Scholarlink

<p>Agriculture, a critical pillar of the global economy, faces persistent challenges related to plant diseases, unpredictable environmental conditions, and declining productivity, all of which impact food security and economic stability. Machine learning, a subset of artificial intelligence, is revolutionizing agricultural practices by enabling data-driven decision-making for plant disease detection and crop yield prediction. Utilizing historical and real-time data, machine learning models have demonstrated accuracy levels of up to 95% in disease identification and have improved crop yield forecasting by 20–30% compared to traditional methods. However, integrating machine learning into conventional farming faces significant barriers, including high initial costs, inconsistencies in data collection, lack of technical expertise among farmers, and infrastructural constraints in rural areas. Additionally, the scalability and interpretability of models remain critical challenges, particularly for smallholder farmers who often lack access to high-quality datasets and sufficient computational resources. This review explores the transformative role of machine learning in agriculture and addresses these integration challenges, emphasizing the need for tailored and scalable solutions. Furthermore, broader implications for sustainability, resource optimization, and economic impact are discussed, providing a comprehensive outlook on future research directions and strategies to facilitate inclusive adoption of artificial intelligence-driven agricultural technologies.</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

The role of machine learning in transforming agricultural practices: insights into crop yield optimization and disease detection

  • 期刊论文

  • 发表日期：

    2025年6月4日

查看全文
  • Agnijit Basu,
  • Abhay Narayan

摘要

Agriculture, a critical pillar of the global economy, faces persistent challenges related to plant diseases, unpredictable environmental conditions, and declining productivity, all of which impact food security and economic stability. Machine learning, a subset of artificial intelligence, is revolutionizing agricultural practices by enabling data-driven decision-making for plant disease detection and crop yield prediction. Utilizing historical and real-time data, machine learning models have demonstrated accuracy levels of up to 95% in disease identification and have improved crop yield forecasting by 20–30% compared to traditional methods. However, integrating machine learning into conventional farming faces significant barriers, including high initial costs, inconsistencies in data collection, lack of technical expertise among farmers, and infrastructural constraints in rural areas. Additionally, the scalability and interpretability of models remain critical challenges, particularly for smallholder farmers who often lack access to high-quality datasets and sufficient computational resources. This review explores the transformative role of machine learning in agriculture and addresses these integration challenges, emphasizing the need for tailored and scalable solutions. Furthermore, broader implications for sustainability, resource optimization, and economic impact are discussed, providing a comprehensive outlook on future research directions and strategies to facilitate inclusive adoption of artificial intelligence-driven agricultural technologies.