• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.57-72
• /
• 2022

In this paper, we aimed to examine the flowering dates of cherry blossom and the peak dates of maple leaves in South Korea, by the combination of temperature observation data from ASOS (Automated Surface Observing System) and NDVI (Normalized Difference Vegetation Index) from MODIS (Moderate Resolution Imaging Spectroradiometer). The more recent years, the faster the flowering dates and the slower the peak dates. This is because of the impacts of climate change with the increase of air temperature in South Korea. By reflecting the climate change, our statistical models could reasonably predict the plant phenology with the CC (Correlation Coefficient) of 0.870 and the MAE (Mean Absolute Error) of 3.3 days for the flowering dates of cherry blossom, and the CC of 0.805 and the MAE of 3.8 for the peak dates of maple leaves. We could suppose a linear relationship between the plant phenology DOY (day of year) and the environmental factors like temperature and NDVI, which should be inspected in more detail. We found that the flowering date of cherry blossom was closely related to the monthly mean temperature of February and March, and the peak date of maple leaves was much associated with the accumulated temperature. Amore sophisticated future work will be required to examine the plant phenology using higher-resolution satellite images and additional meteorological variables like the diurnal temperature range sensitive to plant phenology. Using meteorological grid can help produce the spatially continuous raster maps for plant phenology.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.83-101
• /
• 2022

Accurate atmospheric correction is essential for the analysis of land surface and environmental monitoring. Aerosol optical depth (AOD) information is particularly important in atmospheric correction because the radiation attenuation by Mie scattering makes the differences between the radiation calculated at the satellite sensor and the radiation measured at the land surface. Thus, it is necessary to use high-quality AOD data for an appropriate atmospheric correction of high-resolution satellite images. In this study, we examined the Second Simulation of a Satellite Signal in the Solar Spectrum (6S)-based atmospheric correction results for the Sentinel-2 images in South Korea using raster AOD (MODIS) and single-point AOD (AERONET). The 6S result was overall agreed with the Sentinel-2 level 2 data. Moreover, using raster AOD showed better performance than using single-point AOD. The atmospheric correction using the single-point AOD yielded some inappropriate values for forest and water pixels, where as the atmospheric correction using raster AOD produced stable and natural patterns in accordance with the land cover map. Also, the Sentinel-2 normalized difference vegetation index (NDVI) after the 6S correction had similar patterns to the up scaled drone NDVI, although Sentinel-2 NDVI had relatively low values. Also, the spatial distribution of both images seemed very similar for growing and harvest seasons. Future work will be necessary to make efforts for the gap-filling of AOD data and an accurate bi-directional reflectance distribution function (BRDF) model for high-resolution atmospheric correction. These methods can help improve the land surface monitoring using the future Compact Advanced Satellite 500 in South Korea.

• Journal of Environmental Science International
• /
• v.31 no.9
• /
• pp.735-741
• /
• 2022

Global warming affects forests and their ecology. Diversity in the forest is a buffer that reduces the damage due to global warming. Mixed forests are ecologically more valuable as versatile habitats and are effective in preventing landslides. In Korea, most forests were created by simple afforestation with trees of evergreen species. Typically, evergreen trees are shallow-rooted, and deciduous trees are deep-rooted. Mixed forest tree roots grip the soil effectively, which reduces the occurrence of landslides. Therefore, improving the distribution of tree types is essential to reduce damage due to global warming. For this improvement, the investigation of tree types of the forest is needed. However, determining the tree type distribution of forests that are spread over wide areas is labor-intensive and time-consuming. This study suggests effective methods for determining the distribution of tree types in a forest that is spread across a relatively wide area. Using normalized difference vegetation index and RGB images from unmanned aerial vehicles, each evergreen and deciduous tree, and grassland area can be distinguished. The distinguished image determines the distribution of tree type. This method is effective compared to directly determining the tree type distribution in the forest by the use of manpower. The data from these methods could be applied to plan a mixed forest or to prepare for future damage due to global warming.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.57-69
• /
• 2024

Crop classification plays a vitalrole in monitoring agricultural landscapes and enhancing food production. In this study, we explore the effectiveness of Long Short-Term Memory (LSTM) models for crop classification, focusing on distinguishing between apple and rice crops. The aim wasto overcome the challenges associatedwith finding phenology-based classification thresholds by utilizing LSTM to capture the entire Normalized Difference Vegetation Index (NDVI)trend. Our methodology involvestraining the LSTM model using a reference site and applying it to three separate three test sites. Firstly, we generated 25 NDVI imagesfrom the Sentinel-2A data. Aftersegmenting study areas, we calculated the mean NDVI values for each segment. For the reference area, employed a training approach utilizing the NDVI trend line. This trend line served as the basis for training our crop classification model. Following the training phase, we applied the trained model to three separate test sites. The results demonstrated a high overall accuracy of 0.92 and a kappa coefficient of 0.85 for the reference site. The overall accuracies for the test sites were also favorable, ranging from 0.88 to 0.92, indicating successful classification outcomes. We also found that certain phenological metrics can be less effective in crop classification therefore limitations of relying solely on phenological map thresholds and emphasizes the challenges in detecting phenology in real-time, particularly in the early stages of crops. Our study demonstrates the potential of LSTM models in crop classification tasks, showcasing their ability to capture temporal dependencies and analyze timeseriesremote sensing data.While limitations exist in capturing specific phenological events, the integration of alternative approaches holds promise for enhancing classification accuracy. By leveraging advanced techniques and considering the specific challenges of agricultural landscapes, we can continue to refine crop classification models and support agricultural management practices.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.238-245
• /
• 2024

In this paper, we propose a framework for improving the performance of semantic segmentation of agricultural multispectral image using feature fusion techniques. Most of the semantic segmentation models being studied in the field of smart farms are trained on RGB images and focus on increasing the depth and complexity of the model to improve performance. In this study, we go beyond the conventional approach and optimize and design a model with multispectral and attention mechanisms. The proposed method fuses features from multiple channels collected from a UAV along with a single RGB image to increase feature extraction performance and recognize complementary features to increase the learning effect. We study the model structure to focus on feature fusion and compare its performance with other models by experimenting with favorable channels and combinations for crop images. The experimental results show that the model combining RGB and NDVI performs better than combinations with other channels.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1723-1735
• /
• 2022

Landslides are one of the most prevalent natural disasters, threating both humans and property. Also landslides can cause damage at the national level, so effective prediction and prevention are essential. Research to produce a landslide susceptibility map with high accuracy is steadily being conducted, and various models have been applied to landslide susceptibility analysis. Pixel-based machine learning models such as frequency ratio models, logistic regression models, ensembles models, and Artificial Neural Networks have been mainly applied. Recent studies have shown that the kernel-based convolutional neural network (CNN) technique is effective and that the spatial characteristics of input data have a significant effect on the accuracy of landslide susceptibility mapping. For this reason, the purpose of this study is to analyze landslide vulnerability using a pixel-based deep neural network model and a patch-based convolutional neural network model. The research area was set up in Gangwon-do, including Inje, Gangneung, and Pyeongchang, where landslides occurred frequently and damaged. Landslide-related factors include slope, curvature, stream power index (SPI), topographic wetness index (TWI), topographic position index (TPI), timber diameter, timber age, lithology, land use, soil depth, soil parent material, lineament density, fault density, normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) were used. Landslide-related factors were built into a spatial database through data preprocessing, and landslide susceptibility map was predicted using deep neural network (DNN) and CNN models. The model and landslide susceptibility map were verified through average precision (AP) and root mean square errors (RMSE), and as a result of the verification, the patch-based CNN model showed 3.4% improved performance compared to the pixel-based DNN model. The results of this study can be used to predict landslides and are expected to serve as a scientific basis for establishing land use policies and landslide management policies.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_1
• /
• pp.571-585
• /
• 2017

The number of spaceborne optical sensors including red-edge band has been increasing since red-edge band is known to be effective to enhance the information content on biophysical characteristics of vegetation. Considering that the Agriculture and Forestry Satellite is planning to carry an imaging sensor having red-edge band, we tried to analyze the current status and potential of red-edge band. As a case study, we analyzed the effect of using red-edge band and tried to find the optimum band width and wavelength region of the red-edge band to estimate leaf area index (LAI) of very dense tree canopy. Field spectral measurements were conducted from April to October over two tree species (white oak and pitch pine) having high LAI. Using the spectral measurement data, total 355 red-edge bands reflectance were simulated by varying five band width (10 nm, 20 nm, 30 nm, 40 nm, 50 nm) and 71 central wavelength. Two red-edge based spectral indices(NDRE, CIRE) were derived using the simulated red-edge band and compared with the LAI of two tree species. Both NDRE and CIRE showed higher correlation coefficients with the LAI than NDVI. This would be an alternative to overcome the limitation of the NDVI saturation problem that NDVI has not been effective to estimate LAI over very dense canopy situation. There was no significant difference among five band widths of red-edge band in relation to LAI. The highest correlation coefficients were obtained at the red-edge band of center wavelength near the 720 nm for the white oak and 710 nm for the pitch pine. To select the optimum band width and wavelength region of the red-edge band, further studies are necessary to examine the relationship with other biophysical variables, such as chlorophyll, nitrogen, water content, and biomass.

• Journal of Bio-Environment Control
• /
• v.24 no.4
• /
• pp.301-307
• /
• 2015

High quality transplants are critical for success in crop production. Increasing numbers of growers purchase their transplants from specialized transplant producers instead of growing their own transplants. A drawback of purchasing transplants is the risk of deterioration to transplants during transportation from transplant producers to the growers. This study evaluates the influence of temperature on the quality of grafted tomatoes transplants (Solanum lycopersicum cv. Super Doterang), in order to propose optimum temperature condition for the transportation of grafted tomato transplants. Grafted tomato transplants with visible flower trusses were exposed to different air temperature ($10^{\circ}C$, $25^{\circ}C$, or $40^{\circ}C$) for 2, 4, or 6 hours. After treatment, the NDVI (Normalized Difference Vegetation Index) values of tomato transplants treated at 25 and $40^{\circ}C$ were lower than that at $10^{\circ}C$. The root fresh weight was lowest at $40^{\circ}C$. After transplanting, the transplants that were exposed to the air temperature of $40^{\circ}C$ exhibited chlorosis and blight on lower leaves. The degree of damage on leaves was severer as the high temperature exposure time was longer. The temperature conditions during the transportation also influenced the growth, flowering and fruit set of tomatoes after transplanting. The fruit number and weight of first truss was lowest at $40^{\circ}C$ for 6 hours. Accordingly, it is recommended that the temperature during the transportation should be controlled and kept at the range from 10 to $25^{\circ}C$ even though the period is short (within as six hours) in order to maintain the quality of transplants.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.649-663
• /
• 2019

The 2018 United Nations Development Programme (UNDP) report announced that deforestation in North Korea is the most extreme situation and in terms of climate change, this deforestation is a global scale issue. To respond deforestation, various study and projects are conducted based on remote sensing, but access to public data in North Korea is limited, and objectivity is difficult to be guaranteed. In this study, the forest detection based on density estimation in statistic using Landsat imagery was conducted in Gangwon province which is the only administrative district divided into South and North. The forest spatial data of South Korea was used as data for the labeling of forest and Non-forest in the Normalized Difference Vegetation Index (NDVI), and a threshold (0.6658) for forest detection was set by Gaussian Probability Density Function (PDF) estimation by category. The results show that the forest area decreased until the 2000s in both Korea, but the area increased in 2010s. It is also confirmed that the reduction of forest area on the local scale is the same as the policy direction of urbanization and industrialization at that time. The Kappa value for validation was strong agreement (0.8) and moderate agreement (0.6), respectively. The detection based on the Gaussian PDF estimation is considered a method for complementing the statistical limitations of the existing detection method using satellite imagery. This study can be used as basic data for deforestation in North Korea and Based on the detection results, it is necessary to protect and restore forest resources.

• Korean Journal of Soil Science and Fertilizer
• /
• v.40 no.6
• /
• pp.435-441
• /
• 2007

Ground-based optical sensing over the crop canopy provides information on the mass of plant body which reflects the light, as well as crop nitrogen content which is closely related to the greenness of plant leaves. This method has the merits of being non-destructive real-time based, and thus can be conveniently used for decision making on application of nitrogen fertilizers for crops standing in fields. In the present study relationships among leaf nitrogen content of rice canopy, crop growth status, and Normalized Difference Vegetation Index (NDVI) values were investigated. We measured Green normalized difference vegetation index($gNDVI=({\rho}0.80{\mu}m-{\rho}0.55{\mu}m)/({\rho}0.80{\mu}m+{\rho}0.55{\mu}m)$) and NDVI($({\rho}0.80{\mu}m-{\rho}0.68{\mu}m)/({\rho}0.80{\mu}m+{\rho}0.68{\mu}m)$) were measured by using two different active sensors (Greenseeker, NTech Inc. USA). The study was conducted in the years 2005-06 during the rice growing season at the experimental plots of National Institute of Agricultural Science and Technology located at Suwon, Korea. The experiments carried out with randomized complete block design with the application of four levels of nitrogen fertilizers (0, 70, 100, 130kg N/ha) and same amount of phosphorous and potassium content of the fertilizers. gNDVI and rNDVI increased as growth advanced and reached to maximum values at around early August, G(NDVI) were a decrease in values of observed with the crop maturation. gNDVI values and leaf nitrogen content were highly correlated at early July in 2005 and 2006. On the basis of this finding we attempted to estimate the leaf N contents using gNDVI data obtained in 2005 and 2006. The determination coefficients of the linear model by gNDVI in the years 2005 and 2006 were 0.88 and 0.94, respectively. The measured and estimated leaf N contents using gNDVI values showed good agreement ($R^2=0.86^{***}$). Results from this study show that gNDVI values represent a significant positive correlation with leaf N contents and can be used to estimate leaf N before the panicle formation stage. gNDVI appeared to be a very effective parameter to estimate leaf N content the rice canopy.