Yeji Choi

Dr. Yeji Choi


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
KCKeumgang Cha
Keumgang Cha
JSJunghoon Seo
Junghoon Seo
YCYeji Choi
Yeji Choi
In the training of deep learning models, how the model parameters are initialized greatly affects the model performance, sample efficiency, and convergence speed. Recently, representation learning for model initialization has been actively studied in the remote sensing field. In particular, the appearance characteristics of the imagery obtained using the synthetic aperture radar (SAR) sensor are quite different from those of general electro-optical (EO) images, and thus, representation learning is even more important in remote sensing domain. Motivated from contrastive multiview coding, we propose multimodal representation learning for SAR semantic segmentation. Unlike previous studies, our method jointly uses EO imagery, SAR imagery, and a label mask. Several experiments show that our approach is superior to the existing methods in model performance, sample efficiency, and convergence speed.

11 September 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YCYeji Choi
Yeji Choi
KCKeumgang Cha
Keumgang Cha
MBMinyoung Back
Minyoung Back
HCHyunguk Choi
Hyunguk Choi
TJTaegyun Jeon
Taegyun Jeon
Quantitative precipitation prediction is essential for managing water-related disasters, including floods, landslides, tsunamis, and droughts. Recent advances in data-driven approaches using deep learning techniques provide improved precipitation nowcasting performance. Moreover, it has been known that multi-modal information from various sources could improve deep learning performance. This study introduces the RAIN-F+ dataset, which is the fusion dataset for rainfall prediction, and proposes the benchmark models for precipitation prediction using the RAIN-F+ dataset. The RAIN-F+ dataset is an integrated weather observation dataset including radar, surface station, and satellite observations covering the land area over the Korean Peninsula. The benchmark model is developed based on the U-Net architecture with residual upsampling and downsampling blocks. We examine the results depending on the number of the integrated dataset for training. Overall, the results show that the fusion dataset outperforms the radar-only dataset over time. Moreover, the results with the radar-only dataset show the limitations in predicting heavy rainfall over 10 mm/h. This suggests that the various information from multi-modality is crucial for precipitation nowcasting when applying the deep learning method.

26 November 2023
Verified
Book Chapter
Closed access
PDF file
SKSoyeon Kim
Soyeon Kim
JCJunho Choi
Junho Choi
YCYeji Choi
Yeji Choi
SLSubeen Lee
Subeen Lee
ASArtyom Stitsyuk
Artyom Stitsyuk
JCJaesik Choi
Jaesik Choi

9 September 2020 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
YCYeji Choi
Yeji Choi
SKSeongchan Kim
Seongchan Kim
The understanding of different characteristics of the stratiform and convective system is important for meteorological research, including precipitation retrievals from satellite observations, precipitation parameterization in numerical prediction models, and precipitation climatology. In this study, the possibility of discriminating rain types using deep learning techniques is examined using satellite microwave observation data. Herein, we build two types of deep neural networks for rain type classification, i.e., U-net (RTC-U-net) and fully connected neural network (RTC-fcNN). Experiments are performed with the data obtained from two sensors onboard the global precipitation measurement (GPM) satellite. The brightness temperatures observed from the GPM microwave imager (GMI) are used as input features, whereas rain types retrieved by dual-frequency precipitation radar (DPR) are used as labels. We generated the merged 40- $\times $ -40 pixel data for training and testing the data set by cropping the GMI observed fields overlapping the DPR observations. Overall, the proposed RTC-U-net and RTC-fcNN effectively classify four rain types, i.e., no-rain, stratiform, convective, and others. The total accuracy for the four rain types is 0.95, and the weighted mean of precision, recall, and f-score for stratiform and convective are 0.76, 0.68, and 0.71, respectively. Results show that the proposed techniques can extract the characteristics of each rain type from the data itself. To the best of our knowledge, this study is the first to apply a segmentation method with U-net for rain type classification.

8 October 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Open access
ECEunbin Cho
Eunbin Cho
EKEunbin Kim
Eunbin Kim
YCYeji Choi
Yeji Choi
Cloud cover influences solar radiation reaching the Earth’s surface, impacting industries. Recently, advancements in weather prediction have been made through the use of satellite images and deep learning methods for enhancing the accuracy of cloud variability forecasts. Despite these advancements, computational limitations arise due to the large size of the satellite images. Although conventional practices involving the cropping or downscaling of images into smaller sizes have been employed, these processes have been observed to compromise the accuracy of the predicted images. In this study, we introduce Cloudstream, a novel approach that combines a CNN-based encoder, decoder, and PredRNN-V2 as a backbone model. This approach prioritizes computational efficiency while also maintaining prediction accuracy. Cloudstream predicted future cloud detection image data, training with the dataset of the sequential cloud detection and infrared channel images from the Korean Geostationary Meteorological Satellite GEO-KOMPSAT-2A. Additionally, we explored the utilization of non-patch images in the development of Cloudstream. A quantitative evaluation of the model was performed using two different input sizes for the same geographic area: 128×128 pixels and 512×512 pixels. There are no significant differences in F1 scores between Cloudstream and PredRNN-V2 when processing 128×128 inputs, however, Cloudstream required three times fewer floating-point operations than PredRNN-V2. Additionally, we found that 512×512 high-resolution input images exhibit superior prediction performance compared to 128×128 low-resolution input images. This study contributes to the refinement of deep learning-based video frame prediction models by focusing on optimizing satellite image prediction, addressing computational challenges.

20 July 2018 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
YCYeji Choi
Yeji Choi
DSDong-Bin Shin
Dong-Bin Shin
MJMinsu Joh
Minsu Joh
Passive microwave radiometric signatures are affected by microphysical properties and hydrometeor distributions. Various microphysical properties of hydrometeors assumed in numerical simulations of precipitating clouds cause the different emission and scattering signals. This study compares the radiometric signatures obtained from five microphysics (MP) schemes of the Weather Research and Forecasting (WRF) model during the simulation of eight typhoons with respect to Tropical Rainfall Measuring Mission Microwave Imager observations. The MP schemes include the Thompson (MP8), Morrison two moment (MP10), WRF Double Moment 6 Class (MP16), National Severe Storms Laboratory 2 moment (MP17), and Thompson aerosol-aware (MP28) schemes. The results show that most of the schemes produce insufficient emission/scattering signals from liquid/ice particles over the same rain rate compared to the observations. It was also confirmed that, depending on the schemes, the scattering signals appear to be more variable than the emission signals. In general, MP16 is more frequently identified as the scheme with the smallest biases in both low- and high-frequency channels for individual orbits. However, the results demonstrate that one scheme does not work best in all cases examined here. This suggests that the characteristics assumed in MP schemes should be carefully understood to simulate precipitating clouds. Moreover, comparisons of the radiometric signatures from simulations and observations might be used to understand the uncertainties caused by incorrect assumptions of the microphysical properties of precipitating clouds.