Holocene reef growth R project for Macedo and van Woesik

<p dir="ltr">This code was used for the analysis for "Growth rates for coral reefs peaked at 25 °C through the Holocene" by Tonya Macedo and Robert van Woesik. </p><p><br></p><p dir="ltr">Overview:</p><p dir="ltr">Main dataset: "Holocene_Reef_Growth_Final.csv" is the final dataset used for modeling, containing 1,890 samples. </p><p dir="ltr">Main goals:</p><ol><li>Use a GLMM in INLA to determine fixed effects for coral growth rates during the Holocene. </li><li>Use deep learning to evaluate non-linear relationships between variables of interest and coral reef growth rates through the Holocene. </li><li>Reproduce figures from the publication or generate new figures with new data. </li></ol><p dir="ltr">Main scripts: </p><ol><li>Holocene_INLA_GLMM.R</li><li><ol><li>Sets up model formulas</li><li>Fits models</li><li>Compares and visualizes INLA model results</li></ol></li><li>Holocene_Deep_Learning.R</li><li><ol><li>Sets up the H2O deep learning environment</li><li>Fits 30 models using 6 different deep learning configurations</li><li>Compares and visualizes model results</li></ol></li><li>Holocene_Figures.qmd</li><li><ol><li>Reproduces the figures used in the manuscript</li></ol></li></ol><p dir="ltr">Usage guidance:</p><p dir="ltr">Each script is set up so that it can be run standalone. There is no order that the scripts need to be run. </p><p dir="ltr">The project uses the here package for reproducible file paths, no need to set working directory.</p><p dir="ltr">The repository is organized so that it can be cloned and executed as an R project.</p>