Improved deep learning (inception) CNN for detecting small tectonic plates of broken Anatolian, Turkey

Figures & data

Figure 1. Study area

Figure 2. Train and validation learning curves showing traces plotted for each run

A) Underfitting Model, B) fitting Model

Figure 3. Original inception module as described by (Szegedy et al., 2015)

Figure 4. The architecture of first module of local feature extraction

Figure 5. The architecture of second module of local feature extraction

Figure 6. The architecture of third module of local feature extraction

Figure 7. Multidirectional cardiant linear anomalies of new global marine gravity model obtained from CryoSat-2 and Jason-1 satellites reveals 2014

A) Horizontal, B) Vertical, C) Northeast, D) Northwest

Figure 8. Multidirectional cardiant linear anomalies of global free air surfaces anomalies DTU10, (DTU10GRA_1 min)

A) Horizontal, B) Vertical, C) Northeast, D) Northwest

Figure 9. Extracted fault lines from multidirectional cardiant linear anomalies of global free air surfaces anomalies DTU10, (DTU10GRA_1 min)

A) Horizontal, B) Vertical, C) Northeast, D) Northwest. A) Horizontal, B) Vertical, C) Northeast, D) Northwest

Figure 10. Extracted fault lines from multidirectional cardiant linear anomalies of new global marine gravity model obtained from CryoSat-2 and Jason-1 satellites reveals 2014

A) Horizontal, B) Vertical, C) Northeast, D) Northwest.

Figure 11. Constructed nanoplates boundaries

Szegedy, C., Liu., W., Jia, Y., Sermanet., P., Reed., S., Anguelov., D., Erhan, D., Vanhoucke., V., & Rabinovich, A., 2015. Going deeper with convolutions. In IEEE CVPR, Boston, MA, USA (602), 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1-9, doi: https://doi.org/10.1109/CVPR.2015.7298594.

 Google Scholar