Dear Mr. President: Vote for computational science

You've seen the movies. Scientists with Zeus-like powers in their secret labs using super powerful computers make discoveries that change the world...


You've seen the movies. Scientists with Zeus-like powers in their secret labs using super powerful computers make discoveries that change the world...for good or evil. Over decades and millennia, the future of society and the planet depend on scientific discoveries, enabled by current and future technology, especially high-performance computing. The cure for AIDS and other diseases, tapping into new, clean power sources, understanding and harnessing the dynamics of the universe, forecasting earthquakes and other complex problems are all dependent on utilizing advanced computational resources.

A recent assessment by the President’s Information Technology Advisory Committee (PITAC), entitled "Computational Science: Ensuring America’s Competitiveness,"  found that U.S. preeminence in science and engineering is compromised not just by the lack of focus on education in those domains, but also by a lack of collaboration and sharing within both academia and Federal R&D agencies. According to the PITAC report, "Current efforts are characterized by a short-term orientation, limited strategic planning, and low levels of cooperation among the participants. To address these deficiencies, the report recommends that the National Science and Technology Council  (NSTC) commission the National Academies to convene one or more task forces to develop and maintain a multidecade roadmap for computational science and the diverse fields that increasingly depend on it."  The report also recommends specific initiatives in three areas:

  • Create a new generation of well-engineered, scalable, easy-to-use software suitable for computational science that can reduce the complexity and time to solution for today’s challenging scientific applications and can create accurate models and simulations that answer new questions.
  • Design, prototype, and evaluate new hardware architectures that can deliver larger fractions of peak hardware performance on key applications.
  • Focus on sensor- and data-intensive computational science applications in light of the explosive growth of data.

The report warns that the U.S. is at a tipping point, "with generation-long consequences for scientific leadership, economic competitiveness, and national security if we fail to act with vision and commitment." Based on reports from PITAC, the General Accounting Office (GAO) and other governmental agencies, the U.S. isn't adequately addressing the threats of cybersecurity, the need for graduating more science and engineering majors and now creating a roadmap and shared goals for advanced computing initiatives. Other countries today are equally if not more ambitious today in seeking the answers to grand challenges, ranging from economic forecasting and astrophysics to computational fluid and plasma dynamics, as well as the less savory applications such as simulating the effects of weapons of mass destruction. While the PITAC recommendations are reasonable, they don't amount to much unless the administration and Congress act on them. It's just another political issue that has to be couched in terms of ceding leadership to another country or endangering the U.S. economy to get any attention. If the U.S. wants to attract more Einsteins in the making, then following the recommendation of PITAC regarding computational science is a good start. It's not just a U.S. welfare and stature issue--in the modern, connected, collaborative world, and with increased funding for computational science, the progress of science could be greatly accelerated globally.