Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for automated underwater camera system control for aquaculture systems. An underwater camera system includes (i) a line on which the underwater camera system is mounted, the line detachably affixed to a feeder that provides feed for aquatic livestock, (ii) a sensor manager, (iii) one or more sensors that are managed by the sensor manager, (iv) a line navigation controller, and (v) a first actuator for controlling a distance between the feeder and the underwater camera system. The one or more sensors obtain sensor data and the line navigation controller of the underwater camera system determines a distance to position the underwater camera system beneath the feeder to obtain additional sensor data. The line navigation controller transmits a first message to the first actuator to position the underwater camera system at the determined distance beneath the feeder.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for estimating wave properties of a body of water. A computer-implemented system obtains measurement data for a duration of time from an inertial measurement unit (IMU) onboard an underwater device, generates model input data based on at least the measurement data obtained at the plurality of time points, and processes the model input data to generate model output data indicating one or more wave properties using a machine-learning model. The system further determines, based on at least the one or more wave properties, whether the device is safe to be deployed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for estimating wave properties of a body of water. A computer-implemented system obtains measurement data for a duration of time from an inertial measurement unit (IMU) onboard an underwater device, generates model input data based on at least the measurement data obtained at the plurality of time points, and processes the model input data to generate model output data indicating one or more wave properties using a machine-learning model. The system further determines, based on at least the one or more wave properties, whether the device is safe to be deployed.