In this talk, we will start from the state-of-the-art techniques for predicting kiwifruit flesh firmness in storage by reviewing two popular types of models, i.e., mechanistic models and data-driven models. The pros and cons of these two types of models will be discussed. Particularly, we will show that a specific mechanistic model for kiwifruit flesh firmness driven by differential equations can be solved analytically, and the spectroscopic data can then be incorporated into the analytic solution as covariates via functional regression. The final model can be regarded as a fusion of mechanistic model and statistical regression model. The prediction performance of proposed model is validated on real kiwifruit data and compared with alternative methods. The results show some promise for future study.

Dr. Xun Xiao is currently a Lecturer in Statistics at the Dept. of Mathematics and Statistics, University of Otago, New Zealand. He received B.Sc. in Statistics from the University of Science and Technology of China, China in 2011 and Ph.D. degree from the Dept. of Systems Engineering and Engineering Management at City University of Hong Kong in 2016. His research focuses on various statistics and data analytics problems arising from interdisciplinary areas, including industrial engineering, natural hazard, veterinary science, food science, etc.