DeepWaste Logo.png

DeepWaste research has been published and won national research awards

DeepWaste: Applying Deep Learning to Waste Classification for a Sustainable Planet


Accurate waste disposal, at the point of disposal, is crucial to fighting climate change. When materials that could be recycled or composted get diverted into landfills, they cause the emission of potent greenhouse gases such as methane. Current attempts to reduce erroneous waste disposal are expensive, inaccurate, and confusing. In this work, we propose DeepWaste, an easy-to-use mobile app, that utilizes highly optimized deep learning techniques to provide users instantaneous waste classification into trash, recycling, and compost. We experiment with several convolution neural network architectures to detect and classify waste items. Our best model, a deep learning residual neural network with 50 layers, achieves an average precision of 0.881 on the test set. We demonstrate the performance and efficiency of our app on a set of real-world images.

Published in NeurIPS 2020 Climate Change AI Workshop



A device is disclosed which includes a processor, a screen, and either or
both of a camera and a microphone. The device may receive input related to a waste item, identify the waste item, classify a disposal type for the waste item, and provide a suggestion for disposing of the waste item.

Patent Issued in November of 2021

DeepWaste has won several research awards. These awards and grants go directly into improving DeepWaste.

DeepWaste: Applying Artificial Intelligence for Waste Classification to Combat Climate Change

1) National JSHS Finalist in Environmental Science (2021)

2) US Department of Environmental Quality Grant (2020)

3) 1st Place Chevron Innovation Award at Golden Gate STEM Fair (2021)

4) Ricoh USA Sustainability Award at Golden Gate STEM Fair (2021)

5) Joey Kovacevich Social Innovation Fellowship (2019)