본 연구는 13개의 제한된 출현자료를 바탕으로 아고산대 희귀식물인 흰참꽃나무(Rhododendron sohayakiense var. koreanum)의 기후변화에 따른 잠재 생육지 변화를 예측하였다. 소규모 자료로 인한 예측력 저하를 보완하기 위해 이변량 조합 기반의 소규모 앙상블 모형(Ensemble of Small Models, ESM)을 구축하였다. 환경변수는 CHELSA v2.1 의 Bioclim 및 확장변수와 NASA SRTM(Shuttle Radar Topography Mission) DEM(Digital Elevation Model) 기반 파생 지형변수 중 총 7개(BIO2, gst, gsp, swe, Slope, TPI, TWI)를 선정하였다. R의 ecospat을 이용해 SSP1-2.6, SSP3-7.0, SSP5-8.5 3개 시나리오 하에서 2100년까지 생육지 분포를 예측한 결과 모든 시나리오에서 잠재 생육지는 점차 축소되었고, 특히 SSP5-8.5에서는 대부분의 적합지가 소멸하는 것으로 나타났다. 본 연구는 소량의 출현자료만으 로도 ESM을 적용하여 희귀종의 기후변화 취약성을 정량적으로 도출할 수 있음을 보여주며, 흰참꽃나무의 향후 보전 전략 수립을 위한 기초 자료로 활용될 수 있다.

This study proposes a weighted ensemble deep learning framework for accurately predicting the State of Health (SOH) of lithium-ion batteries. Three distinct model architectures—CNN-LSTM, Transformer-LSTM, and CEEMDAN-BiGRU—are combined using a normalized inverse RMSE-based weighting scheme to enhance predictive performance. Unlike conventional approaches using fixed hyperparameter settings, this study employs Bayesian Optimization via Optuna to automatically tune key hyperparameters such as time steps (range: 10-35) and hidden units (range: 32-128). To ensure robustness and reproducibility, ten independent runs were conducted with different random seeds. Experimental evaluations were performed using the NASA Ames B0047 cell discharge dataset. The ensemble model achieved an average RMSE of 0.01381 with a standard deviation of ±0.00190, outperforming the best single model (CEEMDAN-BiGRU, average RMSE: 0.01487) in both accuracy and stability. Additionally, the ensemble's average inference time of 3.83 seconds demonstrates its practical feasibility for real-time Battery Management System (BMS) integration. The proposed framework effectively leverages complementary model characteristics and automated optimization strategies to provide accurate and stable SOH predictions for lithium-ion batteries.

Rapidly changing environmental factors due to climate change are increasing the uncertainty of crop growth, and the importance of crop yield prediction for food security is becoming increasingly evident in Republic of Korea. Traditionally, crop yield prediction models have been developed by using statistical techniques such as regression models and correlation analysis. However, as machine learning technique develops, it is able to predict the crop yield more accurate than the statistical techniques. This study aims at proposing the onion yield prediction framework to accurately predict the onion yield by using various environmental factor data. Temperature, humidity, precipitation, solar radiation, and wind speed are considered as climate factors and irrigation water and nitrogen application rate are considered as soil factors. To improve the performance of the prediction model, ensemble learning technique is applied to the proposed framework. The coefficient of determination of the proposed stacked ensemble framework is 0.96, which is a 24.68% improvement over the coefficient of determination of 0.77 of the existing single machine learning model. This framework can be applied to the particular farmland so that each farm can get their customized prediction model, which is visualized by the web system.

This study proposes a weight optimization technique based on Mixture Design of Experiments (MD) to overcome the limitations of traditional ensemble learning and achieve optimal predictive performance with minimal experimentation. Traditional ensemble learning combines the predictions of multiple base models through a meta-model to generate a final prediction but has limitations in systematically optimizing the combination of base model performances. In this research, MD is applied to efficiently adjust the weights of each base model, constructing an optimized ensemble model tailored to the characteristics of the data. An evaluation of this technique across various industrial datasets confirms that the optimized ensemble model proposed in this study achieves higher predictive performance than traditional models in terms of F1-Score and accuracy. This method provides a foundation for enhancing real-time analysis and prediction reliability in data-driven decision-making systems across diverse fields such as manufacturing, fraud detection, and medical diagnostics.

We aimed to evaluate the effectiveness of ensemble optimal interpolation (EnOI) in improving the analysis of significant wave height (SWH) within wave models using satellite-derived SWH data. Satellite observations revealed higher SWH in mid-latitude regions (30o to 60o in both hemispheres) due to stronger winds, whereas equatorial and coastal areas exhibited lower wave heights, attributed to calmer winds and land interactions. Root mean square error (RMSE) analysis of the control experiment without data assimilation revealed significant discrepancies in high-latitude areas, underscoring the need for enhanced analysis techniques. Data assimilation experiments demonstrated substantial RMSE reductions, particularly in high-latitude regions, underscoring the effectiveness of the technique in enhancing the quality of analysis fields. Sensitivity experiments with varying ensemble sizes showed modest global improvements in analysis fields with larger ensembles. Sensitivity experiments based on different decorrelation length scales demonstrated significant RMSE improvements at larger scales, particularly in the Southern Ocean and Northwest Pacific. However, some areas exhibited slight RMSE increases, suggesting the need for region-specific tuning of assimilation parameters. Reducing the observation error covariance improved analysis quality in certain regions, including the equator, but generally degraded it in others. Rescaling background error covariance (BEC) resulted in overall improvements in analysis fields, though sensitivity to regional variability persisted. These findings underscore the importance of data assimilation, parameter tuning, and BEC rescaling in enhancing the quality and reliability of wave analysis fields, emphasizing the necessity of region-specific adjustments to optimize assimilation performance. These insights are valuable for understanding ocean dynamics, improving navigation, and supporting coastal management practices.

In this study, the magnetocaloric effect and transition temperature of bulk metallic glass, an amorphous material, were predicted through machine learning based on the composition features. From the Python module ‘Matminer’, 174 compositional features were obtained, and prediction performance was compared while reducing the composition features to prevent overfitting. After optimization using RandomForest, an ensemble model, changes in prediction performance were analyzed according to the number of compositional features. The R2 score was used as a performance metric in the regression prediction, and the best prediction performance was found using only 90 features predicting transition temperature, and 20 features predicting magnetocaloric effects. The most important feature when predicting magnetocaloric effects was the ‘Fe’ compositional ratio. The feature importance method provided by ‘scikit-learn’ was applied to sort compositional features. The feature importance method was found to be appropriate by comparing the prediction performance of the Fe-contained dataset with the full dataset.

It would be advantageous to grow legume forage crops in order to increase the productivity and sustainability of sloped croplands in Hamkyongbukdo. In particular, the identification of potential cultivation areas for alfalfa in the given region could aid decision-making on policies and management related to forage crop production in the future. This study aimed to analyze the climate suitability of alfalfa in Hamkyongbukdo under current and future climate conditions using the Fuzzy Union model. The climate suitability predicted by the Fuzzy Union model was compared with the actual alfalfa cultivation area in the northern United States. Climate data obtained from 11 global climate models were used as input data for calculation of climate suitability in the study region to examine the uncertainty of projections under future climate conditions. The area where the climate suitability index was greater than a threshold value (22.6) explained about 44% of the variation in actual alfalfa cultivation areas by state in the northern United States. The climatic suitability of alfalfa was projected to decrease in most areas of Hamkyongbukdo under future climate scenarios. The climatic suitability in Onseong and Gyeongwon County was analyzed to be over 88 in the current climate conditions. However, it was projected to decrease by about 66% in the given areas by the 2090s. Our study illustrated that the impact of climate change on suitable cultivation areas was highly variable when different climate data were used as inputs to the Fuzzy Union model. Still, the ensemble of the climate suitability projections for alfalfa was projected to decrease considerably due to summer depression in Hamkyongbukdo. It would be advantageous to predict suitable cultivation areas by adding soil conditions or to predict the climate suitability of other leguminous crops such as hairy vetch, which merits further studies.

A machine learning-based algorithms have used for constructing species distribution models (SDMs), but their performances depend on the selection of backgrounds. This study attempted to develop a noble method for selecting backgrounds in machine-learning SDMs. Two machine-learning based SDMs (MaxEnt, and Random Forest) were employed with an example species (Spodoptera litura), and different background selection methods (random sampling, biased sampling, and ensemble sampling by using CLIMEX) were tested with multiple performance metrics (TSS, Kappa, F1-score). As a result, the model with ensemble sampling predicted the widest occurrence areas with the highest performance, suggesting the potential application of the developed method for enhancing a machine-learning SDM.

본 연구는 남한 지역에서 서식하는 멸종 위기 종 2급인 왕은점표범나비의 기후 변화에 따른 서식지 변화를 분석하고자 한다. 이를 위해 단일모델의 장단점을 보완하기 위해서 생물 보전과 동물 생태학 분야에서 널리 사용 되는 앙상블 모델을 활용하여 기후변화 시나리오 자료를 이용하여 현재와 미래 기후 조건에서의 잠재적 서식지 변화를 평가하였다. 연구 결과에 따르면, 미래에는 왕은점표범나비의 서식지가 줄어들 것으로 예상되며, 이 변화 는 기온과 강수량 모두에 영향을 받을 것으로 나타났다. 특히 강수량의 계절적 변동이 가장 큰 영향을 미칠 것으로 분석되었다. 이러한 결과는 기후 변화로 인한 생물종의 서식 분포의 이해를 향상시켜 멸종 위기 종 관리와 생태계 복원과 같은 다양한 분야에서 생물다양성 증진을 위한 중요한 기초 데이터로 활용될 것으로 기대된다.

고성능 콘크리트(HPC) 압축강도는 추가적인 시멘트질 재료의 사용으로 인해 예측하기 어렵고, 개선된 예측 모델의 개발이 필수적 이다. 따라서, 본 연구의 목적은 배깅과 스태킹을 결합한 앙상블 기법을 사용하여 HPC 압축강도 예측 모델을 개발하는 것이다. 이 논 문의 핵심적 기여는 기존 앙상블 기법인 배깅과 스태킹을 통합하여 새로운 앙상블 기법을 제시하고, 단일 기계학습 모델의 문제점을 해결하여 모델 예측 성능을 높이고자 한다. 단일 기계학습법으로 비선형 회귀분석, 서포트 벡터 머신, 인공신경망, 가우시안 프로세스 회귀를 사용하고, 앙상블 기법으로 배깅, 스태킹을 이용하였다. 결과적으로 본 연구에서 제안된 모델이 단일 기계학습 모델, 배깅 및 스태킹 모델보다 높은 정확도를 보였다. 이는 대표적인 4가지 성능 지표 비교를 통해 확인하였고, 제안된 방법의 유효성을 검증하였다.

The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.