Table 2.

Performance parameters of cell concentration models

	Training		Validation		RMSE (log10 g L−1)		Variance (%)
	R 2	Slope	R 2	Slope	CV	p
T. lutea	0.98 ± .01	0.95 ± 0.03	0.96 ± .03	0.97 ± 0.11	0.037 ± 0.012	.035 ± .008	97.10 ± 1.98
P. tricornutum	0.97 ± .01	0.94 ± 0.05	0.96 ± .01	0.97 ± 0.12	0.052 ± 0.008	.043 ± .004	99.16 ± 0.23
T. lutea + P. tricornutum	0.96 ± .01	0.98 ± 0.06	0.93 ± .05	0.99 ± 0.15	0.052 ± 0.013	.048 ± .008	98.08 ± 1.33

Note: Models were built using 75% of the data for training and 25% for validation. Three datasets where tested: using data only from Tisochyrysis lutea (n training = 21, n validation = 7); only from Phaeodactylum tricornutum (n training = 36, n validation = 12); and combined data of T. lutea and P. tricornutum (n training = 57, n validation = 19). The model performance parameters are: coefficients of determination (R ²) and slopes of linear regression for training and validation datasets, RMSE of CV and P, and captured variance.

Abbreviations: CV, cross‐validation; P, prediction; RMSE, root mean square errors.