Fig. 5: Gaussian process regression (GPR). | Nature Communications

Fig. 5: Gaussian process regression (GPR).

From: Data-driven design of electrolyte additives supporting high-performance 5 V LiNi0.5Mn1.5O4 positive electrodes

Fig. 5

Parity plot of GPR-predicted a final area-specific impedance (ASI), b impedance rise (∆ASI), and c final specific capacity (Q) versus measured values for the training set of 28 additive and baseline solvent. The average mean absolute values (MAEs) based on 5-fold cross validation are shown in the legends. Data are presented as mean values (solid circles and squares) +/− one standard deviation (error bars). Blue circles and orange squares indicate to train and test datapoints, respectively. Source data are provided as a Source data file.

Back to article page