Singh Gurpreet, Sharma Sandeep
Department of Computer Engineering and Technology, Guru Nanak Dev University, Amritsar, Punjab, India.
Sci Rep. 2025 Mar 17;15(1):9138. doi: 10.1038/s41598-025-93417-3.
Modern agriculture relies more on technology to boost food production. It aims to improve both the quality and quantity of food. This paper introduces a novel TCRM (Transformative Crop Recommendation Model). It uses advanced machine learning and cloud platforms to give personalized crop recommendations. Unlike traditional methods, TCRM uses real-time data. It includes environmental and agronomic factors to optimize recommendations. The system has SMS alerts for remote farmers. It outperforms baseline algorithms like Logistic Regression, KNN(k-nearest neighbor), and AdaBoost. TCRM empowers farmers with actionable insights, reducing resource wastage while boosting yield. By offering region-specific recommendations, it enhances profitability and promotes sustainable agricultural practices. The model has 94% accuracy, 94.46% precision, and 94% recall. Its F1 score is 93.97%. The fivefold cross-validation score is 97.67%. These findings show that the model can improve precision farming. It can make agriculture more sustainable and efficient.
现代农业更多地依赖技术来提高粮食产量。其目标是提高粮食的质量和数量。本文介绍了一种新颖的TCRM(变革性作物推荐模型)。它使用先进的机器学习和云平台来提供个性化的作物推荐。与传统方法不同,TCRM使用实时数据。它包括环境和农艺因素以优化推荐。该系统为偏远地区的农民提供短信提醒。它优于逻辑回归、KNN(k近邻)和AdaBoost等基线算法。TCRM为农民提供可行的见解,减少资源浪费,同时提高产量。通过提供特定地区的推荐,它提高了盈利能力,促进了可持续农业实践。该模型的准确率为94%,精确率为94.46%,召回率为94%。其F1分数为93.97%。五折交叉验证分数为97.67%。这些发现表明该模型可以改善精准农业。它可以使农业更具可持续性和效率。