Can you characterize the ionosphere with selected digitized
radio-frequency (RF) spectrum
recordings from sounder receiver data?
Congratulations to the winners of the PINS Master Challenge!
The Challenge
Develop an algorithm that characterizes, monitors, and models
ionospheric variation effects on high frequency emissions.
How To Enter
Registration for the PINS Challenge is now closed.
Prizes
View the winners of the PINS Challenge.
The Challenge
Despite starting nearly 100 kilometers above the surface of the Earth, the ionosphere plays an active
role in our day-to-day lives in the form of High-Frequency (HF) Radio propagation (McNamara, 1991; Kelly,
2011). International air traffic controllers, oceanographers using surface wave radars, the space launch
community, and many others are all affected by electron density distribution in the ionosphere. The
ionosphere lets you hear distant AM radio stations in your car but it can also affect the
quality of long-range air traffic control.
Modeling the impacts of the ionosphere on HF Radio can be a significant challenge. Installing and
operating ionospheric bottomside sounding systems, called ionosondes, requires a large amount of
electricity, human resources, and the construction of an entire infrastructure of high-profile
antennas. However, passively receiving a characterized or non-characterized sounder transmission is
considerably more convenient. It requires a fraction of the power and resources, and utilizes
lower-profile equipment that can be installed temporarily.
To do so, IARPA’s High Frequency Geolocation Program (HFGeo) presents the Passive Ionospheric
Non-characterized Sounding (PINS) Prize Challenge, an open innovation competition that asks Solvers to
develop an algorithm that characterizes, monitors, and models ionospheric variation effects on high
frequency emissions.
Solvers are challenged to characterize the ionosphere with selected digitized radio-frequency (RF)
spectrum recordings from sounder receiver data, but not any transmitter data. The PINS Challenge is
an open data science challenge that will take place in two stages: Explorer and Master. Part I, the
Explorer Challenge, will specify the sounder signals to be identified and processed. Part II, the
Master Challenge, will add new data sets along the way. Read more challenge details below!
How to Enter
Overview
The PINS Challenge will be broken up into two phases: Explorer and Master. The Explorer Challenge
will specify the sounder signals to be identified and processed. The Master Challenge will add new
data sets along the way. Top placing Solvers in both challenges will be eligible for cash prizes.
Submissions will be evaluated versus additional ionospheric diagnostic data, as well as on the
originality and promise of the techniques.
The Explorer Challenge will take place prior to the Master Challenge; however, you do not have to
participate in one to do the other. The Master Challenge will require modification of the algorithms
that were developed in the Explorer Challenge. View more technical information on the challenge
The example Solver will receive 3,506 points for this test case which is the sum off
all the points awarded for the answer to each parameter, i.e. 761 + 775 + 970 + 1000.
Successful Explorer Challenge Solvers will also submit a short (3 to 5 page) paper describing
the algorithms that produced their results from Phase 1. Solvers who do not submit a paper will
not be eligible for a prize.
Master Challenge
Solver submissions will be scored as follows:
Ionospheric Parameter
Objective
Points
Example Sol. Results
Example Solver Points
JF
Match values measured by PINS Challenge Team
1000 - | γ (kHz) |
In the same OI ionogram, Solver measures JF of 9000 kHz
PINS Team measures a JF of 9027 kHz
973 points
ƒmaxE
Match values measured by PINS Challenge Team
1000 - | γE (kHz) |
In the same OI ionogram, PINS Team measures an ƒoE of 6761 kHz
Solver presents 6500 kHz
739 points
Identify & segregate the E/F1/F2 layers and multihops
Match labels measured by PINS Challenge Team
Maximum of 1000 points;
points per trace will be
assigned based on the
complexity of the ionogram
PINS Team OI ionogram has (1) 1-hop F2 trace, (2) 2-hop F2 trace & (3) E layer trace.
300 points awarded for (1) & (2);
400 points for (3).
Solver presents (1) and (3)
700 points
h’F2
Match values measured by PINS Challenge Team
1000 - | β (km) |
Solver measures h’F2 of 220 km
PINS Team measures h’F2 of 280 km
940 points
The example Solver will receive 3,352 points for this test case which is the sum off all the
points awarded for the answer to each parameter, i.e. 973 + 739 + 700 + 940.
For both the Explorer and Master Challenge, any Solver Result that produces an Ionospheric Parameter score of less than zero, will be recorded as a zero.
Successful Solvers will also submit short paper describing the algorithms that produced
their results in the Master challenge. Solvers who do not submit a paper will not be eligible for a prize.
The top ten Solvers will then be asked to provide their code for evaluation by the challenge team.
Solvers who do not provide their code will not be eligible for a prize. Distribution of Solver code
will be limited to the challenge prize staff and the US Government and marked with the appropriate US Government Purpose Rights.
Dataset
Over the past few years, the PINS Challenge Team has been digitally recording bands of HF spectrum. These recordings were made from 2 to 30 MHz and consist of in-phase/quadrature (I/Q) voltages measured off a broadband HF antenna connected to Software Defined Radios (SDR). The SDRs were time-synchronized with Global Positioning System (GPS) timing.
The PINS Challenge Team has made these recordings from several locations in the US. Within these recordings
are a variety of signals with various modulations and signal strengths. The recorded signals propagated by
ground and/or skywave.
In addition, to validate the performance of a wide variety of signal processing algorithms, the PINS Challenge
Team has created a large volume of synthetic data that will present both simple and complex signal
environments for algorithm development, testing, and troubleshooting. Using these data, the noise and
interference environments can be gradually escalated in order to improve the performance of a Solver’s
algorithm(s).
Participants with the best winning solutions will be eligible to win from a prize pool of $150,000!
Challenge participants can win prizes by having top scores in either challenge.
Individuals and teams, 18 years of age or older will be able to compete for cash prizes. In order
to earn prize money, solvers need to comply with the challenges eligibility requirements and grant
US Government Purpose Rights to IARPA for the solutions used in the challenge.
However, if you are not eligible (or do not wish to permit the requisite rights) to compete for prizes,
you may still participate in the competition to receive public recognition of your performance but forego
any prizes.
The following resources have been compiled to help familiarize Solvers with the challenge. These
resources are intended to serve as examples of relevant background materials, and identification
here does not constitute a recommendation from IARPA to purchase any for-pay services related to
these resources.
Goodman, J. M. (1991). HF Communications: Science and Technology,
Van Nostrand Reinhold, New York, NY.
Leo F. McNamara. (1991). The Ionosphere: Communications, Surveillance, and Direction Finding
(Orbit: A Foundation Series), Krieger Publishing Company, Malabar FL.
The Intelligence Advanced Research Projects Activity (IARPA) invests in high-risk, high-payoff
research programs to tackle some of the most difficult challenges of the agencies and disciplines
in the Intelligence Community (IC).
