Scholarlink

<p>The adoption of artificial intelligence in agriculture has significantly improved productivity and resource efficiency, yet challenges such as uncertain crop management, weather dependency, and computational inefficiencies persist. To address these limitations, this study proposes the Stacked Recurrent Generative Adversarial-based Crossover Greylag Goose algorithm, an advanced AI-driven approach for optimizing smart farming systems. The Stacked Recurrent Generative Adversarial-based Crossover Greylag Goose algorithm integrates Stacked Recurrent Neural Networks for sequential data processing, Generative Adversarial Networks for synthetic data augmentation, and the Greylag Goose Optimization method with a crossover strategy to enhance model accuracy while reducing computational complexity. Furthermore, the effectiveness of the proposed method is evaluated using key metrics such as F1-Score, accuracy, precision, recall, and sensitivity. Experimental results demonstrate that the proposed algorithm achieves an impressive accuracy of 98.5%, encouraging farmers to adopt smart farming practices confidently. These findings highlight the potential of SRGA-CGG in enhancing precision agriculture, improving decision-making, and promoting sustainable farming practices.</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

Advancing environmental sustainability in agriculture through AI: a study on the SRGA-CGG algorithm

  • 期刊论文

  • 发表日期：

    2025年5月3日

查看全文
  • Shevanthe Sekar,
  • E. Sathiyamoorthy

摘要

The adoption of artificial intelligence in agriculture has significantly improved productivity and resource efficiency, yet challenges such as uncertain crop management, weather dependency, and computational inefficiencies persist. To address these limitations, this study proposes the Stacked Recurrent Generative Adversarial-based Crossover Greylag Goose algorithm, an advanced AI-driven approach for optimizing smart farming systems. The Stacked Recurrent Generative Adversarial-based Crossover Greylag Goose algorithm integrates Stacked Recurrent Neural Networks for sequential data processing, Generative Adversarial Networks for synthetic data augmentation, and the Greylag Goose Optimization method with a crossover strategy to enhance model accuracy while reducing computational complexity. Furthermore, the effectiveness of the proposed method is evaluated using key metrics such as F1-Score, accuracy, precision, recall, and sensitivity. Experimental results demonstrate that the proposed algorithm achieves an impressive accuracy of 98.5%, encouraging farmers to adopt smart farming practices confidently. These findings highlight the potential of SRGA-CGG in enhancing precision agriculture, improving decision-making, and promoting sustainable farming practices.