@article{DormannElithBacheretal.2013,
  author    = {Dormann, Carsten F. and Elith, Jane and Bacher, Sven and Buchmann, Carsten M. and Carl, Gudrun and Carre, Gabriel and Garcia Marquez, Jaime R. and Gruber, Bernd and Lafourcade, Bruno and Leitao, Pedro J. and M{\"u}nkem{\"u}ller, Tamara and McClean, Colin and Osborne, Patrick E. and Reineking, Bjoern and Schr{\"o}der-Esselbach, Boris and Skidmore, Andrew K. and Zurell, Damaris and Lautenbach, Sven},
  title     = {Collinearity a review of methods to deal with it and a simulation study evaluating their performance},
  series = {Ecography : pattern and diversity in ecology ; research papers forum},
  volume    = {36},
  journal   = {Ecography : pattern and diversity in ecology ; research papers forum},
  number    = {1},
  publisher = {Wiley-Blackwell},
  address   = {Hoboken},
  issn      = {0906-7590},
  doi       = {10.1111/j.1600-0587.2012.07348.x},
  pages     = {27 -- 46},
  year      = {2013},
  abstract  = {Collinearity refers to the non independence of predictor variables, usually in a regression-type analysis. It is a common feature of any descriptive ecological data set and can be a problem for parameter estimation because it inflates the variance of regression parameters and hence potentially leads to the wrong identification of relevant predictors in a statistical model. Collinearity is a severe problem when a model is trained on data from one region or time, and predicted to another with a different or unknown structure of collinearity. To demonstrate the reach of the problem of collinearity in ecology, we show how relationships among predictors differ between biomes, change over spatial scales and through time. Across disciplines, different approaches to addressing collinearity problems have been developed, ranging from clustering of predictors, threshold-based pre-selection, through latent variable methods, to shrinkage and regularisation. Using simulated data with five predictor-response relationships of increasing complexity and eight levels of collinearity we compared ways to address collinearity with standard multiple regression and machine-learning approaches. We assessed the performance of each approach by testing its impact on prediction to new data. In the extreme, we tested whether the methods were able to identify the true underlying relationship in a training dataset with strong collinearity by evaluating its performance on a test dataset without any collinearity. We found that methods specifically designed for collinearity, such as latent variable methods and tree based models, did not outperform the traditional GLM and threshold-based pre-selection. Our results highlight the value of GLM in combination with penalised methods (particularly ridge) and threshold-based pre-selection when omitted variables are considered in the final interpretation. However, all approaches tested yielded degraded predictions under change in collinearity structure and the folk lore'-thresholds of correlation coefficients between predictor variables of |r| >0.7 was an appropriate indicator for when collinearity begins to severely distort model estimation and subsequent prediction. The use of ecological understanding of the system in pre-analysis variable selection and the choice of the least sensitive statistical approaches reduce the problems of collinearity, but cannot ultimately solve them.},
  language  = {en}
}
@article{FournierSteinerBrochetetal.2022,
  author    = {Fournier, Bertrand and Steiner, Magdalena and Brochet, Xavier and Degrune, Florine and Mammeri, Jibril and Carvalho, Diogo Leite and Siliceo, Sara Leal and Bacher, Sven and Pe{\~n}a-Reyes, Carlos Andr{\´e}s and Heger, Thierry Jean},
  title     = {Toward the use of protists as bioindicators of multiple stresses in agricultural soils},
  series = {Ecological indicators : integrating monitoring, assessment and management},
  volume    = {139},
  journal   = {Ecological indicators : integrating monitoring, assessment and management},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {1470-160X},
  doi       = {10.1016/j.ecolind.2022.108955},
  pages     = {8},
  year      = {2022},
  abstract  = {Management of agricultural soil quality requires fast and cost-efficient methods to identify multiple stressors that can affect soil organisms and associated ecological processes. Here, we propose to use soil protists which have a great yet poorly explored potential for bioindication. They are ubiquitous, highly diverse, and respond to various stresses to agricultural soils caused by frequent management or environmental changes. We test an approach that combines metabarcoding data and machine learning algorithms to identify potential stressors of soil protist community composition and diversity. We measured 17 key variables that reflect various potential stresses on soil protists across 132 plots in 28 Swiss vineyards over 2 years. We identified the taxa showing strong responses to the selected soil variables (potential bioindicator taxa) and tested for their predictive power. Changes in protist taxa occurrence and, to a lesser extent, diversity metrics exhibited great predictive power for the considered soil variables. Soil copper concentration, moisture, pH, and basal respiration were the best predicted soil variables, suggesting that protists are particularly responsive to stresses caused by these variables. The most responsive taxa were found within the clades Rhizaria and Alveolata. Our results also reveal that a majority of the potential bioindicators identified in this study can be used across years, in different regions and across different grape varieties. Altogether, soil protist metabarcoding data combined with machine learning can help identifying specific abiotic stresses on microbial communities caused by agricultural management. Such an approach provides complementary information to existing soil monitoring tools that can help manage the impact of agricultural practices on soil biodiversity and quality.},
  language  = {en}
}