.png){kind=icon}
.png){kind=icon}
Return
Use of Artificial Intelligence in post-harvest losses management: a current insight
.png){kind=icon}
PRE
AI
H
F
M
A
A
A
G
M
M
M
S
M
L
F
M
DOI：10.1007/s00217-026-05237-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Post-harvest losses remain a major challenge in agri-food systems, particularly in the Global South, where poor handling, storage, and distribution practices cause significant crop waste. These losses weaken food security and create economic and environmental pressure. Artificial Intelligence is increasingly explored as a solution to improve post-harvest efficiency. This review summarizes current applications of AI in post-harvest loss management, focusing on machine learning, deep learning, computer vision, predictive analytics, and Internet of Things technologies. Their roles in real-time monitoring, quality evaluation, spoilage prediction, sorting, and supply chain optimization are highlighted. AI-based tools improve the accuracy of detecting deterioration, forecasting shelf life, and optimizing storage and logistics, leading to reduced losses and better product quality. However, high costs, limited expertise, infrastructure gaps, and data concerns hinder adoption, especially in developing regions. Overall, AI integration offers clear benefits for reducing waste, improving efficiency, and enhancing food security.
Keywords:
Post-harvest losses
Food security
Artificial Intelligence
Machine learning
Internet of Things
Food loss
Deep learning
Robotics and automation
Supervised and unsupervised learning
Future direction
Journal
IF:
3.2
Papers:
6.3K
Citations:
1.3W
Organization
Cited Papers