Scholarlink

<p>This study presents a novel deep learning-driven framework for optimizing crop yield in rice and cowpea by integrating advanced neural architectures with metaheuristic optimization techniques. For rice, the framework leverages Graph Neural Networks (GNNs) for soil intelligence, Gorilla Troop Optimization (GTO) for precision fertilizer management, and Swarm Capsule Networks (SCapsNet) for accurate weed–pest detection. For cowpea the framework employed Federated Graph neural network (Fed-GNNs) for soil sensing across farms. Adaptive fertilization was taken care of with the use of GTO and Pest detection was monitored by the use of Hyperbolic Neural Networks (HNNs). Further an efficient yield forecasting was done by using Spiking Neural Networks (SNNs). The evaluation of the framework for both crops achieved enhanced results such as Rice module achieved 97.6% accurate results and Cowpea model achieved 98%. The proposed GTO- enhanced approach outperformed Transformer based baselines by 3–7% and conventional ML models by 7–10%. This double crop framework with swarm intelligence provides a reliable decision support system for precision farming while outperforming the state-of-the-art baselines.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

GTO-enhanced precision farming framework for enhancing rice and Cowpea yield optimization through soil intelligence, fertilizer management and weed detection

  • 期刊论文

  • 发表日期：

    2026年1月12日

查看全文
  • Jyoti Nanwal,
  • Preeti Sethi

摘要

This study presents a novel deep learning-driven framework for optimizing crop yield in rice and cowpea by integrating advanced neural architectures with metaheuristic optimization techniques. For rice, the framework leverages Graph Neural Networks (GNNs) for soil intelligence, Gorilla Troop Optimization (GTO) for precision fertilizer management, and Swarm Capsule Networks (SCapsNet) for accurate weed–pest detection. For cowpea the framework employed Federated Graph neural network (Fed-GNNs) for soil sensing across farms. Adaptive fertilization was taken care of with the use of GTO and Pest detection was monitored by the use of Hyperbolic Neural Networks (HNNs). Further an efficient yield forecasting was done by using Spiking Neural Networks (SNNs). The evaluation of the framework for both crops achieved enhanced results such as Rice module achieved 97.6% accurate results and Cowpea model achieved 98%. The proposed GTO- enhanced approach outperformed Transformer based baselines by 3–7% and conventional ML models by 7–10%. This double crop framework with swarm intelligence provides a reliable decision support system for precision farming while outperforming the state-of-the-art baselines.