Articles | Volume 14, issue 3
Model evaluation paper
16 Mar 2021
Model evaluation paper |  | 16 Mar 2021

Using Shapley additive explanations to interpret extreme gradient boosting predictions of grassland degradation in Xilingol, China

Batunacun, Ralf Wieland, Tobia Lakes, and Claas Nendel

Related authors

Exploring drought hazard, vulnerability, and related impacts to agriculture in Brandenburg
Fabio Brill, Pedro Henrique Lima Alencar, Huihui Zhang, Friedrich Boeing, Silke Hüttel, and Tobia Lakes
EGUsphere,,, 2024
Short summary
Drought Research Exhibits Shifting Priorities, Trends and Geographic Patterns
Roland Baatz, Gohar Ghazaryan, Michael Hagenlocher, Claas Nendel, Andrea Toreti, and Ehsan Eyshi Rezaei
EGUsphere,,, 2024
Short summary
Evaluation and optimisation of the soil carbon turnover routine in the MONICA model (version 3.3.1)
Konstantin Aiteew, Jarno Rouhiainen, Claas Nendel, and René Dechow
Geosci. Model Dev., 17, 1349–1385,,, 2024
Short summary
Aerial and surface rivers: downwind impacts on water availability from land use changes in Amazonia
Wei Weng, Matthias K. B. Luedeke, Delphine C. Zemp, Tobia Lakes, and Juergen P. Kropp
Hydrol. Earth Syst. Sci., 22, 911–927,,, 2018
Short summary
Climate impacts on human livelihoods: where uncertainty matters in projections of water availability
T. K. Lissner, D. E. Reusser, J. Schewe, T. Lakes, and J. P. Kropp
Earth Syst. Dynam., 5, 355–373,,, 2014
Short summary

Related subject area

Earth and space science informatics
Accelerating Lagrangian transport simulations on graphics processing units: performance optimizations of Massive-Parallel Trajectory Calculations (MPTRAC) v2.6
Lars Hoffmann, Kaveh Haghighi Mood, Andreas Herten, Markus Hrywniak, Jiri Kraus, Jan Clemens, and Mingzhao Liu
Geosci. Model Dev., 17, 4077–4094,,, 2024
Short summary
Focal-TSMP: deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation
Mohamad Hakam Shams Eddin and Juergen Gall
Geosci. Model Dev., 17, 2987–3023,,, 2024
Short summary
Tomofast-x 2.0: an open-source parallel code for inversion of potential field data with topography using wavelet compression
Vitaliy Ogarko, Kim Frankcombe, Taige Liu, Jeremie Giraud, Roland Martin, and Mark Jessell
Geosci. Model Dev., 17, 2325–2345,,, 2024
Short summary
Functional analysis of variance (ANOVA) for carbon flux estimates from remote sensing data
Jonathan Hobbs, Matthias Katzfuss, Hai Nguyen, Vineet Yadav, and Junjie Liu
Geosci. Model Dev., 17, 1133–1151,,, 2024
Short summary
The 4D reconstruction of dynamic geological evolution processes for renowned geological features
Jiateng Guo, Zhibin Liu, Xulei Wang, Lixin Wu, Shanjun Liu, and Yunqiang Li
Geosci. Model Dev., 17, 847–864,,, 2024
Short summary

Cited articles

Abdullah, A. Y. M., Masrur, A., Adnan, M. S. G., Baky, Md. A. A., Hassan, Q. K., and Dewan, A.: Spatio-temporal Patterns of Land Use/Land Cover Change in the Heterogeneous Coastal Region of Bangladesh between 1990 and 2017, Remote Sens., 11, 790,, 2019. 
Aburas, M. M., Ahamad, M. S. S., and Omar, N. Q.: Spatio-temporal simulation and prediction of land-use change using conventional and machine learning models: a review, Environ. Monit. Assess., 191,, 2019. 
Abu-Rmileh, A.: Be careful when interpreting your features importance in XGBoost!, Data Sci., available at:, last access: 14 June 2019. 
Ahmadlou, M., Delavar, M. R., and Tayyebi, A.: Comparing ANN and CART to Model Multiple Land Use Changes: A Case Study of Sari and Ghaem-Shahr Cities in Iran, J. Geomat. Sci. Technol., 6, 292–303, 2016. 
Ahmadlou, M., Delavar, M. R., Basiri, A., and Karimi, M.: A Comparative Study of Machine Learning Techniques to Simulate Land Use Changes, J. Indian Soc. Remote Sens., 47, 53–62,, 2019. 
Short summary
Extreme gradient boosting (XGBoost) can provide alternative insights that conventional land-use models are unable to generate. Shapley additive explanations (SHAP) can interpret the results of the purely data-driven approach. XGBoost achieved similar and robust simulation results. SHAP values were useful for analysing the complex relationship between the different drivers of grassland degradation.