Machine Learning as a Strategic Tool for Helping Cocoa Farmers in Côte D’Ivoire

Sep 17, 2026

Machine learning is presented as a practical approach for social good in smart agriculture, combining environmental benefits with actionable support for small cocoa farmers and regional decision-makers. The work describes how low-cost or open-source AI tools, spanning hardware, software, and open data, can address climate change impacts. Two tasks are developed: mobile-image detection of healthy versus damaged cocoa using YOLOv5m, and large-scale water management forecasting via a new CIWA-net deep neural architecture fed by remote sensors from GRACE NASA and ERA5. Model performance is compared against a baseline CNN.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

Abstract

Introduction

The Complex System That Causes and Is Implied in Anthropological Climate Change

Article Machine Learning as a Strategic Tool for Helping Cocoa Farmers in Côte D’Ivoire Stefano Ferraris, Rosa Meo, Stefano Pinardi, Matteo Salis and Gabriele Sartor Special Issue Artificial Intelligence and Sensors II Edited by Dr. Miguel García-Pineda and Dr. Miguel Arevalillo-Herráez [https://doi.org/10.3390/s23177632](https://doi.org/10.3390/s23177632) sensors Article Machine Learning as a Strategic Tool for Helping Cocoa Farmers in Côte D’Ivoire Stefano Ferraris 1,†, Rosa Meo 2, *,†, Stefano Pinardi 3, Matteo Salis 2 and Gabriele Sartor 2 Citation: Ferraris, S.; Meo, R.; Pinardi, S.; Salis, M.; Sartor, G. Machine Learning as a Strategic Tool for Helping Cocoa Farmers in Côte D’Ivoire. Sensors 2023, 23, 7632 . [https://doi.org/10.3390/s23177632](https://doi.org/10.3390/s23177632) Academic Editors: Miguel García-Pineda and Miguel Arevalillo-Herráez Received: 1 August 2023 Revised: 29 August 2023 Accepted: 30 August 2023 Published: 3 September 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Interuniversity Department of Regional and Urban Studies and Planning, Politecnico di Torino and University of Turin, 10125 Turin, Italy; stefano.ferraris@polito.it 2 Department of Computer Science, University of Turin, 10149 Turin, Italy; matteo.salis@unito.it (M.S.); gabriele.sartor@unito.it (G.S.) 3 Department of Foreign Languages, Literatures and Modern Cultures, University of Turin, 10124 Turin, Italy; stefano.pinardi@unito.it * Correspondence: [rosa.meo@unito.it](rosa.meo@unito.it)[ ](rosa.meo@unito.it)† These authors contributed equally to this work. Abstract: Machine learning can be used for social good. The employment of arti􀀂cial intelligence in smart agriculture has many bene􀀂ts for the environment: it helps small farmers (at a local scale) and policymakers and cooperatives (at regional scale) to take valid and coordinated countermeasures to combat climate change. This article discusses how arti􀀂cial intelligence in agriculture can help to reduce costs, especially in developing countries such as Côte d’Ivoire, employing only low-cost or open-source tools, from hardware to software and open data. We developed machine learning models for two tasks: the 􀀂rst is improving agricultural farming cultivation, and the second is water management. For the 􀀂rst task, we used deep neural networks (YOLOv5m) to detect healthy plants and pods of cocoa and damaged ones only using mobile phone images. The results con􀀂rmit is possible to distinguish well the healthy from damaged ones. For actions at a larger scale, the second task proposes the analysis of remote sensors, coming from the GRACE NASA Mission and ERA5, produced by the Copernicus climate change service. A new deep neural network architecture (CIWA-net) is proposed with a U-Net-like architecture, aiming to forecast the total water storage anomalies. The model quality is compared to a vanilla convolutional neural network. Keywords: cocoa farmers; low-cost smart agriculture; remote sensors monitoring; water resources forecasting; YOLO; U-NET; SITS; deforestation; drought prevision; socio-technical transition 1. Introduction The Anthropocene is the geological era that began when human activities had had a global and evident effect on the ecosphere of lands, oceans, and water worldwide. Human actions are driving anthropological climate change (ACC), which is an effect of humans’socio-economical activities. 1.1. The Complex System That Causes and Is Implied in Anthropological Climate Change Climate change includes global warming: Earth’s weather patterns are caused by the emission of greenhouse gases (GHGs), carbon dio

FAQs

How does the study apply machine learning to help cocoa farmers?

It uses AI for social good in smart agriculture by targeting cocoa cultivation improvement and water management, supporting farmers and policymakers with coordinated countermeasures against climate change.

What is the role of YOLOv5m in the proposed approach?

YOLOv5m is used to detect healthy cocoa plants and pods and identify damaged ones using only mobile phone images, and the results indicate clear separation between healthy and damaged cases.

How is large-scale water management handled in the paper?

The work analyzes remote sensing data from GRACE NASA Mission and ERA5 (Copernicus service) and introduces CIWA-net to forecast total water storage anomaly forecasts, comparing it with a vanilla convolutional neural network.

Sep 17, 2026

Uploaded by Seraphina