Forest microclimate can buffer biotic responses to summer heat waves, which are expected to become more extreme under climate warming. Prediction of forest microclimate is limited because meteorological observation standards seldom include situations inside forests. We use eXtreme Gradient Boosting ‒ a Machine Learning technique ‒ to predict the microclimate of forest sites in Brandenburg, Germany, using seasonal data comprising weather features. The analysis was amended by applying a SHapley Additive explanation to show the interaction effect of variables and individualised feature attributions. We evaluate model performance in comparison to artificial neural networks, random forest, support vector machine, and multi-linear regression. After implementing a feature selection, an ensemble approach was applied to combine individual models for each forest and improve robustness over a given single prediction model. The resulting model can be applied to translate climate change scenarios into temperatures inside forests to assess temperature-related ecosystem services provided by forests.

森林小气候可以缓冲对夏季热浪的生物反应，预计在气候变暖的情况下，这种反应会变得更加极端。由于气象观测标准很少包括森林内部的情况，因此对森林小气候的预测是有限的。我们使用 eXtreme Gradient Boosting（一种机器学习技术）利用包含天气特征的季节性数据来预测德国勃兰登堡森林遗址的小气候。通过应用 SHapley Additive 解释对分析进行了修正，以显示变量和个性化特征属性的交互作用。我们将模型性能与人工神经网络、随机森林、支持向量机和多线性回归进行比较。实施特征选择后，应用集成方法来组合每个森林的单个模型，并提高给定单个预测模型的鲁棒性。由此产生的模型可用于将气候变化情景转化为森林内部的温度，以评估森林提供的与温度相关的生态系统服务。