상수관망의 누수는 수자원 손실 및 시설물 피해의 주요 원인으로, 효과적인 탐지를 위해 다양한 기술이 개발되고 있다. 본 연구는 실제 상수도 누수 사례를 대상으로 청음 데이터를 수집하고, 주파수 및 청각 기반 음향 특징을 추출하여 비지도 학습 기반의 이상 감지 모델을 적용함으로써 누수음을 탐지하는 기법을 제안한다. 청음 신호에 대해 푸리에 변환과 멜 주파수 켑스트럼 계수(MFCC)를 적용하여 총 86개의 음향 특징을 구성하였으며, 랜덤 포레스트를 통해 주요 변수 6개를 선정하였다. 거리 기반 군집 분석을 통해 정상 소음 분포를 구성하고, Isolation Forest 및 Autoencoder 알고리즘을 활용하여 이상 음향을 판별하였다. 비지도 모델에 의해 탐지된 이상 지점이 실제 현장 판단과 부합함을 확인하였다. 정량적 기준 기반의 이상 탐지 결과가 실제 누수 지점과 일관성을 보였다. 본 연구는 실무 적용 가능한 비지도 이상 탐지 접근법을 제시함으로써, 기존 라벨 의존 탐지 방식의 한계를 보완할 수 있음을 시사한다.

The synergistic impacts of global climate change and human activities are causing an unprecedented crisis, resulting in biodiversity loss and diminished ecosystem function. Confronting this challenge necessitates the systematic, long-term accumulation of ecological data as a prerequisite for establishing sound scientific evidence. This review synthesizes and analyzes 66 research papers published between 2014 and 2025 during the 2nd phase of the Korea Long-Term Ecological Research (KLTER) program, aiming to identify key achievements and propose future directions. The core objectives of KLTER include elucidating the mechanisms of structural shifts in biological communities and phenological changes driven by climatic factors, as well as quantifying the ecosystem’s carbon uptake and storage functions essential for achieving carbon neutrality. The analysis of the published research shows that the study topics were concentrated in fields such as insects (35%) and vegetation dynamics/phenology (23%). Keywords like “species,” “change,” and “forest” constituted the central axis of the research. The KLTER program holds significant value in clarifying the organic interactions and complex dynamics of the Korean Peninsula’s ecosystems. Ultimately, the program must advance through a focused commitment to evidence-based ecosystem management, increased investment in integrated research infrastructure, and the development of robust climate change adaptation strategies guided by long-term foresight.

최근 고도화된 딥러닝 모형을 이용하여 하천 수질에 영향을 줄 수 있는 과도한 조류(algae) 발생을 예측하는 연구에 대한 관심이 지속되고 있으며, 모형의 구축에 사용되는 현장 측정 자료의 특성상 다양한 이상치를 포함할 수 있어 데이터의 이상치 관리 필요성이 높아지고 있다. 본 연구에서는 현장 자료의 이상치가 딥러닝 모형의 성능에 미치는 영향을 분석하기 위해 딥러닝 Long Short-Term Memory(LSTM) 모형을 이용하여 하천 조류 발생을 정량적으로 평가하는 지표인 클로로필-a를 예측하는 모형을 구축하였으며, 10%의 이상치를 포함한 자료와 이상치가 포함되지 않은 원본 자료로 학습된 모형의 성능을 비교하였다. 또한 딥러닝 기반 이상치 탐지 알고리즘인 Autoencoder(AE)를 이용하여 이상치를 제거한 후 모형의 성능에 미치는 영향을 비교하였다. 분석 결과 이상치를 포함하지 않은 자료로 학습된 Base 모형과 10%의 이상치를 포함한 자료로 학습된 모형의 Nash-Sutcliffe efficiency(NSE)가 각각 0.882 및 0.858로 나타나 이상치가 모형의 성능을 저하시킬 수 있음을 확인하였다. 한편 AE를 이용하여 이상치를 다양한 비율로(5–20%) 제거한 자료로 학습된 모형의 성능을 분석한 결과 NSE가 0.883–0.896으로 이상치의 제거에 따라 모형의 성능이 Base 모형과 유사한 수준으로 개선되는 것으로 나타났다. 본 연구에서는 이상치가 딥러닝 모형에 미치는 영향을 분석하고 이상치 탐지 모형의 활용에 따른 조류 발생 예측 딥러닝 모형의 성능 향상이 가능함을 확인하였다.

과도한 조류 발생은 수생태계 교란과 수질 악화를 초래하는 대표적인 환경 문제로, 효과적인 관리와 대응을 위해 정확한 예측이 필요하다. 우리나라는 사계절의 기후 특성이 뚜렷하며, 수온이 상승하는 하절기에 조류 발생이 집중되는 경향을 보인다. 이에 따라 실시간 모니터링 자료는 대부분 저농도 상태가 유지되어 데이터 불균형 문제가 발생한다. 본 연구에서는 chlorophyll-a 농도를 기준으로 하천 현장의 조류 발생 수준을 Class 1 (Chl-a ≤ 10 ㎍/L), Class 2 (10 < Chl-a ≤ 50 ㎍/L), Class 3 (Chl-a > 50 ㎍/L)와 같이 3개의 class로 구분하고, 대표적인 앙상블 머신러닝 모형인 extreme gradient boosting (XGB) 알고리즘을 이용하여 조류 발생 수준을 예측하는 분류 모형을 구축하였다. 데이터 불균형 해소를 위해 생성형 인공지능 기반 알고리즘인 conditional generative adversarial network (CGAN)과 전통적인 데이터 보강 알고리즘인 synthetic minority over-sampling technique (SMOTE), 그리고 딥러닝 기반 기법인 autoencoder (AE)를 활용한 3가지 데이터 보강 알고리즘을 활용하여 데이터의 불균형을 개선한 자료를 생성하고 이를 XGB 모형에 적용하여 성능 변화를 비교하였다. 분석 결과 macro average 기준으로 원본 데이터를 사용한 모형의 recall은 0.606이었으나 SMOTE, AE 및 CGAN의 recall은 각각 0.666, 0.682, 0.720으로 크게 개선되었고, F1 score도 데이터 불균형 해소를 통해 약 7–13%의 성능이 향상되는 등 전체적으로 데이터 불균형 해소로 모형의 성능이 향상되었으며 CGAN이 가장 우수한 성능 개선 효과를 보이는 것으로 나타냈다. 본 연구의 결과를 통해 데이터 불균형 해소를 통한 머신러닝 모형 성능 개선 가능성을 확인하였다.

강화학습은 지속적으로 변화하는 환경에서 최적의 해결책을 제시할 수 있도록 구현되는 머신러닝 알고리즘으로 시간 및 조건에 따라 변화하는 시스템의 최적화에 우수한 성능을 보이는 장점을 가지고 있다. 따라서, 최근 운영 조건과 시간에 따라 변화하는 상하수도 시설 및 취수원 등 현장 물환경 관리 최적화에 강화학습을 적용하기 위한 연구에 대한 관심이 높아지고 있다. 본 연구에서는 강화학습이 상하수도 시설 및 물환경 관리에 적용된 사례를 분석하였다. 상하수도 시설의 운영시 시설 운영의 목적에 맞는 처리수 수질을 유지하면서 운영에 필요한 에너지 소비 및 비용을 최소화하는 노력이 중요하다. 강화학습은 데이터에 기반한 반복적인 분석을 통해 시스템 운영의 최적 조건을 학습할 수 있으며, 다양한 연구 사례에서 강화학습의 적용을 통해 상하수도 시설 등의 운영 효율 개선이 가능함을 보여주었다. 하수처리 시설의 경우 강화학습을 활용하여 운영비의 많은 부분을 차지하는 폭기조 산소 공급과 내부 반송 펌프 운전을 최적화할 수 있으며, 정수장의 경우 약품 투입량 절감 등을 통해 운영비 절감 효과를 달성할 수 있음을 확인하였다. 또한, 용수 공급망과 저류조 운영의 최적화를 통해 상수도 및 하천 현장의 오염 발생을 저감할 수 있음을 알 수 있었다. 본 연구를 통해 강화학습을 활용하여 기존의 경험에 기반한 시설 운영 방식의 한계를 개선하고 상하수도 시설 운영 및 물환경 관리 효율 향상에 기여할 수 있음을 확인하였다

생태계 내에서 일어나는 모든 현상은 매우 느리고 긴 시간에 걸쳐서 이루어진다. 그렇기에 생태계 내에서 일어나는 현상을 이해하고 연구하기 위해 장기생태연구가 필요하다. 현재 우리나라의 소나무는 단일 수종으로 가장 넓게 분포하 고 있으나 기후변화 및 음수로의 천이과정 등 다양한 요인에 의하여 변화가 예상된다. 변화과정에 대한 모니터링은 생태계 과정의 이해와 임분관리 등에 있어서 매우 중요한 부분을 차지하므로 장기생태모니터링구에 대한 매목조사와 변화상 분석을 실시하였다. 국가장기생태연구의 조사지로 구축된 지리산 소나무림(100m × 100m)을 대상으로 격년별 (2017년, 2019년, 2021년, 2023년) 4회 매목조사를 실시하였고, 매목조사자료를 바탕으로 밀도, 흉고단면적, 중요치, 직경급 분포, 수간건강상태, 고사율, 이입률 등의 분석을 실시하였다. 소나무개체군의 밀도는 6년 동안 292본/㏊에서 272본/㏊으로 6.8% 가량 감소하였고, 특히 비목나무는 6년 동안 161본/㏊에서 46본/㏊으로 71.4% 가량 크게 감소하였 다. 흉고단면적(㎡/㏊)은 비목나무를 제외한 모든 수종이 증가하였고 이에 따라 중요치는 비목나무만 감소하고 이외 모든 수종은 증가하거나 유지되는 경향으로 나타났다. 직경급 분포에서 전제 구성종은 10㎝ 미만의 직경급이 가장 높은 역 J자형을 보이고 소나무는 30-40㎝의 직경급의 개체목이 가장 많은 정규분포형을 보였다. 소나무의 수간건강상 태에서 AS가 2017년에 76.1%(252본/㏊)로 가장 높게 나타났지만 AL과 DF의 증가로 인해 2023년에 ㏊당 63.4%(210 본/㏊)로 12.8%(42본/㏊)감소하였다. 소나무의 6년간 연평균고사율은 1.18%, 연평균이입률은 진계목이 발생하지 않아 나타나지 않았다. 그러나 비목나무의 6년간 연평균고사율은 19.75%로 높게 나타났다. 지리산 소나무림의 소나무 개체 군 밀도는 감소하나 흉고단면적, 중요치는 유지되어 양호한 생육상태인 것으로 나타났지만 진계목이 발생하지 않았고 이는 소나무가 양수의 특성에 기인된 것으로 판단되었다. 앞으로 소나무개체군, 비목나무개체군, 삼나무개체군, 굴참나 무개체군 등 개체군 변화에 대한 지속적인 후속 연구가 필요할 것으로 판단되었다.

In this study, we have developed a movable defect detection system based on a vision module with machine-learning algorithm for distinguishing product quality. Machine-learning model determined the results in good or no good through images acquired from the vision module consisting of a camera, processor unit, and lighting. To ensure versatility for use in a variety of settings, we have integrated a robot arm and cart for the movable defect detection system, and the robot arm that adjusts the focus length is made to be able to rotate in all directions. The type of defect was divided into eccentricity defect and printing defect. As a result, it was confirmed that classification accuracy showed 0.9901 in our developed device.

In this study, the physical properties and fracture characteristics according to the tensile load are evaluated on the materials of the polymeric filler and carbon fiber-based composite sleeve technique. The polymeric filler and the composite sleeve technique are applied to areas where the pipe body thickness is reduced due to corrosion in large-diameter water pipes. First, the tensile strength of the polymeric filler was 161.48~240.43 kgf/cm2, and the tensile strength of the polyurea polymeric filler was relatively higher than that of the epoxy. However, the tensile strength of the polymeric filler is relatively very low compared to ductile cast iron pipes(4,300 kgf/cm2<) or steel pipes(4,100 kgf/cm2). Second, the tensile strength of glass fiber, which is mainly used in composite sleeves, is 3,887.0 kgf/cm2, and that of carbon fiber is up to 5,922.5 kgf/cm2. The tensile strengths of glass and carbon fiber are higher than ductile cast iron pipe or steel pipe. Third, when reinforcing the hemispherical simulated corrosion shape of the ductile cast iron pipe and the steel pipe with a polymeric filler, there was an effect of increasing the ultimate tensile load by 1.04 to 1.06 times, but the ultimate load was 37.7 to 53.7% compared to the ductile cast iron or steel specimen without corrosion damage. It was found that the effect on the reinforcement of the corrosion damaged part was insignificant. Fourth, the composite sleeve using carbon fiber showed an ultimate load of 1.10(0.61T, 1,821.0 kgf) and 1.02(0.60T, 2,290.7 kgf) times higher than the ductile cast iron pipe(1,657.83 kgf) and steel pipe(2,236.8 kgf), respectively. When using a composite sleeve such as fiber, the corrosion damage part of large-diameter water pipes can be reinforced with same level as the original pipe, and the supply stability can be secured through accident prevention.

In this study, as the proportion of aged pipelines increases rapidly, in the event of an accident caused by corrosion and structural deterioration of metal pipes, appropriate overlay welding is applied in the field to partially repair it. The size of the base steel plate and the selection of a stable welding method were evaluated, and possible problems caused by the overlay welding were identified, and improvement measures were proposed. For the test, a new steel pipe coated with epoxy lining on the inner surface and polyethylene on the outer surface was subjected to a tensile test by processing the repaired specimen through overlay welding with a steel plate after artificial cracking, and structural safety was evaluated after repair. Furthermore, the influences of the size of the throat and the size of the steel plate were analyzed. As a result of the tensile test by dividing the repaired steel plate overlay into a constraint and non-constraint conditions, the tensile load was concentrated in the welded part and damage occurred in the welded part. It was found that the maximum load leading to breakage increases as the size of the welding throat increases. In addition, it was found that the resistance to load increased slightly as the size of the overlaid steel plate increased, but the effect was not significant, confirming the need for repair in consideration of the site conditions. As a result of evaluating the damage to the coating material on the back side of the welding, it was confirmed that the coating material on the opposite side of the welding burned black(epoxy) or was greatly deformed by heat(polyethylene). Therefore, it is necessary to secure structural stability through repainting, etc. in order to prevent damage to the coating material on the opposite side during overlay welding.

The management of algal bloom is essential for the proper management of water supply systems and to maintain the safety of drinking water. Chlorophyll-a(Chl-a) is a commonly used indicator to represent the algal concentration. In recent years, advanced machine learning models have been increasingly used to predict Chl-a in freshwater systems. Machine learning models show good performance in various fields, while the process of model development requires considerable labor and time by experts. Automated machine learning(auto ML) is an emerging field of machine learning study. Auto ML is used to develop machine learning models while minimizing the time and labor required in the model development process. This study developed an auto ML to predict Chl-a using auto sklearn, one of most widely used open source auto ML algorithms. The model performance was compared with other two popular ensemble machine learning models, random forest(RF) and XGBoost(XGB). The model performance was evaluated using three indices, root mean squared error, root mean squared error-observation standard deviation ratio(RSR) and Nash-Sutcliffe coefficient of efficiency. The RSR of auto ML, RF, and XGB were 0.659, 0.684 and 0.638, respectively. The results shows that auto ML outperforms RF, and XGB shows better prediction performance than auto ML, while the differences between model performances were not significant. Shapley value analysis, an explainable machine learning algorithm, was used to provide quantitative interpretation about the model prediction of auto ML developed in this study. The results of this study present the possible applicability of auto ML for the prediction of water quality.

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.

Algal bloom is an ongoing issue in the management of freshwater systems for drinking water supply, and the chlorophyll-a concentration is commonly used to represent the status of algal bloom. Thus, the prediction of chlorophyll-a concentration is essential for the proper management of water quality. However, the chlorophyll-a concentration is affected by various water quality and environmental factors, so the prediction of its concentration is not an easy task. In recent years, many advanced machine learning algorithms have increasingly been used for the development of surrogate models to prediction the chlorophyll-a concentration in freshwater systems such as rivers or reservoirs. This study used a light gradient boosting machine(LightGBM), a gradient boosting decision tree algorithm, to develop an ensemble machine learning model to predict chlorophyll-a concentration. The field water quality data observed at Daecheong Lake, obtained from the real-time water information system in Korea, were used for the development of the model. The data include temperature, pH, electric conductivity, dissolved oxygen, total organic carbon, total nitrogen, total phosphorus, and chlorophyll-a. First, a LightGBM model was developed to predict the chlorophyll-a concentration by using the other seven items as independent input variables. Second, the time-lagged values of all the input variables were added as input variables to understand the effect of time lag of input variables on model performance. The time lag (i) ranges from 1 to 50 days. The model performance was evaluated using three indices, root mean squared error-observation standard deviation ration (RSR), Nash-Sutcliffe coefficient of efficiency (NSE) and mean absolute error (MAE). The model showed the best performance by adding a dataset with a one-day time lag (i=1) where RSR, NSE, and MAE were 0.359, 0.871 and 1.510, respectively. The improvement of model performance was observed when a dataset with a time lag up of about 15 days (i=15) was added.

The increased turbidity in rivers during flood events has various effects on water environmental management, including drinking water supply systems. Thus, prediction of turbid water is essential for water environmental management. Recently, various advanced machine learning algorithms have been increasingly used in water environmental management. Ensemble machine learning algorithms such as random forest (RF) and gradient boosting decision tree (GBDT) are some of the most popular machine learning algorithms used for water environmental management, along with deep learning algorithms such as recurrent neural networks. In this study GBDT, an ensemble machine learning algorithm, and gated recurrent unit (GRU), a recurrent neural networks algorithm, are used for model development to predict turbidity in a river. The observation frequencies of input data used for the model were 2, 4, 8, 24, 48, 120 and 168 h. The root-mean-square error-observations standard deviation ratio (RSR) of GRU and GBDT ranges between 0.182~0.766 and 0.400~0.683, respectively. Both models show similar prediction accuracy with RSR of 0.682 for GRU and 0.683 for GBDT. The GRU shows better prediction accuracy when the observation frequency is relatively short (i.e., 2, 4, and 8 h) where GBDT shows better prediction accuracy when the observation frequency is relatively long (i.e. 48, 120, 160 h). The results suggest that the characteristics of input data should be considered to develop an appropriate model to predict turbidity.

The quantified analysis of damages to wastewater treatment plants by natural disasters is essential to maintain the stability of wastewater treatment systems. However, studies on the quantified analysis of natural disaster effects on wastewater treatment systems are very rare. In this study, a total disaster index (DI) was developed to quantify the various damages to wastewater treatment systems from natural disasters using two statistical methods (i.e., AHP: analytic hierarchy process and PCA: principal component analysis). Typhoons, heavy rain, and earthquakes are considered as three major natural disasters for the development of the DI. A total of 15 input variables from public open-source data (e.g., statistical yearbook of wastewater treatment system, meteorological data and financial status in local governments) were used for the development of a DI for 199 wastewater treatment plants in Korea. The total DI was calculated from the weighted sum of the disaster indices of the three natural disasters (i.e., TI for typhoon, RI for heavy rain, and EI for earthquake). The three disaster indices of each natural disaster were determined from four components, such as possibility of occurrence and expected damages. The relative weights of the four components to calculate the disaster indices (TI, RI and EI) for each of the three natural disasters were also determined from AHP. PCA was used to determine the relative weights of the input variables to calculate the four components. The relative weights of TI, RI and EI to calculate total DI were determined as 0.547, 0.306, and 0.147 respectively.