Prediction of secondary metabolites in hydroponically produced tomatoes: multivariate influence of abiotic climatic factors as well as photosynthesis and transpiration rates

Summary

This is the first study who presents an approach to predict secondary metabolites content in tomatoes using multivariate time series classification of greenhouse sensor data, which includes climatic conditions as well as photosynthesis and transpiration rates. The aim was to find the necessary conditions in a greenhouse to determine the maximum content of secondary metabolites, as higher levels in fruits can promote human health. For this, we defined multiple classification tasks and derived suitable classification function. Cross-validated high accuracy results demonstrate the effectiveness of the approach. Considering a period of three weeks, we found that PPFD levels between 396.0 μmol/m2s and 511.2 μmol/m2s as well as transpiration rates ranging from 4.4 mg H2O/m2s to 7.47 mg H2O/m2s w