The proliferation of artificial intelligence (AI) has brought unprecedented advancements in technology, but it has also raised concerns about its environmental impact, particularly concerning carbon emissions. To address the imperative of environmentally responsible AI, we present in this paper a novel machine learning (ML) pipeline, named CEMAI, meticulously designed to monitor and analyze carbon emissions across the entire lifecycle of ML model development, from data preparation to training and deployment. Our endeavor involves an exhaustive evaluation process underpinned by three distinctive industrial case studies. These case studies are structured around the application of ML models to predict tool wear, estimate remaining useful lifetimes, and detect anomalies in the Industrial Internet of Things (IIoT). Leveraging sensor data originating from CNC machining and broaching operations, our research substantiates empirically the efficacy of carbon emissions as a dependable metric guiding pipeline configuration. The essence of our approach lies in striking a harmonious balance between superior performance and minimal carbon emissions. Our findings reveal the potential to optimize pipeline configurations for ML models in a manner that not only enhances performance but also drastically reduces carbon emissions, thereby underlining the significance of adopting ecologically responsible AI engineering practices.