In Situ Monitoring of Nitrate Content in Leafy Vegetables Using Attenuated Total Reflectance − Fourier-Transform Mid-infrared Spectroscopy Coupled with Machine Learning Algorithm

Vegetables are one of the most important nitrate sources of human diary diet. Establishing of fast and accurate in situ nitrate monitoring approaches that could be used in the plant growth process and vegetable markets is essential. Incorporating the unique feature of N − O asymmetric stretch absorption in the mid-infrared region (1500–1200 cm −1 ), portable attenuated total reflectance–Fourier-transform infrared (ATR-FTIR) spectroscopic instrument, along with the Euclidean distance-modified extreme learning machine (ED-ELM) model, was firstly employed to evaluate the nitrate contents in leafy vegetables. A total of 1224 samples of four popular vegetables (Chinese cabbage, water spinach, celery, and lettuce) were analyzed. The results indicated that the coefficient of variation of nitrate contents between different vegetable samples was large (20–30%) and the value of mean values has highly exceeded the World Health Organization (WHO)–specified maximum tolerance limits. Chinese cabbage: 7550 ± 1664 mg kg −1 ; water spinach: 4219 ± 1029 mg kg −1 ; celery: 4164 ± 1214 mg kg −1 ; lettuce: 4322 ± 1024 mg kg −1 ). Moreover, The ED-ELM model showed a better performance with the RMSE P of 799.7 mg kg −1 (calibration range from 805 to 14,104 mg kg −1 and validation range from 2132 to 11,793 mg kg −1 ), R 2 of 0.93, RPD of 2.22, the optimized calibration dataset number of 100, and the number of hidden neurons of 30. The results confirmed that ATR-FTIR, along with the suitable model algorithms, could be used as a potential rapid and accurate method to monitor the nitrate contents in the fields of agriculture and food safety. Graphical Abstract