• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1117-1132
• /
• 2019

Forest covers 30% of the Earth's land area and plays an important role in global carbon flux through its ability to store much greater amounts of carbon than other terrestrial ecosystems. The Gross Primary Production (GPP) represents the productivity of forest ecosystems according to climate change and its effect on the phenology, health, and carbon cycle. In this study, we estimated the daily GPP for a forest ecosystem using remote-sensed data from Moderate Resolution Imaging Spectroradiometer (MODIS) and machine learning algorithms Support Vector Machine (SVM). MODIS products were employed to train the SVM model from 75% to 80% data of the total study period and validated using eddy covariance measurement (EC) data at the six flux tower sites. We also compare the GPP derived from EC and MODIS (MYD17). The MODIS products made use of two data sets: one for Processed MODIS that included calculated by combined products (e.g., Vapor Pressure Deficit), another one for Unprocessed MODIS that used MODIS products without any combined calculation. Statistical analyses, including Pearson correlation coefficient (R), mean squared error (MSE), and root mean square error (RMSE) were used to evaluate the outcomes of the model. In general, the SVM model trained by the Unprocessed MODIS (R = 0.77 - 0.94, p < 0.001) derived from the multi-sites outperformed those trained at a single-site (R = 0.75 - 0.95, p < 0.001). These results show better performance trained by the data including various events and suggest the possibility of using remote-sensed data without complex processes to estimate GPP such as non-stationary ecological processes.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.29 no.4
• /
• pp.106-116
• /
• 1987

미국 Utah주의 huntington 화력발전소에서 냉각수를 사용하고 버리는 염분농도가 4mmhos/cm 정도로 높아 자연하천으로 그대로 방류 시킬 수 없으며, 미 환경법에 따라 안전처리후 방류할 수 있다. 따라서 이 염분발생 처리방법의 하나로 보리, 밀, 옥수수, 감자 그리고 알팔파등 사료작물의 관개용수로 이용할 수 있는 방법이 장기간 시험연구되고 있다. 현재로서는 이 방법이 경제적인 것으로 평가되고 있으나 장기적으로 이 염분폐수로 인한 토양의 성질변화 작용의 생산량 감소등에 미치는 영향을 구명하기 위해서 1977년에 시작하여 8년 연속 연구사업으로 진행되고 있다. 본 논문에서는 지난 8년간(1977~1984년)의 관측.조사자료를 이용하여 염분 관개용수가 장기적으로 생산량 추정과 계획예측을 위한 자발성과 토양수분변화를 추정할 수 있는 모형에 의하여 연구한 결과를 요약하면 다음과 같다. 1. EC 4mmhos/cm의 염분 관개용수로 8년간 장기간 추출한 결과, 추출용수의 양에 관계내 염분축적은 예상보다 서서히 진행되었으며, 이 염분축적이 작물의 생산량 감소의 주원인은 아니었다. 2. 지난 2년간의 관측 결과, 염분 관개용수에 함유된 10ppm정도의 요소가 작물 특히 보리, 옥수수, 감자등의 생산량 감소의 주원인 것으로 판단된다. 염분용수 진개구에는 하천수 보다 20배가 많은 요소가 축적돼 있었으며, 이는 요소가 토양내에 잘 침투되며, 토양으로 부터 요소를 용달시키려는 염분을 용달시킬 때 보다 후러씬 더 많은 용달용수를 필요로함을 뜻한 작물들의 면요소성을 구명하기위한 모형개발이 요구된다. 3. 염분관개용수로 관개할 때 보리, 옥수수, 감자등의 작물 생산량과 풍작물 생산량은 현저하게 감소하였다. 보리, 옥수수의 염분용수에 의한 생산량과 하천수에 의한 생산량과의 비는 풍건물의 경우 0.6, 매물의 경우 0.5였으며 감자의 경우는 0.2이하였다. 4. 염분용수 관개구와 하천수 관개구의 모든작물에서 풍건물 생산량과 축배량 사이에는 강한 직선적인 관계를 보였다. 보리, 감자의 작물 생산량과 축배량사이에도 선형의 관계가 성립되었으나, 밀과 옥수수의 매물 생산량과 축배량사이에는 곡선적인 관계를 나타내었다.

• Journal of Wetlands Research
• /
• v.15 no.1
• /
• pp.9-17
• /
• 2013

Scirpus planiculmis dominated in Nakdong river estuary is known as food for birds visiting to Nakdong river estuary and plays an important role in material cycle and food web, while repeating growth and production, decomposition process in 1-year interval. Therefore, if it is able to predict effectively biomass or tuber production of Scirpus planiculmis which is food source for estuarine organisms or birds, it can provide very useful information on the Nakdong river estuary management. In this study, regression equation that can predict the tuber production, food for birds, was obtained using initial density of Scirpus planiculmis that can minimize the disturbance of ecosystem and is faster and easier. The correlation analysis results show that density, biomass and tuber production have liner relationship(p<0.001) with 0.6103~0.9950 of correlation coefficients. In addition, the regression equations have high coefficients of determination of 0.3696~0.7145 and it shows that it is able to predict biomass or tuber production while using the estimated regression equation obtained from relationship among the initial density, biomass and tuber production. The results of this study are expected to utilize effectively the management of estuary ecosystem such as management on food source for migratory birds visiting to Nakdong river estuary.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.128-130
• /
• 2021

This study aims to implement a Regression Analysis system for predicting the appropriate production of flatfish. Due to Korea's signing of FTAs with countries around the world and accelerating market opening, Korean flatfish farming businesses are experiencing many difficulties due to the specificity and uncertainty of the environment. In addition, there is a need for a solution to problems such as sluggish consumption and price drop due to the recent surge in imported seafood such as salmon and yellowtail and changes in people's dietary habits. in this study, Using the python module, xlwings, it was used to obtain for the production amount of flatfish and to predict the amount of flatfish to be produced later. was used to predict the amount of flatfish to be produced in the future. Therefore, based on the analysis results of this prediction of flatfish production, the flatfish aquaculture industry will be able to come up with a plan to achieve an appropriate production volume and control supply and demand, which will reduce unnecessary economic loss and promote new value creation based on data. In addition, through the data approach attempted in this study, various analysis techniques such as artificial neural networks and multiple regression analysis can be used in future research in various fields, which will become the foundation of basic data that can effectively analyze and utilize big data in various industries.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.211-218
• /
• 2012

Fossil fuel is used all over the world and it produces greenhouse gases due to fossil fuel use. Therefore, it cause global warming and is serious environmental pollution. In order to decrease the environmental pollution, we should use renewable energy which is clean energy. Among several renewable energy, wind energy is the most promising one. Wind power generation is does not produce environmental pollution and could not be exhausted. However, due to wind power generation has irregular power output, it is important to predict generated electrical energy accurately for smoothing wind energy supply. There, we consider use ramp characteristic to forecast accurate wind power output. The ramp increase and decrease rapidly wind power generation during in a short time. Therefore, it can cause problem of unbalanced power supply and demand and get damaged wind turbine. In this paper, we make prediction models using power ramp rate as well as wind speed and wind direction to increase prediction accuracy. Prediction model construction algorithm used multilayer neural network. We built four prediction models with PRR, wind speed, and wind direction and then evaluated performance of prediction models. The predicted values, which is prediction model with all of attribute, is nearly to the observed values. Therefore, if we use PRR attribute, we can increase prediction accuracy of wind power generation.

• Journal of the Korean earth science society
• /
• v.40 no.6
• /
• pp.599-605
• /
• 2019

Rice yield (kg 10a^-1) in South Korea was estimated by meteorological variables that are influential factors in crop growth. This study investigated the possibility of anticipating the rice yield variability using a simple but an efficient statistical method, a multiple linear regression analysis, on the basis of the annual variation of meteorological variables. Due to heterogeneous environmental conditions by region, the yearly rice yield was assessed and validated for each province in South Korea. The monthly mean meteorological data for the period 1986-2018 (33 years) from 61 weather stations provided by Korean Meteorological Administration was used as the independent variable in the regression analysis. An 11-fold (leave-three-out) cross-validation was performed to check the accuracy of this method estimating rice yield at each province. This result demonstrated that temporal variation of rice yield by province in South Korea can be properly estimated using such concise procedure in terms of correlation coefficient (0.7, not significant). Furthermore, the estimated rice yield well captured spatial features of observation with mean bias of 0.7 kg 10a^-1 (0.15%). This method may offer useful information on rice yield by province in advance as long as accurate agro-meteorological forecasts are timely obtained from climate models.

• Journal of the Korean Institute of Gas
• /
• v.21 no.3
• /
• pp.61-69
• /
• 2017

The commercial development of unconventional gas is pursued in North America because it is more feasible owing to the technology required to improve productivity. Shale reservoir have low permeability and gas production can be carried out through cracks generated by hydraulic fracturing. The decline rate during the initial production period is high, but very low latter on, there are significant variations from the initial production behavior. Therefore, in the prediction of the production rate using deterministic decline curve analysis(DCA), it is not possible to consider the uncertainty in the production behavior. In this study, production rate of the Eagle Ford shale is predicted by Arps Hyperbolic and Modified SEPD. To minimize the uncertainty in predicting the Estimated Ultimate Recovery(EUR), Monte Carlo simulation is used to multi-wells analysis. Also, kernel density function is applied to determine probability distribution of decline curve factors without any assumption.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.419-427
• /
• 2021

Due to the effects of climate change and the reduction of the labor force due to COVID-19, the crop yield, harvest time, and cultivated area are rapidly changing every year. In order to respond flexibly to this situation, attempts to apply smart farm technology based on ICT (Information and Communication Technology) to individual farms are increasing. On the other hand, various stakeholders are trying to predict the yield of crops using artificial intelligence and IoT technology, but accurate prediction is difficult due to the lack of learning data. In this study, in order to overcome the data collection problem limited to a specific institution, a smart farmer service technology based on community mapping was developed in which farmers directly participate, input and share accurate data to predict production. In the process, analysis was performed on napa cabbage, which is a vegetable with a large price change compared to production.

• Journal of the Korean GEO-environmental Society
• /
• v.22 no.3
• /
• pp.15-29
• /
• 2021

The purpose of this study is to establish an ecosystem model that can predict ecosystem fluctuations in the Nakdong estuary, and use this model to calculate total primary production and respiration. AQUATOX model was used as the ecosystem model, and the model was calibrated and verified using the measured data. For the calibration of the model, chlorophyll-a data measured at the Nakdong estuary were used, and the model verification was performed using DO, TN, and TP data. In general, the total primary production and respiration volume vary greatly depending on the season, but the total primary production and respiration in the Nakdong estuary were greatly influenced by the amount of water discharged from Nakdong estuary bank. When the amount of effluent increased, photosynthesis could not be performed due to the loss of phytoplankton living in the lower area, and the total primary production amounted to zero, whereas the respiration increased sharply due to the inflow of organic substances contained in the effluent. The increase in the inflow water means the inflow of organic substances contained in the inflow water, and the organic substances are decomposed by oxidation, reducing dissolved oxygen. Compared with other countries' estuaries, the Nakdong estuary shows the lowest total primary production and because the respiration is larger than the total primary production, the dissolved oxygen is depleted by the oxidation of organic matter.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.389-392
• /
• 2012

에너지관리 지원 서비스는 공장 내에서 일어나는 전력발전 및 전력할당을 데어터 분석 기법 등을 이용하여 효과적으로 관리하는 것을 목적으로 한다. 특히 그 중에서도 태양광, 풍력 등 친환경 에너지를 이용한 에너지관리 시스템은 비용절감 뿐만 아니라 환경보호 측면에서도 중요한 문제라 할 수 있다. 이들 친환경 에너지를 제대로 이용하기 위해서는 그들의 발전량을 정확히 예측할 필요가 있지만 현재의 시스템에는 가장 기본적인 예측법인 최근접 이웃법을 사용하고 있다. 최근접 이웃법의 경우 노이즈와 아웃라이어에 민감하다는 단점이 있기 때문에 이들 상황에 대처할 수 있는 보다 정교한 예측법이 필요하다.