Skip to content
This is NOT an official site of the City of New York. Click here for official AI reports.

NYC Office of Technology and Innovation

NYC - DTPR AI Register

AI-Powered Flood Detection for NYC Streets

What it is for

Safety & Security
  • FloodVision supports flood risk management by detecting flooding and estimating flood depth at road locations across New York City, helping DEP identify and corroborate flooding hot spots in priority areas.

NYC Algorithmic Tools Compliance Report — FloodVision

Run by
Department of Environmental Protection (DEP)
Where
No fixed location
Kept
Not stated by the NYC Office of Technology and Innovation.
Shared with
Accountable organization
Your copy
You cannot see the data it holds about you. What you can do

What it is for

Safety & Security

FloodVision automatically analyzes live road camera footage from the Department of Transportation to detect flooding and estimate water depth across New York City. The system operates fully autonomously and provides flood-detection data to the Department of Environmental Protection to support decisions about flood response priorities. No personal or identifying information about individuals is collected or used — the system only observes road conditions.

What it collects and what happens to it

Data taken in

About a place
Anonymized data
  • Images and video footage from Department of Transportation road cameras at specific NYC street locations, capturing road surface and water conditions. No identifying information about individuals is collected.

NYC Algorithmic Tools Compliance Report — FloodVision

Processing

Computer Vision
  • Computer vision models trained on road camera images and video analyze frames to detect flood presence and estimate water depth. Implemented on Google Cloud Platform's AI cloud offerings by ClearObject.

NYC Algorithmic Tools Compliance Report — FloodVision

What it does

Sensing (Perceptive AI)
Autonomous
  • The system automatically processes DOT road camera images and video to detect the presence of flooding and estimate water depth, without human review of each camera frame.

NYC Algorithmic Tools Compliance Report — FloodVision

Deciding (Analytical AI)
Human decides
  • The system scores and classifies detected flood conditions (presence and approximate depth), producing data points that DEP staff use alongside other information to make flood response decisions.

NYC Algorithmic Tools Compliance Report — FloodVision

Outputs

About a place
Anonymized data
  • The system outputs whether flooding has been detected at a given road camera location and the approximate depth of the flood at that location. This information is provided to DEP to inform flood response decisions.

NYC Algorithmic Tools Compliance Report — FloodVision

A recommendation or prediction
Anonymized data
  • Flood detection results serve as one of several data points that helps corroborate flooding hot spots in priority areas, functioning as an advisory input to DEP's data-driven decision-making process rather than a binding determination.

NYC Algorithmic Tools Compliance Report — FloodVision

Run by

Department of Environmental Protection (DEP)
  • The NYC Department of Environmental Protection's Bureau of Sustainability deploys and operates FloodVision to receive flood-detection information and support data-driven decisions about flooding hot spots in priority areas.

NYC Algorithmic Tools Compliance Report — FloodVision

Built by

ClearObject
  • ClearObject is a professional services vendor that implemented FloodVision using Google Cloud Platform's AI cloud offerings.

NYC Algorithmic Tools Compliance Report — FloodVision

Kept for

Not stated by the NYC Office of Technology and Innovation.

Shared with

Not available to me
  • The flood detection outputs are provided to DEP for internal operational use. No public-facing access mechanism or individual data access portal is described in the register entry.

NYC Algorithmic Tools Compliance Report — FloodVision

Available to the accountable organization
  • Flood detection data is provided to the NYC Department of Environmental Protection to inform data-driven decisions about flood response.

NYC Algorithmic Tools Compliance Report — FloodVision

Stored

Not stated by the NYC Office of Technology and Innovation.

How to read the colours

Can it identify you?

Anonymized data
Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data
Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data
The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides
This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes
This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous
This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the NYC Office of Technology and Innovation, not the vendor.

Your rights

  • Right to Algorithmic TransparencyInformation about FloodVision's operation is publicly disclosed through the NYC Algorithmic Tools Compliance Report, available at the NYC Open Data portal. The register describes the system's purpose, inputs, outputs, vendor, and autonomy level.

Risks and safeguards

  • Civil liberties harmContinuous road camera surveillance infrastructure, even when configured for flood detection only, could be repurposed or expanded to monitor individuals or groups.Safeguard: The register explicitly states no identifying information is collected or disclosed. The system's stated purpose is limited to detecting road flooding conditions, and outputs are restricted to flood presence and depth at geographic locations.