• 대기
• /
• 제25권1호
• /
• pp.1-18
• /
• 2015

The most objective way to overcome the limitation of numerical weather prediction model is to represent the uncertainty of prediction by introducing probabilistic forecast. The uncertainty of the numerical weather prediction system developed due to the parameterization of unresolved scale motions and the energy losses from the sub-scale physical processes. In this study, we focused on the growth of model errors. We performed ensemble forecast to represent model uncertainty. By employing the multi-physics scheme (PHYS) and the stochastic kinetic energy backscatter scheme (SKEBS) in simulating typhoon Rusa (2002), we assessed the performance level of the two schemes. The both schemes produced better results than the control run did in the ensemble mean forecast of the track. The results using PHYS improved by 28% and those based on SKEBS did by 7%. Both of the ensemble mean errors of the both schemes increased rapidly at the forecast time 84 hrs. The both ensemble spreads increased gradually during integration. The results based on SKEBS represented model errors very well during the forecast time of 96 hrs. After the period, it produced an under-dispersive pattern. The simulation based on PHYS overestimated the ensemble mean error during integration and represented the real situation well at the forecast time of 120 hrs. The displacement speed of the typhoon based on PHYS was closest to the best track, especially after landfall. In the sensitivity tests of the model uncertainty of SKEBS, ensemble mean forecast was sensitive to the physics parameterization. By adjusting the forcing parameter of SKEBS, the default experiment improved in the ensemble spread, ensemble mean errors, and moving speed.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2008년도 학술발표회 논문집
• /
• pp.345-351
• /
• 2008

미래의 기후변화 영향평가에 있어 전지구모형(General Circulation Model)은 가장 중요한 자료 중 하나이다. 즉, 온실가스 방출(emission) 시나리오에 기초한 전지구모형의 모의결과를 이용하면 미래 수자원에 대한 정보를 얻을 수 있다. 하지만 미래 수자원은 방출 시나리오, 상세화(downscaling) 기법, 강우-유출모형, 전지구모형의 종류에 따라 크게 달라질 수 있어 매우 큰 불확실성(uncertainty)을 포함하고 있다. 이러한 불확실성을 줄이는 방법 중 하나로 전지구모형의 모의능력에 따라 가중치(weight)를 부여하고 결합(combining)하는 multi-model 앙상블(ensemble) 기법이 선진국을 중심으로 활발히 연구되고 있다. 본 연구에서는 우선 기후변화 영향평가를 위하여 국내에서 사용가능한 전지구모형을 조사하고 그 중CCSM3, CSRIO, ECHAM4, GFDL, MIRCO를 선택하였다. 한강 충주댐 유역에 대하여 과거($1980{\sim}1999$년)와 미래($2030{\sim}2049$년) 기간에 대하여 전지구모형의 기후정보를 간단한 선형보간법을 이용하여 상세화하였다. 다음으로 multi-model 앙상블 기법을 조사하였다. 본 연구에서는 Giorgi et al.(2002)이 제안한 Reliability Ensemble Average(REA) 기법을 적용하여 선형보간법으로 상세화한 전지구모형의 모의결과에 가중치를 주어 불확실성을 줄이는 연구를 수행하였다. 특히 REA를 구성하는 식 중 모형의 편차(bias) 뿐만 아니라 분산(variance)까지 고려함으로서 이를 개선하는 Modified-REA를 제안하였다. 제안한 방안을 이용하여 결합한 전지구모형의 모의결과가 기존 REA의 결과보다 기후정보의 불확실성을 더 줄일 수 있는 것으로 나타났다.

• 대기
• /
• 제28권1호
• /
• pp.15-24
• /
• 2018

Sea ice plays an important role in modulating surface conditions at high and mid-latitudes. It reacts rapidly to climate change, therefore, it is a good indicator for capturing these changes from the Arctic climate. While many models have been used to study the predictability of climate variables, their performance in predicting sea ice was not well assessed. This study examines the predictability of the Arctic sea ice extent from ensemble prediction systems. The analysis is focused on verification of predictability in each model compared to the observation and prediction in particular, on lead time in Sub-seasonal to Seasonal (S2S) scales. The S2S database now provides quasi-real time ensemble forecasts and hindcasts up to about 60 days from 11 centers: BoM, CMA, ECCC, ECMWF, HMCR, ISAC-CNR, JMA, KMA, Meteo France, NCEP and UKMO. For multi model comparison, only models coupled with sea ice model were selected. Predictability is quantified by the climatology, bias, trends and correlation skill score computed from hindcasts over the period 1999 to 2009. Most of models are able to reproduce characteristics of the sea ice, but they have bias with seasonal dependence and lead time. All models show decreasing sea ice extent trends with a maximum magnitude in warm season. The Arctic sea ice extent can be skillfully predicted up 6 weeks ahead in S2S scales. But trend-independent skill is small and statistically significant for lead time over 6 weeks only in summer.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.624-626
• /
• 2023

Credit scoring is a technique used by financial institutions to assess the creditworthiness of potential borrowers. This involves evaluating a borrower's credit history to predict the likelihood of defaulting on a loan. This paper presents an ensemble of two Transformer based models within a framework for discriminating the default risk of loan applications in the field of credit scoring. The first model is FinBERT, a pretrained NLP model to analyze sentiment of financial text. The second model is FT-Transformer, a simple adaptation of the Transformer architecture for the tabular domain. Both models are trained on the same underlying data set, with the only difference being the representation of the data. This multi-modal approach allows us to leverage the unique capabilities of each model and potentially uncover insights that may not be apparent when using a single model alone. We compare our model with two famous ensemble-based models, Random Forest and Extreme Gradient Boosting.

• Asia-Pacific Journal of Atmospheric Sciences
• /
• 제54권4호
• /
• pp.563-573
• /
• 2018

An Expert Seasonal Prediction System for operational Seasonal Outlook (ESPreSSO) is developed based on the APEC Climate Center (APCC) Multi-Model Ensemble (MME) dynamical prediction and expert-guided statistical downscaling techniques. Dynamical models have improved to provide meaningful seasonal prediction, and their prediction skills are further improved by various ensemble and downscaling techniques. However, experienced scientists and forecasters make subjective correction for the operational seasonal outlook due to limited prediction skills and biases of dynamical models. Here, a hybrid seasonal prediction system that grafts experts' knowledge and understanding onto dynamical MME prediction is developed to guide operational seasonal outlook in Korea. The basis dynamical prediction is based on the APCC MME, which are statistically mapped onto the station-based observations by experienced experts. Their subjective selection undergoes objective screening and quality control to generate final seasonal outlook products after physical ensemble averaging. The prediction system is constructed based on 23-year training period of 1983-2005, and its performance and stability are assessed for the independent 11-year prediction period of 2006-2016. The results show that the ESPreSSO has reliable and stable prediction skill suitable for operational use.

• 한국컴퓨터정보학회논문지
• /
• 제28권4호
• /
• pp.41-51
• /
• 2023

본 논문에서는 보행자의 걸음걸이로부터 분노 감정 검출을 위한 다중 시간 윈도 특징 추출 기술을 제안한다. 기존의 걸음걸이 기반 감정인식 기술에서는 보행자의 보폭, 한 보폭에 걸리는 시간, 보행 속력, 목과 흉부의 전방 기울기 각도(Forward Tilt Angle)를 계산하고, 전체 구간에 대해서 최솟값, 평균값, 최댓값을 계산해서 이를 특징으로 활용하였다. 하지만 이때 각 특징은 보행 전체 구간에 걸쳐 항상 균일하게 변화가 발생하는 것이 아니라, 때로는 지역적으로 변화가 발생한다. 이에 본 연구에서는 장기부터 중기 그리고 단기까지 즉, 전역적인 특징과 지역적인 특징을 모두 추출할 수 있는 다중 시간 윈도 특징 추출(Multi-Time Window Feature Extraction) 기술을 제안한다. 또한, 제안하는 특징 추출 기술을 통해 각 구간에서 추출된 특징들을 효과적으로 학습할 수 있는 앙상블 모델을 제안한다. 제안하는 앙상블 모델(Ensemble Model)은 복수의 분류기로 구성되며, 각 분류기는 서로 다른 다중 시간 윈도에서 추출된 특징으로 학습된다. 제안하는 특징 추출 기술과 앙상블 모델의 효과를 검증하기 위해 일반인에게 공개된 3차원 걸음걸이 데이터 세트를 사용하여 시험 평가를 수행했다. 그 결과, 4가지 성능 평가지표에 대해서 제안하는 앙상블 모델이 기존의 특징 추출 기술로 학습된 머신러닝(Machine Learning) 모델들과 비교하여 최고의 성능을 달성하는 것을 입증하였다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2021년도 제64차 하계학술대회논문집 29권2호
• /
• pp.313-315
• /
• 2021

Timely and accurate diagnosis of lung diseases using Chest X-ray images has been gained much attention from the computer vision and medical imaging communities. Although previous studies have presented the capability of deep convolutional neural networks by achieving competitive binary classification results, their models were seemingly unreliable to effectively distinguish multiple disease groups using a large number of x-ray images. In this paper, we aim to build an advanced approach, so-called Ensemble Knowledge Distillation (EKD), to significantly boost the classification accuracies, compared to traditional KD methods by distilling knowledge from a cumbersome teacher model into an ensemble of lightweight student models with parallel branches trained with ground truth labels. Therefore, learning features at different branches of the student models could enable the network to learn diverse patterns and improve the qualify of final predictions through an ensemble learning solution. Although we observed that experiments on the well-established ChestX-ray14 dataset showed the classification improvements of traditional KD compared to the base transfer learning approach, the EKD performance would be expected to potentially enhance classification accuracy and model generalization, especially in situations of the imbalanced dataset and the interdependency of 14 weakly annotated thorax diseases.

• 호남수학학술지
• /
• 제36권1호
• /
• pp.11-27
• /
• 2014

In this paper, we propose closures for multi-phase flow models, which satisfy boundary conditions and conservation constraints. The models governing the evolution of the fluid mixing are derived by applying an ensemble averaging procedure to the microphysical equations characterized by distinct phases. We consider compressible multi species multi-phase flow with surface tension and transport.

• 스마트미디어저널
• /
• 제13권4호
• /
• pp.9-15
• /
• 2024

Tree-based algorithms have been the dominant methods used build a prediction model for tabular data. This also includes personal credit data. However, they are limited to compatibility with categorical and numerical data only, and also do not capture information of the relationship between other features. In this work, we proposed an ensemble model using the Transformer architecture that includes text features and harness the self-attention mechanism to tackle the feature relationships limitation. We describe a text formatter module, that converts the original tabular data into sentence data that is fed into FinBERT along with other text features. Furthermore, we employed FT-Transformer that train with the original tabular data. We evaluate this multi-modal approach with two popular tree-based algorithms known as, Random Forest and Extreme Gradient Boosting, XGBoost and TabTransformer. Our proposed method shows superior Default Recall, F1 score and AUC results across two public data sets. Our results are significant for financial institutions to reduce the risk of financial loss regarding defaulters.

• Ocean Science Journal
• /
• 제41권1호
• /
• pp.1-10
• /
• 2006

Total sea surface temperature (SST) in a coupled GCM is diagnosed by separating the variability into signal variance and noise variance. The signal and the noise is calculated from multi-decadal simulations from the COLA anomaly coupled GCM and the interactive ensemble model by assuming both simulations have a similar signal variance. The interactive ensemble model is a new coupling strategy that is designed to increase signal to noise ratio by using an ensemble of atmospheric realizations coupled to a single ocean model. The procedure for separating the signal and the noise variability presented here does not rely on any ad hoc temporal or spatial filter. Based on these simulations, we find that the signal versus the noise of SST variability in the North Pacific is significantly different from that in the equatorial Pacific. The noise SST variability explains the majority of the total variability in the North Pacific, whereas the signal dominates in the deep tropics. It is also found that the spatial characteristics of the signal and the noise are also distinct in the North Pacific and equatorial Pacific.