Table 2 Prediction of mobility parameters in the case of the physical vapor deposition problem.

From: Inferring topological transitions in pattern-forming processes with self-supervised learning

View full size image

    

Deposition Rate

Average Bulk Mobility

Instance Index

Deposition log(vN)

Deposition Angle

Avg. Surface Mobility

Predicted Deposition

Target Deposition

Sensitivity Score (Si)

Predicted Mobility

Target Mobility

Sensitivity Score (Si)

18444

−4.049

59.776

38.060

0.204

0.118

11.665

4.853

5.852

1.001

6316

−4.014

45.214

32.311

0.214

0.190

41.314

5.430

7.467

0.491

15812

−3.006

61.088

15.890

0.316

0.264

19.311

4.087

4.680

1.686

7304

−2.993

62.599

6.886

0.286

0.173

8.865

4.794

3.070

0.580

1492

−2.026

47.498

19.885

0.773

0.967

5.150

3.514

5.406

0.529

444

−1.990

78.487

18.747

0.581

0.737

6.406

3.857

5.282

0.702

1752

−1.032

82.301

19.825

0.748

0.797

20.576

1.965

2.215

4.011

3772

−0.993

79.439

12.418

0.838

0.980

7.018

2.460

2.601

7.063

  1. An example of instances with high and low sensitivity scores. Instances 1844 and 6316 belong to regime A as identified in Fig. 5c. Instances 15812 and 7304 belong to regime B as identified in Fig. 5c. Instances 1492 and 444 belong to regime C as identified in Fig. 5c. Instances 1752 and 3772 belong to regime D as identified in Fig. 5c. Each regime is separated by horizontal lines.
Back to article page