Adult American eels (Anguilla rostrata) are vulnerable to hydropower turbine mortality during outmigration from growth habitat in inland waters to the ocean where they spawn. Imaging sonar is a reliable and proven technology for monitoring of fish passage and migration; however, there is no efficient automated method for eel detection. We designed a deep learning model for automated detection of adult American eels from sonar data. The method employs convolution neural network (CNN) to distinguish between 14 images of eels and non-eel objects. Prior to image classification with CNN, background subtraction and wavelet denoising were applied to enhance sonar images. The CNN model was first trained and tested on data obtained from a laboratory experiment, which yielded overall accuracies of >98% for image-based classification. Then, the model was trained and tested on field data that were obtained near the Iroquois Dam located on the St. Lawrence River; the accuracy achieved was commensurate with that of human experts.

An automatic system that utilizes data analytics and machine learning to identify adult American eel in data obtained by imaging sonars is created in this study. Wavelet transform has been applied to de-noise the ARIS sonar data and a convolutional neural network model has been built to classify eels and non-eel objects. Because of the unbalanced amounts of data in laboratory and field experiments, a transfer learning strategy is implemented to fine-tune the convolutional neural network model so that it performs well for both the laboratory and field data. The proposed system can provide important information to develop mitigation strategies for safe passage of out-migrating eels at hydroelectric facilities.

Exploiting the sensory physiology of migratory fishes to guide them away from hazards like hydroelectric turbines is of interest to regulatory agencies and hydropower operators to achieve conservation and management goals. Here we describe a river‐scale experiment where out‐migrating adult American eel ( Anguilla rostrata ) were tracked downstream via acoustic telemetry as they encountered a 216 m long floating LED light array on the St. Lawrence River. Eel ( N = 51) spatial responses to light were compared to eels detected on control (no light) nights with the expectation that light would cause eels to deflect laterally along the light array toward the river‐right shore. Eels generally swam near the surface at night, and 39.5% of eels that encountered the light altered their downstream trajectories consistent with lateral deflection, although those responses were relatively modest. However, 76.7% of eels demonstrated diving responses of ≥ 4 m, consistent with seeking darker passage under the light field. Although we observed some degree of light avoidance, additional research is needed to optimize use of light for effective behavioral guidance in large rivers.