amirvarsh / mlproject

MLProject

PERFORMANCE ANALYSIS OF MACHINE LEARNING ALGORITHMS FOR AGRICULTURAL GUIDANCE

Abstract:

As the world is trending into new technologies and implementations therefore it is a necessary goal to trend up in agriculture. Various types of researches have been undergone to improve crop cultivation. Precision Agriculture (PA) will have an affected decrease in the cost desired. PA is a farming management concept based on measuring, and responding to inter and intra-field changeability in crops. The purpose of this paper is to facilitate farmers that they can produce a yield in good quantity as well as good quality. The most popular Machine Learning (ML) algorithm is Random Forest (RF) which belongs to the supervised learning technique. It is a method of joining different classifiers to tackle an unpredictable problem and to increase the performance of the model. The proposed method gives an accuracy of 96.5% as compared to existing methods of Artificial Neural Networks and Support Vector Machines. Our algorithm predicts the user, what crop type would be the most suitable for the selected area by processing the environmental factors with the trained sub-models of the main of the system.

PROBLEM IDENTIFICATION

It has been a major problem to identify what crop to grow, any man has adequate space in the owner’s land. Not only domestic lands but also for farming lands.

SOLUTION

Our algorithm predicts the user, what crop type would be the most suitable for the selected area by collecting the environmental factors for plant growth and processing them with the trained sub-models of the main of the system. By using our algorithm that we developed , farmers can improve crop production.

Accuracy Range

Naive Bayes → 0.990909090909091

SVM → 0.029545454545454545

Logistic Regression → 0.9522727272727273

RF → 0.9954545454545455

XGBoost → 0.9902272727272727

ANN →95.1%

CONCLUSION

The results and analysis section presented the performance evaluation of the Random Forest algorithm, a comparative analysis with other algorithms, and the interpretability of the results. The implications of the findings for agricultural practices were discussed, highlighting the improved crop selection, resource management, climate adaptation, and policy planning.