Artificial Intelligence in Sustainable Fruit Growing: Innovations, Applications, and Future Prospects

  1. Mohamed Islam Keskes

Reviewed by

Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

Log in to save this article

Abstract

The global demand for nutritious food, coupled with environmental and economic constraints, has driven the need for sustainable agricultural practices, particularly in fruit growing. Artificial intelligence (AI) has emerged as a transformative technology to enhance the sustainability and efficiency of fruit production. This review explores the current landscape of AI applications in sustainable fruit growing, focusing on innovations, practical applications, and future prospects. Key AI technologies, including machine learning, computer vision, robotics, and data analytics, are analyzed for their roles in precision agriculture, pest and disease management, yield prediction, and automated orchard management. Notable advancements include AI models achieving over 98% accuracy in detecting pomegranate fruit diseases and robotics reducing labor costs by up to 95%. These applications contribute to environmental sustainability by minimizing resource waste and chemical use, while also improving economic viability and social well-being. However, challenges such as high costs, data requirements, and technical expertise gaps hinder widespread adoption. Future directions involve developing robust, interpretable AI models, integrating with emerging technologies like IoT and blockchain, and addressing climate change and evolving agricultural challenges. This review underscores AI’s potential to revolutionize sustainable fruit growing, ensuring resilient and environmentally friendly fruit production to meet global food demands.

Article activity feed

  1. PREreview

    This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/15713228.

    In this review manuscript, I realized the author's high expertise, the effort to summarize, analyze, present and explain the data about the AI in agriculture in a very scientific and at the same time understandable way. Specifically, the title is clear, the abstract gives the general overview of the manuscript and the language is properly used. The reader is introduced to the topic smoothly with all the essential information, the materials and methods section is well written, as well as the results and discussion. Overall, this manuscript provides a profound understanding of the innovations, applications and future prospects of AI in the agricultural sector. I believe that it significantly contributes to the literature and paves the way for further research, therefore it deserves to be published and for that reason I propose the following comments, to help improve its content.

    1.       There is a repetition in PomeNetV1 and PomeNetV2.

    2.       In Figure 2, correct the text after the image acquisition.

    3.       Please provide the full name of CAGR.

    4.       In Figure 3, please correct "rainfall forecasts", "Sentinel-2", "Deep Neural Networks", "nutrient deficiencies" and R2=0.85.

    5.       In Figure 4, there are many similar cases like in Figure 3.

    6.       Likewise in Figure 5.

    7.       Regarding the barriers, I would also like to add the high computational resources, the lack of technical support and the unreliable internet access in many rural areas.

    8.       In regards to the future research, making AI more accessible to farmers, could probably be added.

    9.       In Figure 6, there is a 2025 in the end of the x-axis.

    Competing interests

    The author declares that they have no competing interests.

  2. Version published to 10.20944/preprints202504.1813.v2
  3. Version published to 10.20944/preprints202504.1813.v1