Applications of Artificial Intelligence for Static Poisson’s Ratio Prediction While Drilling

Table 2

The developed AI models for static Poisson’s ratio prediction.

Authors	Inputs	AI techniques	No. of datapoints	Remarks
Abdulraheem et al. [39]	Travel time and bulk density	ANN, FL, and FN	77	R = 0.10–0.91
Al-anazi et al. [40]	Bulk density, depth, pore pressure, overburden stresses, minimum horizontal stresses, porosity, and compressional and shear travel times	ACE	602	R = 0.997
Tariq et al. [41]	Vp and Vs	ANN	550	Carbonate formations; R = 0.985
Elkatatny et al. [42]	Bulk density and compressional and shear times	ANN	610	Carbonate formations; R = 0.985
Elkatatny [43]	Sonic travel times and bulk density	ANN, ANFIS, and SVM	610	Carbonate formations; R = 0.933–0.985
Tariq et al. [44]	Bulk density, gamma ray, porosity, and Vp and Vs	FN	580	Carbonate formations; R = 0.985
Abdulraheem [45]	Vp and Vs	ANN and FL	75	Carbonate formations; AAPE = 5.16–8.20%
Gowida et al. [46]	Bulk density and sonic log	ANN coupled with DE	692	Sandstone; R = 0.964
Ahmed et al. [47]	Drilling parameters	ANN, ANFIS, and SVM	1775	R = 0.90–0.96

AAPE = average absolute percentage error. DE = differential evolution algorithm.