Skip to main content
Fig. 2 | Microbiome

Fig. 2

From: Predicting microbial community compositions in wastewater treatment plants using artificial neural networks

Fig. 2

Prediction of alpha diversity. a. The framework of ANN models: input data (blue), output data (red), and a predictive model trained to compute output data from input data (purple). Correlations between observed and predicted values of Shannon–Wiener index (b), Pielou’e evenness index (c), species richness (d), and Faith's phylogenetic diversity (e). The 1:1 relationship is shown as a solid black line, and the best fit is shown as the dashed light blue line. The blue-shaded region represents the 95% confidence interval for the best-fit line. We reported the R2 value of the best-fit line between predicted and observed and the R2 observations relative to the 1:1 line. f. Heatmap of importance weights of environmental factors in alpha diversity predictive models

Back to article page