MARINESITU INC — Department of Energy SBIR Phase II: C52-18b

Description

Environmental monitoring of marine energy converters (MECs) often requires continuous optical and acoustical monitoring to detect and classify interactions with marine animals. There is no currently available integrated instrumentation system on the market however that offers real time autonomous data processing capabilities. There is a need for both lower-cost underwater camera systems and user-friendly software for automated data processing to reduce the cost burden of environmental monitoring for the marine energy industry. Phase II Objective: The proposed research effort addresses the need for lower-cost instrumentation and user-friendly environmental monitoring tools through the development and demonstration of modular optical camera systems, imaging sonar software, an instrument integration hub, and an automated cloud-based data management system. These tools are based on those of the Adaptable Monitoring Package (AMP) developed at the University of Washington (UW), which has been specifically tailored for long-term monitoring at marine energy sites. Modularization of both the system hardware and software will enable a system that is well suited for a wide range of user-specified monitoring missions, while minimizing the system cost for both hardware and data management. To achieve the desired system capabilities, in Phase I we developed and demonstrated a novel modular underwater camera system with control and automated target detection software powered by machine learning algorithms. The system cost was verified through production of a first commercial prototype to meet the target of 50% less than other commercially available equivalent systems. In Phase II we are proposing to expand these monitoring capabilities and further reduce monitoring costs to our customers by developing an instrument integration hub, implementing our automated target detection methods for imaging sonars, investigating the best practices for transferring automated data processing methods to new deployment sites, and developing automated cloud-based data management tools. Commercial Applications and Other Benefits: The field of automated image processing through machine learning is advancing at an unprecedented rate and we propose to bring these new techniques to the marine energy industry with this system. By implementing a deployable machine learning system for environmental monitoring with both optical cameras and imaging sonars data mortgages and manual review time will be drastically reduced, allowing for rapid identification of targets and events of interest. Through broad adoption of these techniques, we will be able to evaluate environmental risks and mitigate against any negative impacts. Beyond the marine energy industry this technology will be applicable across the blue economy, including for ocean observations, underwater vehicles, and fisheries management.