Publisher

BSIBSI

Journal Computer Science (CO-SCIENCE)Computer Science (CO-SCIENCE) Abstract

Crop recommendation systems play a crucial role in modern agriculture by helping farmers make data-driven decisions to maximize yield, optimize resource use, and ensure sustainable farming practices. By analyzing environmental and soil parameters, these systems can suggest the most suitable crops for specific conditions, reducing the risks of crop failure and improving overall productivity. This study evaluates the performance of five ensemble learning algorithms—Random Forest, Extra Trees, CatBoost, XGBoost, and LightGBM—for multiclass classification in a crop recommendation system. All models achieved high accuracy above 98%, with Random Forest demonstrating the best and most stable performance. The feature importance analysis revealed that climatic factors, particularly rainfall and humidity, contributed the most to prediction outcomes, followed by macronutrients such as potassium, phosphorus, and nitrogen. In contrast, temperature and soil pH showed relatively lower influence. These findings highlight the dominance of climatic factors over soil chemical properties and demonstrate the capability of ensemble learning methods to capture complex data patterns. Random Forest is recommended as the primary model to support more effective land management and crop cultivation strategies.

Conclusion

The findings of this study demonstrate that climatic factors, particularly humidity and rainfall, exert the greatest influence on crop classification, followed by soil nutrients such as potassium and phosphorus.In contrast, nitrogen, temperature, and pH show relatively minor effects.Among the ensemble learning algorithms tested, Random Forest achieved the best and most stable performance, with accuracy, precision, recall, and F1-score values reaching approximately 0.These results emphasize that climatic conditions should be prioritized in data collection and modeling for crop recommendation systems.

Future Research

Further research should investigate the integration of real-time climatic data, remote sensing imagery, and IoT-based agricultural monitoring to enhance model responsiveness and scalability. Additionally, exploring hybrid ensemble frameworks that combine Random Forest with deep learning or metaheuristic optimization techniques could potentially improve predictive accuracy and interpretability. Finally, continued investigation into explainable AI methods is essential to ensure that future crop recommendation systems remain transparent, user-friendly, and applicable for smart, sustainable agricultural decision support, allowing farmers to better understand the rationale behind recommendations and fostering trust in the technology. These advancements will contribute to more robust and adaptable crop recommendation systems capable of addressing the evolving challenges of modern agriculture and supporting sustainable food production practices. The incorporation of diverse datasets from multiple regions will also be crucial for improving the generalization capabilities of the models and ensuring their effectiveness across varying environmental conditions.

References

1. Penerapan Algoritma Random Forest Untuk Klasifikasi Jenis Daun Herbal | Jurnal Teknologi Sistem Informasi.... jurnal.mdp.ac.id/index.php/jtsi/article/view/3176Penerapan Algoritma Random Forest Untuk Klasifikasi Jenis Daun Herbal Jurnal Teknologi Sistem Informasi jurnal mdp ac index php jtsi article view 3176
2. Multi-criteria Agriculture Recommendation System using Machine Learning for Crop and Fertilizers Prediction.... doi.org/10.12944/carj.11.1.12Multi criteria Agriculture Recommendation System using Machine Learning for Crop and Fertilizers Prediction doi 10 12944 carj 11 1 12
3. A Soil Nutrient Assessment for Crop Recommendation Using Ensemble Learning and Remote Sensing. soil nutrient... mecs-press.org/ijisa/ijisa-v17-n3/v17n3-3.htmlA Soil Nutrient Assessment for Crop Recommendation Using Ensemble Learning and Remote Sensing soil nutrient mecs press ijisa ijisa v17 n3 v17n3 3 html

Metadata

File size	595.92 KB
Pages	7
DMCA	Report