Update README.MD

README.MD

@@ -4,7 +4,7 @@
 
 ## Project Description
 
-In this study, we assess how satellite-observable variables can be used to infer abyssal Meridional Overturning Circulation (MOC) strength using machine learning. We replicate and improve upon previous methods, and provide a thorough baseline for predicting the abyssal MOC strength using regularised linear regression. We incorporate ACCESS, a high-resolution ocean circulation model, and observational RAPID data, an array of sensors that directly measures the Atlantic MOC strength; we are the first to use these to both evaluate and improve predictive models performance in the Southern Ocean. Finally, we provide initial evidence of an approximately linear relationship between satellite-observable variables and abyssal MOC strength, demonstrate the utility of observational data to predict long-range oceanic dependencies, and show that a deep learning model is able to capture latitude-invariant circulation dynamics.
+In this study, we assess how satellite-observable variables can be used to infer abyssal Meridional Overturning Circulation (MOC) strength using machine learning by leveraging the Estimating the Circulation and Climate of the Ocean (ECCO) ocean state estimate. We replicate and improve upon previous methods, and provide a thorough baseline for predicting the abyssal MOC strength using regularised linear regression. We incorporate the Australian Community Climate and Earth System Simulator Ocean Model (ACCESS) a high-resolution numerical ocean circulation model, and observational Rapid Climate Change-Meridional Overturning Circulation and Heatflux Array (RAPID) data, a cross-basin sensor array that directly measures the Atlantic MOC strength. We provide initial evidence of an approximately linear relationship between satellite-observable variables and abyssal MOC strength through model evaluation on both ECCO and ACCESS, demonstrate the utility of observational data to predict long-range oceanic dependencies through integration of RAPID, and show that a deep learning model is able to accurately capture latitude-invariant circulation dynamics across the Southern Ocean in ECCO.
 
 This work was carried out as part of the [Artificial Intelligence for Environmental Risks](https://ai4er-cdt.esc.cam.ac.uk/) (AI4ER) Centre for Doctoral Training Guided Team Challenge (GTC), which ran from November, 2023 to March, 2024.