The generation of food waste at both suppliers’ and consumers’ levels stems from a complex set of interacting behaviours. Computational and mathematical models provide various methods to simulate, diagnose and predict different aspects within the complex system of food waste generation and prevention. This chapter outlines four different modelling approaches that have been used previously to investigate food waste. Discrete Event Simulation: which has been used to examine how the shelf life of milk and many actions taken around shopping and use of milk within a household influence food waste. Machine Learning and Bayesian networks: which have been used to provide insight into the determinates of household food waste. Agent Based Simulation: which has been used to provide insight into how innovation can reduce retail food waste. Mass Balance estimation which has been used to model and estimate food waste from data related to human metabolism and calories consumed.
The generation of food waste at both the supplier and the consumer levels stems from a complex set of interacting behaviours. Computational and mathematical models provide various methods to simulate, diagnose and predict different aspects within the complex system of food waste generation and prevention. This chapter outlines four different modelling approaches that have been used previously to investigate food waste: discrete event simulation, which has been used to examine how the shelf life of milk and many actions taken around shopping and use of milk within a household influence food waste; machine learning and Bayesian networks, which have been used to provide insight into the determinants of household food waste; agent-based modelling, which has been used to provide insight into how innovation can reduce retail food waste; and mass balance estimation, which has been used to model and estimate food waste from data related to human metabolism and calories consumed.
Modelling approaches to food waste: Discrete event simulation; machine learning; bayesian networks; agent based simulation; and mass balance estimation / Kandemier, Cansu; Reynolds, Christian; Verma, Monika; Grainger, Matthew; Stewart, Gavin; Righi, Simone; Piras, Simone; Setti, Marco; Vittuari, Matteo; Quested, Tom. - (2020), pp. 326-343. [10.4324/9780429462795]
Modelling approaches to food waste: Discrete event simulation; machine learning; bayesian networks; agent based simulation; and mass balance estimation
Simone RIGHI;
2020
Abstract
The generation of food waste at both the supplier and the consumer levels stems from a complex set of interacting behaviours. Computational and mathematical models provide various methods to simulate, diagnose and predict different aspects within the complex system of food waste generation and prevention. This chapter outlines four different modelling approaches that have been used previously to investigate food waste: discrete event simulation, which has been used to examine how the shelf life of milk and many actions taken around shopping and use of milk within a household influence food waste; machine learning and Bayesian networks, which have been used to provide insight into the determinants of household food waste; agent-based modelling, which has been used to provide insight into how innovation can reduce retail food waste; and mass balance estimation, which has been used to model and estimate food waste from data related to human metabolism and calories consumed.File | Dimensione | Formato | |
---|---|---|---|
Chapter_Food Waste_Handbook_Reynolds_20 Part Four - Cansu Kandemier, et al. - Modelling Approaches to Food Waste.pdf
Open access
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
631.18 kB
Formato
Adobe PDF
|
631.18 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris