Water Quality Prediction in a Reservoir: Linguistic Model Approach for Interval Prediction

전명근,박진일,정남정,곽근창 제어·로봇·시스템학회 2010 International Journal of Control, Automation, and Vol.8 No.4

It is difficult to predict water quality in a reservoir because of the complex physical, chemical, and biological processes involved. In contrast to the well-known numeric models and artificial neural network models, Linguistic Models (LM) with context-based fuzzy clustering can offer reliable predictions of water quality. The main characteristics of LM are that it is user-centric and that it inher-ently dwells upon collections of highly interpretable and user-oriented entities, such as information granules. In this paper, we propose a model for evaluating water quality and then evaluate the effec-tiveness of the proposed method by performing comparisons on water quality data sets from a reservoir. Finally, we found that the proposed method not only has the better prediction performance than other models, but also can offer reliable intervals for uncertainty evaluation about the water quality.

방류수질 예측을 위한 AI 모델 적용 및 평가

김민철,박영호,유광태,김종락 대한상하수도학회 2024 상하수도학회지 Vol.38 No.1

Occurrence of process environment changes, such as influent load variances and process condition changes, can reduce treatment efficiency, increasing effluent water quality. In order to prevent exceeding effluent standards, it is necessary to manage effluent water quality based on process operation data including influent and process condition before exceeding occur. Accordingly, the development of the effluent water quality prediction system and the application of technology to wastewater treatment processes are getting attention. Therefore, in this study, through the multi-channel measuring instruments in the bio-reactor and smart multi-item water quality sensors (location in bio-reactor influent/effluent) were installed in The Seonam water recycling center #2 treatment plant series 3, it was collected water quality data centering around COD, T-N. Using the collected data, the artificial intelligence-based effluent quality prediction model was developed, and relative errors were compared with effluent TMS measurement data. Through relative error comparison, the applicability of the artificial intelligence-based effluent water quality prediction model in wastewater treatment process was reviewed. Key words: Effluent water quality prediction, Artificial intelligence model, Wastewater treatment process, Smart sensor

머신러닝을 활용한 수도권 약수터 수질 예측 모델 개발

임영우,엄지연,곽기영 한국지능정보시스템학회 2023 지능정보연구 Vol.29 No.1

Due to the prolonged COVID-19 pandemic, the frequency of people who are tired of living indoors visiting nearby mountains and national parks to relieve depression and lethargy has exploded. There is a place where thousands of people who came out of nature stop walking and breathe and rest, that is the mineral spring. Even in mountains or national parks, there are about 600 mineral springs that can be found occasionally in neighboring parks or trails in the metropolitan area. However, due to irregular and manual water quality tests, people drink mineral water without knowing the test results in real time. Therefore, in this study, we intend to develop a model that can predict the quality of the spring water in real time by exploring the factors affecting the quality of the spring water and collecting data scattered in various places. After limiting the regions to Seoul and Gyeonggi-do due to the limitations of data collection, we obtained data on water quality tests from 2015 to 2020 for about 300 mineral springs in 18 cities where data management is well performed. A total of 10 factors were finally selected after two rounds of review among various factors that are considered to affect the suitability of the mineral spring water quality. Using AutoML, an automated machine learning technology that has recently been attracting attention, we derived the top 5 models based on prediction performance among about 20 machine learning methods. Among them, the catboost model has the highest performance with a prediction classification accuracy of 75.26%. In addition, as a result of examining the absolute influence of the variables used in the analysis through the SHAP method on the prediction, the most important factor was whether or not a water quality test was judged nonconforming in the previous water quality test. It was confirmed that the temperature on the day of the inspection and the altitude of the mineral spring had an influence on whether the water quality was unsuitable. 코로나19 팬데믹의 장기화로 인해 실내 생활에 지쳐가는 사람들이 우울감, 무기력증 등을 해소하기 위해 근거리의 산과 국립공원을 찾는 빈도가 폭발적으로 증가하였다. 자연으로 나온 수많은 사람들이 오가는 걸음을 멈추고 숨을 돌리며 쉬어가는 장소가 있는데 바로 약수터이다. 산이나 국립공원이 아니더라도 근린공원 또는 산책로에서도 간간이 찾아볼 수있는 약수터는 수도권에만 약 6백여개가 위치해 있다. 하지만 불규칙적이고 수작업으로 수행되는 수질검사로 인해 사람들은 실시간으로 검사 결과를 알 수 없는 상태에서 약수를 음용하게 된다. 따라서 본 연구에서는 약수터 수질에 영향을 미치는 요인을 탐색하고 다양한 곳에 흩어져 있는 데이터를 수집하여 실시간으로 약수터 수질을 예측할 수 있는 모델을 개발하고자 한다. 데이터 수집의 한계로 인해 서울과 경기로 지역을 한정한 후 데이터 관리가 잘 이루어지고 있는 18개 시의 약 300여개 약수터를 대상으로 2015~2020년의 수질 검사 데이터를 확보하였다. 약수터 수질 적합 여부에 영향을 미칠 것으로 여겨지는 다양한 요인들 중 두 차례의 검토를 거쳐 총 10개의 요인을 최종 선별하였다. 최근 주목받고 있는 자동화 머신러닝 기술인 AutoML 기법을 활용하여 20여가지의 머신러닝 기법들 중 예측 성능 기준 상위 5개의 모델을 도출하 였으며 그 중 catboost 모델이 75.26%의 예측 분류 정확도로 가장 높은 성능을 가지고 있음을 확인하였다. 추가로 SHAP 기법을 통해 분석에 사용한 변인들이 예측에 미치는 절대적인 영향력을 살펴본 결과 직전 수질 검사에서 부적합 판정을 받았는지 여부가 가장 중요한 요인이었으며 그 외 평균 기온, 과거 연속 2번 수질 부적합 판정 기록 유무, 수질 검사 당일 기온, 약수터 고도 등이 수질 부적합 여부에 영향을 미치고 있음을 확인하였다.

연구논문 : 남강중권역 오염부하 전망 및 삭감 시나리오별 하류 수질예측

유재정 ( Jae Jeong Yu ),신석호 ( Suk Ho Shin ),윤영삼 ( Young Sam Yoon ),강두기 ( Doo Kee Kang ) 한국환경영향평가학회 2012 환경영향평가 Vol.21 No.4

Namgang mid-watershed is located in downstream of Nakdong river basin, There are many pollution sources arround this area and it`s control is important to manage a water quality of Nakdong river, A target year of Namgang mid-watershed water environment management plan is 2013, To predict a water quality at downstream of Namgang, we have investigated and forecasted the pollutant source and it`s loading, There are some plan to construction the sewage treatment plants to improve the water quality of Nam river. Those are considered on predicting water quality. As results, it is shown that the population is 343,326 and sewerage supply rate is 79.2% and the livestock is 1,662,000 in Namgang mid-watershed, It is estimated that the population is 333,980, the sewerage supply rate is 86.9% in 2013, The milk cow and cattle were estimated upward and the pigs were downward by 2013. The generated loading of BOD and TP is 75,957 kg/day and 4,311 kg/day, discharged loading is 18,481 kg/day and 988 kg/day respectively in 2006, It were predicted upward the discharged loading of BOD and TP by 4.08% and 6.3% respectively. The results of water quality prediction of Namgang4 site were 2.5 mg/L of BOD and 0.120 mg/L of TP in 2013. It is over the target water quality at that site in 2015 about 25.0% and 9.1% respectively. Consequently, there need another counterplan to reduce the pollutants in that mid-watershed.

밀양강 중권역 오염부하 전망 및 삭감 시나리오별 하류 수질예측

유재정 ( Jae Jeong Yu ),윤영삼 ( Young Sam Yoon ),신석호 ( Suk Ho Shin ),권헌각 ( Hun Gak Kwon ),윤종수 ( Jong Su Yoon ),전영인 ( Young In Jeon ),강두기 ( Doo Kee Kang ),갈병석 ( Byung Seok Kal ) 한국환경과학회 2011 한국환경과학회지 Vol.20 No.5

Milyanggang mid-watershed is located in downstream of Nakdong river basin. The pollutants from that watershed have an direct effect on Nakdong river water quality and it`s control is important to manage a water quality of Nakdong river. A target year of Milyanggang mid-watershed water environment management plan is 2013. To predict a water quality at downstream of Milyang river, we have investigated and forecasted the pollutant source and it`s loading. There are some plan to construction the sewage treatment plants to improve the water quality of Milyang river. Those are considered on predicting water quality. As results, it is shown that the population of Milyanggang mid-watershed is 131,857 and sewerage supply rate is 62.2% and the livestock is 1,775.300 in 2006. It is estimated that the population is 123,921, the sewerage supply rate is 75.5% in 2013. The generated loading of BOD and TP is 40,735 kg/day and 2,872 kg/day in 2006 and discharged loading is 11,818 kg/day and 722 kg/day in 2006 respectively. Discharged loadings were forecasted upward 1.0% of BOD and downward 2.7% of TP by 2013. The results of water quality prediction of Milyanggang 3 site were 1.6 mg/L of BOD and 0.120 mg/L of TP in 2013. It is over the target water quality at that site in 2015 about 6.7% and 20.0% respectively. Consequently, there need another counterplan to reduce the pollutants in that mid-watershed by 2015.

아라천 수질변화 예측 및 수리거동 특성 연구

김윤정,박천홍,남세희,곽병준,권소현,이가람,한인섭 한국수처리학회 2019 한국수처리학회지 Vol.27 No.2

The purpose of this study is predicting water quality change of Ara River depeding on the case of hypothetic scenario that all Gulpo River flow inflow to Ara River. In-addition, Suggesting minimization method by effect of Gulpo River inflow by understanding hydraulic flow properties in streams are performed. The hypothetic scenario of Gulpo River's inflow are consisted as removal of rubber-weir of Gyulhyeon-weir with elimination of concrete-weir(S2) on not(S1) and compare with current condition(S0) of Gyulhyeon-weir. As a result of prediction of water quality change by scenario as follows, range of variation of S1 : TOC -1.1 ~ 19.1%, Chl-a -2.8 ~ 21.0%. range of variation of S2 : TOC -1.1 ~ 18.9%, Chl-a -2.6 ~ 20.8%. As a result of Drifter experience, Operating condition of flowing in and out at once a day are showed distance of surface layer are increased 1~2 km/day to 5~12 km/day. but inflow rater of Seawater are decreased average 14.5 m3/s to 10.4 m3/s(about 28%) then condition of flowing continually twice a day. In conclusion, The maintaing method of transport time of kinetic energy as same direction even less water-flow are effective for reducing retention time on surface layer containing high contamination rate by maximizing influence of density current as Ara River salinity layer. Examination of watershed connection for minimizing effect of water quality of both water-shed by a various water flowing method within improvement of water quality of Gulpo River is possible by this study.

불확실성을 고려한 통합유역모델링

함종화,윤춘경,다니엘 라욱스,Ham, Jong-Hwa,Yoon, Chun-Gyoung,Loucks, Daniel P. 한국농공학회 2007 한국농공학회논문집 Vol.49 No.4

The uncertainty in water quality model predictions is inevitably high due to natural stochasticity, model uncertainty, and parameter uncertainty. An integrated modeling system under uncertainty was described and demonstrated for use in watershed management and receiving-water quality prediction. A watershed model (HSPF), a receiving water quality model (WASP), and a wetland model (NPS-WET) were incorporated into an integrated modeling system (modified-BASINS) and applied to the Hwaseong Reservoir watershed. Reservoir water quality was predicted using the calibrated integrated modeling system, and the deterministic integrated modeling output was useful for estimating mean water quality given future watershed conditions and assessing the spatial distribution of pollutant loads. A Monte Carlo simulation was used to investigate the effect of various uncertainties on output prediction. Without pollution control measures in the watershed, the concentrations of total nitrogen (T-N) and total phosphorous (T-P) in the Hwaseong Reservoir, considering uncertainty, would be less than about 4.8 and 0.26 mg 4.8 and 0.26 mg $L^{-1}$, respectively, with 95% confidence. The effects of two watershed management practices, a wastewater treatment plant (WWTP) and a constructed wetland (WETLAND), were evaluated. The combined scenario (WWTP + WETLAND) was the most effective at improving reservoir water quality, bringing concentrations of T-N and T-P in the Hwaseong Reservoir to less than 3.54 and 0.15 mg ${L^{-1}$, 26.7 and 42.9% improvements, respectively, with 95% confidence. Overall, the Monte Carlo simulation in the integrated modeling system was practical for estimating uncertainty and reliable in water quality prediction. The approach described here may allow decisions to be made based on probability and level of risk, and its application is recommended.

Simulation of algal bloom dynamics in a river with the ensemble Kalman filter

Kim, K.,Park, M.,Min, J.H.,Ryu, I.,Kang, M.R.,Park, L.J. North-Holland Pub. Co ; Elsevier 2014 Journal of hydrology Vol.519 No.4

A simulation framework of algal bloom in a river channel with data assimilation (DA) was developed by employing two numerical models coupled to simulate a watershed and the embedded river channel. The Hydrological Simulation Program-Fortran (HSPF) model simulates flow discharge and water quality from the subwatersheds and the Environmental Fluid Dynamics Code (EFDC) model takes the subwatershed model outputs at the watershed-river confluence points as boundary forcing to simulate river hydrodynamics and water quality. The ensemble Kalman filter (EnKF) was used for assimilation of water quality variables in the framework, linking uncertainty of model simulation and observation. The simulation uncertainty of the HSPF was quantified at the confluence points as simple stochastic error models developed by comparing the model simulation and the observation. The error models reflect uncertainty of both hydrologic and water quality simulation, including uncertainty associated with point and non-point pollution sources in the watershed. The outputs of the HSPF at the confluence points were perturbed with the error models before used in the following ensemble simulation of the EFDC for the main river. DA was conducted with weekly chlorophyll-a data observed along the river to update chlorophyll-a concentrations of the EFDC model grids. The results showed that the model performance was improved by the assimilation: the root mean square error (RMSE) and the mean continuous probability rank score (CPRS) significantly decreased compared to the open-loop simulation. The updated spatial distribution of chlorophyll-a concentration along the river channel was in reasonable agreement with the observation. Although only chlorophyll-a data was involved in the assimilation, phosphate was selected among other water quality variables for update in order to evaluate the effect of chlorophyll-a assimilation on those variables. It turned out that the phosphate simulation was not much improved by the chlorophyll-a data, which was due to weak correlation between the two variables in the model ensemble. Lastly, chlorophyll-a simulation uncertainty in the river attributed to the simulation uncertainty of each variable in the watershed was evaluated. For that, two additional simulations were made, with perturbation only to flow and phosphate respectively at the confluence points. The spread of chlorophyll-a ensemble of each case became significantly narrower than the original case, indicating that the difference is attributed to the uncertainty of the other unperturbed variables.

입력자료 군집화에 따른 앙상블 머신러닝 모형의 수질예측 특성 연구

박정수 ( Jungsu Park ) 한국물환경학회 2021 한국물환경학회지 Vol.37 No.5

Water quality prediction is essential for the proper management of water supply systems. Increased suspended sediment concentration (SSC) has various effects on water supply systems such as increased treatment cost and consequently, there have been various efforts to develop a model for predicting SSC. However, SSC is affected by both the natural and anthropogenic environment, making it challenging to predict SSC. Recently, advanced machine learning models have increasingly been used for water quality prediction. This study developed an ensemble machine learning model to predict SSC using the XGBoost (XGB) algorithm. The observed discharge (Q) and SSC in two fields monitoring stations were used to develop the model. The input variables were clustered in two groups with low and high ranges of Q using the k-means clustering algorithm. Then each group of data was separately used to optimize XGB (Model 1). The model performance was compared with that of the XGB model using the entire data (Model 2). The models were evaluated by mean squared error-observation standard deviation ratio (RSR) and root mean squared error. The RSR were 0.51 and 0.57 in the two monitoring stations for Model 2, respectively, while the model performance improved to RSR 0.46 and 0.55, respectively, for Model 1.

Water Quality Assessment and Turbidity Prediction Using Multivariate Statistical Techniques: A Case Study of the Cheurfa Dam in Northwestern Algeria

( Amina Addouche ),( Ali Righi ),( Mehdi Mohamed Hamri ),( Zohra Bengharez ),( Zahia Zizi ) 한국공업화학회 2022 공업화학 Vol.33 No.6

This work aimed to develop a new equation for turbidity (Turb) simulation and prediction using statistical methods based on principal component analysis (PCA) and multiple linear regression (MLR). For this purpose, water samples were collected monthly over a five year period from Cheurfa dam, an important reservoir in Northwestern Algeria, and analyzed for 12 parameters, including temperature (T°), pH, electrical conductivity (EC), turbidity (Turb), dissolved oxygen (DO), ammonium (NH₄ ⁺), nitrate (NO₃ ^-), nitrite (NO₂ ^-), phosphate (PO₄ ^3-), total suspended solids (TSS), biochemical oxygen demand (BOD5) and chemical oxygen demand (COD). The results revealed a strong mineralization of the water and low dissolved oxygen (DO) content during the summer period. High levels of TSS and Turb were recorded during rainy periods. In addition, water was charged with phosphate (PO₄ ^3-) in the whole period of study. The PCA results revealed ten factors, three of which were significant (eigenvalues >1) and explained 75.5% of the total variance. The F1 and F2 factors explained 36.5% and 26.7% of the total variance, respectively and indicated anthropogenic pollution of domestic agricultural and industrial origin. The MLR turbidity simulation model exhibited a high coefficient of determination (R² = 92.20%), indicating that 92.20% of the data variability can be explained by the model. TSS, DO, EC, NO₃ ^-, NO₂ ^-, and COD were the most significant contributing parameters (p values << 0.05) in turbidity prediction. The present study can help with decision-making on the management and monitoring of the water quality of the dam, which is the primary source of drinking water in this region.