S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels
To better characterize quagga habitat suitability and trophic relationships across six hydrologically connected Arizona waterbodies, we collected water quality and plankton community data at 20 sampling stations from 2021 to 2023. Four waterbodies had established quagga populations, while the remaining two did not, despite suspected opportunities for introduction. Using data reduction techniques and an advanced machine learning (ML) classification algorithm, gradient boosted machine, we identified environmental and ecological conditions that differentiated established from negative stations. Notably, parameters considered crucial to dreissenid invasion (e.g., calcium, alkalinity, temperature, dissolved oxygen) were not among the most important variables to classification, as all examined waterbodies exhibited quagga-suitable ranges. Rather, in this system, the established class was characterized by conditions linked to dreissenid osmoregulation and indicators of primary productivity and trophic state. Further, established stations had lower zooplankton abundances of dreissenid competitors and prey, perhaps resulting from food competition and consumption, respectively. Notably, negative waterbodies, Bartlett Reservoir and Theodore Roosevelt Lake, exhibited different biotic and abiotic conditions from each other. Our study demonstrates that negative waterbodies with suitable calcium concentrations may still have differing invasion risks.
Resources
2 resources available
-
RISE Item Details Page URL for "S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels "
HTML -
PDF File for "S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels "
PDF
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| accessLevel | public |
|---|---|
| accrualPeriodicity | irregular |
| bureauCode |
[ "010:10" ] |
| contactPoint |
{ "fn": "RISE Team", "@type": "vcard:Contact", "hasEmail": "mailto:data@usbr.gov" } |
| description | To better characterize quagga habitat suitability and trophic relationships across six hydrologically connected Arizona waterbodies, we collected water quality and plankton community data at 20 sampling stations from 2021 to 2023. Four waterbodies had established quagga populations, while the remaining two did not, despite suspected opportunities for introduction. Using data reduction techniques and an advanced machine learning (ML) classification algorithm, gradient boosted machine, we identified environmental and ecological conditions that differentiated established from negative stations. Notably, parameters considered crucial to dreissenid invasion (e.g., calcium, alkalinity, temperature, dissolved oxygen) were not among the most important variables to classification, as all examined waterbodies exhibited quagga-suitable ranges. Rather, in this system, the established class was characterized by conditions linked to dreissenid osmoregulation and indicators of primary productivity and trophic state. Further, established stations had lower zooplankton abundances of dreissenid competitors and prey, perhaps resulting from food competition and consumption, respectively. Notably, negative waterbodies, Bartlett Reservoir and Theodore Roosevelt Lake, exhibited different biotic and abiotic conditions from each other. Our study demonstrates that negative waterbodies with suitable calcium concentrations may still have differing invasion risks. |
| distribution |
[ { "@type": "dcat:Distribution", "title": "RISE Item Details Page URL for "S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels "", "accessURL": "https://data.usbr.gov/catalog/8045/item/128739", "mediaType": "text/html", "description": "Landing page for "S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels "" }, { "@type": "dcat:Distribution", "title": "PDF File for "S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels "", "mediaType": "application/pdf", "description": ""S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels " as a PDF file", "downloadURL": "https://data.usbr.gov/rise/content-rise-public/rise/catalog-item/binary/Final%20Report%20ST-2026-21086_508.pdf" } ] |
| identifier | https://datainventory.usbr.gov/rise/item/128739 |
| keyword |
[ "Aquatic Invasive Species", "Decision Trees", "Dreissenid Mussels", "Partial Dependence" ] |
| landingPage | https://data.usbr.gov/catalog/8045/item/128739 |
| modified | 2026-09-09T19:51:15Z |
| publisher |
{ "name": "Bureau of Reclamation", "@type": "org:Organization" } |
| spatial |
"{"type":"Polygon","coordinates":[[[-111.95104,33.45644],[-111.95104,33.92845],[-110.98648,33.92845],[-110.98648,33.45644],[-111.95104,33.45644]]]}"
|
| title | S&T Project 21086 Final Report: Machine Learning Can Refine Models of Environmental Suitability and Ecological Associations for Invasive Quagga Mussels |
