AI research by DARPA seeks to produce more reliable expert guidanceNews
September 27, 2022
ARLINGTON, Va. The Defense Advanced Research Projects Agency (DARPA) has launched what it calls the Automating Scientific Knowledge Extraction and Modeling (ASKEM) program, under which it chose multiple research teams -- sourced from universities and companies -- that will look into the use of artificial intelligence (AI) approaches and tools to create, sustain, and enhance complex models and simulators for various use cases.
According to the ASKEM annoucement, the tools resulting from this research will enable experts to maintain, reuse, and adapt large collections of heterogeneous data, knowledge, and models that are traceable across knowledge sources, model assumptions, and model fitness. The models and simulators will be applied to such uses as modeling of viral epidemics, such as COVID-19, and to the causes and impacts of space weather.
Dr. Joshua Elliott, ASKEM program manager in DARPA’s Information Innovation Office, stated that the goal of ASKEM is to "dramatically accelerate scientific and engineering advances, and improve the sorts of scientific collaboration that can lead to timelier and more reliable expert guidance to support threat detection, interventions, and decision-making, especially in rapidly evolving environments and mission-critical domains.”
ASKEM's 42-month time span is divided into two phases: Phase 1 will focus on the program goals of improving the accuracy, timeliness, and maintainability of models, with Phase 2 emphasizing the objectives of generalizability and scalability.