Application of Various Machine Learning Techniques in Predicting Total Organic Carbon from Well Logs

Table 5

Performance of different sets of inputs.

No.	Inputs	Training		Testing
		R	AAPE (%)	R	AAPE (%)
1	CNP, RHOB, Δt,	0.978	8.5	0.811	25.7
2	CNP, RHOB, GR, Δt, FR	0.987	5.8	0.900	16.5
3	CNP, GR, Δt, FR, K, Th, Ur	0.988	5.5	0.924	14.6
4	RHOB, GR, Δt, FR, K, Th, Ur	0.989	5.2	0.921	14.8
5	CNP, RHOB, GR, Δt, K, Th, Ur	0.985	6.5	0.913	16.6
6	CNP, RHOB, GR, FR, K, Th, Ur	0.988	5.5	0.918	14.6
7	CNP, RHOB, GR, Δt, FR, K, Th, Ur	0.989	5.3	0.931	13.8