Global and local feature (predictor variable) explanations from the XGBoost trained with Quebec data (2014–2021).

<p>Left: bar chart showing the global importance of each feature, measured as the mean absolute SHAP value across all observations. Higher values indicate greater overall influence on the model’s predictions. Right: The local explanation summary plot indicates how each feature observation cont...

Full description

Saved in:

Bibliographic Details
Main Author:	Hamid Ghanbari (6821096) (author)
Other Authors:	Kevin Siebels (22004341) (author), Ariane Dumas (12368759) (author), Emily S. Acheson (5943710) (author), Catherine Bouchard (5675591) (author), Kirsten Crandall (22290884) (author), Patrick A. Leighton (11230127) (author), Nicholas H. Ogden (9367942) (author), Erin E. Rees (3293091) (author)
Published:	2025
Subjects:	Microbiology Ecology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified predicting population establishment multiple spatial scales lower clay content less urban areas land cover types ixodes scapularis </ environmental predictor variables comprehensive machine learning additional predictor variables achieving high sensitivity percent mixed forest contained broadleaf forests tested ml algorithms machine learning framework enabling tick survival 0 ° c percent broadleaf xgboost emerged warmest month study presents study demonstrates southcentral canada slightly higher primary vector prediction models performing model north america lyme disease integrating ml individual contributions growing threat earth observation climate change borne diseases average soc
Tags:	Add Tag No Tags, Be the first to tag this record!

Global and local feature (predictor variable) explanations from the XGBoost trained with Quebec data (2014–2021).

Similar Items