TABLE 1.

Best fit models of cone length (cm) based on 65 Pinus strobiformis stands in Mexico and United States.

Method of variable selection	Machine learning algorithm	Independent variable	RMSE	MAE	R2
PLS	rf	GSP, WINP, SMRPB, Pseudotsuga menziesii, P. cooperi, Arbutus xalapensis	1.755	1.477	0.890
PLS	brnn	GSP, WINP, SMRPB, Pseudotsuga menziesii, P. cooperi, Arbutus xalapensis	1.832	1.514	0.867
ROC	lm	GSP, Pseudotsuga menziesii, MAT, SMRPB, P. arizonica, J. deppeana	1.939	1.536	0.865
PLS	mlpWeightDecay	GSP, WINP, SMRPB, Pseudotsuga menziesii, P. cooperi, Arbutus xalapensis	5.599	4.971	0.191
KW	avNNet	GSP, MAT, Pseudotsuga menziesii, P. strobiformis, P. arizonica, SMRPB	17.852	17.125	0.658
KW	nnet	GSP, MAT, Pseudotsuga menziesii, P. strobiformis, P. arizonica, SMRPB	17.856	17.128	0.621

PLS = Partial Least Squares, ROC = Receiver Operating Characteristic, KW = Kruskal Wallis, rf = Random Forest, brnn = Bayesian Regularized Neural Networks, lm = linear regression, mlpWeightDecay = Multi-Layer Perceptron, nnet = Neural Network, avNNet = Model Averaged Neural Network, RMSE = Root-mean-square error, MAE = Mean Absolute Error, R² = R squared, GSP = Growing season precipitation, April to September, Pseudotsuga menziesii = frequency of occurrence of Pseudotsuga menziesii in the neighborhood, SMRPB = Summer precipitation balance: (jul+aug+sep)/(apr+may+jun), Juniperus deppeana = frequency of occurrence of Juniperus deppeana in the neighborhood, P. arizonica = frequency of occurrence of P. arizonica in the neighborhood, P. strobiformis = frequency of occurrence of P. strobiformis in the neighborhood, P. cooperi = frequency of occurrence of P. cooperi in the neighborhood, Arbutus xalapensis = frequency of occurrence of Arbutus xalapensis, Arctostaphylos pungens = frequency of occurrence of Arctostaphylos pungens MAT = Mean annual temperature (degrees C), WINP = Winter precipitation: (nov+dec+jan+feb).