(CLOSED) Data-Intensive Scientific Machine Learning and Analysis (DE-FOA-0002493)

The DOE SC program in Advanced Scientific Computing Research (ASCR) hereby announces its interest in research applications to explore potentially high-impact approaches in the development and use of artificial intelligence (AI) and machine learning (ML) for scientific insights from massive data generated by simulation, experiments, and observations.

SUPPLEMENTARY INFORMATION
Scientific machine learning is a core component of artificial intelligence, a general-purpose data and computing technology that can be used to assist, augment or automate human skills. Major research advances will be enabled by harnessing DOE investments in massive amounts of scientific data, software for predictive models and algorithms, high-performance computing (HPC) and networking platforms, and the national workforce. The crosscutting nature of machine learning and AI provides strong motivation for formulating a prioritized research agenda.
Scientific Machine Learning and Artificial Intelligence (AI/ML) will have broad use and transformative effects across the DOE. Accordingly, a 2019 Basic Research Needs workshop report identified six Priority Research Directions (PRDs). The first three PRDs describe foundational research themes that are common to the development of Scientific AI/ML methods and correspond to the need for domain-awareness, interpretability, and robustness. The otherthree PRDs describe capability research themes and correspond to the three major use cases of massive scientific data analysis (PRD #4), machine learning-enhanced modeling and simulation (PRD #5), and intelligent automation and decision-support for complex systems (PRD #6).

The principal focus of this Program Announcement is on AI/ML for scientific inference and data analysis (PRD #4). Several recent Office of Science reports [1, 2, 3] have highlighted the benefits and computational, mathematical, and statistical challenges in dealing with massive, complex, and multi-modal data from simulations, experiments, and observations. Foundational research will be needed for developing reliable and efficient tools for scientific advances. Also, new techniques and approaches will likely be needed to reap scientific benefits from the extreme heterogeneity of scientific computing technologies (e.g., processors, memory and interconnect systems, sensors) that are emerging.

Disruptive technology changes are occurring across the science applications, algorithms, and architectures within HPC ecosystems. Recent reports and trends are heralding the convergence of HPC, massive data, and AI/ML on increasingly heterogeneous architectures. Furthermore, the concept of programming is evolving thanks to neural nets that can learn from massive amounts of training data (without being explicitly programmed). Significant innovations will be required in the development of effective paradigms and approaches for realizing the full potential of AI/ML for scientific discovery. Consequently, the funding from this Announcement is not intended to incrementally extend current research in the area of the proposed project. Rather, the proposed projects must reflect viable strategies toward the potential solution of challenging problems in AI/ML research for scientific inference and data analysis. It is expected that the proposed projects will significantly benefit from the exploration of innovative ideas or from the development of unconventional approaches. Proposed approaches may include innovative research with one or more key characteristics, such as asynchronous computations, mixed-precision arithmetic, compressed sensing, coupling frameworks, graph and network algorithms, randomization, Monte Carlo or Bayesian methods, differentiable or probabilistic programming, or other relevant facets.