Digital- twin enabled dairy farming for greenhouse gas emission tracking

The dairy farming industry plays a pivotal role in the agricultural sector. However, its environmental footprint, especially methane and nitrous oxide emissions, has raised concerns. Historically, the industry has relied on conventional methods to forecast and manage waste production and its subsequent carbon emissions. These methods, while functional, often fall short in terms of net-zero planning for dairy farming where instant and continuous monitoring is required. To address this gap, this study presents a novel framework that combines the capabilities of Digital Twin (DT) technology with the power of Machine Learning (ML). The primary objective of this framework is to pave the way for dairy farming practices that are sustainable and align with net-zero emission targets. The results show that when multi-context datasets are used, carbon emission can be predicted with high accuracy.