Exoplanet cartography using convolutional neural networks

Open Access

Table 4

Mean squared error (MSE) of the albedo retrievals.

N_max	Model Earth MSE	Validation MSE
∞	0.0142	0.0162
10⁵	0.0146	0.0185
10⁴	0.0157	0.0210
10³	0.0184	0.0240
10²	0.0262	0.0280
10	0.0284	0.0336

Notes. The architecture from Fig. 18 is trained on normalized light curves to produce albedo maps and then fed light curves of our model Earth and validation light curves to find these errors. Compare with Fig. 19 for visual indication of different MSE levels.

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.