• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.4
• /
• pp.443-463
• /
• 2024

This study sought to improve the accuracy of precipitation prediction by utilizing monthly precipitation data for each region over the past 30 years. Using statistical models (ARIMA, SARIMA) and deep learning models (LSTM, GBM), we learned monthly precipitation data from 1983 to 2012 in Gangneung, Gwangju, Daegu, Daejeon, Busan, Seoul, Jeju, and Chuncheon. Based on this, monthly precipitation was predicted for 10 years from 2013 to 2022. As a result of the prediction, most models accurately predicted the precipitation trend, but showed a tendency to underpredict the actual precipitation. To solve these problems, appropriate models were selected for each region and season. The LSTM model showed suitable results in Gangneung, Gwangju, Daegu, Daejeon, Busan, Seoul, Jeju, and Chuncheon. When comparing forecasting power by season, the SARIMA model showed particularly suitable forecasting performance in winter in Gangneung, Gwangju, Daegu, Daejeon, Seoul, and Chuncheon. Additionally, the LSTM model showed higher performance than other models in the summer when precipitation is concentrated. In conclusion, closely analyzing regional and seasonal precipitation patterns and selecting the optimal prediction model based on this plays a critical role in increasing the accuracy of precipitation prediction.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.3
• /
• pp.107-122
• /
• 2006

The main objective of this study is to develop a web-based Geographic Information System (GIS) application, IGIS(Integrated Groundwater Information Service System), for efficient management of groundwater data. This integrated system includes various groundwater measurements, monitoring data, well data, hydrogeochemical data, hydrogeological maps and diversely analyzed results including time series analysis data for water levels and quality. It will be used efficiently for local government officers to manage groundwater within their districts and also for drillers and investigators to develop wells and assess groundwater conditions. This web-based GIS system was implemented firstly for Cheonan and Daegu city. As a result, the system makes the efficient management, distribution and utilization of groundwater data possible by web-based GIS technology.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.2
• /
• pp.289-299
• /
• 2015

The objective of the present study is to develop statistical quantitative forecast model for PM10 concentration over Seoul. We used three types of data (weather observation data in Korea, the China's weather observation data collected by GTS, and air quality numerical model forecasts). To apply the daily forecast system, hourly data are converted to daily data and then lagging was performed. The potential predictors were selected based on correlation analysis and multicollinearity check. Model validation has been performed for checking model stability. We applied two models (multiple regression model and threshold regression model) separately. The two models were compared based on the scatter plot of forecasts and observations, time series plots, RMSE, skill scores. As a result, a threshold regression model performs better than multiple regression model in high PM10 concentration cases.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.161-170
• /
• 2013

The FX (Foreign Exchange) is a form of exchange for the global decentralized trading of international currencies. The simple sense of Forex is simultaneous purchase and sale of the currency or the exchange of one country's currency for other countries'. We can find the consistent rules of trading by comparing the gradient boosting method and the decision trees methods. Methods such as time series analysis used for the prediction of financial markets have advantage of the long-term forecasting model. On the other hand, it is difficult to reflect the rapidly changing price fluctuations in the short term. Therefore, in this study, gradient boosting method and decision tree method are applied to analyze the short-term data in order to make the rules for the revenue structure of the FX market and evaluated the stability and the prediction of the model.

• 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 the Korean earth science society
• /
• v.43 no.3
• /
• pp.367-385
• /
• 2022

This study evaluates the temperature and precipitation results in East Asia simulated from the Hadley Centre Global Environmental Model version 3 regional climate model (HadGEM3-RA) developed by the UK Met Office. The HadGEM3-RA is conducted in the Coordinated Regional climate Downscaling Experiment-East Asia (CORDEX-EA) Phase II domain for 15 year (2000-2014). The spatial distribution of rainbands produced from the HadGEM3-RA by the summer monsoon is in good agreement with the Asian Precipitation Highly Resolved Observational Data Integration Towards Evaluation of water resources (APRODITE) data over the East Asia. But, precipitation amount is overestimated in Southeast Asia and underestimated over the Korean Peninsula. In particular, the simulated summer rainfall and APRODITE data show the least correlation coefficient and the maximum value of root mean square error in South Korea. Prediction of temperature in Southeast Asia shows underestimation with a maximum error during winter season, while it appears the largest underestimation in South Korea during spring season. In order to evaluate local predictability, the time series of temperature and precipitation compared to the ASOS data of the Seoul Meteorological Station is similar to the spatial average verification results in which the summer precipitation and winter temperature underestimate. Especially, the underestimation of the rainfall increases when the amounts of precipitation increase in summer. The winter temperature tends to underestimate at low temperature, while it overestimates at high temperature. The results of the extreme climate index comparison show that heat wave is overestimated and heavy rainfall is underestimated. The HadGEM3-RA simulated with a horizontal resolution of 25 km shows limitations in the prediction of mesoscale convective system and topographic precipitation. This study indicates that improvement of initial data, horizontal resolution, and physical process are necessary to improve predictability of regional climate model.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_2
• /
• pp.1651-1669
• /
• 2023

Sea ice currently covers approximately 7% of the world's ocean area, primarily concentrated in polar and high-altitude regions, subject to seasonal and annual variations. It is very important to analyze the area and type classification of sea ice through time series monitoring because sea ice is formed in various types on a large spatial scale, and oil and gas exploration and other marine activities are rapidly increasing. Currently, research on the type and area of sea ice is being conducted based on high-resolution satellite images and field measurement data, but there is a limit to sea ice monitoring by acquiring field measurement data. High-resolution optical satellite images can visually detect and identify types of sea ice in a wide range and can compensate for gaps in sea ice monitoring using Geostationary Ocean Color Imager-II (GOCI-II), an ocean satellite with short time resolution. This study tried to find out the possibility of utilizing sea ice monitoring by training a rule-based machine learning model based on learning data produced using high-resolution optical satellite images and performing detection on GOCI-II images. Learning materials were extracted from Liaodong Bay in the Bohai Sea from 2021 to 2022, and a Random Forest (RF) model using GOCI-II was constructed to compare qualitative and quantitative with sea ice areas obtained from existing normalized difference snow index (NDSI) based and high-resolution satellite images. Unlike NDSI index-based results, which underestimated the sea ice area, this study detected relatively detailed sea ice areas and confirmed that sea ice can be classified by type, enabling sea ice monitoring. If the accuracy of the detection model is improved through the construction of continuous learning materials and influencing factors on sea ice formation in the future, it is expected that it can be used in the field of sea ice monitoring in high-altitude ocean areas.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1037-1051
• /
• 2020

The accurate monitoring and forecasting of the intensity of tropical cyclones (TCs) are able to effectively reduce the overall costs of disaster management. In this study, we proposed a multi-task learning (MTL) based deep learning model for real-time TC intensity estimation and forecasting with the lead time of 6-12 hours following the event, based on the fusion of geostationary satellite images and numerical forecast model output. A total of 142 TCs which developed in the Northwest Pacific from 2011 to 2016 were used in this study. The Communications system, the Ocean and Meteorological Satellite (COMS) Meteorological Imager (MI) data were used to extract the images of typhoons, and the Climate Forecast System version 2 (CFSv2) provided by the National Center of Environmental Prediction (NCEP) was employed to extract air and ocean forecasting data. This study suggested two schemes with different input variables to the MTL models. Scheme 1 used only satellite-based input data while scheme 2 used both satellite images and numerical forecast modeling. As a result of real-time TC intensity estimation, Both schemes exhibited similar performance. For TC intensity forecasting with the lead time of 6 and 12 hours, scheme 2 improved the performance by 13% and 16%, respectively, in terms of the root mean squared error (RMSE) when compared to scheme 1. Relative root mean squared errors(rRMSE) for most intensity levels were lessthan 30%. The lower mean absolute error (MAE) and RMSE were found for the lower intensity levels of TCs. In the test results of the typhoon HALONG in 2014, scheme 1 tended to overestimate the intensity by about 20 kts at the early development stage. Scheme 2 slightly reduced the error, resulting in an overestimation by about 5 kts. The MTL models reduced the computational cost about 300% when compared to the single-tasking model, which suggested the feasibility of the rapid production of TC intensity forecasts.

• Journal of the Korean earth science society
• /
• v.41 no.2
• /
• pp.95-110
• /
• 2020

Comparisons between two different surface temperatures from high-resolution ECMWF ReAnalysis 5 (ERA5) and Automated Synoptic Observing System (ASOS) observations were performed to investigate the reliability of the new reanalysis data over South Korea. As ERA5 has been recently produced and provided to the public, it will be highly used in various research fields. The analysis period in this study is limited to 1999-2018 because regularly recorded hourly data have been provided for 61 ASOS stations since 1999. Topographic characteristics of the 61 ASOS locations are classified as inland, coastal, and mountain based on Digital Elevation Model (DEM) data. The spatial distributions of whole period time-averaged temperatures for ASOS and ERA5 were similar without significant differences in their values. Scatter plots between ASOS and ERA5 for three different periods of yearlong, summer, and winter confirmed the characteristics of seasonal variability, also shown in the time-series of monthly error probability density functions (PDFs). Statistical indices NMB, RMSE, R, and IOA were adopted to quantify the temperature differences, which showed no significant differences in all indices, as R and IOA were all close to 0.99. In particular, the daily mean temperature differences based on 1-hour-averaged temperature had a smaller error than the classical daily mean temperature differences, showing a higher correlation between the two data. To check if the complex topography inside one ERA5 grid cell is related to the temperature differences, the kurtosis and skewness values of 90-m DEM PDFs in a ERA5 grid cell were compared to the one-year period amplitude among those of the power spectrum in the time-series of monthly temperature error PDFs at each station, showing positive correlations. The results account for the topographic effect as one of the largest possible drivers of the difference between ASOS and ERA5.