Towards Precision Agriculture Through Crop Classification: A Machine Learning Approach

One essential pillar of the global economy is agriculture. However, the population has surpassed its growth rate regarding land used for cultivation. Consequently, increasing agricultural productivity to meet the demand for food and other derived agricultural products is paramount. The latter can be achieved by exploiting technological advancements, particularly artificial intelligence (AI) through machine learning (ML) models towards precision agriculture. Accordingly, we propose a solution within the pre-harvest stage for crop prediction. Our study analyzes the performance of different ML algorithms and data processing techniques. Moreover, the classification with these models was performed by applying the traditional holdout strategy and cross-validation. Results obtained in two experimental data sets surpass the 99 % accuracy. Ultimately, our solution avoids costly initial investments in hardware and seeks to improve agricultural production productivity through enhanced decision-making with AI.