Earth Observation (EO) data is voluminous and messy. It does not adhere to a standard and is growing at a staggering pace. The increase in raw data exacerbates an age-old problem for those that look to use EO data to drive business decisions. Some industries, such as insurance and re-insurance, are heavily invested in the science of converting these disparate data streams into actionable business intelligence. Their investment is large, and their processes are proprietary. The cost of expertise and computing resources to take on this work is high, and it creates a significant barrier to entry for other entities or industries looking to benefit from earth observation data. In this session, the panel will outline the challenges facing data scientists in working with multiple EO datasets, provide examples of conflicting data structures, and highlight industries that are struggling with using this data. Our speakers will then highlight new techniques that are being developed to align and normalize disparate datasets to allow more accessibility and immediate usability.