Maintaining an effective risk management procedure can counterbalance a critical effect on supply chains. The Agri-food supply chain has characteristics that are unique and complex if compared with a conventional supply chain. Sustainability risk management in the supply chain is the key to a competitive organisation in the long term. The aim of this paper is to review current research on sustainable risk management in the Agri-food industry chain. These reviews were arranged in steps systematically, ranging from searching related to review of supply chain sustainability risk management (SCSRM), reviewing the general framework of SCSRM and the framework of Agri-food SCSRM. Selection of literature review papers in the period 2010-2019, and obtained 30 papers. Risk aspects were analysed using a multi-dimensional approach (economic, social, environmental, technical, and institutional) that influences the sustainability of the Agri-food industry. The results show that there are few studies focusing on risk management to achieve a sustainable supply chain system. Some studies only focus on Triple Bottom Line elements (economic, social, and environmental). Sometimes, these studies do not consider risks from other elements such as technical and institutional aspects that can be influence the sustainability of the Agri-food industry. Technical aspects such as the reliability of technological systems and institutional aspects as policymakers support sustainability in a business process. The contribution of this paper is to provide an initial theoretical framework to guide researchers in analysing risk through a multi-dimensional approach to sustainability.

The agri-food supply chain consists of activities in “farm-to-fork” order, including agriculture (i.e., land cultivation and crop production), production processes, packaging, warehousing systems, distribution, transportation, and marketing. Data analytics hold the key to ensuring future food security, food safety, and ecological sustainability. While emerging ‘smart’ technologies such as the internet of things, machine learning, and cloud computing can change production management practices. The current study presents a systematic review of machine learning (ML) applications in the agri-food supply chain. This framework identifies the role of ML algorithms in providing real-time analytical insights to assist proactive data-driven decision-making processes in the agri-food supply chain. It also guides researchers, practitioners, and policymakers on successful management to increase the productivity and sustainability of agri-food.

The demand for specialty coffee has increased over the past few years, and several cafes and coffee roasteries are starting to enter the market. Coffee roasting is considered art rather than science that requires a lot of experience from a master roaster. The key parameters used to identify the roast status of the beans are the initial temperature and roasting time from bean samples. The degree of roasting is often the first consideration for consumers when buying coffee. Some of the flavor attributes used to assess coffee are body, aroma, and acidity. Many studies have been done to evaluate the quality of roasted coffee experimentally using different parameters. However, these techniques could not be implemented in real-time and have their limitations. The current need for roasteries is a method of controlling the quality of roasted coffee through risk and a real-time approach. This paper presents a review carried out the methods used to determine roasting degree on risk perspective. This review has covered recent research on coffee roasting evaluation methods on physical, physicochemical, and chemical composition changes.