Mapping accretion and its variability in the young open cluster NGC 2264: a study based on u-band photometry

Context. The accretion process has a central role in the formation of stars and planets. Aims. We aim at characterizing the accretion properties of several hundred members of the star-forming cluster NGC 2264 (3 Myr). Methods. We performed a deep ugri mapping as well as a simultaneous u-band+ r-band monitoring of the star-forming region with CFHT/MegaCam in order to directly probe the accretion process onto the star from UV excess measurements. Photometric properties and stellar parameters are determined homogeneously for about 750 monitored young objects, spanning the mass range similar to 0.1-2 M-circle dot. About 40% of the sample are classical (accreting) T Tauri stars, based on various diagnostics (H-alpha, UV and IR excesses). The remaining non-accreting members define the (photospheric + chromospheric) reference UV emission level over which flux excess is detected and measured. Results. We revise the membership status of cluster members based on UV accretion signatures, and report a new population of 50 classical T Tauri star (CTTS) candidates. A large range of UV excess is measured for the CTTS population, varying from a few times 0.1 to similar to 3 mag. We convert these values to accretion luminosities and accretion rates, via a phenomenological description of the accretion shock emission. We thus obtain mass accretion rates ranging from a few 10(-10) to similar to 10(-7) M-circle dot/yr. Taking into account a mass-dependent detection threshold for weakly accreting objects, we find a > 6 sigma correlation between mass accretion rate and stellar mass. A power-law fit, properly accounting for censored data (upper limits), yields. M-acc proportional to M-*(1.4+/-0.3). At any given stellar mass, we find a large spread of accretion rates, extending over about 2 orders of magnitude. The monitoring of the UV excess on a timescale of a couple of weeks indicates that its variability typically amounts to 0.5 dex, i.e., much smaller than the observed spread in accretion rates. We suggest that a non-negligible age spread across the star-forming region may effectively contribute to the observed spread in accretion rates at a given mass. In addition, different accretion mechanisms (like, e. g., short-lived accretion bursts vs. more stable funnel-flow accretion) may be associated to different. M-acc regimes. Conclusions. A huge variety of accretion properties is observed for young stellar objects in the NGC 2264 cluster. While a definite correlation seems to hold between mass accretion rate and stellar mass over the mass range probed here, the origin of the large intrinsic spread observed in mass accretion rates at any given mass remains to be explored.