Predicting cyanobacteria abundance with Bayesian zero-inflated models
Cyanobacterial blooms are a persistent concern to water management and treatment, with blooms potentially causing the release of toxins and degrading water quality. However, previous models have not considered the zero inflation of cyanobacteria count data. Typically, a relatively large proportion o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2023-11-01
|
| Series: | Journal of Hydroinformatics |
| Subjects: | |
| Online Access: | http://jhydro.iwaponline.com/content/25/6/2161 |
| _version_ | 1797428982017163264 |
|---|---|
| author | Yirao Zhang Nicolas M. Peleato |
| author_facet | Yirao Zhang Nicolas M. Peleato |
| author_sort | Yirao Zhang |
| collection | DOAJ |
| description | Cyanobacterial blooms are a persistent concern to water management and treatment, with blooms potentially causing the release of toxins and degrading water quality. However, previous models have not considered the zero inflation of cyanobacteria count data. Typically, a relatively large proportion of measured count data are zeros or non-detects of cyanobacteria, representing either no cyanobacteria was present or the cell number was too low to be detected. Commonly used Poisson and negative binomial models for count data underestimate the probability of zero data, making these models less reliable. This study proposes a Bayesian approach to fit the cyanobacteria abundance data with mixture models that handle zero-inflated data. Predictor variables considered included weather and water quality measures that can easily be obtained day-to-day. The optimal model (zero-inflated negative binomial) was used to predict cyanobacteria alert levels on a separate test set. The ability to predict narrow alert levels was limited, however, 76% accuracy was achieved in predicting cyanobacteria counts above or below 1,000 cells/mL. Parameter estimates were highly variable and demonstrated that complex and uncertain factors influence cyanobacteria count predictions. The modelling approach can be applied to a wide range of environmental problems where zero-inflated data is common.
HIGHLIGHTS
Bayesian mixture models were used to model zero-inflated cyanobacteria count data.;
A Bayesian variable selection method was applied to select important variables.;
A zero-inflated model achieved 76% accuracy in predicting binary alert levels.;
Bayesian framework produced probabilistic categorization of alert levels.;
The model is well suited for management of complex systems with high uncertainty.; |
| first_indexed | 2024-03-09T09:06:37Z |
| format | Article |
| id | doaj.art-f446f9328916469f9ef123d1a978c168 |
| institution | Directory Open Access Journal |
| issn | 1464-7141 1465-1734 |
| language | English |
| last_indexed | 2024-03-09T09:06:37Z |
| publishDate | 2023-11-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Journal of Hydroinformatics |
| spelling | doaj.art-f446f9328916469f9ef123d1a978c1682023-12-02T10:27:50ZengIWA PublishingJournal of Hydroinformatics1464-71411465-17342023-11-012562161217610.2166/hydro.2023.229229Predicting cyanobacteria abundance with Bayesian zero-inflated modelsYirao Zhang0Nicolas M. Peleato1 School of Engineering, Faculty of Applied Science, The University of British Columbia Okanagan, 1137 Alumni Ave, Kelowna, BC, Canada School of Engineering, Faculty of Applied Science, The University of British Columbia Okanagan, 1137 Alumni Ave, Kelowna, BC, Canada Cyanobacterial blooms are a persistent concern to water management and treatment, with blooms potentially causing the release of toxins and degrading water quality. However, previous models have not considered the zero inflation of cyanobacteria count data. Typically, a relatively large proportion of measured count data are zeros or non-detects of cyanobacteria, representing either no cyanobacteria was present or the cell number was too low to be detected. Commonly used Poisson and negative binomial models for count data underestimate the probability of zero data, making these models less reliable. This study proposes a Bayesian approach to fit the cyanobacteria abundance data with mixture models that handle zero-inflated data. Predictor variables considered included weather and water quality measures that can easily be obtained day-to-day. The optimal model (zero-inflated negative binomial) was used to predict cyanobacteria alert levels on a separate test set. The ability to predict narrow alert levels was limited, however, 76% accuracy was achieved in predicting cyanobacteria counts above or below 1,000 cells/mL. Parameter estimates were highly variable and demonstrated that complex and uncertain factors influence cyanobacteria count predictions. The modelling approach can be applied to a wide range of environmental problems where zero-inflated data is common. HIGHLIGHTS Bayesian mixture models were used to model zero-inflated cyanobacteria count data.; A Bayesian variable selection method was applied to select important variables.; A zero-inflated model achieved 76% accuracy in predicting binary alert levels.; Bayesian framework produced probabilistic categorization of alert levels.; The model is well suited for management of complex systems with high uncertainty.;http://jhydro.iwaponline.com/content/25/6/2161bayesian modellingcyanobacteriaenvironmental modellingwater managementzero-inflated |
| spellingShingle | Yirao Zhang Nicolas M. Peleato Predicting cyanobacteria abundance with Bayesian zero-inflated models Journal of Hydroinformatics bayesian modelling cyanobacteria environmental modelling water management zero-inflated |
| title | Predicting cyanobacteria abundance with Bayesian zero-inflated models |
| title_full | Predicting cyanobacteria abundance with Bayesian zero-inflated models |
| title_fullStr | Predicting cyanobacteria abundance with Bayesian zero-inflated models |
| title_full_unstemmed | Predicting cyanobacteria abundance with Bayesian zero-inflated models |
| title_short | Predicting cyanobacteria abundance with Bayesian zero-inflated models |
| title_sort | predicting cyanobacteria abundance with bayesian zero inflated models |
| topic | bayesian modelling cyanobacteria environmental modelling water management zero-inflated |
| url | http://jhydro.iwaponline.com/content/25/6/2161 |
| work_keys_str_mv | AT yiraozhang predictingcyanobacteriaabundancewithbayesianzeroinflatedmodels AT nicolasmpeleato predictingcyanobacteriaabundancewithbayesianzeroinflatedmodels |