Machine Learning Aided Concentration Prediction of Organic Compounds in the Sea Surface Microlayer by Vibrational Spectroscopic MethodsThe Need: The chemical composition of the sea surface microlayer (SSML) plays a crucial role in various environmental processes, impacting atmospheric chemistry and oceanic dynamics. However, traditional analytical methods struggle to efficiently characterize the complex and variable composition of the SSML. There is a growing demand for a technology that can accurately predict concentrations of organic compounds in the SSML to enhance our understanding of its role in environmental systems and improve predictive modeling for climate and meteorological studies. The Technology: Our cutting-edge technology utilizes machine learning aided concentration prediction of organic compounds in the sea surface microlayer (SSML) through vibrational spectroscopic methods. By employing simple vibrational spectroscopic techniques, we analyze the intricate chemical composition of the SSML. The vibrational spectroscopy data is then utilized to train regression-based models, leveraging multiple machine learning architectures such as support vector machines and linear regression. This methodology enables rapid and accurate quantification of saccharide concentrations in both laboratory-made solutions and field samples, facilitating comprehensive insights into SSML dynamics. Commercial Applications:
Benefits/Advantages:
|
Tech IDT2023-297 CollegeLicensing ManagerWillson, Christopher InventorsCategories |