<p>Test accuracy, training accuracy, and overfitting scores (% mean ± standard deviation; n = 10) for models based on four machine learning algorithms: random forest (RF), support vector machine (SVM), Naive Bayes classifier (NV), and convolutional neural network (CNN). Input variable abbreviations: <i>Ave</i>, averaged monthly air temperature and precipitation; <i>AveI</i>, averaged monthly climate indices; <i>CEI</i>, climate extreme indices; and <i>CEI</i>_<i>part</i>, a subset of <i>CEI.</i></p>

Test accuracy, training accuracy, and overfitting scores (% mean ± standard deviation; n = 10) for models based on four machine learning algorithms: random forest (RF), support vector machine (SVM), Naive Bayes classifier (NV), and convolutional neural network (CNN). Input variable abbreviations: Ave, averaged monthly air temperature and precipitation; AveI, averaged monthly climate indices; CEI, climate extreme indices; and CEIpart, a subset of CEI.本数据集提供了基于四类机器学习算法的模型的测试准确率、训练准确率与过拟合得分，所有指标以百分比形式呈现均值±标准差（n=10）。四类机器学习算法分别为随机森林（random forest, RF）、支持向量机（support vector machine, SVM）、朴素贝叶斯分类器（Naive Bayes classifier, NV）及卷积神经网络（convolutional neural network, CNN）。输入变量缩写及对应含义如下：Ave为平均月气温与降水量；AveI为平均月度气候指数；CEI为气候极端指数；CEIpart为CEI的子集。