Skip to main content Skip to main navigation


Green AutoML for Plastic Litter Detection

Daphne Theodorakopoulos; Christoph Manss; Frederic Theodor Stahl; Marius Lindauer
In: ICLR 2023 Workshop on Tackling Climate Change with Machine Learning. International Conference on Learning Representations (ICLR), None, 2023.


The world’s oceans are polluted with plastic waste and the detection of it is an important step toward removing it. Wolf et al. (2020) created a plastic waste dataset to develop a plastic detection system. Our work aims to improve the machine learning model by using Green Automated Machine Learning (AutoML). One aspect of Green-AutoML is to search for a machine learning pipeline, while also minimizing the carbon footprint. In this work, we train five standard neural architectures for image classification on the aforementioned plastic waste dataset. Subsequently, their performance and carbon footprints are compared to an Efficient Neural Architecture Search as a well-known AutoML approach. We show the potential of Green-AutoML by outperforming the original plastic detection system by 1.1% in accuracy and using 33 times fewer floating point operations at inference, and only 29% of the carbon emissions of the best-known baseline. This shows the large potential of AutoML on climate-change relevant applications and at the same time contributes to more efficient modern Deep Learning systems, saving substantial resources and reducing the carbon footprint.

Weitere Links