Table 1 Classification of ML methods employed in ROP prediction.

From: Hybrid physics-machine learning models for predicting rate of penetration in the Halahatang oil field, Tarim Basin

Algorithm

Detail

References

ANN

Three-layer feed-forward back propagation

Bilgesu11, Mendes12, Moran13, Arabjamaloei14

Multi-layer perceptron (MLP) networks trained with a back-propagation algorithm (BP)

Esmaeili15, Ning16, Zare17, Anemangely22

MLP with particle swarm optimization algorithm (PSO) (MLP, a radial basis function (RBF) ANN, SVM)

Sabah23

ANN with an improved genetic algorithm (IGA)

Li25

MLP with Firefly algorithm (FF), Gravitational search algorithm (GSA), Artificial bee colony algorithm (ABC), Independent component analysis (ICA)

Hazbeh28

ANN with 1 hidden layer, 20 neurons, fitnet as a network function, trainbr as a training function, tansig as a transfer function (adaptive neuro-fuzzy inference system (ANFIS), SVM)

Salaheldin29

ANN with extreme learning machine (ELM)

Gan27

combining an attention-based Gated Recurrent Unit network and fully connected neural networks

Zhang32

multilayer perceptron neural network (MLPNN), radial basis function neural network (RBFNN) (adaptive neuro-fuzzy inference system (ANFIS), and support vector regression (SVR))

Brenjkar33

MLP with Bayesian Regularization Algorithm (BRA) (Radial Basis Function, Decision Tree (DT), Least Square Vector Machine (LSSVM))

Mohsen34

SVM

Support vector regression with the genetic algorithm (GA) and the cuckoo search algorithm (CS)

Bodaghi18

least-squares support-vector machines (LSSVM) with cuckoo optimization algorithm (COA), particle swarm optimization (PSO), and genetic algorithms (GA) (SVR-COA, MLP-COA, linear multivariate regression (LMR), and nonlinear multivariate regression (NLMR))

Mohammad26

ε-insensitive SVR and V-SVR

Korhan24

RF

RF (Trees, Bagging)

Hegde19

RF (ANN, SVM, KNN (k-nearest neighbor), decision trees (DT))

Mantha20

RF (SVM, BP, KNN, RBF Network)

Zhang30

RF (SVM, ANN)

Soares7, Song35

RF (MLP)

Kaveh38

Hybrid models

Traditional models with RF, ANN, Linear regression

Hegde21

Traditional models with RF, ELM, BP, SVM

Ren31

DL

long short- term memory (LSTM) neural network, SVR, BP, deep belief neural network (DBN), convolutional neural network (CNN)

Wang36

Generative Adversarial Network (GAN), MLP, CNN

Mohammad37