Generation of Synthetic Density Log Data Using Deep Learning Algorithm at the Golden Field in Alberta, Canada

Table 3

Comparison of Cases 1 and 2 in terms of training, validation, and test data.

Category	Case 1	Case 2
Training and validation data	23 wells	28 wells: 24 wells (the 23 training wells and 1 test well in Case 1) nearby the field + 4 wells among the 5 additional wells at the field; (Case 2-1: 2^nd, 3^rd, 4^th, and 5^th); (Case 2-2: 1^st, 3^rd, 4^th, and 5^th); (Case 2-3: 1^st, 2^nd, 4^th, and 5^th); (Case 2-4: 1^st, 2^nd, 3^rd, and 5^th); (Case 2-5: 1^st, 2^nd, 3^rd, and 4^th)
Test data	1 well (no. 29)	The remaining 1 well among the 5 additional wells at the field; (Case 2-1: 1^st); (Case 2-2: 2^nd); (Case 2-3: 3^rd); (Case 2-4: 4^th); (Case 2-5: 5^th)