Statistical Modelling of Water Quality Time Series – The River Vouga Basin Case Study

Costa, Marco; Monteiro, Magda

doi:10.5772/59062

Cited by 4 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Developing time-series forecasting models for river flows were explored using statistical models [7], [8]. Forecasting models such as the regression and neural network were presented in [9], [10].…”

Section: A Statistical Models and Their Limitationsmentioning

confidence: 99%

“…Some forecasting tools are developed based on statistical models, especially if the seasonal prediction of the water flow is needed as in [7], which forecasts the availability of the water resources supplied by the mountains in central Asia. Another work was introduced in [8], which used the River Vouga Basin in Portugal as a case study utilizing a statistical time series model that analyzed and predicted the water quality. The study showed that for such complex database models, it is challenging to use statistical analysis.…”

Section: A Statistical Models and Their Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary Design of a PSO-Tuned Multigene Symbolic Regression Genetic Programming Model for River Flow Forecasting

Sheta¹,

Abdel-Raouf²,

Fraihat³

et al. 2023

IJACSA

View full text Add to dashboard Cite

The earth's population is growing at a rapid rate, while the availability of water resources remains limited. Water is required for various purposes, including drinking, agriculture, industry, recreation, and development. Accurate forecasting of river flows can have a significant economic impact, particularly in agricultural water management and planning during water resource scarcity. Developing precise river flow forecasting models can greatly improve the management of water resources in many countries. In this study, we propose a two-phase model for predicting the flow of the Blackwater river located in the South Central United States. In the first phase, we use Multigene Symbolic Regression Genetic Programming (MG-GP) to develop a mathematical model. In the second phase, Particle Swarm Optimization (PSO) is employed to fine-tune the model parameters. Fine-tuning the MG-GP parameters improves the prediction accuracy of the model. The newly fine-tuned model exhibits 96% and 94% accuracy in training and testing cases, respectively.

show abstract

Section: A Statistical Models and Their Limitationsmentioning

confidence: 99%

Section: A Statistical Models and Their Limitationsmentioning

confidence: 99%

Evolutionary Design of a PSO-Tuned Multigene Symbolic Regression Genetic Programming Model for River Flow Forecasting

Sheta¹,

Abdel-Raouf²,

Fraihat³

et al. 2023

IJACSA

View full text Add to dashboard Cite

show abstract

“…In environmental variables, it is common to encounter missing values [6,7]. In this work we will use two approaches to impute these missing values, namely the linear interpolation [8], and a linear regression analysis [9] where the independent variable has a strong association with the dependent variable.…”

Section: Introductionmentioning

confidence: 99%

Meteorological Time Series: An Exploratory Statistical and Critical Analysis

Gonçalves

Pereira

Costa

et al. 2022

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

Increasingly, reduction of water availability has been a reality, and population growth, pollution, and climate change have contributed to exacerbating this problem. Dry periods, which occur when precipitation is lower than expected in a given territory, have become more frequent and prolonged, and therefore it is crucial to efficiently manage water use in response to environmental concerns. The main challenge in this work is to present the irrigation problem as an optimal control problem along with the presentation of preliminary results based on an exploratory statistical and critical analysis of daily meteorological variables. The variables considered are: maximum air temperature, minimum air temperature, and total precipitation recorded during the last ten years (2010-2019). The methodology followed, based on state-space models, shows flexibility to allow the integration of new data, updating in real time the model, and the incorporation of covariates that are important to explain the process in analysis.

show abstract

“…Cluster analysis and linear models were used by [11,12] to describe a hydrological space-time series of quality variables and to detect changes in surface water quality data collected in the River Ave hydrological basin, located in the northwest region of Portugal. In [1], the case study of the hydrological basin of the river Vouga, in Portugal was presented. A discrimination analysis of water monitoring sites, using the monthly dissolved oxygen concentration, was proposed by [13], performing the extraction of both trend and seasonal components in a linear mixed-effect state-space model.…”

Section: Introductionmentioning

confidence: 99%

“…The Decree-Law n. 77/2006 complements the WFD by characterizing the waters of a river basin. A regulatory instrument establishes the status of surface waters and groundwater and their ecological potential [1].…”

Section: Introductionmentioning

confidence: 99%

A Time Series Model Comparison for Monitoring and Forecasting Water Quality Variables

Monteiro

Costa

2018

Hydrology

View full text Add to dashboard Cite

Abstract:The monitoring and prediction of water quality parameters are important tasks in the management of water resources. In this work, the performances of time series statistical models were evaluated to predict and forecast the dissolved oxygen (DO) concentration in several monitoring sites located along the main river Vouga, in Portugal, during the period from January 2002 to May 2015. The models being compared are a regression model with correlated errors and a state-space model, which can be seen as a calibration model. Both models allow the incorporation of water quality variables, such as time correlation or seasonality. Results show that, for the DO variable, the calibration model outperforms the regression model for sample modeling, that is, for a short-term forecast, while the regression model with correlated errors has a better performance for the forecasting h-steps ahead framework. So, the calibration model is more useful for water monitoring using an online or real-time procedure, while the regression model with correlated errors can be applied in order to forecast over a longer period of time.

show abstract

Statistical Modelling of Water Quality Time Series – The River Vouga Basin Case Study

Cited by 4 publications

References 23 publications

Evolutionary Design of a PSO-Tuned Multigene Symbolic Regression Genetic Programming Model for River Flow Forecasting

Evolutionary Design of a PSO-Tuned Multigene Symbolic Regression Genetic Programming Model for River Flow Forecasting

Meteorological Time Series: An Exploratory Statistical and Critical Analysis

A Time Series Model Comparison for Monitoring and Forecasting Water Quality Variables

Contact Info

Product

Resources

About