Plateforme numérique de guides culturaux dans un contexte de changement climatique et de baisse des rendements agricoles

Abstract

Digital platform for cultural guides in the context of climate change and declining agricultural yields

In agriculture, crop yield estimation is essential to improve productivity and decision-making processes such as financial market forecasts and solving food security problems. The main objective of this paper is to have tools to predict and improve crop yield prediction accuracy using machine learning (ML) algorithms such as CART¹, KNN² and SVM³. We have developed a mobile app and web app that use these algorithms for practical use by farmers. Tests show that our system (collection and deployment architecture, web application and mobile application) is operational and allows to validate empirical knowledge on agro-climatic parameters in addition to the proactive decision making. The experimental results obtained on agricultural data and the performance of ML algorithms are compared using cross-validation to identify the most efficient following agricultural data. The applications implemented demonstrate that the proposed approach is effective in predicting crop yields and provides farmers with quick and accurate responses to aid decision-making.

--------------------

¹Classification and Regression Trees

²K-nearest neighbors

³Support Vector Machine

 Keywords: Prediction; Machine learning; Artificial intelligence; Digital agriculture