InfraMapDATA CENTERSInfraMap Edu ↗

METHOD · VERSION 0.7

Every claim needs
its evidence.

Our goal is a public record of US data centers at building resolution. This research release establishes the discovery pipeline. It does not yet establish comprehensive coverage.

Find candidates through different sources

Community maps identify visible sites. Air permits, planning applications, utility filings and operator disclosures identify projects and phases. Each source has blind spots, so we keep its identity, retrieval date and supported fields.

The research pipeline captures operator facility directories, SEC disclosures, state filings, hyperscaler plans and county building records. Separate research batches preserve the source documents and proposed matches. Publication follows a review of the building identity, exact source text, quantity definition, date and possible duplicates. Source hashes identify the bytes reviewed; they do not certify accuracy. There is no general SEC crawler.

Keep buildings and campuses separate

An OSM object can represent a building, a campus or a facility point. We retain that distinction. We only draw a building footprint when the source identifies it as a building. An adjacent warehouse, cooling building or office does not become a data center because it is nearby.

Distance alone does not merge records. A match needs shared identifiers or a documented identity review. Shared buildings retain their operator and suite relationships without counting each tenant as a new building. Stable IDs use the source and source identifier, so correcting a name or coordinates does not break its link. Campus records and their buildings must not be summed as distinct facilities.

Show proposed buildings separately

Primary site plans can identify individual buildings before a roof exists. We position each labeled building using documented map controls and keep its point at approximate plan precision. Dashed gold outlines show the proposed building body. They never enter the observed footprint total, and polygon area never becomes reported floor area.

Plan records retain the plan date, control-fit errors and unresolved limits. A small fit error does not prove absolute positional accuracy. An unconfirmed alternative layout, unlocated building label or unresolved shared-building identity stays outside the reviewed count. Address and project points retain their original precision.

Correlate county structures with building polygons

Loudoun County identifies addressable structures and their land use. Our accepted associations require an exact normalized street address, one county data-center structure inside one building polygon, and no competing mapped point, overlapping polygon or duplicate county structure at that address. Ambiguous rows stay unresolved. The county's combined existing-or-permitted status does not prove operation, and construction year does not establish opening year.

Separate power quantities and phases

IT capacity measures critical computing load. Total facility power also includes cooling, lighting and losses. Backup generation, contracted utility service, ultimate campus plans and live IT load are different quantities. Each needs its own scope and effective date.

We keep missing values empty. A standard PUE assumption does not fill a reported field. A generator permit does not establish grid demand. Footprint area is ground coverage, not building floor area. Assessed, permitted and approved floor areas retain their source definitions. County occupancy dates remain separate from operator-reported openings. Planned maximum power and first-phase openings have visible qualifiers.

Later decisions can change an earlier plan. We check amendments, withdrawals and municipal decisions before counting proposed buildings. Historical records remain available when a denied application or an unresolved layout change removes them from the comparable count. A withdrawn proceeding alone does not prove project cancellation.

Some plans contain scanned labels rather than searchable text. A visual transcription records the source page, rendered image hash, individual building location and reviewer. Approximate gross floor labels remain approximate. An explicit uniform floor-area formula may produce a separately labeled derived value; a campus total or roof measurement cannot substitute for building floor area.

Read permits as evidence, not completion

The Virginia register groups entries by registration number and preserves permit revisions. It does not establish current construction or operation. Locality-only records stay in the research queue. Operator directory pins can mark a city center, so those also stay out of the map until we confirm a site location.

Use dated imagery to check construction

The imagery pipeline searches Microsoft Planetary Computer for Sentinel-2 and NAIP scenes. Published assistant reviews record visible conditions and roof-appearance bounds, with source resolution and limitations. They do not count as an independent accuracy audit. For the initial pilot, it samples one location per state, prioritizes source-tagged construction, and selects lower-cloud scenes by month. Every image links to its acquisition metadata. A mosaic can combine scenes from different days. We show those dates and use the later component date when confirming that a roof was visible.

Sentinel-2's 10 m pixels can help identify large changes. They often cannot resolve individual small structures. Scene-wide cloud cover does not prove that the site itself is cloud-free. NAIP offers finer aerial detail, but survey dates can be years apart. These sources support review; neither proves that servers are operating.

A reviewer must record which dated scenes were examined, what is visible, the construction stage, limitations and their name before a record can claim imagery verification. Collecting a timeline alone never changes status.

Show uncertainty and measure errors

We publish unknown fields and the source behind known fields. No percentage score claims certainty. Independent verification is separate from source attribution. The coverage page compares field completeness with a dated Cleanview snapshot and explains the difference in counting units.

Before claiming matching accuracy, we need a stratified sample review that checks identity, coordinates, status and capacity against independent primary evidence. The current release has no completed accuracy audit.

Electrical specifications retain their stated meaning. Utility supply capacity, UPS output and backup generator ratings appear as separate source observations. They do not fill total facility load. Critical IT capacity requires an explicit definition that excludes cooling and other supporting infrastructure.

Trace power beyond the building page

The power evidence catalog preserves utility requests, service contracts, total design load, critical IT capacity and generator records as different quantities. EIA generator status applies to the generator. ISO load queues describe requests and study assumptions. Seasonal values, revised requests and ramp stages are never added together.

Source dates, publication dates and retrieval dates remain separate. Conflicting addresses, future-dated updates and unknown quantities stay visible. Announcement compilations are discovery leads. A building field changes only after its physical identity and the quantity scope pass a separate review.

Building power from CEC filings requires a reviewed physical building identity. A planned replacement does not inherit the predecessor's roof. Historical design values keep their reporting date and qualifier. An attached power building follows the filing's stated scope; a campus total is never divided among buildings.

EIA address associations compare street, city, state and operator name. They do not establish an electrical connection. Source coordinates can be wrong and never replace the mapped building location. Workbook citations identify the file, sheet and cell. The replay checks the source bytes, column header and native plant or generator identifiers.

Sources and reuse

PeeringDB and the retired Edu inventory are excluded from public data. PeeringDB's data terms require separate review; the old inventory has unresolved provenance.

Reproducibility and corrections

Downloads include stable IDs and source links. The release manifest records file hashes. The build checks source permissions, coordinates, identities and capacity provenance before exporting. Source refreshes run on demand; no unattended update schedule is active.

Use a record's correction link to send a public source and the proposed change. The link opens an email draft. It does not edit the published map automatically.