A Review Of Precision And Innovative Farming For Nigerian Farmers

This study successfully developed a logistic regression model (LRM), a machine learning algorithm to assess farmers’ perceptions of precision agriculture (PA) based on key factors such as gender, educational level, farming experience, household size, farm income, access to credit, farm size, and awareness of precision farming. Python programming language was the primary language, utilizing libraries such as numpy, scikit-learn, matplotlib, and seaborn for data processing, model building, and visualization. The dataset comprised 350 samples and was split into training (70%) and testing (30%) sets. The model achieved an accuracy of 81.9%, with a recall of 97.7%, F1 score of 0.899, and precision of 83.3%, demonstrating its effectiveness in identifying positive perceptions of PA. The confusion matrix showed a true positive rate of 84 and a false positive rate of 17, suggesting a need for model improvement in handling false positives. The ROC curve showed an AUC of 0.58 indicating that the model has no discriminatory ability. Overall, the findings suggest that the highlighted factors influence farmers’ perceptions of PA. Python proved highly efficient for implementing this machine learning-based study