Skip to Main content Skip to Navigation
Journal articles

Multi-model ensembles improve predictions of crop-environment-management interactions

Daniel Wallach 1, * Pierre Martre 2 Bo Liu 3, 4 Senthold Asseng 4 Frank Ewert 5, 6 P.J. Thorburn 7 Martin K. van Ittersum 8 Pramod K. Aggarwal 9 Melika Ben Ahmed 10, 11 Bruno Basso 12 Christian Biernath 13 Davide Cammarano 14 Andrew J. Challinor 15, 16 Giacomo de Sanctis 17 Benjamin Dumont 18 Ehsan Eyshi Rezaei 5, 19 Elias Fereres 20 Gerry J Fitzgerald 21, 22 Yimin Gao 4 Margarita Garcia-Vila 20 Sebastian Gayler 23 Christine Girousse 24 Gerrit Hoogenboom 25 Heidi Horan 7 Roberto C. Izaurralde 26, 27 Corbin D. Jones 27 Belay T. Kassie 4 Kurt Christian Kersebaum 28 C. Klein 13 Ann-Kristin Koehler 29 Andrea Maiorano 2, 30 Sara Minoli 31 Christoph Müller 31 Soora Kumar Naresh 32 Claas Nendel 28 Garry J. O'Leary 33 Taru Palosuo 34 Eckart Priesack 13 Dominique Ripoche 35 Reimund Paul Rötter 36 Mikhail A. Semenov 37 Claudio O. Stöckle 10 Pierre Stratonovitch 37 Thilo Streck 23 Iwan Supit 38 Fulu Tao 39 Joost Wolf 40 Ze Zhang 41 
* Corresponding author
Abstract : A recent innovation in assessment of climate change impact on agricultural production has been to use crop multi model ensembles (MMEs). These studies usually find large variability between individual models but that the ensemble mean (e‐mean) and median (e‐median) often seem to predict quite well. However few studies have specifically been concerned with the predictive quality of those ensemble predictors. We ask what is the predictive quality of e‐mean and e‐median, and how does that depend on the ensemble characteristics. Our empirical results are based on five MME studies applied to wheat, using different data sets but the same 25 crop models. We show that the ensemble predictors have quite high skill and are better than most and sometimes all individual models for most groups of environments and most response variables. Mean squared error of e‐mean decreases monotonically with the size of the ensemble if models are added at random, but has a minimum at usually 2‐6 models if best‐fit models are added first. Our theoretical results describe the ensemble using four parameters; average bias, model effect variance, environment effect variance and interaction variance. We show analytically that mean squared error of prediction (MSEP) of e‐mean will always be smaller than MSEP averaged over models, and will be less than MSEP of the best model if squared bias is less than the interaction variance. If models are added to the ensemble at random, MSEP of e‐mean will decrease as the inverse of ensemble size, with a minimum equal to squared bias plus interaction variance. This minimum value is not necessarily small, and so it is important to evaluate the predictive quality of e‐mean for each target population of environments. These results provide new information on the advantages of ensemble predictors, but also show their limitations.
Complete list of metadata
Contributor : Migration ProdInra Connect in order to contact the contributor
Submitted on : Tuesday, May 26, 2020 - 2:39:01 PM
Last modification on : Friday, August 5, 2022 - 3:39:28 PM

Links full text



Daniel Wallach, Pierre Martre, Bo Liu, Senthold Asseng, Frank Ewert, et al.. Multi-model ensembles improve predictions of crop-environment-management interactions. Global Change Biology, Wiley, 2018, 24 (11), pp.5072-5083. ⟨10.1111/gcb.14411⟩. ⟨hal-02625468⟩



Record views