The US $8,000 competition, dubbed Wazihub Soil Moisture Prediction Challenge, is looking for individuals that can predict soil humidity using sensor data.
Organizers say that being able to accurately measure and predict soil humidity will allow farmers to prepare their irrigation schedules optimally and efficiently.
“Sensor-based irrigation and machine learning algorithms can provide farmers with a solution to manage water usage more efficiently. However, current machine learning algorithms built on sensor data require a lot of data for proper training. Stable sensor data is difficult to obtain in rural Africa where many problems arise such as accessibility, limited battery power, lack of internet, humidity/heat problem,” reads an official statement.
“The objective of this Zindi competition is to create a machine learning model capable of predicting the humidity for a particular plot in the next few days, using data from the past. A part of the challenge is to design algorithms that are resilient and can be trained with incomplete data (e.g. missing data points) and unclean data (e.g. lot of outliers).”
Below are some of the conditions for applying:
“If your solution wins a prize, you will be required to submit your winning solution code to us for verification and you thereby agree to assign all worldwide rights of copyright in and to such winning solution to Zindi.
“Your solution must not infringe the rights of any third party and you must be legally entitled to assign ownership of all rights of copyright in and to the winning solution code to Zindi.
Competitors are currently able to register and submit solutions as individuals only. For the avoidance of doubt, individuals and their submissions originating from multiple accounts will be disqualified.
“However, competitors can still collaborate with others and work in teams towards a submission. (We plan to enable team functionality on Zindi in the near future). If collaborating with others as a team, it will be your responsibility to designate one person to submit your team’s solution on your team’s behalf. Prizes are transferred only to the individual user that submitted the winning solution.”
Apply here before October 21.