• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.149-153
• /
• 2006

Precipitation is the most important component and critical to the study of water and energy cycle. This study investigates the propagation of precipitation retrieval uncertainty in the simulation of hydrologic variables for varying spatial resolution on two different vegetation cover. We explore two remotely sensed rain retrievals (space-borne IR-only and radar rainfall) and three spatial grid resolutions. An offline Community Land Model (CLM) was forced with in situ meteorological data In turn, radar rainfall is replaced by the satellite rain estimates at coarser resolution $(0.25^{\circ},\;0.5^{\circ}\;and\;1^{\circ})$ to determine their probable impact on model predictions. Results show how uncertainty of precipitation measurement affects the spatial variability of model output in various modelling scales. The study provides some intuition on the uncertainty of hydrologic prediction via interaction between the land surface and near atmosphere fluxes in the modelling approach.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.107-117
• /
• 1999

A comparison of a neural network approach with the conventional statistical methods, multiple regression and band ratio analyses, for the estimation of water quality parameters in presented in this paper. The Landsat TM image of Lake Daechung acquired on March 18, 1996 and the thirty in-situ sampling data sets measured during the satellite overpass were used for the comparison. We employed a three-layered and feedforward network trained by backpropagation algorithm. A cross validation was applied because of the small number of training pairs available for this study. The neural network showed much more successful performance than the conventional statistical analyses, although the results of the conventional statistical analyses were significant. The superiority of a neural network to statistical methods in estimating water quality parameters is strictly because the neural network modeled non-linear behaviors of data sets much better.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.21 no.1
• /
• pp.29-41
• /
• 2019

Terrestrial Gross Primary Production (GPP) is the largest global carbon flux, and forest ecosystems are important because of the ability to store much more significant amounts of carbon than other terrestrial ecosystems. There have been several attempts to estimate GPP using mechanism-based models. However, mechanism-based models including biological, chemical, and physical processes are limited due to a lack of flexibility in predicting non-stationary ecological processes, which are caused by a local and global change. Instead mechanism-free methods are strongly recommended to estimate nonlinear dynamics that occur in nature like GPP. Therefore, we used the mechanism-free machine learning techniques to estimate the daily GPP. In this study, support vector machine (SVM), random forest (RF) and artificial neural network (ANN) were used and compared with the traditional multiple linear regression model (LM). MODIS products and meteorological parameters from eddy covariance data were employed to train the machine learning and LM models from 2006 to 2013. GPP prediction models were compared with daily GPP from eddy covariance measurement in a deciduous forest in South Korea in 2014 and 2015. Statistical analysis including correlation coefficient (R), root mean square error (RMSE) and mean squared error (MSE) were used to evaluate the performance of models. In general, the models from machine-learning algorithms (R = 0.85 - 0.93, MSE = 1.00 - 2.05, p < 0.001) showed better performance than linear regression model (R = 0.82 - 0.92, MSE = 1.24 - 2.45, p < 0.001). These results provide insight into high predictability and the possibility of expansion through the use of the mechanism-free machine-learning models and remote sensing for predicting non-stationary ecological processes such as seasonal GPP.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_3
• /
• pp.1197-1213
• /
• 2017

This study was carried out to correct shadow area in urban area on KOMPSAT-3 satellite image. For this study, we analyzed characteristics of the shadow area represented by artificial structures in urban area. The proposed shadow correction method divides shadow area into umbra and penumbra areas according to intensity of darkness. The umbra area was detected through the histogram analysis and the statistical method of the NIR image, and then penumbra area and the sunlit area were detected from around the detected umbra area. The correction of the detected umbra and penumbra area were performed by applying the linear correlation correction method. As a result, it was confirmed that the proposed shadow correction method was visually performed well. Quantitative analysis was performed through profile analysis. It is proved that proposed method is useful for shadow area correction.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.2179-2183
• /
• 2008

지금까지 분포형 모형 개발에 대한 많은 노력이 있음에도 불구하고 여러 제약사항들에 의해 잠재력을 보여주는 정도로 활용되어 왔으나, 최근 급속도로 발전하는 컴퓨터의 계산능력, DEM 등 디지털정보의 구축이 진행되어 오고 있고, GIS 및 인공위성 영상기법의 발달로 공간적인 비균질성을 고려하여 유출과정에서 운동역학적인 이론을 기반으로 물의 흐름을 수리학적으로 추적해 나가는 물리적기반의 분포형 유출모형의 활용도가 높아지고 있다. 본 모형개발에 있어 이론적 배경이 된 모형은 1998년부터 일본 교토대학 방재연구소 코지리 연구실에서 개발 중인 Hydro-BEAM으로 유역 물순환의 건전성을 평가하기 위하여 장기간의 유역 내 유량, 수질을 시계열 및 공간적으로 파악하여 유역의 영향평가를 위해 개발된 물리적 기반의 격자구조를 가진 분포형 장기유출 모형이다. 유출량 계산은 유역내 수평 유출량산정 모듈로서 평면 분포형의 격자형을, 연직 분포형으로는 $A{\sim}B$층의 수평유출량은 하천으로 유입하고, C층은 하천유량에 영향을 미치지 않는 지하수층으로 가정하는 다층모형을 이용해서 A층, 지표 및 하도흐름은 운동파 법(kinematic wave)으로, $B{\sim}C$층의 유출량은 선형저류법으로 계산하는 모형이다. 본 연구에서는 격자흐름방향을 4방향에서 8방향으로 개선하였고, 모형의 각종 수문매개변수들을 GIS와 연계하여 직접 입력할 수 있도록 하였으며, 물리적기반의 침투과정을 모의할 수 있도록 Green & Ampt모듈을 추가하고, 향후 레이더 강우 및 수치예보강우의 홍수유출예측을 염두에 두고 격자강우량을 활용할 수 있도록 하는 등 홍수유출해석을 위한 분포형 강우-유출모형으로 개선 하였고, 이를 남강댐유역에 적용해 봄으로써 모형의 적용성을 검토해 보고자 하였다. 홍수기동안의 지표흐름과 지표하 흐름의 시간적 변화와 공간적 분포를 모의할 수 있었으며, 전처리과정으로서 ArcGIS 혹은 ArcView등의 GIS 프로그램을 이용하여 모형에 필요한 ASCII형태의 입력 매개 변수 자료들을 가공하였다. 또한 후처리과정으로서 모형의 수행결과인 유역내의 유출량 분포 등을 GIS상에서 나타낼 수 있도록 ASCII형태로 출력하도록 구성하였다. 남강댐유역을 대상으로 유역을 500m의 정방형 격자로 분할하고 수계망을 통하여 유역 출구까지 운동파이론에 의해 추적 계산하였으며, 수문곡선 비교결과 재현성 높은 결과를 보여주었다. 모형의 정확성 및 실용성에 대한 보다 정확한 평가를 위해서는 향후 다양한 강우 사상 혹은 다양한 크기의 유역에 대한 유출량의 재현성 및 매개변수 등에 검증이 이루어져야 할 것이다.

• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.487-501
• /
• 2020

As a viable option for retrieval of LST (Land Surface Temperature), this paper presents a DNN (Deep Neural Network) based approach using 148 Landsat 8 images for South Korea. Because the brightness temperature and emissivity for the band 10 (approx. 11-㎛ wavelength) of Landsat 8 are derived by combining physics-based equations and empirical coefficients, they include uncertainties according to regional conditions such as meteorology, climate, topography, and vegetation. To overcome this, we used several land surface variables such as NDVI (Normalized Difference Vegetation Index), land cover types, topographic factors (elevation, slope, aspect, and ruggedness) as well as the T₀ calculated from the brightness temperature and emissivity. We optimized four seasonal DNN models using the input variables and in-situ observations from ASOS (Automated Synoptic Observing System) to retrieve the LST, which is an advanced approach when compared with the existing method of the bias correction using a linear equation. The validation statistics from the 1,728 matchups during 2013-2019 showed a good performance of the CC=0.910~0.917 and RMSE=3.245~3.365℃, especially for spring and fall. Also, our DNN models produced a stable LST for all types of land cover. A future work using big data from Landsat 5/7/8 with additional land surface variables will be necessary for a more reliable retrieval of LST for high-resolution satellite images.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.1 s.15
• /
• pp.51-63
• /
• 2000

Dynamic traffic assignment(DTA) has been a topic of substantial research during the past decade. While DTA is gradually maturing, many aspects of DTA still need improvement, especially regarding its formulation and solution algerian Recently, with its promise for In(Intelligent Transportation System) and GIS(Geographic Information System) applications, DTA have received increasing attention. This potential also implies higher requirement for DTA modeling, especially regarding its solution efficiency for real-time implementation. But DTA have many mathematical difficulties in searching process due to the complexity of spatial and temporal variables. Although many solution algorithms have been studied, conventional methods cannot iud the solution in case that objective function or constraints is not convex. In this paper, the genetic algorithm to find the solution of DTA is applied and the Merchant-Nemhauser model is used as DTA model because it has a nonconvex constraint set. To handle the nonconvex constraint set the GENOCOP III system which is a kind of the genetic algorithm is used in this study. Results for the sample network have been compared with the results of conventional method.