Design Intelligence Fostering Formidable Energy Reduction and Enabling Novel Totally Impactful Advanced Technology Enhancements (DIFFERENTIATE) SBIR/STTR | DE FOA 0002108

DIFFERENTIATE (ARPA-E) SBIR/STTR Funding Opportunity FAQs

1) What is the DIFFERENTIATE SBIR/STTR opportunity?

DIFFERENTIATE stands for "Design Intelligence Fostering Formidable Energy Reduction and Enabling Novel Totally Impactful Advanced Technology Enhancements." It is a Department of Energy ARPA-E funding call issued under ARPA-E's joint SBIR/STTR programs. The focus is on speeding up energy technology innovation by embedding modern machine learning methods directly into the engineering design workflow.

2) Which agency is offering this funding?

The opportunity is offered by the U.S. Department of Energy (DOE) through ARPA-E (the Advanced Research Projects Agency-Energy).

3) What is ARPA-E trying to achieve with this program?

ARPA-E is focused on high-risk, high-reward energy ideas that are typically too early for most private investors. The emphasis is on technologies and approaches that can materially improve U.S. energy and economic security and move the needle within a defined, relatively short development window, helping translate scientific advances into early-stage technologies that can attract follow-on funding and commercialization.

4) Is this funding for building a single energy device or for enabling methods?

DIFFERENTIATE is positioned as a strategic investment in enabling design methods. The intent is to fund machine-learning-enhanced design tools and approaches that can be reused across many energy technologies, rather than funding only a single energy device concept.

5) What is the core problem DIFFERENTIATE is trying to solve?

The program targets the bottleneck in energy engineering design where iteration can be slow, expensive, and heavily dependent on expert intuition. This can limit how many ideas are explored and how quickly designs converge. DIFFERENTIATE aims to make the design loop dramatically more productive using ML-enhanced tools.

6) What design workflow does the FOA describe?

The FOA describes a four-step iterative design loop:

1. A concrete challenge is posed (for example, a demanding performance or cost target).
2. A solution is hypothesized and initially refined using reduced order models (simplified, fast models for exploring design space).
3. The concept is tested using high-fidelity tools (such as PDE-based solvers like CFD or finite element analysis) and/or experiments and demonstrations.
4. The concept is updated based on higher-fidelity insights, and the loop repeats.

7) What kinds of machine-learning capabilities is ARPA-E looking for under DIFFERENTIATE?

The FOA highlights three target capability areas:

• Hypothesis generation tools for conceptual design: methods that help propose promising new system concepts, architectures, or configurations (beyond manual brainstorming and incremental tweaks).
• High-fidelity hypothesis evaluation tools for detailed design: approaches integrating ML with expensive simulations and experiments to reduce time-to-answer, guide where to spend compute or lab effort, and extract more value from each run or test.
• Inverse design tools: methods that work backward from desired performance to identify design parameters, structures, or operating strategies that meet goals, often framed as constrained optimization.

8) What does the FOA mean by "hypothesis generation" in engineering design?

In this context, hypothesis generation refers to tools and methods that help create candidate design concepts (system architectures, configurations, or approaches) that are likely to meet a target, rather than relying primarily on human intuition or incremental adjustments to existing designs.

9) What does "high-fidelity hypothesis evaluation" refer to?

It refers to evaluating candidate designs using expensive, high-detail simulations (including PDE-based solvers such as CFD or finite element analysis) and/or experimental testing and demonstrations. DIFFERENTIATE emphasizes using ML to reduce time and cost, prioritize what to simulate or test, and increase the information gained per run.

10) What is "inverse design" in the context of this program?

Inverse design means starting from a desired outcome (performance, cost, constraints) and working backward to determine the design parameters, structures, or operating strategies that achieve that outcome. The FOA frames this as optimization under constraints.

11) What types of expertise or team compositions does the solicitation encourage?

The FOA explicitly encourages cross-disciplinary collaborations that combine:

• mathematical optimization and operations research,
• computer science and machine learning, and
• domain energy engineering expertise.

The underlying assumption is that meaningful acceleration requires strong ML methods paired with deep understanding of physical systems, constraints, and validation pathways used in real energy engineering.

12) What funding mechanism is being used (grant, contract, cooperative agreement)?

The opportunity is described as a discretionary science and technology R&D funding call using a cooperative agreement.

13) What does it mean that this is a cooperative agreement?

Based on the description provided, a cooperative agreement typically implies more active involvement from ARPA-E than a standard grant, such as technical milestones, regular engagement, and programmatic guidance.

14) Is this an SBIR, an STTR, or both?

It is a joint ARPA-E SBIR/STTR solicitation. SBIR and STTR are government-wide programs intended to stimulate private-sector innovation, meet federal R&D needs through small businesses, and increase the odds that federally funded breakthroughs become real products and companies.

15) How does SBIR differ from STTR in the description provided?

From the information provided:

• SBIR explicitly encourages participation by disadvantaged and women-owned small businesses.
• STTR is structured to promote tighter collaborations between small businesses and research institutions.

16) Which project phases will be funded under DIFFERENTIATE?

ARPA-E indicates funding will be provided for Phase I and Phase II only (and not Phase IIs). This indicates a focus on early feasibility (Phase I) followed by a development phase (Phase II) aimed at a more mature prototype or validated approach.

17) What is the funding opportunity number and CFDA listing?

The funding opportunity number is DE-FOA-0002108 and the CFDA listing referenced is 81.135.

18) How many awards does the posting expect to make?

The posting indicates an anticipated small number of awards, with expected awards: 3.

19) What is the award ceiling listed for this opportunity?

The award ceiling is listed at $1,933,010.

20) Who is eligible to apply, based on the summary provided?

Eligibility is listed as unrestricted in the summary (open to any entity type). However, applicants must still comply with SBIR/STTR rules and any additional eligibility clarifications included in the FOA text.

21) What is the concept paper due date mentioned?

The notice references a concept paper due date of May 20, 2019.

22) Does the posting provide any submission timing advice?

Yes. It encourages applicants to submit at least 48 hours before the deadline to avoid last-minute submission issues.

23) What types of modeling and simulation tools are specifically mentioned?

The FOA references reduced order models for early exploration, and high-fidelity tools such as partial differential equation (PDE) based solvers, including examples like CFD (computational fluid dynamics) and finite element analysis.

24) What is an example of a "concrete challenge" mentioned in the design loop description?

An example given is achieving very high efficiency electricity generation from natural gas.

25) What outcomes is the program ultimately trying to enable?

The end goal described is faster iteration, better exploration of complex design spaces, and quicker progression from an idea to a credible engineered solution that can support goals such as reducing energy imports, cutting emissions, improving efficiency across sectors, and keeping the United States at the leading edge of advanced energy technology.