Corn Growth Prediction for the Upcoming Season in Burkina Faso.
Abstract— The economy of many African countries depends heavily on agriculture, forestry and livestock
farming, as well as the exploitation of mineral resources. In Burkina Faso, Traditional cereals, such as
sorghum and millet, dominate food consumption and expenditure of rural households, while urban
households prefer rice and maize. However most farmers today are smallholder or subsistence farmers who
grow crops and rear animals just to feed themselves and their families. The lack of information remains the
number one problem facing most scale farmers today. Nowadays there are many available platforms that we
can retrieve information such as weather information, soil information, yield information that can be used to
build a strong prediction platform. It is from there that we came out with our prediction idea based on Corn
and extended to other crops in the future work. The solution is a web application and mobile application that
will be deployed on the AWS cloud provider. The farmers can install or access from their smartphone or
laptop, and based on their geo position the application provides information about the upcoming season. The
application is a microservice application combines with machine learning tool such as Scikit Learn.
To put in place this solution we use many procedures (extract, clean and store the dataset), technologies
(docker, cloud), programming languages ( Flash, Python) and classification methods (Adaboost, Random
Forests, OLS) to make for the end users accurate predictions. Historic weather conditions were downloaded
using API services from the Darksky.net from 2005 to the current day and then combined with the data of
corn for each province since the same interval date coming from multiple sources AGRA, ministry of
Agriculture, this combined output is used for the training data. The prediction is for each coming agriculture
season in the country.
Index Terms— Customer Productivity, Data Science; Data Analysis, Cloud, JSON, Dataset, Data Warehouse, Docker, Docker image, Machine Learning, Scikit Learn Adaboost, Random Forest, Ordinary Least Squares (OLS).
ZINA Lacina, SUN Yi
Department of Informations Systems, Kobe Institute of Computing, JAPAN
Cite: ZINA Lacina, SUN Yi, "Corn Growth Prediction for the Upcoming Season in Burkina Faso.," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 413-419, Hong Kong, 15-17 June, 2019.