Synthetic Data Generation for Property and Passenger Screening
Past New Requirement Updated
- Solicitation expected
- Estimated value
- $2,000,000 to $5,000,000
- Set-aside
- No set-aside
Forecast facts
- Anticipated award
- Through
- NAICS code
- 541715 Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)
- Place of performance
- Reedsville, PA
- Forecast number
- F2026074280
- Points of contact
-
- Pamela Beresford pamela.beresford@hq.dhs.gov (202) 897-9153
- Karl Harris karl.harris@hq.dhs.gov (202) 815-6552
Forecast details come from DHS's Acquisition Planning Forecast System. Agencies' dates and values are estimates.
About this forecast
The Department of Homeland Security is procuring software tools for synthetic data generation to support machine vision artificial intelligence development in homeland security screening applications, with solicitation release targeted for September 1, 2026 and award on September 30, 2026. The contractor shall develop and demonstrate capabilities in computed tomography synthetic data generation, millimeter wave synthetic data generation, user interface and system integration development, and program management, collaborating with end users at the Science and Technology Directorate, Transportation Security Administration, and other agencies to validate tools and generated images for machine learning development, training, testing, and evaluation.
The estimated award value ranges from $2 million to $5 million under a firm fixed price definitive contract with a period of performance from September 30, 2026 through September 29, 2028. Work is performed in Reedsville, Pennsylvania. Pamela Beresford (202-897-9153, pamela.beresford@hq.dhs.gov) serves as the requirements contact, with Karl Harris (202-815-6552, karl.harris@hq.dhs.gov) as alternate; the Science and Technology Acquisition Division is the contracting office.
Forecast text
Building and testing reliable machine vision Artificial Intelligence (AI) systems requires access to large amounts of high-quality, labeled data. For homeland security applications, there are several barriers to getting this data: 1) threats are constantly evolving; 2) tailored sensor data (particularly threat data) is expensive to acquire; 3) manual annotation is time consuming; and 4) security datasets are massive and difficult to share. To address these challenges, under a series of Other Transaction Agreements, Cignal created the Cignal Engine prototype which is a suite of simulation and multi-spectral data lifecycle tools to support machine vision AI Development and Operations (DevOps).
The Contractor shall develop and demonstrate software tools that support synthetic data generation suitable for public algorithm development (non-sensitive) and Government development, testing, and evaluation (sensitive). It is anticipated that the contractor shall collaborate with potential end users at S&T, TSA, and elsewhere to validate tools and generated images for suitability for machine learning development, training, testing, and evaluation over the course of the contract.
The objective will be accomplished by specifically accomplishing the following tasks:
• Task 1: Program Management
• Task 2: Computed Tomography Synthetic Data Generation
• Task 3: Millimeter Wave Synthetic Data Generation
• Task 4: User Interface and System Integration Development
On GovTribe
Work this forecast
- Track it in your pipeline
- Find teaming partners
- Similar forecasts
- Ask GovTribe AI about this forecast