water requirement was calculated using K-HAS from 1981 to 2021 and set as the label. For each algorithm, twelve models were constructed based on cumulative precipitation, precipitation, crop evapotranspiration, and month. Compared to the CE model, the R² of the CEP model was higher, and MAE, RMSE, and MSE were lower. Comprehensively considering learning performance and learning time, it is judged that the RF algorithm has the best usability and predictive power of five-days is better than three-days. The results of this study are expected to provide the scientific information necessary for the decision-making of on-site water managers is expected to be possible through the connection with weather forecast data. In the future, if the actual amount of irrigation and supply are measured, it is necessary to develop a learning model that reflects this.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11b
• /
• pp.262-269
• /
• 2000

One of the way of the preserving environment is the circulation of materials. Japan's cereal food self-sufficiency rate is less than 30%. Japan imports more than 30 million tons of food every year. Japanese are afraid of international food trade giving damages to environment. Advanced farm mechanization integrated with precision farming is an answer to solve these problems. Crop scientists, soil scientists and agricultural engineers at Kyoto University cooperate together in studying precision agriculture for paddy rice since 1996. Automatic follow-up combine and autonomous vehicle have been developed. Remotely sensing by using machine vision has been studied to measure nitrogen contents. Field map i.e. soil, growth and yield, in paddy field of 0.5 ha has been made. In this report the concept and objectives of advanced farm mechanization and precision agriculture research at Kyoto University are introduced.

• Journal of Biosystems Engineering
• /
• v.25 no.2
• /
• pp.79-88
• /
• 2000

Effects on tractive performance of design parameters of cage wheel as a traction aid to driving tires of tractor in wet paddy field were investigated experimentally. an experimental cage wheel was designed so that the design parameters such as wheel diameter, wheel width, lug pitch and lug angle could be varied during traction test, The traction test was conducted in two different types of wet paddy field ; shallow and deep harpan fields . Experimental results showed that tractive performance is affected by both soil conditions and the design parameters. A considerable improvement on the tractive performance was obtained by using a cage wheel with 45$^{\circ}$ lug angle in shallow hardpan and smaller lug pitch in deep hardpan. The diameter of cage wheel was mostly influential to the tractive performance both in shallow and deep hardpans.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2005.10a
• /
• pp.61-67
• /
• 2005

Agricultural water for rice growing is the important factor of water resources in Korea. so, it is imperative to know the practice of water management in paddy field. The experimental site has been operated in order to investigate water management practice and water supply discharge since 2001. There are 8 irrigation areas which are observed the water supply discharge in this site. We have investigate the water management practice in this site and we know that the practical date of rice growing stages and the date for calculating the water demand in paddy field. So, There is much differences between the calculated water demand and practical water supply. We could reduce the differences by calculating the water demand using the practical date of rice growing stages.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.42
• /
• pp.1-8
• /
• 2000

To examine the irrigation water uses in Sunjin river basin, existing status and operation records of headworks facilities including reservoirs, pumping stations, tube wells, and diversion dams were surveyed and analyzed for the period of 1994∼1998. Daily irrigation demand and water use were estimated for the irrigated paddy field using penman equation, Thank model, reservoir water balance model and daily pumping rate of pumping stations. Irrigation water use from multi-purpose dams in the basin was not included in this study.

• Journal of Biosystems Engineering
• /
• v.36 no.3
• /
• pp.163-170
• /
• 2011

Analysis of load on major parts of the tractor power drive line is critical for efficient and optimum design of a tractor. The purpose of this study was to evaluate severeness of the tractor PTO driving axle during rotary tillage operation. First, S-N (stress vs. number of cycle) curve of a PTO driving gear was obtained through the fatigue life test using a PTO dynamometer. Second, PTO severeness was evaluated during rotary tillage operation. Torque measurement system was constructed with strain-gauge sensors to measure torque of a PTO axle, an I/O interface to acquire the sensor signals, and an embedded system to calculate severeness. The severeness of PTO was analyzed using measured torque data during rotary tillage. In the PTO gear life fatigue test, breakage time and bending stress of the gear were measured by tooth widths and torque change during the fatigue life test. The S-N curve showed a good linear relationship between bending stress and number of cycle (life) with a coefficient of determination of 0.97. For PTO severenss evaluation, rotary tillage operations were conducted at two PTO rotational speeds (level-1, level-2) under different paddy and upland field sites with different soil conditions. Results of averaged relative severeness for PTO level-1 and PTO level-2 were 1.96 and 3.34, respectively, at paddy field sites, and they were 1.36 and 2.51, respectively, at upland field sites. The results showed that the PTO driving axle experienced more severe load during rotary tillage at paddy fields than at upland sites, and relative severeness was greater at the higher PTO rotational speed under all of the soil conditions.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.553-563
• /
• 2006

This study aims to produce land-cover maps of Korean peninsula using multi-temporal MODIS (Moderate Resolution Imaging Spectroradiometer) imagery. To solve the low spatial resolution of MODIS data and enhance classification accuracy, Linear Spectral Mixture Analysis (LSMA) was employed. LSMA allowed to determine the fraction of each surface type in a pixel and develop vegetation, soil and water fraction images. To eliminate clouds, MVC (Maximum Value Composite) was utilized for vegetation fraction and MinVC (Minimum Value Composite) for soil fraction image respectively. With these images, using ISODATA unsupervised classifier, southern part of Korean peninsula was classified to low and mid level land-cover classes. The results showed that vegetation and soil fraction images reflected phenological characteristics of Korean peninsula. Paddy fields and forest could be easily detected in spring and summer data of the entire peninsula and arable land in North Korea. Secondly, in low level land-cover classification, overall accuracy was 79.94% and Kappa value was 0.70. Classification accuracy of forest (88.12%) and paddy field (85.45%) was higher than that of barren land (60.71%) and grassland (57.14%). In midlevel classification, forest class was sub-divided into deciduous and conifers and field class was sub-divided into paddy and field classes. In mid level, overall accuracy was 82.02% and Kappa value was 0.6986. Classification accuracy of deciduous (86.96%) and paddy (85.38%) were higher than that of conifers (62.50%) and field (77.08%).

• Korean Journal of Environmental Biology
• /
• v.41 no.4
• /
• pp.463-472
• /
• 2023

The insecticidal activities of 27 different commercial products with environmentally friendly organic material(EFOM) against Scotinophara lurida, a major rice pest, were evaluated in the laboratory using spraying methods on plants and insects. Seven plant-derived organic farming materials (EFOM-8, -10, -12, -13, -19, -20, and -26) with high insecticidal effects when sprayed directly on the insect's body rather than on the plant were selected. In the indoor rice pot test, all 7 EFOMs showed an insecticidal rate of over 73.3% under flooding conditions. Notably, EFOM-13 and EFOM-20 demonstrated much higher insecticidal rates, ranging from 1.5 to 1.8 times, in flooding conditions compared to drained conditions. In the semi-paddy field test, EFOM-10 (80% garlic extract), EFOM-13 (62% neem extract), and EFOM-26 (70% sophora extract+28% ethyl alcohol+2% pyrethrum extract) exhibited a higher control value of 88.9% in the irrigated paddy on the 7th day, surpassing the control values in the drained paddy by 1.4 to 1.9 times. The control value in the irrigated rice paddy field sprayed with EFOM-10 reached 86.2% on the 7th day, which was 1.4 times higher than 61.9% in the drained paddy. Taken together, the findings suggest that direct contact of the insect's body with sufficient amounts of spray solution and the maintenance of paddy irrigation can enhance the controlling effect of EFOMs. These findings will be valuable in developing an optimal S. lurida control strategy for application in rice paddy fields in the near future.

• Environmental Engineering Research
• /
• v.15 no.2
• /
• pp.123-126
• /
• 2010

Modeling non-point pollution across multiple scales has become an important environmental issue. As a more representative and practical approach in quantifying and qualifying surface water, a modular neural network (MNN) was implemented in this study. Two different site-scales ($1.5\;{\times}\;10^5$ and $1.62\;{\times}\;10^6\;m^2$) with the same plants, soils, and paddy field management practices, were selected. Hydrologic data (rainfall, irrigation and surface discharge) and water quality data (time-series nutrient loadings) were continuously monitored and then used for the verification of MNN performance. Correlation coefficients (R) for the results predicted from the networks versus measured values were within the range of 0.41 to 0.95. The small block could be extrapolated to the large field for the rainfall-surface drainage process. Nutrient prediction produced less favorable results due to the complex phenomena of nutrients in the drainage water. However, the feasibility of using MNN to generate improved prediction accuracy was demonstrated if more hydrologic and environmental data are provided. The study findings confirmed the estimation accuracy of the upscaling from a small-segment block to large-scale paddy field, thereby contributing to the establishment of water quality management for sustainable agriculture.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 1999.10c
• /
• pp.371-374
• /
• 1999

Mountain agricultural land should become to the land use considering natural environmental conditions with characteristics of natural suitability . In this study , an evaluation of natural suitability was done for Pyongchang-gun , Kangwon-Do which has a lot of mountain agricultural lands using GIS according to the kind of land use (paddy, field, ordinary upland field, grassland, orchard land, forest).