| 000 | 00000nam 2200000zi 4500 |
| 001 | 9.910026 |
|---|
| 003 | CaOODSP |
|---|
| 005 | 20251031142448 |
|---|
| 006 | m o d f |
|---|
| 007 | cr mn||||||||| |
|---|
| 008 | 220407t20222022onca ob f000 0 eng d |
|---|
| 040 | |aCaOODSP|beng|erda|cCaOODSP |
|---|
| 043 | |an-cn--- |
|---|
| 086 | 1 |aM183-2/8877E-PDF |
|---|
| 100 | 1 |aPatwa, B., |eauthor. |
|---|
| 245 | 10|aPredictive models for first arrivals on seismic reflection data, Manitoba, New Brunswick, and Ontario / |cB. Patwa, P.L. St-Charles, G. Bellefleur, and B. Rousseau. |
|---|
| 264 | 1|a[Ottawa] : |bGeological Survey of Canada, |c2022. |
|---|
| 264 | 4|c©2022 |
|---|
| 300 | |a1 online resource (41 pages) : |billustrations (chiefly colour). |
|---|
| 336 | |atext|btxt|2rdacontent |
|---|
| 337 | |acomputer|bc|2rdamedia |
|---|
| 338 | |aonline resource|bcr|2rdacarrier |
|---|
| 490 | 1 |aOpen file ; |v8877 |
|---|
| 504 | |aIncludes bibliographical references (pages 40-41). |
|---|
| 520 | 3 |a"First arrivals are the primary waves picked and analyzed by seismologists to infer properties of the subsurface. Here we try to solve a problem in a small subsection of the seismic processing workflow: first break picking of seismic reflection data. We formulate this problem as an image segmentation task. Data is preprocessed, cleaned from outliers and extrapolated to make the training of deep learning models feasible. We use Fully Convolutional Networks (specifically UNets) to train initial models and explore their performance with losses, layer depths, and the number of classes. We propose to use residual connections to improve each UNet block and residual paths to solve the semantic gap between UNet encoder and decoder which improves the performance of the model. Adding spatial information as an extra channel helped increase the RMSE performance of the first break predictions. Other techniques like data augmentation, multitask loss, and normalization methods, were further explored to evaluate model improvement"--Abstract, page 1. |
|---|
| 650 | 0|aSeismic reflection method|xData processing. |
|---|
| 650 | 0|aDeep learning (Machine learning) |
|---|
| 650 | 6|aMéthode sismique-réflexion|xInformatique. |
|---|
| 650 | 6|aApprentissage profonde. |
|---|
| 710 | 2 |aGeological Survey of Canada, |eissuing body. |
|---|
| 830 | #0|aOpen file (Geological Survey of Canada)|v8877.|w(CaOODSP)9.506878 |
|---|
| 856 | 40|qPDF|s9.08 MB|uhttps://publications.gc.ca/collections/collection_2022/rncan-nrcan/m183-2/M183-2-8877-eng.pdf |
|---|
| 856 | 4 |qHTML|sN/A|uhttps://doi.org/10.4095/329758 |
|---|