论文标题
深度学习未解决的镜头灯曲面
Deep Learning Unresolved Lensed Lightcurves
论文作者
论文摘要
重力镜头的源可能没有解决或混合多个图像，并且在时间变化的来源中，来自各个图像的光曲线可能会重叠。我们使用卷积神经网既将光曲线分类为由于释放，双重或四边形的镜头来源，并且适合时间延迟。随着时间的推移，专注于镜头超新星系统延迟$ΔT\ gtrsim6 $天，我们在识别图像的数量时达到了100 \％的精度，然后将时间延迟估计为$σ_{Δt} \ Day，大约是$ 1000 \ times $速度$ $ \ times $速度相对于我们以前的Monte Carlo Carlo Carlo Carlo技术。对于通量噪声级别$ \ sim10 \％$，这也成功了。对于$ΔT\，在[2,6] $天中，我们获得94--98 \％精度，具体取决于图像配置。我们还使用部分光曲面探索，其中观测仅在最大光线接近最大光线，而无需上升时间数据并量化成功。
Gravitationally lensed sources may have unresolved or blended multiple images, and for time varying sources the lightcurves from individual images can overlap. We use convolutional neural nets to both classify the lightcurves as due to unlensed, double, or quad lensed sources and fit for the time delays. Focusing on lensed supernova systems with time delays $Δt\gtrsim6$ days, we achieve 100\% precision and recall in identifying the number of images and then estimating the time delays to $σ_{Δt}\approx1$ day, with a $1000\times$ speedup relative to our previous Monte Carlo technique. This also succeeds for flux noise levels $\sim10\%$. For $Δt\in[2,6]$ days we obtain 94--98\% accuracy, depending on image configuration. We also explore using partial lightcurves where observations only start near maximum light, without the rise time data, and quantify the success.
