Design Intelligence Fostering Formidable Energy Reduction and Enabling Novel Totally Impactful Advanced Technology Enhancements (DIFFERENTIATE) | DE FOA 0002107

Opportunity Information: Apply for DE FOA 0002107

The DIFFERENTIATE funding opportunity is an ARPA-E (DOE) research and development program focused on speeding up energy technology innovation by weaving modern machine learning methods directly into the engineering design workflow. ARPA-E exists to back high-potential, high-impact energy technologies that are still too early or too risky for typical private-sector investment, with the broader national goals of improving U.S. economic and energy security, cutting energy-related emissions (including greenhouse gases), reducing reliance on foreign energy imports, and strengthening U.S. technological leadership. Awards under this announcement are issued as cooperative agreements, meaning ARPA-E expects to be actively involved in project execution and management rather than acting as a hands-off funder.

At the center of DIFFERENTIATE is a practical view of how real engineering design happens: an iterative loop where teams start with a clearly stated challenge (for example, achieving very high-efficiency power generation at acceptable cost), propose candidate concepts, refine them using lower-cost models, then test and evaluate those concepts using expensive, high-fidelity simulations or experiments (like computational fluid dynamics, finite element analysis, or system demonstrations). The results of those higher-fidelity evaluations feed back into the next design iteration. This loop can be slow, expensive, and heavily dependent on human intuition and experience. DIFFERENTIATE is trying to compress that cycle time by creating machine-learning-enhanced tools that make engineers faster and more productive at every major step, especially in places where optimization problems and complex tradeoffs normally create bottlenecks.

The program lays out three main tool areas it wants to advance. First are machine-learning-enhanced hypothesis generation tools, essentially improved conceptual design capabilities that help teams generate and refine promising ideas more quickly than traditional brainstorming plus basic modeling. Second are machine-learning-enhanced high-fidelity hypothesis evaluation tools, aimed at detailed design, where ML can reduce the time and cost of running or guiding high-fidelity solvers and experiments, potentially by learning surrogate models, improving sampling strategies, or focusing computation on the most informative regions of the design space. Third are inverse design tools, which work in the opposite direction from conventional design: instead of manually proposing a design and checking how it performs, inverse design starts from the desired performance targets and uses optimization and ML to suggest designs likely to meet those targets, potentially exploring non-obvious solutions that human designers might miss.

ARPA-E emphasizes that these advances require interdisciplinary teams, and the FOA explicitly encourages collaborations that combine mathematicians, operations research analysts, computer scientists, and energy engineers (and other relevant specialists). The underlying idea is that many energy technology challenges share common mathematical structures (especially optimization under constraints, uncertainty, and expensive evaluation functions), so better general-purpose ML-enabled design methods could translate across multiple domains of energy R&D and accelerate progress broadly, not just in a single niche technology.

From the funding details provided, this was published as Funding Opportunity Number DE-FOA-0002107 under CFDA 81.135, categorized as discretionary funding for science and technology and other R&D. Eligibility is described as unrestricted (open to any type of entity, subject to any further clarifications in the full FOA). The award ceiling listed is $5,000,000, with an expectation of about 7 awards. The original closing date for concept papers was May 20, 2019, and applicants were encouraged to submit at least 48 hours before the deadline. The full announcement and submission instructions were made available through ARPA-E’s FOA website.

• The Department of Energy, Advanced Research Projects Agency Energy in the science and technology and other research and development sector is offering a public funding opportunity titled "Design Intelligence Fostering Formidable Energy Reduction and Enabling Novel Totally Impactful Advanced Technology Enhancements (DIFFERENTIATE)" and is now available to receive applicants.
• Interested and eligible applicants and submit their applications by referencing the CFDA number(s): 81.135.
• This funding opportunity was created on Apr 05, 2019.
• Applicants must submit their applications by May 20, 2019 The Concept Paper Due Date is 05/20/2019. Applicants are strongly encouraged to submit their applications at least 48 hours in advance of the submission deadline.. (Agency may still review applications by suitable applicants for the remaining/unused allocated funding in 2026.)
• Each selected applicant is eligible to receive up to $5,000,000.00 in funding.
• The number of recipients for this funding is limited to 7 candidate(s).
• Eligible applicants include: Unrestricted (i.e., open to any type of entity above), subject to any clarification in text field entitled Additional Information on Eligibility.

Apply for DE FOA 0002107

[Watch] Creating a grant proposal using the step-by-step wizard inside the applicant portal: