Utilization of convolutional neural networks for H I source finding - Team FORSKA-Sweden approach to SKA Data Challenge 2

Open Access

Table 2

Parameters of the source characterization step and their respective range used for sampling parameter values.

		Value

Parameter	Type	Min	Max
Mask threshold	Float	0	1
Min. line flux integral	Float	0	50
Min. merge radius	Integer	1	5
Max. merge radius	Integer	1	100
Min. spatial size	Integer	1	5
Max. spatial size	Integer	5	30
Min freq. size	Integer	1	50
Max freq. size	Integer	50	400
Min. number of voxels	Integer	1	300
Max spatial mask dilation	Integer	1	5
Max freq. mask dilation	Integer	1	20

Notes. The results were based on the mask, as obtained with a value of the mask threshold parameter, together with the predicted catalog created from that mask and the values of the remaining parameters of this table.

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.