For several fish species, age and other important biological information is manually inferred from visual scrutinization of scales, and reliable automatic methods are not widely available. Here, we apply Convolutional Neural Networks (CNN) with transfer learning on a novel dataset of 9056 images of Atlantic salmon scales for four different prediction tasks. We predicted fish origin (wild/farmed), spawning history (previous spawner/non-spawner), river age, and sea age. We obtained high prediction accuracy for fish origin (96.70%), spawning history (96.40%), and sea age (86.99%), but lower accuracy for river age (63.20%). Against six human expert readers with an additional dataset of 150 scales, the CNN showed the second-highest percentage agreement for sea age (94.00%, range 87.25±97.30%), but the lowest agreement for river age (66.00%, range 66.00– 84.68%). Estimates of river age by expert readers exhibited higher variance and lower levels of agreement compared to sea age and may indicate why this task is also more difficult for the CNN. Automatic interpretation of scales may provide a cost- and time-efficient method of predicting fish age and life-history traits.

对于几种鱼类，年龄和其他重要的生物学信息是通过对鳞片的目视检查手动推断出来的，可靠的自动方法尚不广泛。在这里，我们将卷积神经网络（CNN）与转移学习一起应用到9056张大西洋鲑鱼鳞片的新颖数据集上，以完成四种不同的预测任务。我们预测了鱼类的起源（野生/养殖），产卵历史（先前的产卵者/非产卵者），河流年龄和海洋年龄。我们对鱼类起源（96.70％），产卵史（96.40％）和海年龄（86.99％）的预测准确性较高，但对河龄（63.20％）的准确性较低。在六名人类专家读者以及150个规模的额外数据集中下，CNN显示的海年龄百分比一致性最高（94.00％，范围87.25±97.30％），但河年龄百分比一致性最低（66.00％，范围66）。00– 84.68％）。与海洋年龄相比，专家读者对河流年龄的估计显示出较高的方差和较低的一致性，并且可能表明为什么这项任务对于CNN来说也更加困难。秤的自动解释可以提供一种经济高效的方法来预测鱼类的年龄和生活史特征。