Periodic Reporting for period 1 - OWL (Hyper-Spectral Laser Induced Fluorescence LiDAR to detect Submerged Oil over Water in real-time on a molecular level.)
Reporting period: 2024-07-01 to 2025-02-28
Ocean Visuals' project centers on the development and deployment of the Oil-in-Water Locator (OWL), a cutting-edge technological solution designed to address the complex challenges of monitoring and safeguarding the marine environment, including open waters and coastal areas. By utilizing advanced Hyperspectral Laser Induced Fluorescence (HLIF) LiDAR techniques, OWL can detect, classify, and quantify oil spills and chemical pollution as a film on the water surface and within the depths of the water column in dissolved, emulsified, and submerged forms. This innovation impacts response strategies and empowers real-time, accurate, and comprehensive surveillance, revolutionizing our ability to protect and manage marine ecosystems, mitigate environmental damage, and ensure the safety of coastal regions.
For decades, (satellite) radar and camera systems have been the primary early warning and detection method of oil in water. As oil is intrinsically lighter than water, the hydrocarbons will float on the surface. But recent scientific reports from some of the largest oil spills globally have revealed that as much as 30-40% submerged after a brief period. Typically, 2 to 4 hours, depending on the oil type and meteorological conditions. Meteorologic conditions at sea, like currents, play a significant role in the pattern of submerged oil spills. Ocean Visuals seeks to solve the challenges related to where oil spills occur, where they will end up, what type of oil and the area of the actual spill. This will aid energy companies and enforcement agencies in their capacities of early warning of oil spills, perform in-situ classification of oil type through AI and machine learning, pattern matching techniques. Correlation with other (meteorological) data will create better prediction models as real-time data is collected from the surface and water column.
For decades, (satellite) radar and camera systems have been the primary early warning and detection method of oil in water. As oil is intrinsically lighter than water, the hydrocarbons will float on the surface. But recent scientific reports from some of the largest oil spills globally have revealed that as much as 30-40% submerged after a brief period. Typically, 2 to 4 hours, depending on the oil type and meteorological conditions. Meteorologic conditions at sea, like currents, play a significant role in the pattern of submerged oil spills. Ocean Visuals seeks to solve the challenges related to where oil spills occur, where they will end up, what type of oil and the area of the actual spill. This will aid energy companies and enforcement agencies in their capacities of early warning of oil spills, perform in-situ classification of oil type through AI and machine learning, pattern matching techniques. Correlation with other (meteorological) data will create better prediction models as real-time data is collected from the surface and water column.
The first stage of the project targeted further technological development of three classes of OWL systems: Sea OWL for shipborne operation, Air OWL for airborne surveillance, and Elf – a lightweight system for Unmanned Airborne Vehicles (drones). The proprietary HLIF LiDAR technique of Ocean Visuals served as a base for enhancements and unifications of main principal hardware blocks.
They are the sensing laser, hyperspectral detector coupled with telescopes of various apertures defined by the sensing distance, and a smart controller providing fully unattended operational control of OWL systems accompanied by AI-based hyperspectral data analysis. The OWL hardware was optimised for a modular design, consisting of unified opto-mechanical and opto-electronics blocks used for all classes of OWL systems. This development on the unification provided hardware flexibility on a modular level, regardless of sensor type when we increase production volumes.
Another task of the first stage was related to the development of the OWL operational interface and OWL™MAP software for data analysis, visualisation, and reporting. This development based on the Web Feature Service (WFS) standard provides data integration with 3rd party mapping and visualization services such as ArcGIS, QGIS. In addition to the web-based user interface, the software started supporting common desktop and mobile platforms (Linux, MacOS, Windows, Android, iOS) natively for increased performance and user experience.
They are the sensing laser, hyperspectral detector coupled with telescopes of various apertures defined by the sensing distance, and a smart controller providing fully unattended operational control of OWL systems accompanied by AI-based hyperspectral data analysis. The OWL hardware was optimised for a modular design, consisting of unified opto-mechanical and opto-electronics blocks used for all classes of OWL systems. This development on the unification provided hardware flexibility on a modular level, regardless of sensor type when we increase production volumes.
Another task of the first stage was related to the development of the OWL operational interface and OWL™MAP software for data analysis, visualisation, and reporting. This development based on the Web Feature Service (WFS) standard provides data integration with 3rd party mapping and visualization services such as ArcGIS, QGIS. In addition to the web-based user interface, the software started supporting common desktop and mobile platforms (Linux, MacOS, Windows, Android, iOS) natively for increased performance and user experience.
The use of the reference spectral database for the identification of oil and chemical pollution identification by the pattern-matching technique is a key distinguishing feature of OWL systems. The spectral database consisting of the HLIF spectra measured in the laboratory with the oil samples was designed as an analytical part of the OWL operational software to be uploaded to the OWL system for real-time analysis of the HLIF spectral data. The development of AI-driven spectral analysis was started.