A systematic review of explainable artificial intelligence for spectroscopic agricultural quality assessment

• State-of-the-art XAI methods are discussed. • The application of XAI combined with spectroscopic models for agri-food product quality is reviewed. • Challenges and future trends of spectroscopic XAI methods are outlined. The introduction of complex machine learning models has greatly improved the accuracy and practical use of spectroscopic analyses in agriculture. However, users often struggle to understand how these models operate internally or how specific features contribute to the predictions. This lack of clarity can hinder innovation in agricultural spectroscopy, especially in selecting appropriate spectral wavelengths for domain specific applications or designing portable and low-cost devices.…

• NI
  National Institute of Food and Agriculture

  Award: AM21SCMPMS1010
• FA
  Foreign Agricultural Service