• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.207-209
• /
• 2003

Quantifying crop production is one of the most important applications of remote sensing in which the temporal and up-to-date data can play very important role in avoiding any immediate insufficiency in agricultural production. A combination of climatic data and biophysical parameters derived from Landsat7 ETM+ was used to develop a mathematical model for wheat yield forecast in different geographically wide Wheat growing districts in Egypt. Leaf Area Index (LAI) and fraction of Absorbed Photosynthetically Active Radiation (fAPAR) with temperature were used in the modeling. The model includes three sub-models representing the correlation between the reported yield and each individual variable. Simulation results using district statistics showed high accuracy of the derived correlations to estimate wheat production with a percentage standard error (%S.E.) of 1.5% in El- Qualyobia district and average (%S.E.) of 7% for the whole wheat areas.

• International journal of advanced smart convergence
• /
• v.13 no.3
• /
• pp.335-344
• /
• 2024

This study explores advanced machine learning techniques for improving crop yield prediction in smart farming, utilizing multi-temporal spectral data from drone-based multispectral imagery. Conducted in garlic orchards in Andong, Gyeongbuk Province, South Korea, the research examines the effectiveness of various vegetation indices and cutting-edge models, including LSTM, CNN, Random Forest, and XGBoost. By integrating these models with the Analytic Hierarchy Process (AHP), the study systematically evaluates the factors that influence prediction accuracy. The integrated approach significantly outperforms single models, offering a more comprehensive and adaptable framework for yield prediction. This research contributes to precision agriculture by providing a robust, AI-driven methodology that enhances the sustainability and efficiency of farming practices.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.38 no.2
• /
• pp.97-107
• /
• 1996

This study was performed to derive the formula of sediment yield and predict the sediment elevation for fresh desalted reservoirs. Data analyzed was from 3 fresh desalted reservoirs of Sapkyo, Asan, and Namyang. Average sediment yield calculated from the sediment survey data was $279m^3/km^2/$ year for Sapkyo lake, $523m^3/km^2/$ year for Namyang lake, and $190m^3/km^2/$ year for Asan lake. The trap efficiency for Sapkyo lake was 63%. The formula of sediment yield was derived as $Q_s=6,461{\times}A{^-0.44}$ for fresh desalted reservoir. Sediment yield in fresh desalted reservoirs was much higher than that in inland reservoirs located in the same watershed, because of long trap time in fresh desalted reservoirs.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.13 no.1
• /
• pp.121-130
• /
• 1993

The major objective of this study is to develop practical methods for estimating sediment yield rates of medium size watersheds of which areas range from 200 to $2,000km^2$. For this purpose, this study adopts an empirical method of statistical approach and another empirical method of weighting the watershed characteristics factors. A total of 13 data points for sediment yield rate, including five data points from reservoir deposit data and eight data points from sampled river-sediment data have been collected. Meanwhile, seven factors that may affect the sediment yield rate of a watershed have been selected. They are drainage density, rainfall erosivity, ground cover and land use, soil erodibility, topography, river-bed material characteristics, and watershed area. In the companion paper following this paper, methods for estimating sediment yield rate are to be developed using the 13 data points collected and seven watershed characteristics factors selected in this study.

• Asian-Australasian Journal of Animal Sciences
• /
• v.8 no.3
• /
• pp.295-300
• /
• 1995

Data from purebred and crossbred cattle involving Holstein and the Local breed in Bangladesh were used to estimate the genetic effects on average daily milk yield and birth weight A total of 877 records on average daily milk yield for 4 types of breed groups and a total of 418 records on birth weight for 5 breed groups were analyzed. Two different methods were applied in this study; the least squares analysis of variance approach and the linear regression approach. Breed group effects were highly significant for both average daily milk yield and birth weight. The result showed that straightbred Holstein produced the highest milk yield and the 7/8 crosses ranked highest in birth weight For the two traits, the additive breed effect was highly significant, whereas the individual heterosis effect was not significant. Furthermore, this study showed a negative maternal heterosis for average daily milk yields and a positive maternal heterosis for birth weight Comparing the breed least squares means obtained from the linear regression approach revealed that straightbred Holstein produced the highest average milk yield and the 3/4 crosses were predicted to have the largest birth weight. It is indicated that the linear regression approach can adequately separate the genetic component of performance, estimate unknown crossbreeding parameters and predict unknown performance of crosses which are not include in the original data.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.11
• /
• pp.23-31
• /
• 2020

This paper investigates the impact of monetary policy independence shock on bond yield by allowing for heterogeneous coefficients in the model based on panel data for 19 developing countries using quarterly data from 1991 to 2016. First, we estimate the model using conventional panel VAR estimation with the assumption of homogeneous coefficients across countries. Second, by performing Chow and Roy-Zellner tests to check the homogeneity assumption, we find that the assumption does not hold in the model. Third, we apply a mean-group estimation for panel VAR as a solution for heterogeneity panel model. The results reveal that central bank independence is effective in reducing bond yield with the maximum at period 6 after the shock. Shock one standard deviation bond yield has a negative effect on consumption and investment. We determine that central bank independence has a contradictory effect on real activity; a negative effect on consumption but a positive influence on investment for the first two years after the shock. Additionally, we split our sample into three groups to make the subgroups pool. Our empirical result shows that monetary policy independence shock reduces bond yield. Meanwhile, the response of economic activity to bond yield varies for all three groups.

• Journal of Environmental Science International
• /
• v.33 no.7
• /
• pp.511-522
• /
• 2024

The optimal yield is defined as the amount of groundwater that maintains a dynamic equilibrium state of the groundwater system over a long period. We examined the current problems, improvements, and methods for estimating the optimal groundwater yield in Korea, considering sustainable groundwater development. The optimal yield for individual wells and the sustainable yield for the entire groundwater basin were reviewed. Generally, the optimal yield for individual wells can be determined using long-term pumping and step drawdown tests. The optimal yield can be determined by groundwater quantity and quality, economic, and water use rights factors. The optimal yield of individual wells in the groundwater basin must be determined within the total sustainable amount of the entire groundwater basin, such that the optimal yield of a new well must be less than the remaining total sustainable amount, exempting the total optimal yield of the existing wells. Therefore, the optimal yield may be determined based on the estimated optimal yield at least twice per year. In addition, if groundwater level and pumping quantity data for at least one year are available, it may be effective to use the Hill, Harding, and zero groundwater-level change methods to re-estimate the optimal yield.

• Journal of Forest and Environmental Science
• /
• v.24 no.3
• /
• pp.119-126
• /
• 2008

Growth and yield prediction methods, ranging from whole-stand models to individual-tree models, have been developed for forest types managed for wood production. The resultant models are used for a host of purposes including inventory updating, management planning, evaluation of silvicultural alternatives, and harvest scheduling. Because of the large investment in developing growth and yield models for improved genotypes and silvicultural practices for loblolly pine (Pinus taeda) in the Southern United States, this region serves to illustrate approaches for modelling intensively managed forests. Analytical methods and computing power generally do not restrict development of reliable growth and yield models. However, long-term empirical observations on stand development, which are time consuming and expensive to obtain, often limit modelling efforts. Given that growth and yield models are used to project present volumes and to evaluate alternative treatment effects, data of both the inventory type and the experimental type are needed. Data for developing stand simulators for loblolly pine plantations have been obtained from a combination of permanent plots in operational forest stands and silvicultural experiments; these data collection efforts are described and summarized. Modelling is essential for integrating and synthesizing diverse information, identifying knowledge gaps, and making informed decisions. The questions being posed today are more complex than in the past, thus further accentuating the need for comprehensive models for stand development.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.4
• /
• pp.383-390
• /
• 2016

Remote sensing data has been widely used in the estimation of crop yields by employing statistical methods such as regression model. Machine learning, which is an efficient empirical method for classification and prediction, is another approach to crop yield estimation. This paper described the corn yield estimation in Iowa State using four machine learning approaches such as SVM (Support Vector Machine), RF (Random Forest), ERT (Extremely Randomized Trees) and DL (Deep Learning). Also, comparisons of the validation statistics among them were presented. To examine the seasonal sensitivities of the corn yields, three period groups were set up: (1) MJJAS (May to September), (2) JA (July and August) and (3) OC (optimal combination of month). In overall, the DL method showed the highest accuracies in terms of the correlation coefficient for the three period groups. The accuracies were relatively favorable in the OC group, which indicates the optimal combination of month can be significant in statistical modeling of crop yields. The differences between our predictions and USDA (United States Department of Agriculture) statistics were about 6-8 %, which shows the machine learning approaches can be a viable option for crop yield modeling. In particular, the DL showed more stable results by overcoming the overfitting problem of generic machine learning methods.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.6
• /
• pp.111-117
• /
• 2009

The RUSLE(Revised Universal Soil Loss Equation) has been most widely used to estimate sediment yield in Korea. However RUSLE factors have not been verified based on measured data of sediment yield. The analysis of characteristics for the rainfall erosivity factor R was performed in this study. The R factor of RUSLE is expressed as multiple of total rainfall energy and maximum 30 min rainfall intensity. In this study, the characteristics of 10 rainfall energy equations were investigated using data measured in Gangneung experimental watershed, and applicability of each equations was reviewed based on results of the correlation analysis between measured sediment yield and total rainfall, between measured sediment yield and maximum intensity, and between measured sediment yield and total rainfall energy yield. Also, the relationship of I30 and I60 was proposed using 10-min rainfall data during 9 years.