Multi-source Data Ingestion for Warfighters

Navy SBIR 25.2 - Topic N252-096
Naval Sea Systems Command (NAVSEA)
Pre-release 4/2/25   Opens to accept proposals 4/23/25   Closes 5/21/25 12:00pm ET
   [ View Q&A ]

N252-096 TITLE: Multi-source Data Ingestion for Warfighters

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Trusted AI and Autonomy

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Develop a capability that mines information from authoritative sources and reduces operator workload and errors.

DESCRIPTION: Operators of theater-level command and control systems, such as the AN/UYQ-100 Undersea Warfare Decision Support System (USW/DSS), must consider a wide range of sources when forming recommendations for Fleet operations. Operators currently manually access a range of authoritative sources in search of the best information upon which to base Fleet operations decisions. Creating the required range of reports involves significant effort that can take hours to complete. Research must be done, then data collected, and finally uniquely formatted reports generated that are provided to a range of consumers. During complex wartime operations, this reliance on manual means to access information introduces an error-prone environment and creates a heavy sailor workload.

Current mission preparation requires operators to spend numerous hours searching Secret Internet Protocol Router Network (SIPRNET) websites and various publications. Current information is stored in a variety of different formats, including hardcopy information, websites, platform status information contained in meta-data communicated over USW-DSS, and embedded recording systems. This information is not stored or tagged in a manner that enables operators to perform rapid searches for data analytics. The Navy seeks a technology to mine authoritative data in various stored formats and provide an intuitive user interface for generating accurate reports. This capability will reduce error-prone situations and time involved to make Fleet operations decisions. The desired technology will allow machine learning to search for vital information, allowing the operator to focus on interpretation of data rather than the mechanics of the search process. There is currently no commercial product that will meet the required technological need.

The technology sought must rapidly access and parse data types across different authoritative sources to produce results within an intuitive user interface. The data to be accessed includes USW-DSS recordings, operational information, authoritative intelligence, lessons learned, estimated probabilities from prior maneuvers, and historical and projected environmental data. The user interface must enable users access to this data as they need it, and in the standardized formats required by USW-DSS and connected systems. The data mining capability and user interface must operate at multiple security levels (e.g., Unclassified up to TS-SCI), supported by an architecture that could allow information at multiple security levels to be ported up to the highest level of security required for a specific effort. The technology will enable data from previous missions to be easily recalled and overlaid with current data to show history of deployments for contacts of interest and activity levels.

The data mining algorithm must provide for authoritative data availability to appropriate access privileges. It must also meet current Information Assurance (IA) specifications for classification security. No known commercial application is capable of meeting the Navy’s requirement to mine from authoritative sources across multiple security levels and meet IA specifications.

Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. owned and operated with no foreign influence as defined by 32 U.S.C. § 2004.20 et seq., National Industrial Security Program Executive Agent and Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Counterintelligence and Security Agency (DCSA) formerly Defense Security Service (DSS). The selected contractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances. This will allow contractor personnel to perform on advanced phases of this project as set forth by DCSA and NAVSEA in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material during the advanced phases of this contract IAW the National Industrial Security Program Operating Manual (NISPOM), which can be found at Title 32, Part 2004.20 of the Code of Federal Regulations.

PHASE I: Develop a concept for a data mining capability and associated user interface that meets the requirements as stated in the Description section above. Demonstrate the feasibility of the concept in meeting Navy needs and will establish that the concept can be feasibly produced by sample testing, modeling and simulation and or analysis. The Phase I Option, if exercised, will include the initial design specifications and capabilities description to build a prototype solution in Phase II.

PHASE II: Develop, deliver, and demonstrate a prototype data mining capability and associated user interface. Demonstrate the functionality in a series of user designed sprints with fleet operators to refine the user interface for evaluation. The prototype will be evaluated to determine its capability in meeting the performance goals as defined in the Description. System performance would ideally be demonstrated through installation and prototype testing using the cloud-based USW-DSS prototyping infrastructure provided by the government.

It is probable that the work under this effort will be classified under Phase II (see Description section for details).

PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the data mining capability and user interface to Navy use. Finalize the software design and algorithm prototype, for evaluation to determine its effectiveness in an operationally relevant environment in USW-DSS. Support the Navy for test and validation in accordance with the IWS 5.0 USW-DSS Peer Review Group.

The technology will have private sector commercial potential for any secure system such as banking and medical information requiring access and analysis of historical information, reports, and trends analysis.

REFERENCES:

  1. Jadhav, Pramod Pandurang. "11 - Advanced data mining for defense and security applications." Artificial Intelligence in Data Mining Theories and Applications. Academic Press, 2021, pp. 223-241. https://www.sciencedirect.com/science/article/abs/pii/B9780128206010000094
  2. "AN/UYQ-100 Undersea Warfare Decision Support System (USW-DSS), Last updated 20 Sep 2021." Navy Fact File. https://www.navy.mil/Resources/Fact-Files/Display-FactFiles/Article/2166791/anuyq-100-undersea-warfare-decision-support-system-usw-dss/
  3. Grover, Lov K. "A fast quantum mechanical algorithm for database search." (Updated version) Proceedings, STOC 1996, Philadelphia PA USA, pp. 212-219. http://arxiv.org/pdf/quant-ph/9605043.pdf
  4. "Department of Defense (DoD) Cloud Computing Security Requirements Guide (SRG)," Defense Information Systems Agency (DISA) 21 Jun 2024.. https://dl.dod.cyber.mil/wp-content/uploads/stigs/zip/U_Cloud_Computing_Y24M07_SRG.zip
  5. "National Industrial Security Program Executive Agent and Operating Manual (NISP), 32 U.S.C. § 2004.20 et seq. (1993)." https://www.ecfr.gov/current/title-32/subtitle-B/chapter-XX/part-2004

KEYWORDS: Data mining; AN/UYQ-100 Undersea Warfare Decision Support System; complex wartime operations; intuitive user interface; Information Assurance (IA) specifications; history of deployments


** TOPIC NOTICE **

The Navy Topic above is an "unofficial" copy from the Navy Topics in the DoD 25.2 SBIR BAA. Please see the official DoD Topic website at www.dodsbirsttr.mil/submissions/solicitation-documents/active-solicitations for any updates.

The DoD issued its Navy 25.2 SBIR Topics pre-release on April 2, 2025 which opens to receive proposals on April 23, 2025, and closes May 21, 2025 (12:00pm ET).

Direct Contact with Topic Authors: During the pre-release period (April 2, 2025, through April 22, 2025) proposing firms have an opportunity to directly contact the Technical Point of Contact (TPOC) to ask technical questions about the specific BAA topic. The TPOC contact information is listed in each topic description. Once DoD begins accepting proposals on April 23, 2025 no further direct contact between proposers and topic authors is allowed unless the Topic Author is responding to a question submitted during the Pre-release period.

DoD On-line Q&A System: After the pre-release period, until May 7, 2025, at 12:00 PM ET, proposers may submit written questions through the DoD On-line Topic Q&A at https://www.dodsbirsttr.mil/submissions/login/ by logging in and following instructions. In the Topic Q&A system, the questioner and respondent remain anonymous but all questions and answers are posted for general viewing.

DoD Topics Search Tool: Visit the DoD Topic Search Tool at www.dodsbirsttr.mil/topics-app/ to find topics by keyword across all DoD Components participating in this BAA.

Help: If you have general questions about the DoD SBIR program, please contact the DoD SBIR Help Desk via email at [email protected]

Topic Q & A

4/22/25  Q.
  1. Is there an existing ontology or tagging system that the proposed solution should support for ingestion and search?
  2. Would a cognitive-perceptual approach to data filtering (reducing information fatigue) be considered complementary to the mission?
  3. Are there known constraints or limitations related to integrating with USW-DSS systems or file formats?
  4. Is IA compliance expected in Phase I, or scoped for architectural planning with later implementation in Phase II?
   A.
  1. None. Any/all technical solutions will be welcome and evaluated.
  2. Yes, information fatigue is a part of this overall effort. A sailor may have the cycles to search for the right answer but how many pages will they look at before giving up? If presented with 2 conflicting answers, how much further digging can be tolerated? Don't take this as an endorsement of your specific approach to data filtering; just that it could form a part of your overall solution to this topic.
  3. As a part of the shipboard combat system, CV-TSC has highly restricted connections to data repositories today. It must run on fleet hardware which then provides limitations to the environment. For instance…no GPUs in CV-TSC. CV-TSC is also ‘bare-metal’ as in no virtualization or containers today. Things also with large license costs will be hard to transition w/in the existing budget. Biggest challenge however is probably access to the various repositories of the data; all will be SIPR Token protected at the minimum. Some may require accounts.
  4. The solution, once integrated into CV-TSC must be able to get an ATO with all used software/libraries etc. But there are no specific requirements per se that must be addressed in the concept development Phase 1
4/21/25  Q. Can you list the systems that were deemed insufficient for this prupose?
   A. N/A. There are no real systems that are providing this service today. This is manual operator/user functions today; lookup on SIPRNET or via hard-copy of relevant ASW-related "facts" that are required for optimum system employment.
4/21/25  Q. What sample datasets are you prepared to provide?
   A. This can be discussed with awardees. Sources documents are all classified and unclass stand-ins are not readily available.
4/21/25  Q. Data aggregation inherently introduces classification escalation challenges: to what degree (if any at all) do you expect providers to engineer mitigations & controls for this?
   A. Proper labelling of classified data is a mandate. Proposal should address how that will be maintained.
4/21/25  Q. How much does this solicitation regard the eventual fully featured delivery of ADVANA’s capabilities? Was this written assuming that a full scope completion of ADVANA for data fusion would still not suffice?
   A. As we understand things, ADVANA was developed by DOD and Booz Allen Hamilton as a data aggregation capability across hundreds of data sources, with a focus on financial and acquisition databases. This topic seeks a tool that can assist operators with tactically relevant war-fighting data on a limited computational footprint.

The topic was written presuming that the innovation required could be accomplished by a small business starting with a TRL 2-3 for an ACAT 4 system. At the time of writing, the authors were not persuaded that an existing or planned AIML and data fusion capability would meet the unique requirements of this topic.
4/21/25  Q.
  1. Are there preferred data source types or formats (e.g., metadata from sensors, operational logs, archived intelligence reports) that should be emphasized in the Phase I feasibility demonstration?
  2. Will the government provide synthetic or representative datasets during Phase I, or is the offeror expected to generate or simulate representative data independently?
  3. Does the government have specific UI design standards or formatting requirements (e.g., templates used within USW-DSS) that the proposed interface should align with?
  4. Should the proposed capability include any analytics, alerting, or anomaly detection functionality beyond data aggregation and formatting?
  5. Are there any preferred machine learning methods or architectures (e.g., transformer models, vector search) for document parsing, data fusion, or semantic understanding in this context?
  6. Is there an existing data tagging ontology or structured schema that should be used to annotate or classify multi-source data during Phase I?
  7. Can proposed solutions leverage containerized architectures (e.g., Kubernetes, Docker) to demonstrate modularity and future integration potential with cloud-based DSS environments?
  8. Will Phase I demonstration need to account for multi-level security compliance (e.g., TS-SCI data handling), or is that expected to be addressed primarily in Phase II?
   A.
  1. Primarily documents (word, PDF, PPTs etc.) and webpages. This could be something like a submarine's max speed, the range of their weapons, the primary tracking frequency the DDG held the contact on last night, ratio for their primary reduction gear or the number of turns per knot.
  2. This can be discussed in phase 1. Source documents are all classified and unclass stand-ins are not readily available.
  3. There are templates and guides etc. but this isn't required as part of Phase 1. Phase 2 will start to evaluate integration and this work would be included at that time.
  4. Not strictly required but any/all technical solutions will be welcome and evaluated as part of the whole proposal concept
  5. None. Any/all technical solutions will be welcome and evaluated.
  6. No. Proper labelling of classified data and its releasability is a mandate. Proposal should address how that will be maintained. For instance all data cannot be marked secret just because run on a secret system. If parts are really CUI or Confidential the solution cannot say its actually Secret.
  7. Yes for demonstration purposes. But to transition it must run on fleet hardware and runtime environment. For instance…no GPUs in CV-TSC. CV-TSC is also ‘bare-metal’ as in no virtualization or containers today. That may change by the time this SBIR transitions but the future cannot be predicted.
  8. A demonstration of the specific is not strictly required for phase 1 but an explanation within your proposal would be the minimum. Focus more on "reaching out" to appropriate sources at the designated enclave level and properly retrieving, storing and tagging the information. A TS enclave can also store S, C and U data. So if we obtain something that is U on the TS enclave system how do i KNOW that it is U when its stored and handled?


[ Return ]