Please note that the details of this Challenge are no longer open. This challenge is awarded and is no longer accepting new submissions. You can:
Challenge General Fusion Challenge: Data-Driven Prediction of Plasma Performance
General Fusion Challenge: Data-Driven Prediction of Plasma Performance
STATUS: Awarded
Active Solvers: 684
Posted: Dec 10 2015
Challenge ID: 9933692
 
Team Project Rooms are available on this Challenge. Team Share Challenge Share
Abstract

General Fusion is interested in identifying patterns in their experimental data that will allow the company to further improve the performance of its plasma. Extensive data is recorded for each plasma shot and hundreds of gigabytes of shot data is being made available for this Challenge. The task is to use this data to produce an algorithm capable of predicting early in the shot lifetime the overall shot performance. In addition, other correlations and factors that impact shot performance are being sought. 

This is a Reduction-to-Practice Challenge that requires a written proposal, development of an algorithm that accomplishes the Challenge task, and delivery of source code implementing the algorithm.

Overview

The Seeker, General Fusion, engineers and operates several plasma injectors, each of which, when in operating order, can generate a compact toroid plasma every few minutes, equating to hundreds or thousands of plasmas (or “shots”) per week. Over five years, approximately one hundred thousand plasma shots have been executed by General Fusion. Each shot produces hundreds of megabytes of data from hundreds of diagnostic channels and control variables. 

The Seeker is interested in identifying patterns in their experimental data that will allow the company to further improve the performance of its plasma. The task is to use this data to produce an algorithm capable of predicting early in the shot lifetime the overall shot performance. In addition, other correlations and factors that impact shot performance are being sought. 

Multiple awards are available for this Challenge. A First Place Award of $20,000 USD is available for the best performing algorithm while several Secondary Awards of $2,000 USD each may be made for identifying novel correlations that predict a shot's performance. 

The submission to the Challenge should include the following:

  1. A detailed description of the proposed Solution, including:
    1. A description of the novel correlations identified and/or predictors of shot performance.
    2. A description of the prediction algorithm employed, in sufficient detail for others to re-implement the algorithm.
  2. Output from the algorithm as applied to the Testing dataset in the format described in the Detailed Description and Requirements section of the Challenge.
  3. Well-commented and understandable computer source code implementing the algorithm presented in the Solution.

To receive the First Place Award, the Solver will not have to transfer their exclusive IP rights to the Seeker.  Instead, they will grant to the Seeker non-exclusive license to practice their solution and utilize the submitted algorithm and source code. To receive a Secondary Award, the Solver will grant to the Seeker non-exclusive license to their solution, excluding the submitted algorithm and computer source code

Submissions to this Challenge must be received by 11:59 PM (US Eastern Time) on 13-APR-2016.  Late submissions will not be considered.

 

About the Seeker

General Fusion is developing the fastest, most practical, and lowest cost path to commercial fusion energy. Established in 2002, the company and its 65 employees are supported by a global syndicate of leading energy venture capital funds, industry leaders, and technology pioneers. 

Fusion energy holds immense promise as a clean, safe and abundant energy source. Fusion generates neither pollution nor greenhouse gases and is fueled by hydrogen isotopes which are easily extracted from seawater and derived from lithium, in abundant supply. There is enough fusion fuel to power the planet for hundreds of millions of years. 

General Fusion’s Magnetized Target Fusion system uses a sphere, filled with molten lead-lithium that is pumped to form a vortex. On each pulse, magnetically-confined plasma is injected into the vortex. An array of hammers around the sphere impacts and drives a pressure wave into the center of the sphere, compressing the plasma to fusion conditions. 

For more information on General Fusion, visit www.generalfusion.com.

What is InnoCentive?
InnoCentive is the global innovation marketplace where creative minds solve some of the world's most important problems for cash awards up to $1 million. Commercial, governmental and humanitarian organizations engage with InnoCentive to solve problems that can impact humankind in areas ranging from the environment to medical advancements.

What is an RTP Challenge?

An InnoCentive RTP (Reduction to Practice) Challenge is a prototype that proves an idea, and is similar to an InnoCentive Theoretical Challenge in its high level of detail. However, an RTP requires the Solver to submit a validated solution, either in the form of original data or a physical sample. Also the Seeker is allowed to test the proposed solution. For details about treatment of IP rights, please see the Challenge-Specific Agreement.

Share This Challenge
InnoCentive Trust Partners