All Issue

2021 Vol.63, Issue 2 Preview Page
Evaluation of Surrogate Monitoring Parameters for SS and T-P Using Multiple Linear Regression and Random Forest

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

Minhyuk Jeunga
,
Jina Beomb
,
Dongho Choic
,
Young-joo Kimd
,
Younggu Here
,
Kwangsik Yoonf†
정 민혁a
,
범 진아b
,
최 동호c
,
김 영주d
,
허 용구e
,
윤 광식f†
aPh.D. Student, Department of Rural and Bio-Systems Engineering, Chonnam National University
a박사 전남 대학교 농촌 생명 시스템 공학과 학생
bPh.D. Student, Department of Rural and Bio-Systems Engineering, Chonnam National University
b박사 전남 대학교 농촌 생명 시스템 공학과 학생
cResearcher, Presidential Water Commission Support Department Planning and Operation, Republic of Korea Presidential Water Commission
c대통령 물위원회 지원부 기획 운영부 연구원
dProfessor, Department of Cadastre and Civil Engineering, VISION College of Jeonju
d전주 비전 대학 지적 토목 공학과 교수
eAssistant Professor, Tropical Research and Education, Department of Agricultural and Biological Engineering, University of Florida
e플로리다 대학교 농업 및 생물 공학과 열대 연구 및 교육 조교수
fProfessor, Department of Rural and Bio-Systems Engineering, Chonnam National University
f전남 대학교 농촌 생물 시스템 공학과 교수
† Corresponding author Tel.: +82-10-3081-5320, Fax: +82-62-530-2158 E-mail: ksyoon@chonnam.ac.kr
2021. pp. 51-60
PDF XML Citation
Abstract

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 NPS 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.

References

REFERENCES

1
G. Afendras and M. Markatou, Journal of Statistical Planning and Inference, Optimality of training/test size and resampling effectiveness in cross-validation, 199; 286-301 (2019)10.1016/j.jspi.2018.07.005
2
H. Akaike, In Second International Symposium on Information Theory, Information theory and an extension of the maximum likelihood principle; 267-281 (1973)
3
American Public Health Association (APHA), 21st ed. Standard Methods for the Examination of Water and Waste Water, USA. Washington DC. (2001)
4
L. Breiman, Machine Learning, Random forests, 45; 5-32 (2001)
5
L. Breiman, J. Friedman, R. A. Olshen and C. J. Stone, Classification and Regression Trees, Wadsworth. CRC press. (1984)
6
H. Camdevyren, N. Demyr, A. Kanik and S. Keskyn, Ecological Modelling, Use if principal component scores in multiple linear regression models for prediction of Chlorophyll-a in reservoirs, 181(4); 581-589 (2005)10.1016/j.ecolmodel.2004.06.043
7
S. Chattergee and A. S. Hadi, Sensitivity Analysis in Linear Regression, USA. Wiley. (1988)
8
I. Chenini and S. Khemiri, International Journal of Environmental Science and Technology, Evaluation of ground water quality using multiple linear regression and structural equation modeling, 6(3); 509-519 (2009)10.1007/bf03326090
9
D. K. DeForest, K. V. Brix, L. M. Tear and W. J. Adams, Environmental Toxicology and Chemistry, Multiple linear regression models for predicting chronic aluminum toxicity to freshwater aquatic organisms and developing water quality guidelines, 37(1); 80-90 (2018)10.1002/etc.3922
10
R. Diaz-Uriate and S. A. de Andrés, BMC Bioinformatics, Gene selection and classification of microarray data using random forest, 7; 3 (2006)10.1186/1471-2105-7-3
11
F. Granata, S. Papirio, G. Esposito, R. Gargano and G. Marinis, Water, Machine learning algorithms for the forecasting of wastewater quality indicators, 9(2); 105 (2017)10.3390/w9020105
12
M. Hasanipanah, R. S. Faradonbeh, H. B. Amnieh, D. J. Armaghani and M. Monjezi, Engineering with Computers, Forecasting blast-induced ground vibration developing a CART model, 33; 307-316 (2017)10.1007/s00366-016-0475-9
13
J. S. Horsburgh, A. S. Jones, D. K. Stevens, D. G. Tarboton and N. O. Mesner, Environmental Modelling and Software, A sensor network for high frequency estimation of water quality constituent fluxes using surrogates, 25(9); 1031-1044 (2009)10.1016/j.envsoft.2009.10. 012
14
J. N. Houser, P. J. Mulholland and K. O. Maloney, Journal of Environmental Quality, Upland disturbance affects headwater stream nutrients and suspended sediments during baseflow and stormflow, 35; 352-365 (2006)10.2134/jeq2005.0102
15
I. F. Johanna and S. Petra, Journal of Hydrology, A turbidity-based method to continuously monitor sediment, carbon and nitrogen flows in mountainous watersheds, 513; 45-57 (2014)10.1016/j.jhydrol.2014.03.034
16
A. S. Jones, K. S. David, S. H. Jefery and O. Nancy, Journal of the American Water Resources Association, Surrogate measures for providing high frequency estimates of total suspended solids and total phosphorus concentrations, 47(2); 239-253 (2011)10.1111/j.1752-1688.2010.00505.x
17
P. Jordan, A. Arnscheidt and H. Mcgrogan, Hydrology and Earth System Science, Characterising phosphorus transfers in rural catchments using a continuous bankside analyser, 11; 372-381 (2007)10.5194/hess-11-372-2007
18
M. Ließ, B. Glaser and B. Huwe, Geoderma, Uncertainty in the spatial prediction of soil texture comparison of regression tree and random forest models, 170; 70-79 (2012)10.1016/j.geoderma.2011.10.010
19
D. N. Moriasi, J. G. Arnold, M. W. Van Liew, R. L. Bingner, R. D. Harmel and T. L. Veith, Transactions of the ASABE, Model evaluation guidelines for systematic quantification of accuracy in watershed simulations, 50(3); 885-900 (2007)10.13031/2013.23153
20
J. L. Montgomery, 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, Environmental Science and Technology, The waters network: an integrated environmental observatory network for water research, 41(19); 6642-6647 (2007)10.1021/es072618f
21
J. E. Nash and J. V. Sutcliffe, Journal of Hydrology, River flow forecasting through conceptual models part I – a discussion of principles, 10(3); 282-290 (1970)10.1016/0022-1694(70)90255-6
22
I. Ouedraogo, P. Defourny and M. Vanclooster, Hydrogeology Journal, Application of random forest regression and comparison of its performance to multiple linear regression in modeling groundwater nitrate concentration at the African continent scale, 27(3); 1-18 (2018)10.1007/s10040-018-1900-5
23
A. M. Prasad, L. R. Iverson and A. Liaw, Ecosystems, Newer classification and regression tree techniques: bagging and random forests for ecological prediction, 9; 181-199 (2006)10.1007/s10021-005-0054-1
24
M. A. Razi and K. A. Athappilly, Expert Systems with Applications, A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models, 29(1); 65-74 (2005)10.1016/j.eswa.2005.01.006
25
V. Rodriguez-Galiano, M. P. Mendes, M. J. Garcia-soldado, M. Chica-Olmo and L. Ribeiro, Science of the Total Environment, 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), 476-477; 189-206 (2014)10.1016/j.scitotenv.2014.01.001
26
H. Ruegner, M. Schwientek, B. Beckingham, B. Kuch and P. Grathwohl, Environmental Earth Sciences, Turbidity as a proxy for total suspended solids (TSS) and particle facilitated pollutant transport in catchments, 69; 373-380 (2013)10.1007/s12665-013-2307-1
27
D. Scholefield, T. L. Goff, J. Braven, L. Dbdon, T. Long and M. Butler, Science of the Total Environment, Concerted diurnal patterns in riverine nutrient concentrations and physical conditions, 344; 201-210 (2005)10.1016/ j.scitotenv.2005.02.014
28
S. Settle, A. Goonetilleke and G. Ayoko, Water, Air, and Soil Pollution, Determination of surrogate indicators for phosphorus and solids in urban stormwater: application of multivariate data analysis techniques, 182; 149-161 (2007)10.1007/s11270-006-9328-2
29
B. Singh, P. Sihag and K. Singh, Modeling Earth Systems and Environment, Modeling of impact of water quality on infiltration rate of soil by random forest regression, 3; 999-1004 (2017)10.1007/s40808-017-0347-3
30
M. Snipes and C. D. Taylor, Wine Economics and Policy, Model selection and Akaike information criteria: an example from wine ratings and prices, 3(1); 3-9 (2014)10.1016/j.wep.2014.03.001
31
United States Environmental Protection Agency (USEPA), ” 841-B-07-006, United States Environmentl Protection Agency, “An approach for using load duration curves in the development of TMDLs; 1-68 (2007)
32
J. Verzani, 2nd ed. for the text “Using R for introductory statistics”, Data sets, etc, Version 2.0-6 (2018)
33
A. Villa, J. Fölster and K. Kyllmar, Environmental Monioring and Assessment, Determining suspended solids and total phosphorus from turbidity: comparison of high-frequency sampling with conventional monitoring methods, 191; 605 (2019)10.1007/s10661-019-7775-7
34
H. Wang, Y. Zhao, R. L. Pu and Z. Z. Zhang, Remote Sensing, Mapping Robinia pseudoacacia forest health conditions by using combined spectral, spatial, and textural information extracted from IKONOS imagery and random forest classifier, 7(7); 9020-9044 (2015)10.3390/rs70709020
35
M. Zambrano-Bigiarini, Goodness-of-fit functions for comparison of simulated and observed hydrological time series, Version 0.3-10 (2017)
36
A. D. Ziegler, L. X. Xi and C. Tantasarin, IAHS-AISH publication, Sediment load monitoring in the Mae Sa catchment in Northern Thailand; 86-91 (2011)
Information
  • Publisher :The Korean Society of Agricultural Engineers
  • Publisher(Ko) :한국농공학회
  • Journal Title :Journal of Korean Society of Agricultural Engineers
  • Journal Title(Ko) :한국농공학회논문집
  • Volume : 63
  • No :2
  • Pages :51-60
  • Received Date : 2020-11-27
  • Revised Date : 2021-02-03
  • Accepted Date : 2021-02-03
  • DOI :https://doi.org/10.5389/KSAE.2021.63.2.051
Journal Informaiton Journal of Korean Society of Agricultural Engineers Journal of Korean Society of Agricultural Engineers
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
Journal Informaiton Journal Informaiton - close