• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.134-134
• /
• 2021

Precipitation is a crucial component of water cycle and play a key role in hydrological processes. Traditionally, gauge-based precipitation is the main method to achieve high accuracy of rainfall estimation, but its distribution is sparsely in mountainous areas. Recently, satellite-based precipitation products (SPPs) provide grid-based precipitation with spatio-temporal variability, but SPPs contain a lot of uncertainty in estimated precipitation, and the spatial resolution quite coarse. To overcome these limitations, this study aims to generate new grid-based daily precipitation using Automatic weather system (AWS) in Korea and multiple SPPs(i.e. CHIRPSv2, CMORPH, GSMaP, TRMMv7) during the period of 2003-2017. And this study used a machine learning based Random Forest (RF) model for generating new merging precipitation. In addition, several statistical linear merging methods are used to compare with the results of the RF model. In order to investigate the efficiency of RF, observed data from 64 observed Automated Synoptic Observation System (ASOS) were collected to evaluate the accuracy of the products through Kling-Gupta efficiency (KGE), probability of detection (POD), false alarm rate (FAR), and critical success index (CSI). As a result, the new precipitation generated through the random forest model showed higher accuracy than each satellite rainfall product and spatio-temporal variability was better reflected than other statistical merging methods. Therefore, a random forest-based ensemble satellite precipitation product can be efficiently used for hydrological simulations in ungauged basins such as the Mekong River.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• Journal of the Korean Wood Science and Technology
• /
• v.43 no.4
• /
• pp.456-462
• /
• 2015

365 pieces of domestic $38{\times}140{\times}3600mm$ Red pine structural lumber were machine graded conforming to a softwood structural lumber standard (KS F 3020). The allowable bending stresses calculated for each grade were compared with the values currently tabulated in the standard. Four calculation methods for lower $5^{th}$ percentile bending stress were non-parametric estimation with 75% confidence level, 2-parameter and 3-parameter Weibull distribution fit, and bending modulus of rupture (MOR)-modulus of elasticity (MOE) regression based method. Only the data set of Grades E8, E9, and E10 were statistically eligible for the $5^{th}$ percentile calculation. The MOR-MOE regression based method only was able to estimate the lower $5^{th}$ percentile values theoretically for the full range of grades. The results showed that all allowable bending stresses calculated were lower than the design values tabulated in the standard. This implies that the current machine grading system has the pitfall of structural safety. Improvement in current machine grading system could be achieved by introducing the bending strength and stiffness combination grade system.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.11-17
• /
• 2019

In recent years, damage and loss of life and property have been occurred frequently due to swelling waves in the East Sea. Swelling waves are not easy to predict because they are caused by various factors. In this research, we build a model for predicting the swelling waves occurrence in the East Coast of Korea using machine learning technique. We collect historical data of unloading interruption in the Pohang Port, and collect air pressure, wind speed, direction, water temperature data of the offshore Pohang Port. We select important variables for prediction, and test various machine learning prediction algorithms. As a result, tide level, water temperature, and air pressure were selected, and Random Forest model produced best performance. We confirm that Random Forest model shows best performance and it produces 88.86% of accuracy

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.781-791
• /
• 2022

It is crucial to provide forest fire risk forecast information to minimize forest fire-related losses. In this research, forecast models of forest fire risk at a mid-range (with lead times up to 7 days) scale were developed considering past, present and future conditions (i.e., forest fire risk, drought, and weather) through random forest machine learning over South Korea. The models were developed using weather forecast data from the Global Data Assessment and Prediction System, historical and current Fire Risk Index (FRI) information, and environmental factors (i.e., elevation, forest fire hazard index, and drought index). Three schemes were examined: scheme 1 using historical values of FRI and drought index, scheme 2 using historical values of FRI only, and scheme 3 using the temporal patterns of FRI and drought index. The models showed high accuracy (Pearson correlation coefficient >0.8, relative root mean square error <10%), regardless of the lead times, resulting in a good agreement with actual forest fire events. The use of the historical FRI itself as an input variable rather than the trend of the historical FRI produced more accurate results, regardless of the drought index used.

• Journal of Korean Society of Forest Science
• /
• v.109 no.3
• /
• pp.259-270
• /
• 2020

Extreme weather events, such as heat and drought, have occurred frequently over the past two decades. This has led to continuous reports of cases of forest damage due to physiological stress, not pest damage. In 2014, pine trees were collectively damaged in the forest genetic resources reserve of Sogwang-ri, Uljin, South Korea. An investigation was launched to determine the causes of the dieback, so that a forest management plan could be prepared to deal with the current dieback, and to prevent future damage. This study aimedto 1) understand the topographic and structural characteristics of the area which experienced pine tree dieback, 2) identify the main causes of the dieback, and 3) predict future risk areas through the use of machine-learning techniques. A model for identifying risk areas was developed using 14 explanatory variables, including location, elevation, slope, and age class. When three machine-learning techniques-Decision Tree, Random Forest (RF), and Support Vector Machine (SVM) were applied to the model, RF and SVM showed higher predictability scores, with accuracies over 93%. Our analysis of the variable set showed that the topographical areas most vulnerable to pine dieback were those with high altitudes, high daily solar radiation, and limited water availability. We also found that, when it came to forest stand characteristics, pine trees with high vertical stand densities (5-15 m high) and higher age classes experienced a higher risk of dieback. The RF and SVM models predicted that 9.5% or 115 ha of the Geumgang Pine Forest are at high risk for pine dieback. Our study suggests the need for further investigation into the vulnerable areas of the Geumgang Pine Forest, and also for climate change adaptive forest management steps to protect those areas which remain undamaged.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.1
• /
• pp.17-27
• /
• 2021

In this paper, we develop a galaxy image classification method based on hand-crafted features and machine learning techniques. Additionally, we provide an empirical analysis to reveal which combination of the techniques is effective for galaxy image classification. To achieve this, we developed a framework which consists of four modules such as preprocessing, feature extraction, feature post-processing, and classification. Finally, we found that the best technique for galaxy image classification is a method to use a median filter, ORB vector features and a voting classifier based on RBF SVM, random forest and logistic regression. The final method is efficient so we believe that it is applicable to embedded environments.

• Computers and Concrete
• /
• v.33 no.6
• /
• pp.739-754
• /
• 2024

This study presents an innovative AI-driven approach to assess the ultimate axial load in Double-Skinned Profiled Steel sheet Composite Walls (DPSCWs). Utilizing a dataset of 80 entries, seven input parameters were employed, and various AI techniques, including Linear Regression, Polynomial Regression, Support Vector Regression, Decision Tree Regression, Decision Tree with AdaBoost Regression, Random Forest Regression, Gradient Boost Regression Tree, Elastic Net Regression, Ridge Regression, and LASSO Regression, were evaluated. Decision Tree Regression and Random Forest Regression emerged as the most accurate models. The top three performing models were integrated into a hybrid approach, excelling in accurately estimating DPSCWs' ultimate axial load. This adaptable hybrid model outperforms traditional methods, reducing errors in complex scenarios. The validated Artificial Neural Network (ANN) model showcases less than 1% error, enhancing reliability. Correlation analysis highlights robust predictions, emphasizing the importance of steel sheet thickness. The study contributes insights for predicting DPSCW strength in civil engineering, suggesting optimization and database expansion. The research advances precise load capacity estimation, empowering engineers to enhance construction safety and explore further machine learning applications in structural engineering.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1109-1123
• /
• 2020

In South Korea with forest as a major land cover class (over 60% of the country), many wildfires occur every year. Wildfires weaken the shear strength of the soil, forming a layer of soil that is vulnerable to landslides. It is important to identify the severity of a wildfire as well as the burned area to sustainably manage the forest. Although satellite remote sensing has been widely used to map wildfire severity, it is often difficult to determine the severity using only the temporal change of satellite-derived indices such as Normalized Difference Vegetation Index (NDVI) and Normalized Burn Ratio (NBR). In this study, we proposed an approach for determining wildfire severity based on machine learning through the synergistic use of Sentinel-1A Synthetic Aperture Radar-C data and Sentinel-2A Multi Spectral Instrument data. Three wildfire cases-Samcheok in May 2017, Gangreung·Donghae in April 2019, and Gosung·Sokcho in April 2019-were used for developing wildfire severity mapping models with three machine learning algorithms (i.e., Random Forest, Logistic Regression, and Support Vector Machine). The results showed that the random forest model yielded the best performance, resulting in an overall accuracy of 82.3%. The cross-site validation to examine the spatiotemporal transferability of the machine learning models showed that the models were highly sensitive to temporal differences between the training and validation sites, especially in the early growing season. This implies that a more robust model with high spatiotemporal transferability can be developed when more wildfire cases with different seasons and areas are added in the future.

• Journal of Korean Society of Forest Science
• /
• v.109 no.1
• /
• pp.72-80
• /
• 2020

Two strategies for calculating economic feasibility are the machine rate and cash-flow methods. This study used the cash-flow method to evaluate the economic feasibility of the HAM300 yarding operation for extracting tree length logs in Larix kaempferi forest stands. In financial analysis based on 7-year cash-flow, the net present value and pay-back period method were used. We analyzed two scenarios: operating opportunities (50, 100, 150, and 200 days per year) and productivity change yield (7.5 and 10.5 ㎥/scheduled machine hour: SMH). The analysis indicated that high rates of return on extraction activity investment can be achieved when machines are used for >150 days per year. In addition, improved productivity (10.5 ㎥/SMH) increased financial feasibility compared to current productivity (7.5 ㎥/SMH) when machines were operated for 100 days per year. These results suggest that the appropriateness of HAM300 harvesting depends on the number of annual operating days and productivity.