TGISAI Readiness for Transport Data
Making the world's transport data queryable by AI agents, and by anyone who can ask a question in plain language.
The problem
Transport information spans three fundamentally different worlds that no single standard or platform connects today.
Structured statistical data (country-level indicators, time series, transport statistics) is the most mature. The Transport Data Commons (TDC) is building the trusted metadata and standards layer for this data, using the SDMX standard (the ISO framework used by the World Bank, IMF, OECD, and Eurostat for statistical data exchange). The SDMX community issued a joint statement on AI-readiness in September 2025, committing to make official statistics discoverable by AI agents. TDC and SDMX are the right foundation for structured transport data.
Geospatial and infrastructure data lives in spatial formats (GeoJSON, ArcGIS, OGC services) that statistical standards don't cover. Road networks, port locations, climate risk layers, infrastructure condition. SDMX 3.0 added support for attaching spatial references to statistics, but native geospatial data like topological networks or satellite-derived layers needs its own access patterns.
Unstructured knowledge is the largest and least accessible category. Policy reports, NDC commitments, project evaluations, research findings, transport news. No data standard covers it. Yet it holds the institutional knowledge that gives numbers their meaning: why a country's road investment dropped, what a new corridor strategy commits to, what HVT or RECaP research found.
Today these three worlds don't talk to each other. TGIS uses agentic AI to connect them: TDC and SDMX for structured data, agent-accessible interfaces for geospatial sources, and retrieval-augmented search for unstructured knowledge.
What TGIS does
TGIS uses agentic AI to extend what's possible with existing transport data. It complements existing platforms rather than replacing them:
Accelerate SDMX and TDC adoption. Building SDMX data structures for new statistical domains traditionally takes years of international committee work. Transport has no formal global SDMX domain package. AI agents can compress the preparatory work: analysing existing national datasets, comparing structures, generating draft data structure definitions. Expert committees then review rather than build from scratch. Agents can also help onboard new data providers to TDC's SDMX standards faster by automating format conversion and validation.
Bridge the geospatial gap. SDMX is the right standard for statistical data, but transport decisions also need spatial infrastructure data. Road networks, climate risk exposure, port locations, corridor analysis: these live in GIS formats that statistical standards don't cover. TGIS provides agent-accessible interfaces for sources like OPSIS (infrastructure networks), PortWatch (maritime trade disruptions), and Overture Maps, and can combine their outputs with SDMX statistical data in a single query.
Policy reports, NDC commitments, project evaluations, and research findings hold the institutional knowledge that gives numbers their meaning. TGIS makes this unstructured knowledge searchable. AI agents with retrieval-augmented generation (RAG) can search and synthesise it alongside structured data, connecting a country's stated policy commitments with its actual spending and infrastructure outcomes.
AI chatbots are appearing across the sector: TDC has an early-stage AI assistant for discovering datasets and reports, ADB is exploring one for the Asian Transport Outlook, CKAN-based bots are being deployed on open data portals. Each queries a single organisation's data. TGIS enables cross-source queries, providing the layer that any of these tools could draw on.
Who's behind it
TGIS is led by the RIDE programme (Research on Infrastructure in Developing Economies), funded by UK International Development / FCDO, with technical delivery supported by the Frontier Tech Hub. The aim is a system built in partnership with multilateral development banks (ADB, AfDB, EBRD, EIB, CAF, IDB), UN agencies (UNECE, UNDESA), and sector organisations. No single institution owns it.
TDC (Transport Data Commons) is the foundation. TDC is the initiative building trusted metadata, SDMX-based data standards, and shared guidance for global transport data. It is a layer above individual data sources, working to make them discoverable and interoperable. TGIS builds on that foundation, using agentic AI to accelerate TDC's standards work, extend reach into geospatial and unstructured data that SDMX doesn't cover, and enable cross-source queries that make TDC's holdings more useful to a wider range of tools and agents.
Why now
The UN Decade of Sustainable Transport (2026–2035) launched in December 2025 with monitoring goals but no data infrastructure to track progress. AI capabilities have reached the point where querying heterogeneous data in natural language is technically feasible and affordable. The data already exists: our audit found 14 of 25 sources with open APIs requiring no authentication. The bottleneck is fragmentation, not availability.
Starting point
A proof of concept with 10 sources spanning different data types, transport modes, and institutions:
| Source | What it covers |
|---|---|
| World Bank Open Data | Country-level transport indicators |
| OPSIS (Oxford) | Global infrastructure networks + climate risk |
| PortWatch (IMF/Oxford) | Maritime trade disruptions |
| OECD / ITF | Transport statistics across member countries |
| IATI / DAC | Aid and investment flows into transport |
| ADB Asian Transport Outlook | 450+ indicators across 51 Asia-Pacific economies |
| Africa Transport Observatory | Continental transport corridor data |
| TDC | Multi-modal datasets via single API |
| AfDB Data Portal | African infrastructure and economic indicators |
| SLOCAT NDC Tracker | Climate policy commitments mapped to transport |
This is deliberately not dominated by any single institution. The full data registry covers all 25+ audited sources, with active wrappers for these 10.
What it enables
With these sources connected, an AI agent can answer questions that no single platform handles today:
- "Is Kenya on track for its transport NDC commitments, and what does the evidence say about the interventions it's chosen?" This combines SLOCAT policy data, IATI spending, OPSIS infrastructure, World Bank indicators, and HVT research findings.
- "Which East African road corridors have the highest climate risk relative to their trade importance?" Joins OPSIS climate exposure with PortWatch trade data and World Bank indicators.
- "How does transport investment per km of road compare across FCDO priority countries?" Links IATI/DAC financial flows with infrastructure network data.
- "What did HVT research find about bus rapid transit in Sub-Saharan Africa, and which countries have since invested in it?" Pulls from unstructured research outputs alongside IATI spending records.
These are questions that currently take a research team weeks to assemble. An agent with access to the right sources can pull them together in minutes.
TGIS supports queries in any language, works at both global and country level, and serves any AI tool, from TDC's own assistant to standalone analytical pipelines.