Advancing crop recommendation system with supervised machine learning and explainable artificial intelligence.

Area of Science:

• Agricultural Science
• Computer Science
• Data Science

Background:

• Agriculture is vital for economies, but faces challenges in meeting global food demands due to shrinking arable land.
• Increasing crop productivity is essential to address food security concerns for a growing global population.
• Machine learning (ML) offers potential solutions for optimizing agricultural practices, including crop selection.

Purpose of the Study:

• To develop and evaluate a machine learning model for accurate crop recommendation.
• To leverage soil, weather, and nutrient data for improved agricultural decision-making.
• To integrate Explainable Artificial Intelligence (XAI) for enhanced model interpretability and trust.

Main Methods:

• A crop recommendation dataset was utilized for model training.
• Gradient Boosting, a machine learning algorithm, was employed for crop prediction.
• The model's performance was assessed using accuracy, precision, recall, and F1 score metrics.

Main Results:

• The proposed Gradient Boosting model achieved high performance metrics: 99.27% accuracy, 99.32% precision, 99.36% recall, and 99.32% F1 score.
• The model demonstrated strong capability in recommending suitable crops based on environmental and nutrient parameters.
• The integration of Explainable Artificial Intelligence (XAI) provided detailed insights into the recommendation process.

Conclusions:

• The developed machine learning model offers a highly accurate and reliable tool for agricultural crop recommendation.
• The model's explainability through XAI empowers agronomists with data-driven insights for faster and more precise crop selection.
• This approach contributes to enhancing agricultural productivity and sustainability in the face of global food security challenges.