[논문]다중 선형 회귀 분석과 랜덤 포레스트를 이용한 SS, T-P 대리모니터링 기법 평가

정민혁; 범진아; 최동호; 김영주; 허용구; 윤광식

doi:10.5389/ksae.2021.63.2.051

다중 선형 회귀 분석과 랜덤 포레스트를 이용한 SS, T-P 대리모니터링 기법 평가
Evaluation of Surrogate Monitoring Parameters for SS and T-P Using Multiple Linear Regression and Random Forest 원문보기

한국농공학회논문집 = Journal of the Korean Society of Agricultural Engineers, v.63 no.2, 2021년, pp.51 - 60

정민혁 (Department of Rural and Bio-Systems Engineering, Chonnam National University) , 범진아 (Department of Rural and Bio-Systems Engineering, Chonnam National University) , 최동호 (Presidential Water Commission Support Department Planning and Operation, Republic of Korea Presidential Water Commission) , 김영주 (Department of Cadastre and Civil Engineering, VISION College of Jeonju) , 허용구 (Tropical Research and Education, Department of Agricultural and Biological Engineering, University of Florida) , 윤광식 (Department of Rural and Bio-Systems Engineering, Chonnam National University)

Abstract ▼ AI-Helper

Effective nonpoint source (NPS) pollution management requires frequent water quality monitoring, which is, however, often costly to be implemented in practice. Statistical techniques and machine learning methods allow us to identify and focus on fundamental environmental variables that have close relationships with NPS pollutants of interest. This study developed surrogate models to predict the concentrations of suspended sediment (SS) and total phosphorus (T-P) from turbidity and runoff discharge rates using multiple linear regression (MLR) and random forest (RF) methods. The RF models provided acceptable performance in predicting SS and T-P, especially when runoff discharge rates were high. The RF models outperformed the MLR models in all the cases. Such finding highlights the potential of RF techniques and models as a tool to identify fundamental environmental variables that are measured in relatively inexpensive ways or freely available but still able to provide information required to quantify the concentrations of NP S pollutants. The analysis of relative importance rates showed that the temporal variations of SS and T-P concentrations could be more effectively explained by that of turbidity than runoff discharge rate. This study demonstrated that the advanced statistical techniques such as machine learning could help to improve the efficiency of NPS pollutants monitoring.

주제어

표/그림 (9)

그림 Fig. 1 Locations of the study watersheds and NPS pollutant monitoring stations
표 Table 1 Classifications of hydrologic conditions
표 Table 2 Summary statistics of predictors and variables to predict SS and T-P
그림 Fig. 2 Overall procedures of predicting SS and TP using random forest and multiple linear regression
그림 Fig. 3 Responses of MSE to the number of trees (K)
그림 Fig. 4 Daily runoff and flow duration curve of the study site
그림 Fig. 5 Comparison between the NPS pollutants observed and simulated using the MLR and RF models (a) SS using MLR in low flow condition; (b) SS using RF in low flow condition; (c) T-P using MLR in low flow condition; (d) T-P using RF in low flow condition. (e) SS using MLR in high flow condition; (f) SS using RF in high flow condition; (g) T-P using MLR in high flow condition; (h) T-P using RF in high flow condition
그림 Fig. 6 Relative importance rates of runoff discharge rates and turbidity in predicting SS and T-P concentrations
표 Table 3 Performance evaluation of the MLR and RF models in predicting SS and T-P concentrations

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

Moreover, the runoff in high flow condition shows higher relative importance than low flow condition, which is related to the high concentrations of T-P in farming period. This study demonstrated the machine learning techniques could help to improve the efficiency of NPS pollutant monitoring and prediction by identifying fundamental environmental variables that are relatively easily obtained but still closely related to the NPS pollutants. The results also showed that turbidity could serve as a surrogate water quality parameter for SS and T-P concentrations at acceptable accuracy levels.
This study explored the potential of the RF algorithm as a tool to efficiently identify primary variables that can serve as surrogate for NPS pollutants. We developed prediction models using MLR (traditional statistical model) and RF (the latest statistical data mining technique) and compared their performance to demonstrate their capacities and potentials.
We developed prediction models using MLR (traditional statistical model) and RF (the latest statistical data mining technique) and compared their performance to demonstrate their capacities and potentials. This study focused on SS and T-P that are common NPS pollutants in Korea.

가설 설정

(d) T-P using RF in low flow condition. (e) SS using MLR in high flow condition; (f) SS using RF in high flow condition; (g) T-P using MLR in high flow condition; (h) T-P using RF in high flow condition

제안 방법

8°C and 1, 391 mm, respectively. A set of water pressure sensor and logger (OTT Orpheus mini, Germany) was installed to monitor the level of streamflow, and the velocity (VALEPORT model 002, UK) and cross section of flow were measured six times during the monitoring period. The flow level measurements were converted to discharge data using a flow rating curve developed for the outlet of the study catchment.
As both models provided similar accuracy when predicting SS and T-P from turbidity and runoff discharge rates, their performance was further investigated in terms of AIC values (Table 3). The AIC values of the RF model are lower than those of the MLR model, indicating that the RF model is more suitable for predicting SS and T-P that the MLR model in this study.
Then, we separated the flow conditions into high-flow periods (the exceedance probability equal to or less than 10%) and low-flow ones (the exceedance probability greater than 10%) so that the flow-dependent behavior of NPS pollutant transport can be examined in the study. Stormwater samples were taken every hour in the first 24 hours of a storm event using an automatic sampler (ISCO portable sampler 6712, USA), and the sampling interval was increased to 6 hours for the rest of the event. The concentrations of SS and T-P were analyzed in a laboratory according to the standard water pollution test method (APHA, 2001).
The flow duration curve was then developed from flow observations and the flow conditions was seperated using Table 1. Then, we separated the flow conditions into high-flow periods (the exceedance probability equal to or less than 10%) and low-flow ones (the exceedance probability greater than 10%) so that the flow-dependent behavior of NPS pollutant transport can be examined in the study. Stormwater samples were taken every hour in the first 24 hours of a storm event using an automatic sampler (ISCO portable sampler 6712, USA), and the sampling interval was increased to 6 hours for the rest of the event.
This study explored the potential of the MLR and RF model as a tool to identify surrogate environmental variables in two different flow conditions for the concentrations of NPS pollutants such as SS and T-P in agricultural sub-watershed. The performance of the MLR and RF models was evaluated with the 80% for training set and 20% for validation set.

대상 데이터

This study has monitored SS and T-P at the outlet of a catchment, Wol-jeong (WJ), located within the Pungyeongjeongcheon watershed in Korea for two years, from 01/01/2017 and 12/31/2018 (Fig. 1). WJ is mostly covered by agricultural land uses (86%) including rice paddy fields and upland.

이론/모형

Stormwater samples were taken every hour in the first 24 hours of a storm event using an automatic sampler (ISCO portable sampler 6712, USA), and the sampling interval was increased to 6 hours for the rest of the event. The concentrations of SS and T-P were analyzed in a laboratory according to the standard water pollution test method (APHA, 2001). The monitored water quality variables and predictors such as turbidity and runoff discharge rates are summarized in Table 2.
The potential relationships between the pollutants of interest (SS and T-P) and the primary environmental variables (discharge rates and turbidity) were explored using the MLR and RF methods. RF is the combination of tree-based classification methods such as a regression tree developed by Breiman, (2001).
for validation; Afendras and Markatou, 2019). To validate the models, we used four different statistics and criteria: the Nash-Sutcliffe efficiency (NSE) coefficient, the coefficients of determination (R²), p-value (P), and the Akaike information criterion (AIC) (Nash and Sutcliffe, 1970; Akaike, 1973; Snipes and Taylor, 2014).

성능/효과

5 and Table 3. Overall, the MLR model prediction of SS and T-P in the low and high flow conditions were acceptable with R² and NSE greater than 0.5, except T-P in low flow condition. The T-P prediction for the low flow condition shows acceptable R² but low NSE.
3). The AIC values of the RF model are lower than those of the MLR model, indicating that the RF model is more suitable for predicting SS and T-P that the MLR model in this study.
6). The analysis of relative importance showed that turbidity was more closely associated with the SS and T-P concentrations than discharge rates with importance rates ranging from 52% to 86% depending on the flow conditions. As mentioned above, the runoff in high flow condition shows higher relative importance than low flow condition, which is related to the high concentrations of T-P in farming period.

참고문헌 (36)

Afendras, G., and M. Markatou, 2019. Optimality of training/test size and resampling effectiveness in cross-validation. Journal of Statistical Planning and Inference 199: 286-301. doi:10.1016/j.jspi.2018.07.005.

상세보기
Akaike, H., 1973. Information theory and an extension of the maximum likelihood principle. In Second International Symposium on Information Theory, 267-281.
American Public Health Association (APHA), 2001. Standard Methods for the Examination of Water and Waste Water. 21st ed, Washington DC, USA.
Breiman, L., 2001. Random forests. Machine Learning 45: 5-32.
Breiman, L., J. Friedman, R. A. Olshen, and C. J. Stone, 1984. Classification and Regression Trees. Wadsworth: CRC press.
Camdevyren, H., N. Demyr, A. Kanik, and S. Keskyn, 2005. Use if principal component scores in multiple linear regression models for prediction of Chlorophyll-a in reservoirs. Ecological Modelling 181(4): 581-589. doi:10.1016/j.ecolmodel.2004.06.043.

상세보기
Chattergee, S., and A. S. Hadi, 1988. Sensitivity Analysis in Linear Regression. USA, Wiley.
Chenini, I., and S. Khemiri, 2009. Evaluation of ground water quality using multiple linear regression and structural equation modeling. International Journal of Environmental Science and Technology 6(3): 509-519. doi:10.1007/BF03326090.

상세보기
DeForest, D. K., K. V. Brix, L. M. Tear, and W. J. Adams, 2018. Multiple linear regression models for predicting chronic aluminum toxicity to freshwater aquatic organisms and developing water quality guidelines. Environmental Toxicology and Chemistry 37(1): 80-90. doi:10.1002/etc.3922.

상세보기
Diaz-Uriate, R., and S. A. de Andres, 2006. Gene selection and classification of microarray data using random forest. BMC Bioinformatics 7: 3. doi:10.1186/1471-2105-7-3.

상세보기
Granata, F., S. Papirio, G. Esposito, R. Gargano, and G. Marinis, 2017. Machine learning algorithms for the forecasting of wastewater quality indicators. Water 9(2): 105. doi:10.3390/w9020105.

상세보기
Hasanipanah, M., R. S. Faradonbeh, H. B. Amnieh, D. J. Armaghani, and M. Monjezi, 2017. Forecasting blast-induced ground vibration developing a CART model. Engineering with Computers 33: 307-316. doi:10.1007/s00366-016-0475-9.

상세보기
Horsburgh, J. S., A. S. Jones, D. K. Stevens, D. G. Tarboton, and N. O. Mesner, 2009. A sensor network for high frequency estimation of water quality constituent fluxes using surrogates. Environmental Modelling and Software 25(9): 1031-1044. doi:10.1016/j.envsoft.2009.10.012.

상세보기
Houser, J. N., P. J. Mulholland, and K. O. Maloney, 2006. Upland disturbance affects headwater stream nutrients and suspended sediments during baseflow and stormflow. Journal of Environmental Quality 35: 352-365. doi:10.2134/jeq2005.0102.

상세보기
Johanna, I. F., and S. Petra, 2014. A turbidity-based method to continuously monitor sediment, carbon and nitrogen flows in mountainous watersheds. Journal of Hydrology 513: 45-57. doi:10.1016/j.jhydrol.2014.03.034.

상세보기
Jones, A. S., K. S. David, S. H. Jefery, and O. Nancy, 2011. Surrogate measures for providing high frequency estimates of total suspended solids and total phosphorus concentrations. Journal of the American Water Resources Association 47(2): 239-253. doi:10.1111/j.1752-1688.2010.00505.x.

상세보기
Jordan, P., A. Arnscheidt, and H. Mcgrogan, 2007. Characterising phosphorus transfers in rural catchments using a continuous bankside analyser. Hydrology and Earth System Science 11: 372-381. doi:10.5194/hess-11-372-2007.

상세보기
LieB, M., B. Glaser, and B. Huwe, 2012. Uncertainty in the spatial prediction of soil texture comparison of regression tree and random forest models. Geoderma 170: 70-79. doi:10.1016/j.geoderma.2011.10.010.

상세보기
Moriasi, D. N., J. G. Arnold, M. W. Van Liew, R. L. Bingner, R. D. Harmel, and T. L. Veith, 2007. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE. 50(3): 885-900. doi:10.13031/2013.23153.

상세보기
Montgomery, J. L., T. C. Harmon, C. N. Haas, R. Hooper, N. L. Clesceri, W. Graham, W. J. Kaiser, A. Snaderson, B. Minsker, J. Schnoor, and P. Brezonik, 2007. The waters network: an integrated environmental observatory network for water research. Environmental Science and Technology 41(19): 6642-6647. doi:10.1021/es072618f.

상세보기
Nash, J. E., and J. V. Sutcliffe, 1970. River flow forecasting through conceptual models part I - a discussion of principles. Journal of Hydrology. 10(3): 282-290. doi:10.1016/0022-1694(70)90255-6.

상세보기
Ouedraogo, I., P. Defourny, and M. Vanclooster, 2018. Application of random forest regression and comparison of its performance to multiple linear regression in modeling groundwater nitrate concentration at the African continent scale. Hydrogeology Journal 27(3): 1-18. doi:10.1007/s10040-018-1900-5.

상세보기
Prasad, A. M., L. R. Iverson, and A. Liaw, 2006. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9: 181-199. doi:10.1007/s10021-005-0054-1.

상세보기
Razi, M. A., and K. A. Athappilly, 2005. A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models. Expert Systems with Applications 29(1): 65-74. doi:10.1016/j.eswa.2005.01.006.

상세보기
Rodriguez-Galiano, V., M. P. Mendes, M. J. Garcia-soldado, M. Chica-Olmo, and L. Ribeiro, 2014. Predictive modeling of groundwater nitrate pollution using random forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (Southern Spain). Science of the Total Environment 476-477: 189-206. doi:10.1016/j.scitotenv.2014.01.001.

상세보기
Ruegner, H., M. Schwientek, B. Beckingham, B. Kuch, and P. Grathwohl, 2013. Turbidity as a proxy for total suspended solids (TSS) and particle facilitated pollutant transport in catchments. Environmental Earth Sciences 69: 373-380. doi:10.1007/s12665-013-2307-1.

상세보기
Scholefield, D., T. L. Goff, J. Braven, L. Dbdon, T. Long, and M. Butler, 2005. Concerted diurnal patterns in riverine nutrient concentrations and physical conditions. Science of the Total Environment 344: 201-210. doi:10.1016/j.scitotenv.2005.02.014.

상세보기
Settle, S., A. Goonetilleke, and G. Ayoko, 2007. Determination of surrogate indicators for phosphorus and solids in urban stormwater: application of multivariate data analysis techniques. Water, Air, and Soil Pollution 182: 149-161. doi:10.1007/s11270-006-9328-2.

상세보기
Singh, B., P. Sihag, and K. Singh, 2017. Modeling of impact of water quality on infiltration rate of soil by random forest regression. Modeling Earth Systems and Environment 3: 999-1004. doi:10.1007/s40808-017-0347-3.

상세보기
Snipes, M., and C. D. Taylor, 2014. Model selection and Akaike information criteria: an example from wine ratings and prices. Wine Economics and Policy 3(1): 3-9. doi:10.1016/j.wep.2014.03.001.

상세보기
United States Environmental Protection Agency (USEPA), 2007. "An approach for using load duration curves in the development of TMDLs." 841-B-07-006, United States Environmentl Protection Agency, 1-68.
Verzani, J., 2018. Data sets, etc. for the text "Using R for introductory statistics". 2nd ed. Version 2.0-6.
Villa, A., J. Folster, and K. Kyllmar, 2019. Determining suspended solids and total phosphorus from turbidity: comparison of high-frequency sampling with conventional monitoring methods. Environmental Monioring and Assessment 191: 605. doi:10.1007/s10661-019-7775-7.

상세보기
Wang, H., Y. Zhao, R. L. Pu, and Z. Z. Zhang, 2015. Mapping Robinia pseudoacacia forest health conditions by using combined spectral, spatial, and textural information extracted from IKONOS imagery and random forest classifier. Remote Sensing 7(7): 9020-9044. doi:10.3390/rs70709020.

상세보기
Zambrano-Bigiarini, M., 2017. Goodness-of-fit functions for comparison of simulated and observed hydrological time series. Version 0.3-10.
Ziegler, A. D., L. X. Xi, and C. Tantasarin, 2011. Sediment load monitoring in the Mae Sa catchment in Northern Thailand, IAHS-AISH publication 86-91.

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증