Deep-SDMs in the open oceans - INPUT DATA

<p>This repository contains input files to train the Deep-SDM model described in the preprint <a href="https://doi.org/10.1101/2023.08.11.551418">Predicting species distributions in the open oceans with convolutional neural networks.</a></p> <p>This deposit contains:</p> <p>1. Training data: CSV dataset + 38 subfolders with data for each species (named after its GBIF id)</p> <p>2. Prediction data:</p> <p>2.1. Global use case (solstices &amp; equinoxes of 2021): CSV dataset + data folder</p> <p>2.2. Western Indian Ocean use case: CSV dataset + data folder</p> <p>3. <em>species.csv </em>contains the taxonomic name of each taxon, as well as its GBIF id.</p> <p>4. <em>stats.npy</em> contains normalization factors for the data files</p> <pre><code class="language-python">meds, perc1, perc99 = np.load("stats.npy") item = np.load(file)[:,:,:25] real_values = (perc99 - perc1) * item + perc1</code></pre> <p>&nbsp;</p> <p>Each of these elements can be downloaded separately by scrolling to the <em>Files</em> section.</p>