Nasslahsen et al. (2025) AI and IoT in Precision Agriculture: Image Classification in Action

Identification

• Journal: Lecture notes in networks and systems
• Year: 2025
• Date: 2025-10-07
• Authors: Zineb Nasslahsen, Nawal Zaakour, El Mehdi Elaroussi, Karim Abouelmehdi
• DOI: 10.1007/978-3-032-01536-5_120

Research Groups

ELITES Laboratory, Computer of Science Department, Chouaib Doukkali University, El Jadida, Morocco

Short Summary

This paper reviews the recent advancements and applications of AI and IoT in precision agriculture, specifically focusing on image classification for tasks such as disease and pest detection, crop health monitoring, phenotyping, and weed detection. It highlights how the integration of deep learning models with IoT devices enables real-time, data-informed decision-making in smart farming.

Objective

• To assess and focus on the recent contributions and applications of AI-powered image classification, integrated with IoT, across various domains of precision agriculture.

Study Configuration

• Spatial Scale: Various agricultural settings (conceptual review of applications).
• Temporal Scale: Recent developments and real-time application capabilities for continuous monitoring.

Methodology and Data

• Models used: Deep learning models, including Convolutional Neural Networks (CNNs).
• Data sources: Visual data (images) and environmental sensor data, collected via Internet of Things (IoT) devices. Data processing leverages edge and cloud computing.

Main Results

• The combination of AI and IoT significantly enhances smart farming by providing real-time control, monitoring, and automation with data-informed decision-making.
• AI-powered image classification is crucial for identifying crops, diseases, agricultural pests, monitoring crop health, phenotyping, and detecting weeds.
• Deep learning models, such as CNNs, continuously improve the classification of visual data.
• IoT devices facilitate constant collection of both visual and environmental sensor data, improving response detection.
• Edge and cloud computing enable efficient processing and analysis of large volumes of image data.

Contributions

• Provides a focused review of recent contributions of AI and IoT in agricultural image classification.
• Emphasizes the synergistic benefits of integrating AI (particularly deep learning) with IoT for real-time, data-driven decision-making in precision agriculture.
• Categorizes and discusses diverse applications of this combined technology, showcasing its impact on various aspects of smart farming.

Funding

Not explicitly mentioned in the provided text.

Citation

@article{Nasslahsen2025AI,
  author = {Nasslahsen, Zineb and Zaakour, Nawal and Elaroussi, El Mehdi and Abouelmehdi, Karim},
  title = {AI and IoT in Precision Agriculture: Image Classification in Action},
  journal = {Lecture notes in networks and systems},
  year = {2025},
  doi = {10.1007/978-3-032-01536-5_120},
  url = {https://doi.org/10.1007/978-3-032-01536-5_120}
}