View in EDS

Data centric Artificial Intelligence for agrifood domain: A systematic mapping study.

Saved in:
Bibliographic Details
Title: Data centric Artificial Intelligence for agrifood domain: A systematic mapping study.
Authors: Benfenati, Domenico1 (AUTHOR) domenico.benfenati@unina.it, Amalfitano, Domenico1 (AUTHOR) domenico.amalfitano@unina.it, Russo, Cristiano1 (AUTHOR) cristiano.russo@unina.it, Tommasino, Cristian1 (AUTHOR) cristian.tommasino@unina.it, Rinaldi, Antonio Maria1 (AUTHOR) antoniomaria.rinaldi@unina.it
Source: Computers & Electronics in Agriculture. Dec2025:Part A, Vol. 239, pN.PAG-N.PAG. 1p.
Subjects: Artificial intelligence, Data quality, Reproducible research, Agricultural industries, Crop science, Acquisition of data, Pest control
Abstract: The agrifood sector is progressively utilizing Artificial Intelligence to address challenges related to food production, environmental sustainability, and resource efficiency. However, the quality, availability and integration of data continue to represent significant obstacles in the development of reliable AI systems. The paradigm of Data-Centric Artificial Intelligence entails a shift in focus from solely optimizing models to prioritizing the enhancement of data quality, thus facilitating the development of robust AI solutions. To investigate the adoption of this paradigm, we conducted a systematic mapping study of data-centric artificial intelligence approaches in the agrifood domain over the past decade. Our review process identified 31 primary studies that employed Data-Centric Artificial Intelligence techniques in areas such as crop monitoring, pest detection, soil quality assessment, and yield optimization. The findings of our mapping reveal a growing use of methods such as data augmentation, dataset creation, and data quality enhancement. However, we also highlighted limited dataset standardization and challenges to reproducibility. The objective of this review is to provide a comprehensive overview of the latest advancements and prospects in Data-Centric Artificial Intelligence for agricultural and food industry applications. • This review maps Data-Centric AI research in Agrifood for the last ten years. • Data quality, augmentation, and dataset creation are key focus areas in current studies. • Pest detection and crop monitoring are the most targeted Agrifood applications. • Lack of open datasets and code limits reproducibility in many Agrifood studies. • Insights support researchers in enhancing Data-Centric AI approaches for Agrifood. [ABSTRACT FROM AUTHOR]
Copyright of Computers & Electronics in Agriculture is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:The agrifood sector is progressively utilizing Artificial Intelligence to address challenges related to food production, environmental sustainability, and resource efficiency. However, the quality, availability and integration of data continue to represent significant obstacles in the development of reliable AI systems. The paradigm of Data-Centric Artificial Intelligence entails a shift in focus from solely optimizing models to prioritizing the enhancement of data quality, thus facilitating the development of robust AI solutions. To investigate the adoption of this paradigm, we conducted a systematic mapping study of data-centric artificial intelligence approaches in the agrifood domain over the past decade. Our review process identified 31 primary studies that employed Data-Centric Artificial Intelligence techniques in areas such as crop monitoring, pest detection, soil quality assessment, and yield optimization. The findings of our mapping reveal a growing use of methods such as data augmentation, dataset creation, and data quality enhancement. However, we also highlighted limited dataset standardization and challenges to reproducibility. The objective of this review is to provide a comprehensive overview of the latest advancements and prospects in Data-Centric Artificial Intelligence for agricultural and food industry applications. • This review maps Data-Centric AI research in Agrifood for the last ten years. • Data quality, augmentation, and dataset creation are key focus areas in current studies. • Pest detection and crop monitoring are the most targeted Agrifood applications. • Lack of open datasets and code limits reproducibility in many Agrifood studies. • Insights support researchers in enhancing Data-Centric AI approaches for Agrifood. [ABSTRACT FROM AUTHOR]
ISSN:01681699
DOI:10.1016/j.compag.2025.110847