Free Access
Table C.1.
Overview of the RMSE of different machine learning models.
| Sample | RMSE | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Input | Model | Train | Test | 70 μm | 100 μm | 160 μm | 250 μm | 360 μm | 500 μm | Total |
| UV–MIR (14) | Neural network | Mixed | Mixed | 0.22 | 0.19 | 0.17 | 0.18 | 0.20 | 0.21 | 0.20 |
| UV–MIR (14) | Random forest | Mixed | Mixed | 0.22 | 0.19 | 0.18 | 0.20 | 0.22 | 0.24 | 0.21 |
| UV–MIR (14) | Linear regression | Mixed | Mixed | 0.23 | 0.21 | 0.21 | 0.23 | 0.25 | 0.27 | 0.23 |
| UV–MIR + redshift (15) | Neural network | Mixed | Mixed | 0.21 | 0.19 | 0.16 | 0.17 | 0.19 | 0.20 | 0.19 |
| UV–MIR, no 3.4 μm (13) | Neural network | H-ATLAS | DustPedia | 0.30 | 0.33 | 0.41 | 0.47 | 0.50 | 0.53 | 0.43 |
| UV–MIR (14) | Neural network | DustPedia | H-ATLAS | 0.26 | 0.25 | 0.30 | 0.38 | 0.43 | 0.47 | 0.36 |
| UV–MIR (14) | Neural network | DustPedia | DustPedia | 0.29 | 0.27 | 0.27 | 0.28 | 0.29 | 0.30 | 0.28 |
| UV–MIR (14) | Neural network | H-ATLAS | H-ATLAS | 0.20 | 0.17 | 0.13 | 0.14 | 0.16 | 0.18 | 0.16 |
| SDSS–MIR (12) | Neural network | Mixed | Mixed | 0.23 | 0.20 | 0.17 | 0.19 | 0.21 | 0.22 | 0.20 |
| 2MASS–MIR (7) | Neural network | Mixed | Mixed | 0.25 | 0.22 | 0.20 | 0.23 | 0.25 | 0.27 | 0.24 |
Notes. All test sets are independent of the training sets. When the same sample is listed for the train and test set, 4 separate models are trained in a 4-fold train-test split (see Sect. 2.3).
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.