Connecting environmental data for clearer analysis

Environmental information was dispersed across structured datasets, spreadsheets, field notes, technical reports and PDF documents. This made it difficult for the project team to locate relevant evidence and compare observations across the site.

Inconsistent identifiers created another challenge. Reported results could not always be traced easily to their original records, adding time and complexity to technical review. The information covered soil and groundwater conditions, along with air data, and needed to be organized in a consistent structure without losing its connection to the source material.

Our initial assignment focused on assessing options for digitizing and retrieving these records. Near-term reporting needs soon called for a working data foundation that could make the information easier to access and use.

Our team developed a common data model and dedicated database for the site’s environmental information. We extracted and loaded structured records, then expanded the process to capture tabular information embedded in historical PDF reports.

Microsoft Power BI dashboards gave the project team a clearer way to explore the resulting datasets, validate data quality and support reporting needs. Clear links to source documentation allowed reviewers to confirm where individual records originated.

We also developed an initial AI-assisted conversational search capability. This created another way to locate relevant content held across the historical document collection and began connecting document search with structured data access.

Environmental specialists worked alongside our data engineering team throughout delivery. Together, we reviewed data assumptions and resolved operating-unit identifiers. We also refined the dashboards around the project team’s technical workflows. This iterative approach kept the technology focused on how the information would be reviewed and applied.

The integrated platform gives the project team a more accessible and consistent way to work with environmental information. Current and historical records can be located and compared within a connected data environment, with clear links back to source documentation.

This provides a stronger foundation for technical review and regulatory analysis. It also reduces reliance on separate files and disconnected document searches when preparing environmental information for reporting.