As the world population grows rapidly nowadays, the demand for food has come to rise. The escalating demand for food has caused substantial wastage and loss, which not only hampers food security efforts but also aggravates greenhouse gas (GHG) emissions, intensifying the environmental crisis. Among numerous countries, Malaysia, with its diverse agricultural profile, emerges as a good fit for our case study. This study chooses the clustering technique to examine food sector data in Malaysia and investigate the link between the clustering results on food data and the data on GHG emissions. This case study aims to find crops depending on their production efficiency, underline those that match major waste, and estimate their contribution to greenhouse gas emissions. Three clustering techniques, Gaussian Mixture Modelling (GMM), Birch, and Density Peak clustering, are applied in the Production and Supply Utilisation Accounts (SUA) datasets, help to identify and cluster crops based on their similar traits to acquire uncovered patterns between the food sector and environmental issues. Using cutting-edge clustering algorithms and visualization tools, this study investigated in-depth the complex interactions among food production, waste, and greenhouse gas emissions in Malaysia. By addressing food production efficiency and waste reduction, the outcome will be a cascade of benefits that not only improve food security but also help to lessen negative environmental effects. This study illuminates the multifaceted dynamics of food production, waste, and environmental impact, offering valuable insights and pathways toward a more sustainable future for Malaysia and potentially other nations.
Read full abstract