.svg){kind=logo}
A MATHEMATICAL MODEL FOR MULTI-CLASS PREDICTION OF AN INTELLIGENT SWOLLEN SHOOT DISEASE SYSTEM BASED ON AGRO-ENVIRONMENTAL DATA
Keywords:
multinomial logistic regression, swollen shoot, multi-class prediction, precision agriculture, applied artificial intelligenceDOI:
https://doi.org/10.17654/0972087125020Abstract
The cocoa sector, a major economic pillar in West Africa, is facing a concerning phytosanitary threat: Cocoa Swollen Shoot Virus (CSSV), mainly transmitted by mealybugs. This viral disease leads to a progressive decline of plantations, affecting yields and compromising the socio-economic resilience of producers. Faced with the limitations of traditional detection methods, which are often delayed, this study proposes an innovative AI-based approach for predicting CSSV infection stages. Using a multinomial logistic regression model, 250 cocoa plants were simulated with eight agro-environmental variables including plant age, proximity to infection source, soil moisture, ambient temperature, planting density, varietal resistance, phytosanitary treatment, and mealybug level. The supervised classification achieved a recall of 77.4% for healthy plants, but weaker performance for infected classes (21.4% and 6.3%), reflecting the complexity of intermediate stages. An interactive map was generated to geographically visualize predictions, facilitating risk zone prioritization. Additionally, 30-day dynamic simulations showed over 80% loss of healthy plants without intervention. These results confirm the relevance of AI as a predictive tool capable of guiding farmers in their health decisions. Future perspectives include the integration of multi-source data, training on real data, and deployment of embedded tools for predictive, optimized, and sustainable agricultural e-health.
Received: April 20, 2025
Accepted: May 20, 2025
References
F. B. Agusto, M. C. A. Leite, F. Owusu-Ansah, O. Domfeh, N. Hritonenko and B. Chen-Charpentier, Cacao sustainability: The case of cacao swollen-shoot virus co-infection, PLOS ONE 19(3) (2024), e0294579.
https://doi.org/10.1371/journal.pone.0294579.
M. Doumbia, B. Kouassi, A. Touré and K. Yao, Development of bio-solutions for the treatment of cocoa swollen shoot disease: A modeling approach, Journal of Agricultural Research 112 (2024), 78-92.
D. W. Hosmer, S. Lemeshow and R. X. Sturdivant, Applied Logistic Regression, 3rd ed., Wiley, 2013.
I. Fofana, I. Amoako-Attah and A. K. Quainoo, Early detection and spatial analysis of cocoa swollen shoot virus disease using remote sensing and GIS, Precision Agriculture 22(4) (2021), 1054-1072.
https://doi.org/10.1007/s11119-020-09772-z.
A. Al-Sheikh, J. K. Alhassan and A. A. Ibrahim, Deep learning-based detection of cocoa leaf diseases using convolutional neural networks, Computers and Electronics in Agriculture 205 (2023), 107598.
https://doi.org/10.1016/j.compag.2023.107598.
A. S. Adegoke, A. B. Folarin and A. O. Ogunleye, Detection of swollen shoot virus in cacao leaves using deep extraction and ensemble classifiers, International Journal of Agricultural Informatics 13(2) (2022), 45-59.
M. Li, Y. Zhang and J. Huang, Bayesian spatial modeling for prediction of plant viral disease outbreaks: Application to cocoa swollen shoot virus, Environmental Modelling and Software 134 (2020), 104839.
https://doi.org/10.1016/j.envsoft.2020.104839.
K. Kourou, T. P. Exarchos, K. P. Exarchos, M. V. Karamouzis and D. I. Fotiadis, Machine learning applications in cancer prognosis and prediction: A review, Computational and Structural Biotechnology Journal 13 (2015), 8-17.
https://doi.org/10.1016/j.csbj.2014.11.005.
D.-G. Owusu-Manu, M. F. Antwi-Afari, D. J. Edwards and E. A. Pärn, IoT and machine learning for real-time monitoring of cocoa farms in Ghana, Computers in Industry 132 (2021), 103504. https://doi.org/10.1016/j.compind.2021.103504.
A. Niang, M. Diop and B. Sarr, Hybrid machine learning models for forecasting cocoa viral diseases using environmental indicators, African Journal of Agricultural Research 17(12) (2022), 1534-1545.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 PUSHPA PUBLISHING HOUSE, PRAYAGRAJ, INDIA
This work is licensed under a Creative Commons Attribution 4.0 International License.
_________________________
Attribution: Credit Pushpa Publishing House as the original publisher, including title and author(s) if applicable.
Non-Commercial Use: For non-commercial purposes only. No commercial activities without explicit permission.
Contact Puspha Publishing House for more info or permissions.
