Predicting recreational water quality advisories: A comparison of statistical methods

Brooks, Wesley; Corsi, Steven R.; Fienen, Michael N.; Carvin, Rebecca

doi:10.1016/j.envsoft.2015.10.012

Cited by 50 publications

(37 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The precipitation variables were significant variables for both ENT and E. coli at both HA and GW (Table 2). A number of previous studies used rainfall‐associated variables as input data to develop statistical models to simulate the FIB levels in beach water (Brooks et al, 2013, 2016; Feng et al, 2015; Francy, 2009; Gonzalez et al, 2012; Jones et al, 2013; Molina et al, 2014; Nevers and Whitman, 2011; Shively et al, 2016; Telech et al, 2009; Thoe et al, 2014). Similar to the results of this study (Fig.…”

Section: Discussionmentioning

confidence: 99%

“…In this study, the dependence of the two FIB on the tidal level and air temperature was not statistically significant, except for E. coli at GW, even though several studies have considered the wave height (Brooks et al, 2013; Feng et al, 2015; Francy, 2009; Molina et al, 2014; Nevers and Whitman, 2011; Shively et al, 2016; Telech et al, 2009; Thoe et al, 2014) and air temperature (Brooks et al, 2013; Gonzalez et al, 2012; Molina et al, 2014; Nevers and Whitman, 2011; Shively et al, 2016; Telech et al, 2009; Thoe et al, 2014) as inputs. No published studies have used SS as an input variable; however, some studies have used turbidity, which could be a proxy for SS (Brooks et al, 2013, 2016; Francy, 2009; Gonzalez et al, 2012; Molina et al, 2014; Shively et al, 2016; Telech et al, 2009). …”

Section: Discussionmentioning

confidence: 99%

“…Statistical models have used the wind direction as an input variable for simulating FIB concentrations in beach waters (Brooks et al, 2013;Molina et al, 2014;Shively et al, 2016;Thoe et al, 2014). Conversely, the wind speed did not significantly affect the changes in the FIB concentrations at HA and GW, even though several past studies have used it as an input variable (Brooks et al, 2013(Brooks et al, , 2016Molina et al, 2014;Shively et al, 2016;Thoe et al, 2014).…”

Section: Dependence Of Fecal Indicator Bacteria On the Independent Vamentioning

confidence: 99%

“…Instead, sampling locations, which are influenced by the discharge of a WWTP, have been used as input variables to predict E. coli and ENT at beaches on Lake Michigan ( Jones et al, 2013). Brooks et al (2016) simulated the E. coli concentration using 14 statistical models; these models used river discharge data that included the influence of WWTP effluent. Telech et al (2009) discussed the significance of WWTP discharge volumes as a potential factor affecting the ENT density, even though they did not use it as an input.…”

Section: Dependence Of Fecal Indicator Bacteria On the Independent Vamentioning

confidence: 99%

“…Multiple linear regression (MLR) methods have been used to predict the levels of Escherichia coli (Brooks et al, 2016; Francy, 2009; Gonzalez et al, 2012; Nevers and Whitman, 2011; Shively et al, 2016), enterococcus (ENT) (Feng et al, 2015; Gonzalez et al, 2012; Molina et al, 2014; Telech et al, 2009; Thoe et al, 2014), fecal coliform (Thoe et al, 2014), and Bacteroidales (Gonzalez et al, 2012). To predict the E. coli concentration at seven Wisconsin beaches, Brooks et al (2016) applied multiple regression models: MLR, binary logistic regression, partial least squares, sparse partial least squares, and the generalized boosted model. To simulate fecal coliform and ENT concentrations in Santa Monica beach water, Thoe et al (2014) implemented regression models and machine learning models: MLR, binary logistic regression, partial least squares, classification tree, and artificial neural network (ANN).…”

mentioning

confidence: 99%

See 4 more Smart Citations

Development of a Nowcasting System Using Machine Learning Approaches to Predict Fecal Contamination Levels at Recreational Beaches in Korea

et al. 2018

View full text Add to dashboard Cite

Microbial contamination in beach water poses a public health threat due to waterborne diseases. To reduce the risk of exposure to fecal contamination, informing beachgoers in advance about the microbial water quality is important. Currently, determining the level of fecal contamination takes 24 h. The objective of this study is to predict the current level of fecal contamination (enterococcus [ENT] and Escherichia coli) using readily available environmental variables. Artificial neural network (ANN) and support vector regression (SVR) models were constructed using data from the Haeundae and Gwangalli Beaches in Busan City. The input variables included the tidal level, air and water temperature, solar radiation, wind direction and velocity, precipitation, discharge from the wastewater treatment plant, and suspended solid concentration in beach water. The dependence of fecal contamination on the input variables was statistically evaluated; precipitation, discharge from the wastewater treatment plant, and wind direction at the two beaches were positively correlated to the changes in the two bacterial concentrations (p < 0.01), whereas solar radiation was negatively correlated (p < 0.01). The performance of the ANN model for predicting ENT and E. coli at Gwangalli Beach was significantly higher than that of the SVR model with the training dataset (p < 0.05). Based on the comparison of residual values between the predicted and observed fecal indicator bacteria concentrations in two models, the ANN demonstrated better performance than SVR. This study suggests an effective prediction method to determine whether a beach is safe for recreational use. Core Ideas Enterococcus and E. coli concentrations were predicted using machine learning models. Nine variables collected from two beach waters were tested as input for the models. The ANN performed better than SVR for predicting fecal indicator bacteria concentrations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Dependence Of Fecal Indicator Bacteria On the Independent Vamentioning

confidence: 99%

Section: Dependence Of Fecal Indicator Bacteria On the Independent Vamentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Development of a Nowcasting System Using Machine Learning Approaches to Predict Fecal Contamination Levels at Recreational Beaches in Korea

et al. 2018

View full text Add to dashboard Cite

show abstract

Evaluating multiple predictive models for beach management at a freshwater beach in the Great Lakes region

Madani

Seth

2020

J of Env Quality

View full text Add to dashboard Cite

Recreational water quality is currently monitored at Sandpoint Beach on Lake St. Clair using culture‐based enumeration of Escherichia coli. Using water quality and weather data collected over 4 yr, several multiple linear regression (MLR)‐based models were developed for near real‐time prediction of E. coli concentration and were tested using independent data from the fifth year. Model performance was assessed by the determination of metrics such as RMSE, accuracy, specificity, sensitivity, and area under the receiver operating characteristic curve (AUROC). Each of the developed MLR models described herein resulted in increased correct responses for both exceedance and non‐exceedance of the applicable standard as compared to predictions based on E. coli measurements (persistence models, using the previous day's E. coli concentration), which is the method currently being used. The AUROC values for persistence models are between 0.5 and 0.6, as compared to >0.7 for all the MLR models described herein. Among the MLR models, model performance improved when qualitative sky weather condition, which is commonly reported but was not previously used in similar models, was included. To select the best model, a principal coordinate analysis was used to combine multiple model performance metrics and provide a more sensitive tool for model comparison. Although models developed using 2, 3, and 4 yr of monitoring data provided reasonable performance, the model developed using the most recent 2‐yr data was marginally better. Thus, data from the most recent 2 yr are likely sufficient as a training dataset for updating the MLR model for Sandpoint Beach in the future.

show abstract

Machine learning for hydrologic sciences: An introductory overview

Liang

2021

WIREs Water

111

View full text Add to dashboard Cite

The hydrologic community has experienced a surge in interest in machine learning in recent years. This interest is primarily driven by rapidly growing hydrologic data repositories, as well as success of machine learning in various academic and commercial applications, now possible due to increasing accessibility to enabling hardware and software. This overview is intended for readers new to the field of machine learning. It provides a non-technical introduction, placed within a historical context, to commonly used machine learning algorithms and deep learning architectures. Applications in hydrologic sciences are summarized next, with a focus on recent studies. They include the detection of patterns and events such as land use change, approximation of hydrologic variables and processes such as rainfall-runoff modeling, and mining relationships among variables for identifying controlling factors. The use of machine learning is also discussed in the context of integrated with process-based modeling for parameterization, surrogate modeling, and bias correction. Finally, the article highlights challenges of extrapolating robustness, physical interpretability, and small sample size in hydrologic applications.

show abstract

Predicting recreational water quality advisories: A comparison of statistical methods

Cited by 50 publications

References 35 publications

Development of a Nowcasting System Using Machine Learning Approaches to Predict Fecal Contamination Levels at Recreational Beaches in Korea

Development of a Nowcasting System Using Machine Learning Approaches to Predict Fecal Contamination Levels at Recreational Beaches in Korea

Evaluating multiple predictive models for beach management at a freshwater beach in the Great Lakes region

Machine learning for hydrologic sciences: An introductory overview

Contact Info

Product

Resources

About