Vhatkar Kapil Netaji, Koparde Shweta Ashish, Kothari Sonali, Sarwade Jayesh, Sakur Kishor
Department of Computer Engineering, Dr. D. Y. Patil Institute of Technology, Pimpri, Pune, India.
Symbiosis Institute of Technology - Pune Campus, Symbiosis International (Deemed University), Pune, India.
MethodsX. 2025 Jun 3;14:103418. doi: 10.1016/j.mex.2025.103418. eCollection 2025 Jun.
Improving soil health evaluation and crop output forecasting are essential for developing sustainable agricultural methods. By applying data-driven insights, farmers may optimize resources, increase productivity, and promote environmental sustainability. The intricacy of environmental conditions and the lack of access to trustworthy data make it difficult to anticipate crop yields and evaluate soil health accurately. The goal of this research is•to make sophisticated models for precise crop production forecasting and thorough evaluation of soil health,•to improve sustainability by optimize farming methods, and•to assist farmers in making well-informed decisions.Iterative Partitioning-Ensemble Filter (IP-EF) is a technique used for feature selection, enhancing model performance by iteratively partitioning data and refining feature subsets. Back-propagation Neural Network (BPNN) is an SL algorithm applied for predicting complex patterns, especially in crop yield and soil health assessments. Multi-Source Data Fusion-Geographical Information Systems (MSDF-GIS) combines diverse data sources with GIS to map and analyze spatial agricultural data, improving decision-making for sustainable farming practices. These methods collectively optimize prediction accuracy and resource management. The result shows that the suggested model significant improvement in precision, recall, and F1-Score for crop yield, reaching 93 %, 94 %, and 93 %, implemented using Python software. Future advancements may include real-time monitoring, integrating AI by IoT expedients for dynamic decision-making, and enhancing sustainability by minimizing water usage, fertilizers, and environmental impact in agriculture.
改善土壤健康评估和作物产量预测对于发展可持续农业方法至关重要。通过应用数据驱动的见解，农民可以优化资源、提高生产力并促进环境可持续性。环境条件的复杂性以及缺乏可靠数据使得准确预测作物产量和评估土壤健康变得困难。本研究的目标是：创建用于精确作物产量预测和全面土壤健康评估的复杂模型；通过优化耕作方法提高可持续性；帮助农民做出明智的决策。迭代分区集成滤波器（IP-EF）是一种用于特征选择的技术，通过迭代划分数据和细化特征子集来提高模型性能。反向传播神经网络（BPNN）是一种用于预测复杂模式的监督学习算法，尤其适用于作物产量和土壤健康评估。多源数据融合地理信息系统（MSDF-GIS）将不同数据源与GIS相结合，以绘制和分析空间农业数据，改善可持续农业实践的决策。这些方法共同优化了预测准确性和资源管理。结果表明，使用Python软件实现的建议模型在作物产量的精确率、召回率和F1分数方面有显著提高，分别达到93%、94%和93%。未来的进展可能包括实时监测、通过物联网手段集成人工智能以进行动态决策，以及通过减少农业用水、肥料和环境影响来提高可持续性。
