According to Yale University, biomass is widely considered a renewable alternative to fossil fuels and many experts say it could play a key role in the fight against climate change. Biomass stores carbon and can be converted into bio-based products and energy that can be used to improve soil, purify wastewater and produce renewable raw materials.
However, economic constraints and challenges in optimizing and controlling biomass conversion have hindered large-scale biomass production.
Yale's School of the Environment has produced a new study, led by Yuan Yao, assistant professor of industrial ecology and sustainable systems, and doctoral candidate Hannah Szu-Han Wang. It provides an analysis of current machine learning applications for biomass and biomass-derived materials (BDM) to determine whether machine learning advances the research and development of biomass products. The study authors found that machine learning has not been applied throughout BDM's life cycle, limiting its ability to develop, Yale said.
Yao's study examines how emerging technologies and industrial development will impact the environment, with a focus on bioeconomy and sustainable production. Wang worked in the production of biomaterials during her master's research. The two researchers said they were interested in continuing this research to find out whether machine learning could help with best practices for creating BDM, a key component of a bio-based economy, and predict their performance as sustainable materials.
“There are so many combinations of biomass raw materials, conversion technologies and BDM applications. If we want to try every combination using the traditional trial-and-error experimental approach, it takes a lot of time, labor, effort and energy. We're already generating a lot of data from these previous experiments, so we're asking ourselves, can we apply machine learning to figure out how to better design BDM?” Yao explains.
For the study, published in Resources, Conservation and Recycling, Yao and Wang reviewed more than 50 papers published since 2008 to understand the capabilities, current limitations and future potential of machine learning in supporting sustainable development and applications of BDM.
Their findings indicated that while a few studies applied machine learning to address data challenges for life cycle assessment, most studies only applied machine learning to predict and optimize the technical performance of biomass conversion and applications. No machine learning applications assessed across the entire lifecycle, from biomass cultivation to BDM production and end-use applications.
“Most studies apply machine learning to only a very small part of the entire BDM life cycle,” Yao said. “Our argument is that if you really want to integrate sustainability into the development of this material, we need to consider the entire life cycle of the materials, from how they are generated to their potential environmental impact. We believe that machine learning has the potential to support sustainability-based designs for biomass materials.”
Wang said the study led to further research into data gaps in machine learning on biomass-derived materials.
“We have found a future direction that people have not yet explored in sustainability assessments for BDM. There needs to be a complete path prediction to increase our understanding of how different factors related to BDM interact and contribute to sustainability.”
Source: Bioenergy-news.com
