2022 Early Hearing Detection & Intervention Virtual Conference

March 13 - 15, 2022

5/25/2021 | 2:00 PM - 3:30 PM | MATHEMATICAL MODELING FOR EPT PREDICTION | Virtual Platform

MATHEMATICAL MODELING FOR EPT PREDICTION

Recognizing the consequences of anthropogenic actions on stream health is challenging on a landscape scale. Logging, mining, and road construction are such actions affecting watersheds of Marquette County, Michigan. Although there are well-established modeling methods in freshwater ecology, such as traditional linear models, non-traditional and newly emerging methods may be able to provide valuable insights into macroinvertebrate changes with potentially better accuracy. Our objective is to use the natural distribution of our response variable (EPT) to justify beta and gamma regression analysis and compare these to traditional linear modeling. Emerging modeling techniques new to the field of statistics – topological data analysis – may also have promising growth in displaying patterns of water quality within long-term datasets. Long-term data sets are a unique and invaluable resource in providing vital background information for biotic models that may help differentiate between impacts of natural variation and anthropogenic changes in stream ecosystems. Through careful and extensive traditional and nontraditional modeling techniques of ecological datasets, there is a high potential to have more comprehensive, evidence-based conclusions.

Data science
Stream
Pollution

Presentation:
This presentation has not yet been uploaded.

Handouts:
Handout is not Available

Transcripts:
CART transcripts are NOT YET available, but will be posted shortly after the conference

Presenters/Authors

Jacob Wielgomas (), Wayne State University, go5328@wayne.edu;