The MALOPH project proposes to combine relevant upper ocean physics and hurricane severity information with machine learning techniques to assess pre-hurricane conditions and establish new metrics. Transient upper ocean warming is a main contributor to the process of hurricane development. An unusually warmer ocean can potentially “fuel” the atmosphere with more energy, favoring storm development with higher intensification rates. Yet, surprisingly, little progress has been made to improve representation of oceanic conditions in hurricane intensity prediction, taking into account all that happens underneath the ocean’s surface. Traditionally, in addition to the atmospheric variables, hurricane tracking and intensity predictions primarily rely on near-surface ocean variables (heat fluxes or sea surface temperature). However, surface variables do not fully capture the large amounts of heat trapped at depths far from surface interaction that can emerge to the surface and fuel storm systems. Furthermore, predicting future ocean-atmosphere interactions requires advanced methods and modeling tools to explore complex relationships between components. We believe that improved knowledge of pre-hurricane conditions and forecasts can be achieved using a hybrid modeling approach that combines machine learning models and information from the underlying ocean physics. A better understanding of the ocean changes dominating hurricane formation will help improve hurricane prediction methods. This framework will include a relevance criterion to rank the dominant factors according to their performance predicting hurricane activity/intensity.
The main objective of the MALOPH project is to identify relationships between ocean variables and conditions in hurricane development over decisive regions using machine learning techniques. The MALOPH project also aims to propose a new metric as a “severity score” in anticipation of the development of a storm or hurricane.