Influence of model complexity, training collinearity, collinearity shift, predictor novelty, and their interactions on ecological forecasting

<p dir="auto">This is a repository for revised manuscript submitted to <em>Global Ecology and Biogeography</em>.</p> <p dir="auto">Update: The manuscript was accepted by Global Ecology and Biography and published online on 29 November 2023.</p> <p dir="auto">Preprint: The 1st version submitted to&nbsp;<em>Proceedings of the National Academy of Sciences (PNAS)</em>&nbsp;can be found at:&nbsp;<a href="https://doi.org/10.32942/X2MS38" rel="nofollow">https://doi.org/10.32942/X2MS38</a></p> <p dir="auto">DOI:&nbsp;<a href="https://doi.org/10.1111/geb.13793" rel="nofollow">https://doi.org/10.1111/geb.13793</a></p> <p dir="auto">Citation: Chen, X., Liang, Y., &amp; Feng, X. (2023). Influence of model complexity, training collinearity, collinearity shift, predictor novelty and their interactions on ecological forecasting.&nbsp;<em>Global Ecology and Biogeography</em>, 33, 371-384.</p> <p dir="auto">GitHub repository: https://github.com/xinxxxin/Influence-of-collinearity-and-novelty-on-ecological-forecasting/tree/main</p>