Suchergebnisse

Background: The prediction of biogeographical patterns from a large number of driving factors with complex interactions, correlations and non-linear dependences require advanced analytical methods and modeling tools. This study compares different statistical and machine learning-based models for predicting fungal productivity biogeographical patterns as a case study for the thorough assessment of the performance of alternative modeling approaches to provide accurate and ecologically-consistent predictions. Methods: We evaluated and compared the performance of two statistical modeling techniques, namely, generalized linear mixed models and geographically weighted regression, and four techniques based on different machine learning algorithms, namely, random forest, extreme gradient boosting, support vector machine and artificial neural network to predict fungal productivity. Model evaluation was conducted using a systematic methodology combining random, spatial and environmental blocking together with the assessment of the ecological consistency of spatially-explicit model predictions according to scientific knowledge. Results: Fungal productivity predictions were sensitive to the modeling approach and the number of predictors used. Moreover, the importance assigned to different predictors varied between machine learning modeling approaches. Decision tree-based models increased prediction accuracy by more than 10% compared to other machine learning approaches, and by more than 20% compared to statistical models, and resulted in higher ecological consistence of the predicted biogeographical patterns of fungal productivity. Conclusions: Decision tree-based models were the best approach for prediction both in sampling-like environments as well as in extrapolation beyond the spatial and climatic range of the modeling data. In this study, we show that proper variable selection is crucial to create robust models for extrapolation in biophysically differentiated areas. This allows for reducing the dimensions of the ecosystem space described by the predictors of the models, resulting in higher similarity between the modeling data and the environmental conditions over the whole study area. When dealing with spatial-temporal data in the analysis of biogeographical patterns, environmental blocking is postulated as a highly informative technique to be used in cross-validation to assess the prediction error over larger scales. ; This work was supported by the Secretariat for Universities and of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund. This work was partially supported by the Spanish Ministry of Science, Innovation and Universities (Grant No. RTI2018–099315-A-I00). J.A.B. benefitted from a Serra-Húnter Fellowship provided by the Government of Catalonia.

Fungi are responsible for many of the processes that occur in natural ecosystems and largely determine forest ecosystem dynamics, such as the ability of trees to access limiting nutrients and sequester carbon. Understanding and predicting climate change impacts on fungal dynamics over large scales is key in order to gain further insights into the effects of global change on natural ecosystem functioning and related ecosystem services. In this study, we use predictive models based on machine learning algorithms to estimate, in a spatially explicit way, the historical and future (1976–2100) evolution of mycorrhizal and saprotrophic macrofungal productivity in Mediterranean forest areas under climate change scenarios. The greatest changes in total productivity, as well as mycorrhizal fungi, are predicted to occur in subalpine and montane pine forests, where fungal productivity is estimated to decrease, and will be more pronounced under climate change scenarios with higher expected increase in temperature. In contrast to mycorrhizal species, saprotrophic fungi could benefit from pronounced changes in climate and increase their productivity in supra- and mesomediterranean regions at mid-range elevations. Moreover, we estimated that fungal productivity has also changed historically in some scattered areas where changes in climate over the years may have led to a decrease in productivity. This study contributes to raising awareness on the need for anticipating potential global change impacts on this key element of ecosystem functioning, and for deploying possible management policies oriented toward maintaining the important role of fungal productivity in both climate change mitigation and adaptation. ; We thank the "Agencia Estatal de Meteorología (AEMET)" and "Servei Meteorològic de Catalunya (SMC)" for providing daily weather station data. This work was supported by the Secretariat for Universities and of the Ministry of Business and Knowledge of the Government of Catalonia and the European Social Fund. This work was ...