Internet of Things based Predictive Crop Yield Analysis: A Distributed Approach

Fausto Vizcaíno Naranjo, Fredy Cañizares Galarza, Edmundo Jalón Arias

Universidad Regional Autónoma de los Andes (UNIANDES), Ecuador

Email: ua.faustovizcaino@uniandes.edu.ec; dir.santodomingo@uniandes.edu.ec; uq.sistemas@uniandes.edu.ec

Abstract

The intersection of IoT technology and machine learning has ushered in a new era of precision agriculture, offering innovative solutions to the pressing challenges of food security and environmental sustainability. This paper presents a comprehensive study on the integration of IoT sensors and machine learning techniques for crop yield prediction, with a focus on the ten most consumed crops worldwide. Leveraging a wealth of historical data encompassing environmental variables, pest conditions, and crop-specific attributes collected by IoT sensors, we develop and rigorously evaluate a predictive model employing gradient-boosting regressors. Our findings reveal that the proposed model excels in capturing the intricate relationships between IoT sensor data and crop yield predictions, outperforming established ML regressors in a series of comprehensive experimental comparisons. These results underscore the potential of data-driven decision-making in agriculture, equipping farmers and policymakers with tools to optimize resource allocation, risk management, and sustainable farming practices. In the context of a growing global population and changing climate, the insights from this research hold significant promise for transforming precision agriculture and enhancing global food production.

Keywords: Precision Agriculture, IoT Sensors; Agriculture Technology; Sensor Data Analysis; Data-driven Farming, Smart Farming; Predictive Analytics; Agricultural IoT; Sensor Networks.