The vast quantity of strong galaxy–galaxy gravitational lenses expected by future large-scale surveys necessitates the development of automated methods to efficiently model their mass profiles. For this purpose, we train an approximate Bayesian convolutional neural network (CNN) to predict mass profile parameters and associated uncertainties, and compare its accuracy to that of conventional parametric modelling for a range of increasingly complex lensing systems. These include standard smooth parametric density profiles, hydrodynamical EAGLE galaxies, and the inclusion of foreground mass structures, combined with parametric sources and sources extracted from the Hubble Ultra Deep Field. In addition, we also present a method for combining the CNN with traditional parametric density profile fitting in an automated fashion, where the CNN provides initial priors on the latter’s parameters. On average, the CNN achieved errors 19 ± 22 per cent lower than the traditional method’s blind modelling. The combination method instead achieved 27 ± 11 per cent lower errors over the blind modelling, reduced further to 37 ± 11 per cent when the priors also incorporated the CNN-predicted uncertainties, with errors also 17 ± 21 per cent lower than the CNN by itself. While the CNN is undoubtedly the fastest modelling method, the combination of the two increases the speed of conventional fitting alone by factors of 1.73 and 1.19 with and without CNN-predicted uncertainties, respectively. This, combined with greatly improved accuracy, highlights the benefits one can obtain through combining neural networks with conventional techniques in order to achieve an efficient automated modelling approach.

中文翻译：

---

强镜头建模：贝叶斯神经网络与参数轮廓拟合的比较与结合

未来大规模调查所预期的大量强星系-星系引力透镜需要开发自动化方法来有效地模拟它们的质量分布。为此，我们训练了一个近似贝叶斯卷积神经网络 (CNN) 来预测质量分布参数和相关的不确定性，并将其精度与一系列日益复杂的透镜系统的传统参数建模的精度进行比较。其中包括标准平滑参数密度剖面、流体动力学鹰星系，以及包含前景质量结构，以及从哈勃超深场提取的参数源和源。此外，我们还提出了一种以自动方式将 CNN 与传统参数密度分布拟合相结合的方法，其中 CNN 提供了后者参数的初始先验。平均而言，CNN 的误差比传统方法的盲建模低 19 ± 22%。与盲建模相比，组合方法的误差降低了 27 ± 11%，当先验还包含 CNN 预测的不确定性时，进一步降低到 37 ± 11%，误差也比 CNN 本身低 17 ± 21% . 虽然 CNN 无疑是最快的建模方法，但两者的结合将单独传统拟合的速度分别提高了 1.73 和 1.19 倍，有和没有 CNN 预测的不确定性。这与大大提高的准确性相结合，