Application of extreme gradient boosting and Shapley Additive explanations to predict temperature regimes inside forests from standard open-field meteorological data. (October 2022)

• Record Type: Journal Article
• Authors: Ghafarian, Fatemeh; Wieland, Ralf; Lüttschwager, Dietmar; Nendel, Claas
• Is Part Of: Environmental modelling & software. Volume 156(2022)
• Publication Date: 2022-10
• Subjects: Cooling effect -- Machine learning -- Ensemble method -- Ecosystem services; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2022.105466
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: 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. Highlights: We used XGBoost to predict temperature dynamics inside forests for ecosystem service assessment and the results are compared to those of other machine learning methods such as artificial neural networks (ANN), random forest (RF), support vector machine regression (SVR). Air temperature, soil temperature, global radiation, and relative humidity provided by meteorological stations are sufficient to reproduce inside-forest temperatures. We introduced an ensemble method to make the prediction more accurate. We applied Shapley Additive explanations to interpret the results of the XGBoost model. XGBoost performed slightly better than other ML methods for estimating forest temperature from weather stations' data.