Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

General diagram of shear wave predicting.

More »

Fig 1 Expand

Table 1.

the main structural differences among different algorithms.

More »

Table 1 Expand

Fig 2.

ANN structure diagram.

More »

Fig 2 Expand

Fig 3.

LSTM network cell internal structure.

More »

Fig 3 Expand

Fig 4.

LSTM network overall structure.

More »

Fig 4 Expand

Fig 5.

diagram of the GAN-LSTM network.

Note: In the Fig 4, , , are the set of network parameters of feature extractor, the generator and the discriminator respectively; and are loss functions for the generator and the discriminator.

More »

Fig 5 Expand

Fig 6.

structure of the GAN-LSTM network.

More »

Fig 6 Expand

Table 2.

Statistical characteristics of variables of two wells.

More »

Table 2 Expand

Fig 7.

Scatter diagram of logging curves in Well A.

More »

Fig 7 Expand

Fig 8.

Scatter diagram of logging curves in Well B.

More »

Fig 8 Expand

Fig 9.

Correlation of logging curves with shear wave velocity.

More »

Fig 9 Expand

Fig 10.

Logging sequence conversion.

More »

Fig 10 Expand

Table 3.

The GAN-LSTM network parameters.

More »

Table 3 Expand

Fig 11.

Flowchart of the algorithm.

More »

Fig 11 Expand

Table 4.

Feature vectors generated by LSTM and GAN-LSTM.

More »

Table 4 Expand

Fig 12.

Predictive results of three neural networks in well B.

More »

Fig 12 Expand

Table 5.

Network deployment environment and training time.

More »

Table 5 Expand

Fig 13.

Local amplification comparison in Well B (the upper part marked in

Fig 12).

More »

Fig 13 Expand

Fig 14.

Local amplification comparison in Well B (the lower part marked in

Fig 12).

More »

Fig 14 Expand

Fig 15.

Comparison of the probability distribution of the three prediction methods.

More »

Fig 15 Expand

Fig 16.

The relative error of the three forecasting methods.

More »

Fig 16 Expand

Table 6.

Comparison of accuracy under different methods in two wells.

More »

Table 6 Expand

Fig 17.

MAE different methods in well B.

More »

Fig 17 Expand

Fig 18.

Cross plots of different methods.

More »

Fig 18 Expand

Fig 19.

Comparison of CNN [

35], GRU [36] and GANLSTM.

More »

Fig 19 Expand

Fig 20.

Prediction of LSTM and proposed GAN-LSTM network under different input in Well B.

(Input length from left to right is set as 5, 7, 9, 11). (Mark the upper and lower parts of the curve in red for comparison).

More »

Fig 20 Expand

Fig 21.

Local magnification of LSTM and GANLSTM’s prediction under different input length.

(upper part in Fig 20). (The input length of (a), (b), (c), (d) is set as 5,7,9,11, respectively).

More »

Fig 21 Expand

Fig 22.

Local magnification of LSTM and GANLSTM’s prediction under different input length.

(lower part in Fig 20). (The input length of (a), (b), (c), (d) is set as 5,7,9,11, respectively).

More »

Fig 22 Expand

Table 7.

Evaluation of prediction in Well B under different input window length.

More »

Table 7 Expand

Fig 23.

Comparison of R2 of results between LSTM and GANLSTM.

More »

Fig 23 Expand

Fig 24.

Comparison of MAE of results between LSTM and GANLSTM.

More »

Fig 24 Expand