Abstract
In the midst of growing concern about global warming, which has become of great importance more than ever, a concerted international effort is needed to limit the temperature rise to around 1.5 degrees Celsius. To mitigate the worst impact of climate change, a global effort to achieve net zero by 2050 is a must, which is essential to cut the emissions to close to zero while the rest is captured from the atmosphere. This ambitious goal would not be possible without proper coordination and active participation from the waste management sector and industries, which significantly contribute to global greenhouse gas emissions. It is necessary that the net zero is aligned with all the actors to cover the scope of controlling emissions occurring at the source and emissions associated with the production of energy consumed by the industry. This also includes the indirect emissions derived from the industry's activities from sources that are not managed by the industry itself. It is understood that at this global scale, the collection of data, processing, and analytics to reach the targeted net zero becomes nearly impossible for humans to handle. The application of artificial intelligence (AI), especially machine learning and deep learning, among other subsets, could be instrumental in collecting, processing, and analysing big data in real-time with automation and optimisation and elucidating trends and patterns of emission and waste generation from industries, to name a few. This study aims to systematically assess and map the research trend, potentials of AI toward accomplishing net zero, and barriers to AI application in pollution reduction and waste management. This systematic review and mapping as complementary approaches could offer vital insights for further decision-making among inter-governmental agencies.
