Scholarlink

<p>Modern agriculture, at the crossroads of productivity and sustainability, is rapidly evolving from empirical methods to data-driven management through Internet of Things (IoT) and Artificial Intelligence (AI), marking the rise of Agriculture 4.0. Although Agriculture 4.0 has been widely studied, its application remains little explored in resource-limited areas, such as farming communities in underdeveloped and developing countries like Senegal, which face the challenges of food self-sufficiency and where agriculture remains traditional. The integration of smart technologies offers a strategic response to the challenges of food security and climate change by improving the productivity, sustainability, and efficiency of agricultural resources. This study therefore aims to address the lack of relevant analysis on the contributions of these technologies for sustainable and resilient agricultural systems. This paper explores several facets of Agriculture 4.0 through a study of the main agronomic indicators and environmental factors in order to analyse their influences on agricultural yield performance. A taxonomy of agricultural data highlighting their heterogeneity and legal issues has also been proposed. In fact, this paper deeply reviews the main aspects of Agriculture 4.0, identifying IoT and AI solutions deployed in various agricultural contexts and themes. This exhaustive sample of solutions is based on 100 recent and relevant research papers, from 2023 to 2025, in various online scientific databases, such as Springer, IEEE, MDPI, Science Direct, PMC, and Google Scholar. It also emerges from this study that the most used communication and data transmission technologies are LoRa and Wi-Fi, while AI algorithms, such as Random Forest and Convolutional Neural Networks (CNN) are commonly applied in predictive yield modelling and resource management optimization. Moreover, this work identifies advantages and limitations on smart agriculture proposals based on IoT and AI technologies, and discusses the key-challenging open research issues and solutions that need to be addressed to provide guidelines for innovative contributions that drive sustainable and productive agriculture.</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

Review of smart agriculture for resource-limited areas highlighting limits, opportunities and key-challenges for sustainable IoT and AI-based solutions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月24日

查看全文
  • Alioune Cisse,
  • Ousmane Diallo,
  • EL Hadji Malick Ndoye,
  • Ousseynou Sene

摘要

Modern agriculture, at the crossroads of productivity and sustainability, is rapidly evolving from empirical methods to data-driven management through Internet of Things (IoT) and Artificial Intelligence (AI), marking the rise of Agriculture 4.0. Although Agriculture 4.0 has been widely studied, its application remains little explored in resource-limited areas, such as farming communities in underdeveloped and developing countries like Senegal, which face the challenges of food self-sufficiency and where agriculture remains traditional. The integration of smart technologies offers a strategic response to the challenges of food security and climate change by improving the productivity, sustainability, and efficiency of agricultural resources. This study therefore aims to address the lack of relevant analysis on the contributions of these technologies for sustainable and resilient agricultural systems. This paper explores several facets of Agriculture 4.0 through a study of the main agronomic indicators and environmental factors in order to analyse their influences on agricultural yield performance. A taxonomy of agricultural data highlighting their heterogeneity and legal issues has also been proposed. In fact, this paper deeply reviews the main aspects of Agriculture 4.0, identifying IoT and AI solutions deployed in various agricultural contexts and themes. This exhaustive sample of solutions is based on 100 recent and relevant research papers, from 2023 to 2025, in various online scientific databases, such as Springer, IEEE, MDPI, Science Direct, PMC, and Google Scholar. It also emerges from this study that the most used communication and data transmission technologies are LoRa and Wi-Fi, while AI algorithms, such as Random Forest and Convolutional Neural Networks (CNN) are commonly applied in predictive yield modelling and resource management optimization. Moreover, this work identifies advantages and limitations on smart agriculture proposals based on IoT and AI technologies, and discusses the key-challenging open research issues and solutions that need to be addressed to provide guidelines for innovative contributions that drive sustainable and productive agriculture.