• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.103-110
• /
• 2022

Since satellite images generally include clouds in the atmosphere, it is essential to detect or mask clouds before satellite image processing. Clouds were detected using physical characteristics of clouds in previous research. Cloud detection methods using deep learning techniques such as CNN or the modified U-Net in image segmentation field have been studied recently. Since image segmentation is the process of assigning a label to every pixel in an image, precise pixel-based dataset is required for cloud detection. Obtaining accurate training datasets is more important than a network configuration in image segmentation for cloud detection. Existing deep learning techniques used different training datasets. And test datasets were extracted from intra-dataset which were acquired by same sensor and procedure as training dataset. Different datasets make it difficult to determine which network shows a better overall performance. To verify the effectiveness of the cloud detection network such as Cloud-Net, two types of networks were trained using the cloud dataset from KOMPSAT-3 images provided by the AIHUB site and the L8-Cloud dataset from Landsat8 images which was publicly opened by a Cloud-Net author. Test data from intra-dataset of KOMPSAT-3 cloud dataset were used for validating the network. The simulation results show that the network trained with KOMPSAT-3 cloud dataset shows good performance on the network trained with L8-Cloud dataset. Because Landsat8 and KOMPSAT-3 satellite images have different GSDs, making it difficult to achieve good results from cross-sensor validation. The network could be superior for intra-dataset, but it could be inferior for cross-sensor data. It is necessary to study techniques that show good results in cross-senor validation dataset in the future.

• Journal of the Korean Solar Energy Society
• /
• v.38 no.6
• /
• pp.27-36
• /
• 2018

Typical Meteorological Year Dataset is necessary for the renewable energy feasibility study. Since National Renewable Energy Laboratory has been built Typical Meteorological Year Dataset in 1978, gridded datasets taken from numerical weather prediction or satellite imagery are employed to produce Typical Meteorological Year Dataset. In general, Typical Meteorological Year Dataset is generated by using long-term in-situ observations. However, solar insolation is not usually measured at synoptic observing stations and therefore it is limited to build the Typical Meteorological Year Dataset with only in-situ observation. This study attempts to build the Typical Meteorological Year Dataset with satellite derived solar insolation as an alternative and then we evaluate the Typical Meteorological Year Dataset made by using satellite derived solar irradiance at Daejeon ground station. The solar irradiance is underestimated when satellite imagery is employed.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1224-1226
• /
• 2003

Dust-storm is one of the heaviest hazardous weather which frequently affects most part of northern China in spring. Satellite multi-spectral observations can provide significant information for detecting and quantitative determining the property of dust-storm . An algorithm to monitor dust-storm automatically was developed based on satellite observation. The algorithm utilizes split widows technique and spectral classification technique and also developed a new dust remote sensing product Infra -red Difference Dust Index (IDDI) proxy dust-loading dataset using GMS-5.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.459-466
• /
• 2023

In the last decade, artificial intelligence's dramatic advancement with the development of various deep learning techniques has significantly contributed to remote sensing fields and satellite image applications. Among many prominent areas, super-resolution research has seen substantial growth with the release of several benchmark datasets and the rise of generative adversarial network-based studies. However, most previously published remote sensing benchmark datasets represent spatial resolution within approximately 10 meters, imposing limitations when directly applying for super-resolution of small objects with cm unit spatial resolution. Furthermore, if the dataset lacks a global spatial distribution and is specialized in particular land covers, the consequent lack of feature diversity can directly impact the quantitative performance and prevent the formation of robust foundation models. To overcome these issues, this paper proposes a method to generate benchmark datasets by simulating the modulation transfer functions of the sensor. The proposed approach leverages the simulation method with a solid theoretical foundation, notably recognized in image fusion. Additionally, the generated benchmark dataset is applied to state-of-the-art super-resolution base models for quantitative and visual analysis and discusses the shortcomings of the existing datasets. Through these efforts, we anticipate that the proposed benchmark dataset will facilitate various super-resolution research shortly in Korea.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.96-99
• /
• 2003

Land cover map is a typical GIS database which shows the Earth's physical surface differentiated by standardized homogeneous land cover types. Satellite images acquired by Landsat TM were primarily used to produce a land cover map of 7 land cover classes; however, it now becomes to produce a more accurate land cover classification dataset of 23 classes thanks to higher resolution satellite images, such as SPOT-5 and IKONOS. The use of the newly produced high resolution land cover map of 23 classes for such activities to estimate non-point sources of pollution like water pollution modeling and atmospheric dispersion modeling is expected to result a higher level of accuracy and validity in various environmental monitoring results. The estimation of pollution from non-point sources using GIS-based modeling with land cover dataset shows fairly accurate and consistent results.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.395-407
• /
• 2023

Super-resolution (SR) has great significance in image processing because it enables downstream vision tasks with high spatial resolution. Recently, SR studies have adopted deep learning networks and achieved remarkable SR performance compared to conventional example-based methods. Deep-learning-based SR models generally require low-resolution (LR) images and the corresponding high-resolution (HR) images as training dataset. Due to the difficulties in obtaining real-world LR-HR datasets, most SR models have used only HR images and generated LR images with predefined degradation such as bicubic downsampling. However, SR models trained on simple image degradation do not reflect the properties of the images and often result in deteriorated SR qualities when applied to real-world images. In this study, we propose an image degradation model for HR satellite images based on the modulation transfer function (MTF) of an imaging sensor. Because the proposed method determines the image degradation based on the sensor properties, it is more suitable for training SR models on remote sensing images. Experimental results on HR satellite image datasets demonstrated the effectiveness of applying MTF-based filters to construct a more realistic LR-HR training dataset.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.180-180
• /
• 2023

To improve global risk management, understanding the characteristics and distribution of precipitation is crucial. However, obtaining spatially and temporally resolved climatic data remains challenging due to sparse gauge observations and limited data availability, despite the use of satellite and reanalysis products. To address this challenge, merging available precipitation products has been introduced to generate spatially and temporally reliable data by taking advantage of the strength of the individual products. However, most of the existing studies utilize all the available products without considering the varying performances of each dataset in different regions. Comprehensively considering the relative contributions of each parent dataset is necessary since their contributions may vary significantly and utilizing all the available datasets for data merging may lead to significant data redundancy issues. Hence, for this study, we introduce a site-specific precipitation merging method that utilizes the Quadruple Collocation (QC) approach, which acknowledges the existence of error-cross correlation between the parent datasets, to create a high-resolution global daily precipitation data from 2001-2020. The performance of multiple gridded precipitation products are first evaluated per region to determine the best combination of quadruplets to be utilized in estimating the error variances through the QC approach and computation of merging weights. The merged precipitation is then computed by adding the precipitation from each dataset in the quadruplet multiplied by each respective merging weight. Our results show that our approach holds promise for generating reliable global precipitation data for data-scarce regions lacking spatially and temporally resolved precipitation data.

• Journal of Korean Society for Atmospheric Environment
• /
• v.34 no.3
• /
• pp.493-507
• /
• 2018

Due to high spatio-temporal variability of amount and optical/microphysical properties of atmospheric aerosols, satellite-based observations have been demanded for spatiotemporal monitoring the major aerosols. Observations of the heavy aerosol episodes and determination on the dominant aerosol types from a geostationary satellite can provide a chance to prepare in advance for harmful aerosol episodes as it can repeatedly monitor the temporal evolution. A new geostationary observation sensor, namely the Advanced Himawari Imager (AHI), onboard the Himawari-8 platform, has been observing high spatial and temporal images at sixteen wavelengths from 2016. Using observed spectral visible reflectance and infrared brightness temperature (BT), the algorithm to find major aerosol type such as volcanic ash (VA), desert dust (DD), polluted aerosol (PA), and clean aerosol (CA), was developed. RGB color composite image shows dusty, hazy, and cloudy area then it can be applied for comparing aerosol detection product (ADP). The CALIPSO level 2 vertical feature mask (VFM) data and MODIS level 2 aerosol product are used to be compared with the Himawari-8/AHI ADP. The VFM products can deliver nearly coincident dataset, but not many match-ups can be returned due to presence of clouds and very narrow swath. From the case study, the percent correct (PC) values acquired from this comparisons are 0.76 for DD, 0.99 for PA, 0.87 for CA, respectively. The MODIS L2 Aerosol products can deliver nearly coincident dataset with many collocated locations over ocean and land. Increased accuracy values were acquired in Asian region as POD=0.96 over land and 0.69 over ocean, which were comparable to full disc region as POD=0.93 over land and 0.48 over ocean. The Himawari-8/AHI ADP algorithm is going to be improved continuously as well as the validation efforts will be processed by comparing the larger number of collocation data with another satellite or ground based observation data.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.375-386
• /
• 2022

The city of Khartoum, the capital of Sudan, was heavily damaged by the flood of the Nile in 2020. Classification using satellite images can define the damaged area and help emergency response. As Synthetic Aperture Radar (SAR) uses microwave that can penetrate cloud, it is suitable to use in the flood study. In this study, Random Forest classifier, one of the supervised classification algorithms, was applied to the flood event in Khartoum with various sizes of the training dataset and number of images using Sentinel-1 SAR. To create a training dataset, we used unsupervised classification and visual inspection. Firstly, Random Forest was performed by reducing the size of each class of the training dataset, but no notable difference was found. Next, we performed Random Forest with various number of images. Accuracy became better as the number of images in creased, but converged to a maximum value when the dataset covers the duration from flood to the completion of drainage.