Replication Data for: Reconstructing past vegetation with Random Forest Machine Learning, sacrificing the dynamic response for robust results

Fig.1 PMIP SAT ensenble spread (nc file) Fig. 2 Simulated (ML) global biome distribution for PI, MH and LGM Fig. 3-5 Perturbation simulation results of ML and LPJ-GUESS Ref: Reconstructing past vegetation with Random Forest Machine Learning, sacrificing the dynamic response for robust results by Amelie Lindgren, Zhengyao Lu, Qiong Zhang, Gustaf Hugelius, JAMES (2020) For any question, please contact: [e-mail]; [e-mail]