PLSR	Partial least squares regression
GPR	Gaussian process regression
R2	Coefficient of determination
RMSE	Root mean square error
ARI	Anthocyanin reflectance index
mARI	Modified anthocyanin reflectance index
VARI	Visible atmospherically resistant vegetation index
ACI	Anthocyanin content index
PROSPECT	Leaf optical properties spectra
ANN	Artificial neural network
PRESS	Predictive residual sum of squares
SS	Sum of squares
GP	Gaussian process
ARD	Automatic relevance determination
r	Pearson correlation coefficient
P	Significance level for correlation
SBBR	Sequential backward band removal
σm	Characteristic length scale for a variable in GPR
|β|	Absolute value of the regression coefficient β in PLSR
R	Reflectance
log(1/R)	Logarithmic transformation to R
NDVI	Normalized difference vegetation index
Mathematical symbols and notation in Section 2.3
Matrixes are capitalized and vectors are in the lowercase bold type. The subscript asterisk (e.g., X*) indicates the test set quantity.
′	The transpose of a matrix or vector
𝒟	Data set: 𝒟 = {(xi, yi,)|i = 1, 2, …, n}
ℝb	b-dimensional real numbers
∼	Distributed according to (e.g., Gaussian distribution)
𝒢𝒫	Gaussian process
𝒩	Gaussian (normal) distribution
${\sigma }_n^2$	Noise variance
0	Vector of all 0′s
k(x,y)	Covariance (or kernel) function evaluated at x and y
K(X,Y)	Covariance (or Gram) matrix evaluated with X and Y
y|x and p(y|x)	Conditional random variable y given x and the corresponding probability
θ	Vector of hyperparameters
f	Gaussian process latent function values