Support Vector Machine in Precision Agriculture: A review

The Support Vector Machine (SVM) is a Machine Learning (ML) algorithm which may be used for acquiring solutions towards better crop management. The applications of SVM in precision agriculture (PA) are compared by identifying its interactions with variables, comparing its model performance, highlighting its strengths and weaknesses, as well as suggestions for improvements. From the perspective of six ML applications in PA, we confirmed features which may benefit the model in general (e.g. feature selection) or specific applications (e.g. phenology). SVM was found to outperform most models, with an inconclusive comparison with Random Forest (RF) and inferior to Deep Learning (DL). To our knowledge, this review highlights and summarizes recently renewed efforts of improving SVM performance in PA through its integration with DL, which is believed to be an upcoming trend for ML model development in modern PA.

Automated summary

The Support Vector Machine (SVM) shows excellent performance in precision agriculture (PA), with comparisons to other machine learning algorithms highlighting its strengths and weaknesses in model performance and characteristics.