International Journal of Life Science and Agriculture Research

Rwanda’s agriculture sector plays a critical role in the country’s economy, but farmers often face challenges in selecting the most suitable crops for their fields due to recommendation practices that focus primarily on soil nutrient analysis and neglect important factors such as climate variability and geographic altitude. This study presents the development of a data-driven crop recommendation system designed to address these limitations by using various data sources including soil test results, historical and forecast weather patterns, and crop-specific requirements, with machine learning algorithms applied to generate customized crop recommendations. While XGBoost achieved the highest accuracy at 98.25%, the Random Forest model, which achieved an accuracy of 96.7%, was selected for deployment because its better balance between precision and recall helps minimize the risk of resource inefficiencies from incorrect recommendations, and its more evenly distributed feature importance enhances generalizability across diverse farming conditions. The final model was integrated into a scalable analytics platform to ensure usability and impact, demonstrating how combining advanced data analytics with machine learning can enhance decision-making in agriculture, support sustainable farming practices, and improve yields in Rwanda.

Nutrients, predictive modeling, seasonal data, crop yield.

1. C. Qu and X. Hao, “Agriculture drought and food security monitoring over the horn of africa (hoa) from space,” 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics), 08 2018. 
2. “Employment indicators 2000–2022 (october 2024 update),” Statistics, 10 2024. [Online]. Available: https://www.fao.org/statistics/highlights-archive/highlights-detail/ employment-indicators-2000-2022-%28september-2024-update%29/en 
3. Z. Cui and et al., “Pursuing sustainable productivity with millions of smallholder farmers,” Nature, vol. 555, pp. 363–366, 2018. 
4. D. Modi, A. V. Sutagundar, V. Yalavigi, and A. Aravatagimath, “Crop recommendation using machine learning algorithm,” in 2021 5th International Conference on Information Systems and Computer Networks (ISCON). IEEE, 2021, pp. 1–5. 
5. D. TuYizere, V. Uwase, M. Niyonkuru, G. Ndanyunzwe, M. Kabutware, P. Singadi, R. Uwera, and G. Okeyo, “Ai-driven precision farming: A holistic approach to enhance food and nutrition security in africa,” pp. 1–6, 07 2024. [Online]. Available: https://ieeexplore.ieee.org/stamp/ stamp.jsp?tp=&arnumber=10622109 
6. E. Musabanganji and Others, “Improving agricultural productivity in rwanda,” Agroforestry Systems, pp. 112–125, 2019. 
7. R. Kumar and Others, “Hybrid models for crop recommendation,” Agricultural Computing, pp. 78–92, 2021. 
8. A. Cyemezo and Others, “Time-series forecasting for crop yield prediction using multilayer perceptrons,” International Journal of Scientific Research and Publications, vol. 9, no. 7, pp. 22–35, July 2019. 
9. N. Cantore, “The crop intensification program in rwanda: a sustainability analysis.” [Online]. Available: https://rema.gov.rw/rema doc/pei/Report ODI AM.pdf 
10. M. Kabirigi, S. Mugambi, B. S. Musana, G. T. Ngoga, J. C. Muhutu, J. Rutebuka, V. M. Ruganzu, I. Nzeyimana, and N. L. Nabahungu, “Estimation of soil erosion risk, its valuation and economic implications for agricultural production in western part of rwanda,” Journal of Experimental Biology and Agricultural Sciences, vol. 5, pp. 525–536, 09 2017. 
11. H. Amit, “Xgboost vs linear regression: A practical guide.” [Online]. Available: https://medium.com/@heyamit10/ xgboost-vs-linear-regression-a-practical-guide-aa09a68af12b 
12. Sruthi, “Understanding random forest algorithm with examples.” [Online]. Available: https://www.analyticsvidhya.com/blog/2021/06/ understanding-random-forest/