Estimation of a contaminant source in an estuary with an inverse problem approach

Parolin, Radael de Souza; Neto, Antônio José da Silva; Rodrigues, Pedro Paulo Gomes Watts; Llanes‐Santiago, Orestes

doi:10.1016/j.amc.2015.03.054

Cited by 8 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When the independent variable X is known, PLS can be used to predict the dependent variable Y. The calculation procedure is given in Equations (12) and (13).…”

Section: Obtaining Fault Parameters By the Pls Algorithmmentioning

confidence: 99%

“…The most widely used method to solve such a problem is its least squares (LSQ) formulation as the minimization of an error function between the real measurements and their calculated values, similar to the above improved parameter estimation methods. Meanwhile, meta-heuristics for LSQ optimization are popular due to their inherent advantages, like their global optimum and the few requirements for problem formulation [11,12]. However, the running speed of the LSQ-based method is slow owing to its time-consuming iterative optimization of fault parameters.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Inverse Problem Approach to Model-Based Fault Diagnosis of a Distillation Column

et al. 2020

View full text Add to dashboard Cite

Early-stage fault detection and diagnosis of distillation has been considered an essential technique in the chemical industry. In this paper, fault diagnosis of a distillation column is formulated as an inverse problem. The nonlinear least squares algorithm is used to evaluate fault parameters embedded in a nonlinear dynamic model of distillation once abnormal symptoms are detected. A partial least squares regression model is built based on fault parameter history to explicitly predict the development of fault parameters. With the stripper of Tennessee Eastman process as example, this novel approach is tested for step- and random-type faults and several factors affecting its efficiency are discussed. The application result shows that the hybrid inverse problem approach gives the correct change of fault parameter at a speed far faster than the base approach with only a nonlinear model.

show abstract

“…When the independent variable X is known, PLS can be used to predict the dependent variable Y. The calculation procedure is given in Equations (12) and (13).…”

Section: Obtaining Fault Parameters By the Pls Algorithmmentioning

confidence: 99%

mentioning

confidence: 99%

A Hybrid Inverse Problem Approach to Model-Based Fault Diagnosis of a Distillation Column

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Among many inverse tracking methods used in the groundwater system, the optimization method was frequently used in river systems, which iterates the calculations based on the advection-diffusion process to reach the global solution of contaminant source as an ill-posed problem. Parolin et al [16] carried out a hybrid heuristic algorithm, which included the Luus-Jaakola method (LJ), particle collision algorithm (PCA), ant colony optimization (ACO), and golden section method (GS), to identify the spill location and intensity of contaminant source in an estuary. Zhang and Xin [17] used the basic Genetic Algorithm (GA) to identify the spill location and spill mass of contaminant sources in a small straight river.…”

Section: Introductionmentioning

confidence: 99%

Identification Framework of Contaminant Spill in Rivers Using Machine Learning with Breakthrough Curve Analysis

Kwon

Noh

Seo

et al. 2021

IJERPH

View full text Add to dashboard Cite

To minimize the damage from contaminant accidents in rivers, early identification of the contaminant source is crucial. Thus, in this study, a framework combining Machine Learning (ML) and the Transient Storage zone Model (TSM) was developed to predict the spill location and mass of a contaminant source. The TSM model was employed to simulate non-Fickian Breakthrough Curves (BTCs), which entails relevant information of the contaminant source. Then, the ML models were used to identify the BTC features, characterized by 21 variables, to predict the spill location and mass. The proposed framework was applied to the Gam Creek, South Korea, in which two tracer tests were conducted. In this study, six ML methods were applied for the prediction of spill location and mass, while the most relevant BTC features were selected by Recursive Feature Elimination Cross-Validation (RFECV). Model applications to field data showed that the ensemble Decision tree models, Random Forest (RF) and Xgboost (XGB), were the most efficient and feasible in predicting the contaminant source.

show abstract

“…Zhou et al (2016) introduced an adjoint data assimilation method into the parameter inversion of a river water quality model to obtain the longitudinal dispersion coefficient of the 1D water quality model. Parolin, Neto, Rodrigues, and Llanes Santiago (2015) used Luus-Jaakola, particle collision algorithm, and ant colony optimization methods to identify the source location and utilized a golden section method to estimate source intensity. Yeh, Chang, and Lin (2007) combined tabu search and simulated annealing algorithm to form a hybrid heuristic algorithm for identifying an underground location for water pollution source.…”

Section: Introductionmentioning

confidence: 99%

Inversion of multiple parameters for river pollution accidents using emergency monitoring data

Jing

Yang

Zhou

et al. 2019

Water Environment Research

View full text Add to dashboard Cite

This study presented a new inversion algorithm on the basis of least squares method for river point pollution sources. A series of numerical experiments was conducted to verify the accuracy of the proposed inversion algorithm. The general solution of the one‐dimensional (1D) pollutant transport equation is the governing equation of this method. Pollutant concentrations at various hypothetical monitoring points should be observed at two moments to obtain the point pollution source parameters, namely, velocity, longitudinal dispersion coefficient, emission moment of the pollution source, emission location, and emission intensity. Monitoring error was considered a random noise in the numerical experiments. The inversion result error was 3.69% when the monitoring error was 5%. Although the monitoring error reached 20%, the maximum error of inversion parameters was 8.58%. In addition, the effects of river flow velocity, contaminant decay rates, monitoring point setting, and time intervals between two sampling groups were analyzed in hypothetic cases. Practitioner points Present a new inversion algorithm for river point pollution sources. Multiple parameters can be obtained by inversion. The unknown river velocity does not affect the result of parameter inversion. Different levels of pollutant concentration monitoring errors are considered.

show abstract

Estimation of a contaminant source in an estuary with an inverse problem approach

Cited by 8 publications

References 11 publications

A Hybrid Inverse Problem Approach to Model-Based Fault Diagnosis of a Distillation Column

A Hybrid Inverse Problem Approach to Model-Based Fault Diagnosis of a Distillation Column

Identification Framework of Contaminant Spill in Rivers Using Machine Learning with Breakthrough Curve Analysis

Inversion of multiple parameters for river pollution accidents using emergency monitoring data

Contact Info

Product

Resources

About