PL EN
Improving Crop Yield Predictions in Morocco Using Machine Learning Algorithms
 
More details
Hide details
1
Laboratory of Engineering Sciences and Modeling, Faculty of Sciences - Ibn Tofail University, Campus Universitaire, BP 133, Av. de L'Université, Kenitra, Morocco
 
2
LyRICA – Laboratory of Research in Computer Science, Data Sciences and Knowledge Engineering, School of Information Sciences Rabat, Av. Allal Al Fassi, Rabat, Morocco
 
 
Corresponding author
Rachid Ed-Daoudi   

Laboratory of Engineering Sciences and Modeling, Faculty of Sciences - Ibn Tofail University, Campus Universitaire, BP 133, Av. de L'Université, Kenitra, Morocco
 
 
J. Ecol. Eng. 2023; 24(6):392-400
 
KEYWORDS
TOPICS
ABSTRACT
In Morocco, agriculture is an important sector that contributes to the country's economy and food security. Accurately predicting crop yields is crucial for farmers, policy makers, and other stakeholders to make informed decisions regarding resource allocation and food security. This paper investigates the potential of Machine Learning algorithms for improving the accuracy of crop yield predictions in Morocco. The study examines various factors that affect crop yields, including weather patterns, soil moisture levels, and rainfall, and how these factors can be incorporated into Machine Learning models. The performance of different algorithms, including Decision Trees, Random Forests, and Neural Networks, is evaluated and compared to traditional statistical models used for crop prediction. The study demonstrated that the Machine Learning algorithms outperformed the Statistical models in predicting crop yields. Specifically, the Machine Learning algorithms achieved mean squared error values between 0.10 and 0.23 and coefficient of determination values ranging from 0.78 to 0.90, while the Statistical models had mean squared error values ranging from 0.16 to 0.24 and coefficient of determination values ranging from 0.76 to 0.84. The Feed Forward Artificial Neural Network algorithm had the lowest mean squared error value (0.10) and the highest R² value (0.90), indicating that it performed the best among the three Machine Learning algorithms. These results suggest that Machine Learning algorithms can significantly improve the accuracy of crop yield predictions in Morocco, potentially leading to improved food security and optimized resource allocation for farmers.
Journals System - logo
Scroll to top