Search

In this paper we investigate how implementing machine learning could improve the efficiency of the search for Trans-Neptunian Objects (TNOs) within Dark Energy Survey (DES) data when used alongside orbit fitting. The discovery of multiple TNOs that appear to show a similarity in their orbital parameters has led to the suggestion that one or more undetected planets, an as yet undiscovered "Planet 9", may be present in the outer Solar System. DES is well placed to detect such a planet and has already been used to discover many other TNOs. Here, we perform tests on eight different supervised machine learning algorithms, using a dataset consisting of simulated TNOs buried within real DES noise data. We found that the best performing classifier was the Random Forest which, when optimised, performed well at detecting the rare objects. We achieve an area under the receiver operating characteristic (ROC) curve, (AUC) $= 0.996 \pm 0.001$. After optimizing the decision threshold of the Random Forest, we achieve a recall of 0.96 while maintaining a precision of 0.80. Finally, by using the optimized classifier to pre-select objects, we are able to run the orbit-fitting stage of our detection pipeline five times faster., Comment: Published in PASP, 16 pages, 6 figures

We present the first rest-frame UV population study of 17 heavily reddened, high-luminosity (E(B-V)$_{\rm{QSO}}\gtrsim$ 0.5; L$_{\rm{bol}}>$ 10$^{46}$ergs$^{-1}$) broad-line quasars at $1.5 < z < 2.7$. We combine the first year of deep, optical, ground-based observations from the Dark Energy Survey (DES) with the near infrared VISTA Hemisphere Survey (VHS) and UKIDSS Large Area Survey (ULAS) data, from which the reddened quasars were initially identified. We demonstrate that the significant dust reddening towards the quasar in our sample allows host galaxy emission to be detected at the rest-frame UV wavelengths probed by the DES photometry. By exploiting this reddening effect, we disentangle the quasar emission from that of the host galaxy via spectral energy distribution (SED) fitting. We find evidence for a relatively unobscured, star-forming host galaxy in at least ten quasars, with a further three quasars exhibiting emission consistent with either star formation or scattered light. From the rest-frame UV emission, we derive instantaneous, dust-corrected star formation rates (SFRs) in the range 25 < SFR$_{\rm{UV}}$ < 365 M$_{\odot}$yr$^{-1}$, with an average SFR$_{\rm{UV}}$ = 130 $\pm$ 95 M$_{\odot}$yr$^{-1}$. We find a broad correlation between SFR$_{\rm{UV}}$ and the bolometric quasar luminosity. Overall, our results show evidence for coeval star formation and black hole accretion occurring in luminous, reddened quasars at the peak epoch of galaxy formation., Comment: 21 pages, 8 figures, MNRAS Accepted