Use of supervised and unsupervised approaches to make zonal application maps for variable-rate application of crop growth regulators in commercial cotton fields

Table 5 Main parameters of the PCA-based approach of the unsupervised framework (UF) for fields-dates to create the zonal application maps

Farm (Field)	Date/(mm/dd/YY)	DAE /d	Correlation	Bartlett's test (P-value)	Cumulative variance /%	Communality
1(A)	03/10/2023	35	0.33; –0.07	8.42e-144	75	0.698; 0.699; 0.956
1(A)	03/23/2023	48	0.01; 0.06	3.97e-22	71	0.944; 0.637; 0.553
2(B)	04/18/2023	86	0.30; 0.01	3.64e-55	77	0.663; 0.658; 0.987
2(B)	05/03/2023	108	0.30; –0.15	5.70e-65	77	0.639; 0.705; 0.969
3(C)	03/22/2023	40	0.43; –0.53	0	85	0.829; 0.983; 0.726
3(C)	05/11/2023	88	0.22; –0.43	0	81	0.744; 0.993; 0.695

DAE refers to days after seedling emergence of the corresponding field-data collection. Correlation refers to the correlation of plant height with NDVI and sand:clay, respectively. Bartlett's test was used to determine the P-value and respective suitability for PCA use (P-value < 0.05 indicates an acceptable use of PCA analysis). The cumulative variance refers to the proportion of variability explained by the first two PCs. Communality refers to each variable's (height, NDVI, sand:clay, respectively) proportion of variability explained by the first two PCs

ISSN: 2523-3254