Figure 1.
TEM inversion results considering IP-induced polarization effect. (a) represents the predicted TEM signal corresponding to the inversion iteration step, and (b) represents the predicted geoelectric structure corresponding to the inversion iteration step.
Figure 1.
TEM inversion results considering IP-induced polarization effect. (a) represents the predicted TEM signal corresponding to the inversion iteration step, and (b) represents the predicted geoelectric structure corresponding to the inversion iteration step.
Figure 2.
LSTM network architecture diagram.
Figure 2.
LSTM network architecture diagram.
Figure 3.
Assuming the central node (purple) represents the current geoelectric layer. The green nodes depict the connections to the current layer. We acquire spatial features by obtaining the topological relationships between the current geoelectric layer and its surrounding layers.
Figure 3.
Assuming the central node (purple) represents the current geoelectric layer. The green nodes depict the connections to the current layer. We acquire spatial features by obtaining the topological relationships between the current geoelectric layer and its surrounding layers.
Figure 4.
GCN-LSTM Model Framework.
Figure 4.
GCN-LSTM Model Framework.
Figure 5.
Training processes of the proposed neural networks correspond to different learning rates, network depths, and regularization rates. (a) represents the training loss decay; (b) represents the loss decay of valid dataset.
Figure 5.
Training processes of the proposed neural networks correspond to different learning rates, network depths, and regularization rates. (a) represents the training loss decay; (b) represents the loss decay of valid dataset.
Figure 6.
The predictions of different neural network models for the five-strata geoelectric structure based on TEM responses. (a) represents the depth-resistivity relationship chart for the assumed and predicted five-strata geoelectric structures. (b) represents the depth-IP (Induced Polarization) parameter relationship chart for the assumed and predicted five-strata geoelectric structures.
Figure 6.
The predictions of different neural network models for the five-strata geoelectric structure based on TEM responses. (a) represents the depth-resistivity relationship chart for the assumed and predicted five-strata geoelectric structures. (b) represents the depth-IP (Induced Polarization) parameter relationship chart for the assumed and predicted five-strata geoelectric structures.
Figure 7.
Misfit analysis of predicting the five-strata geoelectric structure using different neural network models based on TEM responses. (a) Depth and resistivity misfits of the predicted five-strata geoelectric structure, (b) Depth and IP parameter misfits of the predicted five-layer geoelectric structure, (c) Induced magnetic field misfits in the predicted TEM responses, (d) Induced EMF misfits in the predicted TEM responses.
Figure 7.
Misfit analysis of predicting the five-strata geoelectric structure using different neural network models based on TEM responses. (a) Depth and resistivity misfits of the predicted five-strata geoelectric structure, (b) Depth and IP parameter misfits of the predicted five-layer geoelectric structure, (c) Induced magnetic field misfits in the predicted TEM responses, (d) Induced EMF misfits in the predicted TEM responses.
Figure 8.
The predictions of different neural network models for the nine-strata geoelectric structure based on TEM responses. (a) represents the depth-resistivity relationship chart for the assumed and predicted nine-strata geoelectric structures. (b) represents the depth-IP (Induced Polarization) parameter relationship chart for the assumed and predicted nine-strata geoelectric structures.
Figure 8.
The predictions of different neural network models for the nine-strata geoelectric structure based on TEM responses. (a) represents the depth-resistivity relationship chart for the assumed and predicted nine-strata geoelectric structures. (b) represents the depth-IP (Induced Polarization) parameter relationship chart for the assumed and predicted nine-strata geoelectric structures.
Figure 9.
Misfit analysis of predicting the nine-strata geoelectric structure using different neural network models based on TEM responses. (a) Depth and resistivity misfits of the predicted nine-strata geoelectric structure, (b) Depth and IP parameter misfits of the predicted nine-layer geoelectric structure, (c) Induced magnetic field misfits in the predicted TEM responses, (d) Induced EMF misfits in the predicted TEM responses.
Figure 9.
Misfit analysis of predicting the nine-strata geoelectric structure using different neural network models based on TEM responses. (a) Depth and resistivity misfits of the predicted nine-strata geoelectric structure, (b) Depth and IP parameter misfits of the predicted nine-layer geoelectric structure, (c) Induced magnetic field misfits in the predicted TEM responses, (d) Induced EMF misfits in the predicted TEM responses.
Figure 10.
Inversion outcomes of the five-strata geoelectric model with an intermediate polarization layer. (a) represent the theoretical geoelectric model and inversed geoelectric model; (b) represent the predictive polarization parameters and the theoretical parameters; (c) represent the HZ data fitting curve.
Figure 10.
Inversion outcomes of the five-strata geoelectric model with an intermediate polarization layer. (a) represent the theoretical geoelectric model and inversed geoelectric model; (b) represent the predictive polarization parameters and the theoretical parameters; (c) represent the HZ data fitting curve.
Figure 11.
A 3D simulation model of a seafloor massive sulfide (SMS) deposit is depicted here. With the upwelling of magmatic-hydrothermal fluids (in red), gradual alteration of the surrounding rock layers occurs, resulting in the formation of alteration zones. These alteration zones, progressing from the inner to outer regions, exhibit varying degrees of alteration—strong, moderate, and weak (in green). In the intermediate space between two magmatic-hydrothermal upwelling channels, there is an alteration zone (in yellow) that does not make direct contact with the seafloor surface, along with a buried intact sulfide sedimentary mineral deposit (in black).
Figure 11.
A 3D simulation model of a seafloor massive sulfide (SMS) deposit is depicted here. With the upwelling of magmatic-hydrothermal fluids (in red), gradual alteration of the surrounding rock layers occurs, resulting in the formation of alteration zones. These alteration zones, progressing from the inner to outer regions, exhibit varying degrees of alteration—strong, moderate, and weak (in green). In the intermediate space between two magmatic-hydrothermal upwelling channels, there is an alteration zone (in yellow) that does not make direct contact with the seafloor surface, along with a buried intact sulfide sedimentary mineral deposit (in black).
Figure 12.
Comparison between the gradient inversion and the SMS model of the proposed GCN-LSTM networks inversion.
Figure 12.
Comparison between the gradient inversion and the SMS model of the proposed GCN-LSTM networks inversion.
Table 1.
Performance of the dataset under different neural network architectures.
Table 1.
Performance of the dataset under different neural network architectures.
| The Stack Depth | Loss |
---|
Train | Valid |
---|
GCN + LSTM | 15 | 10 | 5 | 0.08 | 0.22 |
GCN | 9 | 6 | 3 | 0.12 | 1.86 |
LSTM | 6 | 4 | 2 | 12.94 | 3.17 |
MLP | 15 | 10 | 5 | 0.16 | 2.04 |
Table 2.
Comparative details of four network models’ predictions for the five-strata geoelectric model parameters.
Table 2.
Comparative details of four network models’ predictions for the five-strata geoelectric model parameters.
| rho1 | rho2 | rho3 | rho4 | rho5 |
---|
Synthetic | 50 | 300 | 100 | 500 | 200 |
GCN + LSTM | 49.72 | 294.01 | 99.01 | 516.67 | 198.07 |
GCN | 46.19 | 299.70 | 104.13 | 474.36 | 211.40 |
LSTM | 46.39 | 305.93 | 108.02 | 543.94 | 188.85 |
MLP | 48.96 | 341.54 | 107.87 | 426.10 | 210.80 |
| h1 | h2 | h3 | h4 | - |
Synthetic | 200 | 250 | 300 | 500 | |
GCN + LSTM | 197.80 | 246.51 | 289.21 | 488.01 | |
GCN | 182.96 | 244.69 | 270.20 | 472.07 | |
LSTM | 199.31 | 243.80 | 301.43 | 476.49 | |
MLP | 212.36 | 260.88 | 304.71 | 457.72 | |
| c1 | c2 | c3 | c4 | c5 |
Synthetic | - | - | 0.3 | 0.3 | - |
GCN + LSTM | - | - | 0.293 | 0.294 | - |
GCN | - | - | 0.279 | 0.286 | - |
LSTM | - | - | 0.280 | 0.272 | - |
MLP | - | - | 0.288 | 0.335 | - |
Table 3.
Misfit details of four network models’ predictions for the five-strata geoelectric model parameters.
Table 3.
Misfit details of four network models’ predictions for the five-strata geoelectric model parameters.
| Hz | Vz | rho | Thickness (h) | c |
---|
MAPE | RMSE | MAPE | RMSE | MAPE | RMSE | MAPE | RMSE | MAPE | RMSE |
---|
GCN + LSTM | 2.80 | 10.31 | 3.60 | 12.91 | 2.09 | 2.48 | 2.61 | 2.93 | 7.84 | 1.45 |
GCN | 4.84 | 6.80 | 14.2 | 30.67 | 5.86 | 6.27 | 2.60 | 3.23 | 19.10 | 3.51 |
LSTM | 7.23 | 28.1 | 5.833 | 12.94 | 4.90 | 5.84 | 5.54 | 6.44 | 25.32 | 4.29 |
MLP | 19.86 | 72.9 | 21.72 | 60.44 | 8.17 | 9.01 | 6.55 | 8.15 | 20.54 | 3.90 |
Table 4.
Comparative details of four network models’ predictions for the nine-strata geoelectric model parameters.
Table 4.
Comparative details of four network models’ predictions for the nine-strata geoelectric model parameters.
| rho1 | rho2 | rho3 | rho4 | rho5 | rho6 | rho7 | rho8 | rho9 |
---|
Synthetic | 50 | 300 | 100 | 500 | 200 | 100 | 300 | 50 | 200 |
GCN + LSTM | 49.51 | 294.54 | 101.09 | 520.51 | 208.18 | 100.92 | 294.98 | 51.77 | 198.85 |
GCN | 54.36 | 319.12 | 104.57 | 467.58 | 194.41 | 93.78 | 270.07 | 48.16 | 207.98 |
LSTM | 49.32 | 311.66 | 95.14 | 450.98 | 201.29 | 95.59 | 326.77 | 54.06 | 195.71 |
MLP | 51.42 | 341.59 | 90.57 | 453.96 | 190.50 | 112.99 | 290.16 | 46.60 | 179.12 |
| h1 | h2 | h3 | h4 | h5 | h6 | h7 | h8 | - |
Synthetic | 200 | 250 | 300 | 500 | 300 | 100 | 200 | 300 | - |
GCN + LSTM | 208.09 | 238.33 | 300.97 | 510.82 | 290.38 | 98.37 | 193.75 | 294.66 | - |
GCN | 205.01 | 252.15 | 296.34 | 478.74 | 300.10 | 105.23 | 210.50 | 304.56 | - |
LSTM | 180.99 | 258.57 | 320.23 | 547.15 | 273.42 | 99.01 | 203.30 | 311.20 | - |
MLP | 193.83 | 240.60 | 266.80 | 490.26 | 263.24 | 103.44 | 170.66 | 306.59 | - |
| c1 | c2 | c3 | c4 | c5 | c6 | c7 | c8 | c9 |
Synthetic | - | 0.3 | - | 0.4 | - | 0.2 | - | 0.5 | - |
GCN + LSTM | - | 0.30 | - | 0.40 | - | 0.19 | - | 0.48 | - |
GCN | - | 0.31 | - | 0.40 | - | 0.18 | - | 0.47 | - |
LSTM | - | 0.31 | - | 0.39 | - | 0.18 | - | 0.55 | - |
MLP | - | 0.28 | - | 0.41 | - | 0.20 | - | 0.46 | - |
Table 5.
Misfit details of four network models’ predictions for the nine-strata geoelectric model parameters.
Table 5.
Misfit details of four network models’ predictions for the nine-strata geoelectric model parameters.
| Hz | Vz | rho | Thickness (h) | c |
---|
| MAPE | RMSE | MAPE | RMSE | MAPE | RMSE | MAPE | RMSE | MAPE | RMSE |
---|
GCN + LSTM | 1.13 | 1.66 | 1.78 | 3.61 | 1.56 | 1.86 | 2.12 | 2.33 | 0.89 | 1.41 |
GCN | 9.40 | 11.04 | 10.40 | 14.50 | 4.53 | 5.17 | 6.53 | 7.19 | 2.35 | 3.81 |
LSTM | 11.91 | 12.99 | 17.04 | 22.51 | 6.31 | 6.76 | 2.00 | 2.67 | 3.20 | 5.14 |
MLP | 10.93 | 11.79 | 24.69 | 42.50 | 8.79 | 10.05 | 5.13 | 5.72 | 3.12 | 5.52 |
Table 6.
Inversion accuracy with noise data.
Table 6.
Inversion accuracy with noise data.
HKH-Type Model | RMSE (%) | MAE (%) | Re-MAE |
---|
no noise | 14.07 | 4.04 | 4.04 |
5% noise | 20.31 | 9.91 | 4.91 |
10% noise | 31.59 | 17.68 | 7.68 |