• 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.96 no.5
• /
• pp.591-601
• /
• 2007

Spatial information on forest biomass is an important factor to evaluate the capability of forest as a carbon sequestrator and is a core independent variable required to drive models which describe ecological processes such as carbon budget, hydrological budget, and energy flow. The objective of this study is to understand the relationship between satellite image and field data, and to quantitatively estimate and map the spatial distribution of forest biomass. Landsat Enhanced Thematic Mapper (ETM+) derived vegetation indices and field survey data were applied to estimate the biomass distribution of mountainous forest located in Gwangneung Experimental Forest (230 ha). Field survey data collected from the ground plots were used as the dependent variable, forest biomass, while satellite image reflectance data (Band 1~5 and Band 7), Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), and RVI (Ratio Vegetation Index) were used as the independent variables. The mean and total biomass of Gwangneung catchment area were estimated to be about 229.5 ton/ha and $52.8{\times}10^3$ tons respectively. Regression analysis revealed significant relationships between the measured biomass and Landsat derived variables in both of deciduous forest ($R^2=0.76$, P < 0.05) and coniferous forest ($R^2=0.75$, P < 0.05). However, there still exist many uncertainties in the estimation of forest ecosystem parameters based on vegetation remote sensing. Developing remote sensing techniques with adequate filed survey data over a long period are expected to increase the estimation accuracy of spatial information of the forest ecosystem.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.2
• /
• pp.107-116
• /
• 2016

Airborne or spaceborne remote sensing can increase the efficiency of seabed material surveys compared with field surveying using a vessel. For the same seabed material, the optical remote sensing image shows variation in the reflectance depending on the water depth, which is due to the absorption and scattering by the water column. This study suggests a correction procedure to use the hyperspectral image for seabed material analysis. The study is conducted in the coastal area from Sacheonjin Port to Gyungpo Beach in Gangwon-do. The hyperspectral image is acquired using the CASI-1500 sensor. The diffuse attenuation coefficient is estimated for each band through regression models between the water reflectance and depth. Then, the coefficient is applied to each band of the image. As a result, the completely corrected image can be interpreted for a deeper area, although the interpretable area is very shallow without water column correction. Additionally, the water column corrected image shows decreased variation of reflectance with various water depths.

• Korean Journal of Remote Sensing
• /
• v.26 no.1
• /
• pp.21-27
• /
• 2010

This paper presents a numerical simulation of the radar backscattering from oil spills on ocean surface. At first, a one-dimensionally rough sea surface is numerically generated for a given wind speed at HEBEI SPIRIT accident. Then, an oil-spilled sea surface is represented with a two-layered medium, which is generated by adding a thin low-dielectric oil layer on the randomly-rough highdielectric sea surface. The backscattering coefficients of various oil-spilled sea surfaces are obtained using the Method of Moments and Monte Carlo technique for various surface roughness, oil-layer thicknesses, frequencies, polarizations and incidence angles. The numerical method is verified with theoretical models for simple structures. The reduction of the backscattering coefficients due to the lowdielectric oil-layers on sea surfaces has been analyzed. These numerical results will help to detect any oil spills on sea surfaces, and consequently, to classify SAR images.

• Korean Journal of Remote Sensing
• /
• v.25 no.4
• /
• pp.375-381
• /
• 2009

In this paper, synthetic aperture radar (SAR) clutter images are simulated based on the extensive analyses for radar backscatter characteristics of various earth surfaces, and the simulated images are compared with measured SAR images. At first, the surface parameters including soil moisture content and surface roughness parameters and other parameters for vegetation canopies are measured for various surfaces. The backscattering coefficients for the surfaces are computed using theoretical and empirical models for surface scattering and the radiative transfer for vegetation-canopy scattering. Then, the digital elevation map (DEM) and land cover map (LCM) are used for the SAR image generation. The SAR impulse response (correlation function) is also employed to simulated reliable SAR images. Finally, the appropriate speckle and texture parameters for various earth surfaces are used for generating the SAR clutter images.

• Journal of The Geomorphological Association of Korea
• /
• v.24 no.3
• /
• pp.105-118
• /
• 2017

The debris slope landforms which are existent in Korean mountains is generally on the steep slopes and mostly covered by vegetation, it is difficult to investigate the landform. Therefore a scientific method is required to come up with an effective field investigation plan. For this purpose, the use of Remote Sensing and GIS technologies for a spatial analysis is essential. This study has extracted the potential area of debrisslope landform formation using Fuzzy set and Bayesian Predictive Discriminate Model as mathematical data integration methods. The first step was to obtain information about debris locations and their related factors. This information was verified through field investigation and then used to build a database. In the second step, the map that zoning the study area based on the degree of debris formation possibility was generated using two modeling methods, and then cross validation technique was applied. In order to quantitatively analyze the accuracy of two modeling methods, the calculated potential rate of debrisformation within the study area was evaluated by plotting SRC(Success Rate Curve) and calculating AUC(Area Under the Curve). As a result, the prediction accuracy of Fuzzy set model wes 83.1% and Bayesian Predictive Discriminate Model wes 84.9%. It showed that two models are accurate and reliable and can contribute to efficient field investigation and debris landform management.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.327-341
• /
• 2022

Cloud removal is often required to construct time-series sets of optical images for environmental monitoring. In regression-based cloud removal, the selection of an appropriate regression model and the impact analysis of the input images significantly affect the prediction performance. This study evaluates the potential of Gaussian process (GP) regression for cloud removal and also analyzes the effects of cloud-free optical images and spectral bands on prediction performance. Unlike other machine learning-based regression models, GP regression provides uncertainty information and automatically optimizes hyperparameters. An experiment using Sentinel-2 multi-spectral images was conducted for cloud removal in the two agricultural regions. The prediction performance of GP regression was compared with that of random forest (RF) regression. Various combinations of input images and multi-spectral bands were considered for quantitative evaluations. The experimental results showed that using multi-temporal images with multi-spectral bands as inputs achieved the best prediction accuracy. Highly correlated adjacent multi-spectral bands and temporally correlated multi-temporal images resulted in an improved prediction accuracy. The prediction performance of GP regression was significantly improved in predicting the near-infrared band compared to that of RF regression. Estimating the distribution function of input data in GP regression could reflect the variations in the considered spectral band with a broader range. In particular, GP regression was superior to RF regression for reproducing structural patterns at both sites in terms of structural similarity. In addition, uncertainty information provided by GP regression showed a reasonable similarity to prediction errors for some sub-areas, indicating that uncertainty estimates may be used to measure the prediction result quality. These findings suggest that GP regression could be beneficial for cloud removal and optical image reconstruction. In addition, the impact analysis results of the input images provide guidelines for selecting optimal images for regression-based cloud removal.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.123-127
• /
• 2002

In this paper, we propose spatial prediction model for landslide hazard mapping that can account for the fuzziness of boundaries in thematic maps showing the different environmental impacts, depending on the scales and the resolutions of them. The fuzziness or uncertainty of boundary is represented in favourability function based on fuzzy object concept and the effects of them are quantitatively evaluated with the help of cross validation procedures. To illustrate the proposed schemes, a case study from Boeun, Korea was carried out. As a result, the proposed schemes are helpful to account for intrinsic uncertainties in categorical maps and can be effectively adopted in spatial prediction models for other purposes.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.518-523
• /
• 2002

Nowadays the Rational Function Model (RFM), an abstract sensor model, is substituting physical sensor models for highly complicated imaging geometry. But RFM is algorithm to be required many Ground Control Points (GCP). In case of RFM of the third order, At least forty GCP are required far RFM generation. The purpose of this study is to research more efficient algorithm on GCP and accurate algorithm similar to RFM. The Polynomial Camera Model is relatively accurate and requires a little GCP in comparisons of RFM. This paper introduces how to generate Polynomial Camera Model and fundamental algorithms for construction of 3-D topographic data using the Polynomial Camera Model information in the Kompsat stereo pair and describes how to generate the 3-D ground coordinates by manual matching. Finally we tried to extract height information for the whole image area with the stereo matching technique based on the correlation.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.177-180
• /
• 2008

Many researches have been tried to extract building models and created a 3D cyber city from LiDAR data. In this paper, the approach of extracting complex building by using airborne LiDAR data combined with airborne orthoimagery has been performed. The pseudo-building elevations were derived from modified discrete return LiDAR data. Based on information property of the pseudo-height, building features could be extracted. The results of this study indicated the improvement of building extraction.