2020
DOI: 10.1002/lno.11568
|View full text |Cite
|
Sign up to set email alerts
|

Predicting atrazine concentrations in waterbodies across the contiguous United States: The importance of land use, hydrology, and water physicochemistry

Abstract: Atrazine contamination is ubiquitous in North American surface waters, but the dependency of the herbicide's distribution on landscape and within-lake processes is currently poorly known. We sought to identify novel predictors of atrazine and to build a coherent framework to model its concentration in waterbodies through the development of binomial-gamma hurdle models and LASSO regression models. We constructed models for over 900 waterbodies in the contiguous United States using data from the 2012 U.S. EPA Na… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 25 publications
(8 citation statements)
references
References 88 publications
(100 reference statements)
0
8
0
Order By: Relevance
“…The two steps of the two-stage machine learning model framework can be implemented by (1) converting MICX values to a binary variable, TRUE if above the detection limit and FALSE if not; then using the binarized variable along with other observational data as input variables to build a binary classifier to predict the presence of MICX; and (2) only using the data instances where MICX concentrations are above the detection limit to build a regressor to predict the concentration of MICX. Note that this two-stage machine learning model described above is not explicitly designed for MICX but can be applied to all left-censored response variables, such as heavy metal and volatile organic pollutants. , …”
Section: Methodsmentioning
confidence: 99%
“…The two steps of the two-stage machine learning model framework can be implemented by (1) converting MICX values to a binary variable, TRUE if above the detection limit and FALSE if not; then using the binarized variable along with other observational data as input variables to build a binary classifier to predict the presence of MICX; and (2) only using the data instances where MICX concentrations are above the detection limit to build a regressor to predict the concentration of MICX. Note that this two-stage machine learning model described above is not explicitly designed for MICX but can be applied to all left-censored response variables, such as heavy metal and volatile organic pollutants. , …”
Section: Methodsmentioning
confidence: 99%
“…We based our E2 concentrations in the present study of 2.3 and 25 ug/L on these results. Atrazine concentrations were based on environmentally relevant concentrations 6,27 and concentrations reported to elicit feminization in A. blanchardi and Rhinella arenarum. 4,28 Methanol (0.04 mL, 0.0002% of exposure water) was used as a carrier for all treatments and added to the negative control.…”
Section: Experimental Exposuresmentioning
confidence: 99%
“…[20] Non-target plants, including important wildflowers and crops, can also be affected by the uncontrolled usage of ATZ, leading to reduced biodiversity and agricultural yield losses. Concerns regarding human health including the disruption of the human endocrine system [21] and increased risks of teratogenesis, [8,22,23] mutagenesis, [24] and carcinogenesis [25,26] are due to the ATZ-contaminated water that enters the human body through the food chain. [27] The persistence of ATZ in the environment, its ecological disruptions, and potential health risks highlight the need to develop sustainable alternatives to cope with the issues of ATZ contamination.…”
Section: Introductionmentioning
confidence: 99%