Scholarlink

<p>Global food security confronting unforeseen due to a rising population, climate variability and environmental stressors. While digital transformation is rapid, the agriculture sector exacting cohesive integration of advanced technologies to transition from conventional agriculture practices to agriculture 5.0 and 6.0 for a sustainable future. This study critically evaluates the synergistic integration of emerging technologies and geospatial intelligence for smart agriculture, while identifying literature gaps and future research directions. This study followed PRISMA framework for the studies published from 2010 to 2026. Based on the predefined keyword combinations related to AI, smart agriculture, and geospatial technologies, 43 eligible studies were selected for detailed case study analysis. The study synthesizes the integration of artificial intelligence (AI) models, Machine Learning (ML), Deep Learning (DL), Convolutional Neural Networks (CNNs), spatiotemporal deep learning (SDL), transformers, multimodal data fusion strategies and transfer learning with geospatial tools including GIS, Remote Sensing, GPS, UAVs, satellite imagery, LiDAR and IoT based sensing systems. AI and geospatial integration significantly enhance prediction accuracy rate, spatial resolution, yield forecasting, soil assessment, pest and disease detection, and real time decision making in crop monitoring. Multi source data fusion improves scalability and sustainability outcomes, which helps to achieve the sustainable development goals (SDGs). However, challenges persist in infrastructure limitations, data interoperability, high implementation costs, and technical expertise gaps. This study bridges key technical gaps and provides an integrative analytical framework linking AI algorithms with geospatial platforms. The study addresses modern computational themes, such as SDL and transformers, multi modal data fusion strategies, and transfer learning. This study presents a strategic roadmap for developing resource efficient agricultural systems, supporting sustainable intensification and global food security.</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

Artificial Intelligence and Geospatial Synergy for Smart Agriculture: Next Generation Farming Future

  • 期刊论文

  • 发表日期：

    2026年7月28日

查看全文
  • Subhrajit Mandal,
  • Anamika Yadav,
  • A. K. Priya,
  • Alagar Karthick

摘要

Global food security confronting unforeseen due to a rising population, climate variability and environmental stressors. While digital transformation is rapid, the agriculture sector exacting cohesive integration of advanced technologies to transition from conventional agriculture practices to agriculture 5.0 and 6.0 for a sustainable future. This study critically evaluates the synergistic integration of emerging technologies and geospatial intelligence for smart agriculture, while identifying literature gaps and future research directions. This study followed PRISMA framework for the studies published from 2010 to 2026. Based on the predefined keyword combinations related to AI, smart agriculture, and geospatial technologies, 43 eligible studies were selected for detailed case study analysis. The study synthesizes the integration of artificial intelligence (AI) models, Machine Learning (ML), Deep Learning (DL), Convolutional Neural Networks (CNNs), spatiotemporal deep learning (SDL), transformers, multimodal data fusion strategies and transfer learning with geospatial tools including GIS, Remote Sensing, GPS, UAVs, satellite imagery, LiDAR and IoT based sensing systems. AI and geospatial integration significantly enhance prediction accuracy rate, spatial resolution, yield forecasting, soil assessment, pest and disease detection, and real time decision making in crop monitoring. Multi source data fusion improves scalability and sustainability outcomes, which helps to achieve the sustainable development goals (SDGs). However, challenges persist in infrastructure limitations, data interoperability, high implementation costs, and technical expertise gaps. This study bridges key technical gaps and provides an integrative analytical framework linking AI algorithms with geospatial platforms. The study addresses modern computational themes, such as SDL and transformers, multi modal data fusion strategies, and transfer learning. This study presents a strategic roadmap for developing resource efficient agricultural systems, supporting sustainable intensification and global food security.