Algorithm Challenge To Aid Environmental Protection
Written by Sue Gee
Monday, 09 June 2014
A new Marathon Match contest on [topcoder] is sponsored by the US Environment Protection Agency and has $15,000 in prizes. The challenge is to use past records and environmental data to devise an algorithm, that will be deployed in an Android app, to predict future cyanobacterial harmful blooms.
One of the EPA's great concerns is the proliferation of cyanobacterial harmful blooms (cyanoHABs) in the nation's lakes. The goal of this challenge is to develop an algorithm that is able to predict the behavior of cyanoHABs in a particular area in near future using data such as past history of cyanoHABs concentration in different areas, weather information, survey of land usage and information on what crops were cultivated in agricultural areas.
The resulting algorithm will then be deployed in an Android app with mapping and data visualization capabilities. The app will inform local and federal policy makers about locations where bloom events are likely to occur, allowing them to concentrate their efforts in those areas.
If you want to know more about the problem posed by cyanobacteria and why urgent action is need this video from University of North Carolina, Chapel Hill provides the background:
The challenge has a deadline of June 28th and is open to all members of the [topcoder] community with the exception of those in the Quebec province of Canada, Iran, Cuba, North Korea, Sudan or Syria. After joining [topcoder], which is free, you can start to enter its contests immediately.
For this Marathon Match there are five cash prizes for the best performers:
1st place $6,000
2nd place $4,000
3rd place $2,750
4th place $1,500
5th place $700
Contestant have to devise a prediction algorithm based on past concentrations of cyanobacteria records, along with other data such as weather information, survey of land usage and what crops were cultivated in agricultural areas using only the data sets and test cases supplied. Solutions can be implemented in C++, Java, C# or VB. Python solutions are specifically disallowed. Although you must not submit a description of how you algorithm works during the submission phase, the winners will need to do so within 7 days to be awarded prize money.
Full details of the data sets, together with definitions to be used and notes of the memory and time limits are given on the Marathon Match page for CyanoHABsPredictor.
Given the controversy surrounding chatbots and the Turing Test, it would seem unwise for neural networks to challenge the same problem. As you might guess, they have and the result is the predictable [ ... ]