Hugging Face's logo

GeoBrain
/
ground-roll-attenuation

PyTorch
seismic
ground-roll
denoising
unet
resunet
dncnn
attention-unet
Model card Files
xet
 Community
ZDDWLIG commited on
Commit
384d19f
·
verified ·
1 Parent(s): 6459c9c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +11 -10
README.md CHANGED
@@ -50,6 +50,7 @@ Five ground-roll intensity levels produce paired noisy / noise-label records:
50
 
51
  - **DDPM cDDPM** (`ddpm`) — Conditional DDPM (DDPM-2c) jointly modeling signal and ground-roll distributions. Modified U-Net with time embedding, self-attention bottleneck, 5 ResNet levels.
52
  - **Enhanced Atten-UNet** (`enhanced_atten_unet`) — U-Net with residual blocks + attention-gated skip connections, trained with hybrid MSE + AFM (adaptive frequency modulation) loss. Base channels: 32, depth: 4.
 
53
  - **Pix2Pix cGAN** (`pix2pix`) — Pix2Pix cGAN with 7-level U-Net generator (Conv4×4 stride 2, LeakyReLU) and 4-level PatchGAN discriminator. Trained with adversarial + L1 (λ=100) loss.
54
  - **SANet** (`sanet`) — Soft Attention Network: multi-branch parallel convs (3×3, 5×5, 7×7) + spatial soft attention + residual blocks. Base channels: 32, 8 blocks.
55
 
@@ -128,9 +129,9 @@ Mean ± std over 3 seeds on the held-out test shot (FFID=9), evaluated on 2D-fla
128
  | Attention UNet | 7.85 | 29.4786±1.3513 | 48.5979±1.3514 | 0.9974±0.0007 | 0.000577±0.000109 | 0.000014±0.000004 | 0.003745±0.000557 |
129
  | Enhanced Atten-UNet | 8.2 | 11.9244±0.4043 | 33.7566±0.4043 | 0.9288±0.0024 | 0.008774±0.000263 | 0.000422±0.000039 | 0.020535±0.000949 |
130
  | SANet | 0.23 | 21.4884±0.3003 | 40.6078±0.3002 | 0.9886±0.0009 | 0.003088±0.000175 | 0.000087±0.000006 | 0.009328±0.000324 |
131
- | Physics CNN | 7.27 | 22.3319±0.5078 | 36.2584±0.5077 | 0.9728±0.0028 | 0.006262±0.000573 | 0.000238±0.000027 | 0.015402±0.000889 |
132
  | Pix2Pix cGAN | 48.84 | 15.9398±0.4189 | 35.0591±0.4189 | 0.9755±0.0041 | 0.004174±0.001219 | 0.000313±0.000031 | 0.017676±0.000864 |
133
- | DDPM cDDPM | 50.61 | 15.4040±1.4496 | 29.3304±1.4496 | 0.9066±0.0416 | 0.012975±0.002109 | 0.001208±0.000366 | 0.034466±0.005503 |
134
 
135
  ### Noise Level 3.0
136
 
@@ -143,9 +144,9 @@ Mean ± std over 3 seeds on the held-out test shot (FFID=9), evaluated on 2D-fla
143
  | Attention UNet | 7.85 | 24.3939±1.2177 | 49.5338±1.2177 | 0.9964±0.0011 | 0.000630±0.000141 | 0.000011±0.000003 | 0.003358±0.000453 |
144
  | Enhanced Atten-UNet | 8.2 | 18.5837±0.9329 | 36.8940±0.9330 | 0.9580±0.0027 | 0.006279±0.000549 | 0.000208±0.000045 | 0.014354±0.001559 |
145
  | SANet | 0.23 | 17.1129±0.2490 | 42.2528±0.2490 | 0.9876±0.0006 | 0.002294±0.000126 | 0.000060±0.000003 | 0.007717±0.000222 |
146
- | Physics CNN | 7.27 | 21.2933±0.2677 | 36.0215±0.2677 | 0.9613±0.0015 | 0.007664±0.000260 | 0.000250±0.000016 | 0.015815±0.000491 |
147
  | Pix2Pix cGAN | 48.84 | 8.9322±0.3070 | 34.0721±0.3071 | 0.9725±0.0015 | 0.003538±0.000607 | 0.000392±0.000028 | 0.019796±0.000702 |
148
- | DDPM cDDPM | 50.61 | 14.6481±1.7167 | 29.3762±1.7167 | 0.9154±0.0353 | 0.012519±0.001434 | 0.001211±0.000418 | 0.034405±0.006392 |
149
 
150
  ### Noise Level 5.0
151
 
@@ -158,9 +159,9 @@ Mean ± std over 3 seeds on the held-out test shot (FFID=9), evaluated on 2D-fla
158
  | Attention UNet | 7.85 | 21.9546±1.0678 | 50.6163±1.0678 | 0.9965±0.0011 | 0.000618±0.000068 | 0.000009±0.000002 | 0.002961±0.000359 |
159
  | Enhanced Atten-UNet | 8.2 | 21.4265±0.8323 | 38.8217±0.8323 | 0.9708±0.0019 | 0.004890±0.000354 | 0.000133±0.000024 | 0.011488±0.001072 |
160
  | SANet | 0.23 | 14.2619±0.1390 | 42.9236±0.1390 | 0.9875±0.0004 | 0.001949±0.000145 | 0.000051±0.000002 | 0.007142±0.000115 |
161
- | Physics CNN | 7.27 | 21.8948±0.1265 | 36.8837±0.1264 | 0.9690±0.0001 | 0.006944±0.000087 | 0.000205±0.000006 | 0.014317±0.000209 |
162
  | Pix2Pix cGAN | 48.84 | 5.6983±0.6128 | 34.3600±0.6128 | 0.9688±0.0031 | 0.004315±0.001284 | 0.000369±0.000053 | 0.019175±0.001360 |
163
- | DDPM cDDPM | 50.61 | 14.4170±1.4478 | 29.4060±1.4478 | 0.9140±0.0382 | 0.012570±0.001544 | 0.001187±0.000353 | 0.034165±0.005404 |
164
 
165
  ### Noise Level 7.0
166
 
@@ -173,9 +174,9 @@ Mean ± std over 3 seeds on the held-out test shot (FFID=9), evaluated on 2D-fla
173
  | Attention UNet | 7.85 | 17.9454±2.7925 | 49.1059±2.7925 | 0.9947±0.0031 | 0.000686±0.000241 | 0.000014±0.000008 | 0.003623±0.001098 |
174
  | Enhanced Atten-UNet | 8.2 | 23.4293±1.1926 | 40.4008±1.1926 | 0.9785±0.0012 | 0.003988±0.000376 | 0.000093±0.000023 | 0.009608±0.001265 |
175
  | SANet | 0.23 | 12.0953±0.1912 | 43.2559±0.1912 | 0.9877±0.0008 | 0.001822±0.000184 | 0.000047±0.000002 | 0.006875±0.000151 |
176
- | Physics CNN | 7.27 | 22.2912±0.4163 | 37.4043±0.4163 | 0.9701±0.0034 | 0.006623±0.000452 | 0.000182±0.000018 | 0.013494±0.000653 |
177
  | Pix2Pix cGAN | 48.84 | 3.4396±0.3167 | 34.6001±0.3168 | 0.9692±0.0026 | 0.003104±0.000211 | 0.000347±0.000025 | 0.018629±0.000672 |
178
- | DDPM cDDPM | 50.61 | 14.3006±1.6218 | 29.4137±1.6218 | 0.9035±0.0324 | 0.012902±0.001538 | 0.001195±0.000397 | 0.034213±0.006054 |
179
 
180
  ### Noise Level 9.0
181
 
@@ -188,9 +189,9 @@ Mean ± std over 3 seeds on the held-out test shot (FFID=9), evaluated on 2D-fla
188
  | Attention UNet | 7.85 | 15.7861±2.7603 | 48.8849±2.7604 | 0.9940±0.0033 | 0.000822±0.000303 | 0.000015±0.000008 | 0.003715±0.001128 |
189
  | Enhanced Atten-UNet | 8.2 | 24.8580±1.5442 | 41.5847±1.5442 | 0.9820±0.0028 | 0.003487±0.000463 | 0.000072±0.000023 | 0.008417±0.001415 |
190
  | SANet | 0.23 | 10.5793±0.1366 | 43.6780±0.1367 | 0.9884±0.0006 | 0.001715±0.000084 | 0.000043±0.000001 | 0.006548±0.000104 |
191
- | Physics CNN | 7.27 | 23.0216±0.3917 | 38.2117±0.3917 | 0.9726±0.0024 | 0.006038±0.000219 | 0.000151±0.000013 | 0.012295±0.000550 |
192
  | Pix2Pix cGAN | 48.84 | 0.0373±2.6620 | 33.1360±2.6620 | 0.9660±0.0036 | 0.004698±0.000950 | 0.000555±0.000367 | 0.022771±0.007399 |
193
- | DDPM cDDPM | 50.61 | 14.2884±1.1511 | 29.4785±1.1511 | 0.9251±0.0252 | 0.012315±0.001360 | 0.001153±0.000280 | 0.033771±0.004296 |
194
 
195
 
196
  ## References
 
50
 
51
  - **DDPM cDDPM** (`ddpm`) — Conditional DDPM (DDPM-2c) jointly modeling signal and ground-roll distributions. Modified U-Net with time embedding, self-attention bottleneck, 5 ResNet levels.
52
  - **Enhanced Atten-UNet** (`enhanced_atten_unet`) — U-Net with residual blocks + attention-gated skip connections, trained with hybrid MSE + AFM (adaptive frequency modulation) loss. Base channels: 32, depth: 4.
53
+ - **physics** (`physics`) —
54
  - **Pix2Pix cGAN** (`pix2pix`) — Pix2Pix cGAN with 7-level U-Net generator (Conv4×4 stride 2, LeakyReLU) and 4-level PatchGAN discriminator. Trained with adversarial + L1 (λ=100) loss.
55
  - **SANet** (`sanet`) — Soft Attention Network: multi-branch parallel convs (3×3, 5×5, 7×7) + spatial soft attention + residual blocks. Base channels: 32, 8 blocks.
56
 
 
129
  | Attention UNet | 7.85 | 29.4786±1.3513 | 48.5979±1.3514 | 0.9974±0.0007 | 0.000577±0.000109 | 0.000014±0.000004 | 0.003745±0.000557 |
130
  | Enhanced Atten-UNet | 8.2 | 11.9244±0.4043 | 33.7566±0.4043 | 0.9288±0.0024 | 0.008774±0.000263 | 0.000422±0.000039 | 0.020535±0.000949 |
131
  | SANet | 0.23 | 21.4884±0.3003 | 40.6078±0.3002 | 0.9886±0.0009 | 0.003088±0.000175 | 0.000087±0.000006 | 0.009328±0.000324 |
132
+ | Physics CNN | 7.27 | 18.4921±0.2762 | 37.6115±0.2762 | 0.9761±0.0019 | 0.004793±0.000336 | 0.000174±0.000011 | 0.013170±0.000419 |
133
  | Pix2Pix cGAN | 48.84 | 15.9398±0.4189 | 35.0591±0.4189 | 0.9755±0.0041 | 0.004174±0.001219 | 0.000313±0.000031 | 0.017676±0.000864 |
134
+ | DDPM cDDPM | 50.61 | 15.2259±0.8568 | 34.3452±0.8568 | 0.9522±0.0151 | 0.008696±0.000650 | 0.000372±0.000070 | 0.019237±0.001856 |
135
 
136
  ### Noise Level 3.0
137
 
 
144
  | Attention UNet | 7.85 | 24.3939±1.2177 | 49.5338±1.2177 | 0.9964±0.0011 | 0.000630±0.000141 | 0.000011±0.000003 | 0.003358±0.000453 |
145
  | Enhanced Atten-UNet | 8.2 | 18.5837±0.9329 | 36.8940±0.9330 | 0.9580±0.0027 | 0.006279±0.000549 | 0.000208±0.000045 | 0.014354±0.001559 |
146
  | SANet | 0.23 | 17.1129±0.2490 | 42.2528±0.2490 | 0.9876±0.0006 | 0.002294±0.000126 | 0.000060±0.000003 | 0.007717±0.000222 |
147
+ | Physics CNN | 7.27 | 13.6227±0.1192 | 38.7626±0.1192 | 0.9659±0.0015 | 0.005110±0.000210 | 0.000133±0.000004 | 0.011532±0.000159 |
148
  | Pix2Pix cGAN | 48.84 | 8.9322±0.3070 | 34.0721±0.3071 | 0.9725±0.0015 | 0.003538±0.000607 | 0.000392±0.000028 | 0.019796±0.000702 |
149
+ | DDPM cDDPM | 50.61 | 9.5060±0.8835 | 34.6459±0.8835 | 0.9523±0.0126 | 0.008285±0.000596 | 0.000348±0.000066 | 0.018585±0.001832 |
150
 
151
  ### Noise Level 5.0
152
 
 
159
  | Attention UNet | 7.85 | 21.9546±1.0678 | 50.6163±1.0678 | 0.9965±0.0011 | 0.000618±0.000068 | 0.000009±0.000002 | 0.002961±0.000359 |
160
  | Enhanced Atten-UNet | 8.2 | 21.4265±0.8323 | 38.8217±0.8323 | 0.9708±0.0019 | 0.004890±0.000354 | 0.000133±0.000024 | 0.011488±0.001072 |
161
  | SANet | 0.23 | 14.2619±0.1390 | 42.9236±0.1390 | 0.9875±0.0004 | 0.001949±0.000145 | 0.000051±0.000002 | 0.007142±0.000115 |
162
+ | Physics CNN | 7.27 | 12.1360±0.1360 | 40.7978±0.1359 | 0.9730±0.0003 | 0.004344±0.000106 | 0.000083±0.000003 | 0.009123±0.000143 |
163
  | Pix2Pix cGAN | 48.84 | 5.6983±0.6128 | 34.3600±0.6128 | 0.9688±0.0031 | 0.004315±0.001284 | 0.000369±0.000053 | 0.019175±0.001360 |
164
+ | DDPM cDDPM | 50.61 | 6.3973±0.8802 | 35.0590±0.8802 | 0.9515±0.0151 | 0.008145±0.000723 | 0.000316±0.000061 | 0.017722±0.001756 |
165
 
166
  ### Noise Level 7.0
167
 
 
174
  | Attention UNet | 7.85 | 17.9454±2.7925 | 49.1059±2.7925 | 0.9947±0.0031 | 0.000686±0.000241 | 0.000014±0.000008 | 0.003623±0.001098 |
175
  | Enhanced Atten-UNet | 8.2 | 23.4293±1.1926 | 40.4008±1.1926 | 0.9785±0.0012 | 0.003988±0.000376 | 0.000093±0.000023 | 0.009608±0.001265 |
176
  | SANet | 0.23 | 12.0953±0.1912 | 43.2559±0.1912 | 0.9877±0.0008 | 0.001822±0.000184 | 0.000047±0.000002 | 0.006875±0.000151 |
177
+ | Physics CNN | 7.27 | 10.3815±0.6121 | 41.5420±0.6121 | 0.9747±0.0034 | 0.003940±0.000423 | 0.000071±0.000010 | 0.008387±0.000593 |
178
  | Pix2Pix cGAN | 48.84 | 3.4396±0.3167 | 34.6001±0.3168 | 0.9692±0.0026 | 0.003104±0.000211 | 0.000347±0.000025 | 0.018629±0.000672 |
179
+ | DDPM cDDPM | 50.61 | 4.1267±1.0183 | 35.2872±1.0183 | 0.9531±0.0084 | 0.007908±0.000441 | 0.000301±0.000066 | 0.017282±0.001957 |
180
 
181
  ### Noise Level 9.0
182
 
 
189
  | Attention UNet | 7.85 | 15.7861±2.7603 | 48.8849±2.7604 | 0.9940±0.0033 | 0.000822±0.000303 | 0.000015±0.000008 | 0.003715±0.001128 |
190
  | Enhanced Atten-UNet | 8.2 | 24.8580±1.5442 | 41.5847±1.5442 | 0.9820±0.0028 | 0.003487±0.000463 | 0.000072±0.000023 | 0.008417±0.001415 |
191
  | SANet | 0.23 | 10.5793±0.1366 | 43.6780±0.1367 | 0.9884±0.0006 | 0.001715±0.000084 | 0.000043±0.000001 | 0.006548±0.000104 |
192
+ | Physics CNN | 7.27 | 9.1850±0.2127 | 42.2838±0.2126 | 0.9783±0.0032 | 0.003351±0.000221 | 0.000059±0.000003 | 0.007690±0.000187 |
193
  | Pix2Pix cGAN | 48.84 | 0.0373±2.6620 | 33.1360±2.6620 | 0.9660±0.0036 | 0.004698±0.000950 | 0.000555±0.000367 | 0.022771±0.007399 |
194
+ | DDPM cDDPM | 50.61 | 2.4782±0.8597 | 35.5770±0.8597 | 0.9582±0.0070 | 0.007742±0.000481 | 0.000281±0.000055 | 0.016694±0.001645 |
195
 
196
 
197
  ## References