Introduction

Estimated time: 12 minutes

The hackathon invites participants to explore how digital data sources can be combined to address research questions related to global challenges and cultural heritage. The hackathon is designed as a series of activities collaboratively exploring data and computing across Digital Research Infrastructure (DRI) to pilot innovative research directions.

The integration of data from heterogeneous sources is explored through a series of use cases or scenarios, which touch on different infrastructures, tools, disciplinary perspectives and skills. While the hackathon proposes a set of scenarios, participants are encouraged to think expansively. While doing so, participants are invited to reflect on the strengths and needs of these data services, the availability of tools, and the knowledge barriers to developing research approaches based on these infrastructures. The role of Artificial Intelligence models in supporting coding and agentic processes in software development is of further interest.

During the hackathon, participants gain practical knowledge and insights into data services, community-generated code, and innovative AI-assisted methods.

To design a scenario, we will go through the following steps:

Step 1: Familiarisation with the scenarios

Read the summary of each scenario, as it sets out a proposed context and general theme to be investigated, and begin shaping your research questions.

Step 2: Find data

Explore the proposed datasets and others in the DRI services to identify suitable datasets, sub-datasets and associated metadata that can potentially help address your research question/s.

Step 3: Create a dataset: Merging, cleaning and storing

Explore how can the data be combined data including using languages such as Python, AI models and visualisation tools, to support decision-making and interpretation.

Step 4: Update the github repo

Using the findings, update the repositoy for this resource to record and communicate to other the progress for this scenario.

Discussion

Challenge: Use the following guiding questions during the day:

• What research questions have you identified?
• Why are they important in the context of your chosen scenario?
• Which data need to be linked to address your research question/s?
• What are the main challenges faced when working with these infrastructures?
• How could the developed or envisaged workflows, and the addressing of research question/s, benefit the economy, society, or support the SDGs?