Table 2. Summary of the Research Related to the Prediction of Organic Matter in Shale.
| refs | study conducted | technique | method type | input parametersa | geological field study |
|---|---|---|---|---|---|
| Tan et al.24 | prediction of TOC | artificial intelligence | epilson-SVR, nu-SCR, SMO-SVR, and RBF | CNL, GR, AC, K, TH, U, PE, RHOB, and RT | Huangping syncline, China |
| Rui et al.25 | prediction of TOC | artificial intelligence | SVM | wireline log data such as RHOB, GR, SP, RT, and DT | Beibu Gulf basin |
| Lawal et al.27 | prediction of TOC | artificial intelligence | ANN | XRD data: SiO2, Al2O3, MgO, and CaO | Devonian Shale |
| Sultan28 | prediction of TOC | artificial intelligence | self-adaptive differential evolution-based ANN | well logs: GR, DT, RT, and RHOB | Devonian Shale |
| Mahmoud56 | prediction of TOC | artificial intelligence | ANN | well logs: GR, DT, RT, and RHOB | Devonian Shale |
| Zhao et al.50 | prediction of TOC | regression | nonlinear | CNL | Ordos Basin in China and Bakken Shale of North Dakota |
| Wang et al.53 | prediction of TOC | regression | nonlinear | DT and RT | Sichuan Basin, Southern China |
| Alizadeh et al.46 | prediction of TOC and S2 | artificial intelligence | ANN | DT and RT | Dezful Embayment, Iran |
| Handhal et al.45 | prediction of TOC | artificial intelligence | SVR, ANN, KNN, random forest, and rotation forest | GR, RHOB, NPHI, RllD, and DT | Rumaila Oil Field, Iran |
| Wang et al.48 | TOC, S1, and S2 | artificial intelligence | ANN | RHOB, NPHI, RT, and DT | Bohai Bay Basin, China |
GR = γ-ray, RHOB = bulk density, LLD = deep lateral log, LLS = shallow lateral log, MSFL = microspherical focused log, RILD = deep induction resistivity log, DT = compressional wave travel time, TH = thorium, U = uranium, K = potassium, RT = resistivity log, NPHI = neutron porosity, SP = spontaneous potential, CNL = compensated neutron log, PE = photoelectric index, SiO2 = silicondioxide, Al2O3 = aluminiumdioxide, MgO = magnesium oxide, and CaO = calcium oxide.