On the 29th of July, Zindi, an African Data Science Competition website (African Kaggle) announced the commencement of Wazihub Soil Moisture Prediction Challenge. This competition ensues as a result of climate change which creates the need for the agricultural sector in Africa to devise means for adaptation. One crucial step in solving this challenge is being able to accurately measure and predict soil humidity in their fields as this will allow farmers to prepare their irrigation schedules optimally and efficiently.
To measure and predict the soil humidity, sensor-based irrigation and machine learning algorithms are required. However, building machine learning algorithms on sensor data will require a lot of data to be trained properly. Also, it is difficult to obtain stable sensor data in rural Africa due to many challenges such as accessibility, poor power supply, lack of internet, humidity and/or heat problem.
Therefore, this Zindi competition requires the participants 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. The more challenging part of this competition is designing a set of algorithms that are resilient and can be trained with incomplete data (e.g. missing data points) and unclean data (e.g. lot of outliers), with the resulting model capable of informing farmers when to anticipate water needs and therefore prepare their irrigation schedules accordingly.
WAZIHUB is an innovation project for Africa aiming to create an Open Hub of IoT and Big data cutting-edge and African-grade solutions, co-designed by African people where these solutions can then be adapted to match local service needs.
Are you a beginner or expert Data Scientist and you will like to earn some money while you solve problems with your skills, join the competition: Wazihub Soil Moisture Prediction Challenge
Deadline:21 – 10 -2019