Algal-bacterial interactions include mutualism, commensalism, and predation. However, how multiple environmental conditions that regulate the strength and prevalence of a given interaction remains unclear. Here, we test the hypothesis that the prevailing algal-bacterial interaction shifted in two years (2005 versus 2015), due to increased temperature (T) and Saharan dust depositions in high-mountain lakes of Sierra Nevada (S Spain). Our results support the starting hypothesis that the nature of the prevailing algal-bacterial interaction shifted from a bacterivory control exerted by algae to commensalism, coinciding with a higher air and water T as well as the lower ratio sestonic nitrogen (N): phosphorous (P), related to greater aerosol inputs. Projected global change conditions in Mediterranean region could decline the functional diversity and alter the role of mixotrophy as a carbon (C) by-pass in the microbial food web, reducing the biomass-transfer efficiency up the web by increasing the number of trophic links.

Most weather forecasting models are not able to accurately reproduce the great variability existing in the measurements of the diffuse component of photosynthetically active radiation (PAR; 400–700 nm) under all sky conditions. Based on the well‐known relationship between the diffuse fraction (k) and the clearness index (k_t), this study addresses improvements in estimations by proposing adaptations of previous models, which were previously applied only to the total solar irradiance (TSI; 280–3,000 nm). In order to reproduce this variability, additional parameters were introduced. The models were tested employing a multisite database gathered at the Mediterranean basin. Since Artificial Neural Network (ANN) models are not limited to fixed coefficients to predict the diffuse fraction of PAR (k_PAR), these types of models are more accurate than empirical ones, reaching determination coefficients (r²) up to 0.998. However, the simpler linear model proposed by Foyo‐Moreno et al. (2018), https://doi.org/10.1016/j.atmosres.2017.12.012 shows a similar performance to the ANN models, directly predicting the diffuse component of PAR (PAR_Diffuse) from TSI_Diffuse, with a r² up to 0.997. Results obtained here also determine that the most important variables for estimating PAR_Diffuse are k_t or k_t,PAR, and the apparent solar time (AST). Therefore, PAR_Diffuse can be modeled using TSI measured in most radiometric stations, reaching r² up to 0.858 for empirical models and 0.970 for ANN models. This modified approach will allow for the very accurate construction of long‐term data series of PAR_Diffuse in regions where continuous measurements of PAR are not available.