Wazihub and Microsoft, in collaboration with Zindi, have partnered on a competition for data scientists to build machine learning models that predict soil moisture that can help farmers efficiently manage water usage.
In the face of climate change, the agricultural sector in Africa needs to adapt its practices. Being able to accurately measure and predict soil humidity in their fields 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.
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).
Test your forecasting skills on @wazihub's Soil Humidity Challenge and stand a chance to win prizes to the value of $8000.
— Zindi (@ZindiAfrica) August 9, 2019
This resulting model will enable farmers to anticipate water needs and prepare their irrigation schedules.
The top five winners that are based in Africa will win IoT kits and a gateway (the same hardware used in this experiment) from Wazihub.
The top three winners will also win cash prizes.
Note that the competition is open to anyone based anywhere, but the prizes will be awarded only to participants that are based in Africa and with a verified mailing address in Africa.
If one of the top winners is not based in Africa, the leaderboard will remain the same, but the prize will go to the next winner on the leaderboard that is based in Africa.
The retail value of each IoT kit is approximately $500 USD.
1st Prize: $2,000 USD + 1 Gateway + 3 IoT Kits (worth approximately $1,500 USD)
2nd Prize: $1,250 USD + 1 Gateway + 2 IoT Kits (worth approximately $1,000 USD)
3rd Prize: $750 USD + 1 Gateway + 1 IoT Kits (worth approximately $500 USD each)
4th to 5th Prize: 1 Gateway + 1 IoT Kits (worth approximately $500 USD each)
Competition closes on 20 October 2019 and final submissions must be received by 11:59 PM GMT.
Click here to join the competition and to get more information.