Fixing the past to fix the future

About this presentation

It’s often said that ‘data is the new oil’, however, this doesn’t fully capture the complex nature of data utilisation in advanced analytics and artificial intelligence, particularly within scientific domains. The value of scientific data lies not just in its availability but in its relevance, provenance, and contextual meaning. Historical data, often stored in handwritten lab notebooks, PDFs, and institutional knowledge repositories, provides a rich repository of information about past successes and failures in core research areas. However, this valuable data is frequently incompatible with modern data management systems and electronic lab notebooks (ELNs). To fully capitalise on AI and develop robust analytical models and databases for research, it is imperative to convert these unstructured, archival data sources into structured, accessible formats. These comprehensive records, encapsulated within legacy archives, are crucial for creating balanced and effective AI systems. By transforming historical data, the accuracy and capabilities of new technologies can be enhanced, ensuring that the legacy of scientific knowledge informs and enriches future innovation. In this talk, we underscore the significance of historical data transformation in unlocking the potential of AI-driven research and emphasise the need for a systematic approach to integrate legacy data into contemporary scientific workflows