The Intelligence Advanced Research Projects Activity (IARPA), within the Office of the Director of National Intelligence (ODNI), recently launched a new challenge in August aimed at developing algorithms to accurately predict the changes seen in a chemical’s infrared (IR) spectrum caused by changes in its molecular environment.
The challenge, titled Modeling of Reflectance Given Only Transmission of High-concentration Spectra for Chemical Recognition Over Widely-varying Environments, also known as Morgoth’s Crown, is part of the Standoff Illuminator for Measuring Absorbance and Reflectance Infrared Light Signatures (SILMARILS) program and will utilize a global group of researchers to “foster innovation in chemical detection through crowdsourcing.”
According to ODNI, the goal of the month-long competition is to develop models and algorithms to predict how the bulk spectrum of a chemical will shift depending on the environment in which it is deposited.
Trace chemical detection and identification is a critical component for a number of security, counterterrorism and quality control applications. Each combination of particle conditions is considered a separate, independent entry in libraries for chemical detection, which limits the number of chemicals a single library can hold.
Morgoth’s Crown will invite a variety of government experts, academics, chemical industry professionals and developers, with or without experience in chemical detection, to produce accurate IR spectral models for a variety of potential humanitarian efforts.
As part of the challenge, IARPA will provide participants with spectra of a set of bulk chemicals and surfaces, along with a spectra of a subset of the combinations of the chemicals as training data. From there, participants will be asked to generate an algorithm to predict the spectra of the remaining combinations of chemicals on surfaces.
Participants who develop the most accurate and complete solutions will be eligible for cash awards from a prize purse of $50,000.