MSGID: 1:317/3 64080f6f   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Study examines potential use of machine learning for sustainable   
   development of biomass    
      
     Date:   
         March 7, 2023   
     Source:   
         Yale University   
     Summary:   
         Machine learning can be valuable in supporting sustainable   
         development of biomass if it is applied across the entire lifecyle   
         of biomass and biomass-derived products, according to a new study.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
   FULL STORY   
   ==========================================================================   
   Biomass is widely considered a renewable alternative to fossil fuels,   
   and many experts say it can play a critical role in combating climate   
   change. Biomass stores carbon and can be turned into bio-based products   
   and energy that can be used to improve soil, treat wastewater, and   
   produce renewable feedstock.   
      
      
   ==========================================================================   
   Yet large-scale production of it has been limited due to economic   
   constraints and challenges to optimizing and controlling biomass   
   conversion.   
      
   A new study led by Yale School of the Environment's Yuan Yao,   
   assistant professor of industrial ecology and sustainable systems, and   
   doctoral student Hannah Szu-Han Wang, analyzed current machine learning   
   applications for biomass and biomass-derived materials (BDM) to determine   
   if machine learning is advancing the research and development of biomass   
   products. The study authors found that machine learning has not been   
   applied across the entire life cycle of BDM, limiting its ability for   
   development.   
      
   Yao's research investigates how emerging technologies and industrial   
   development will affect 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 pursuing this study to find out if machine learning   
   could help with best practices for creating BDM, a chief component of a   
   bio-based economy, as well as predicting their performance as sustainable   
   materials.   
      
   "There are so many combinations of biomass feedstock, conversion   
   technologies, and BDM applications. If we want to try each combination   
   using the traditional trial-and-error experimental approach, this will   
   take a lot of time, labor, effort, and energy. We already generate a   
   lot of data from these past experiments, so we are asking, can we apply   
   machine learning to help us to figure out how we can better design   
   BDM?" Yao explains.   
      
   For the study, which was 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. What they found is 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. None   
   reviewed machine learning applications across the entire lifecycle,   
   from biomass cultivation to BDM production and end-use applications.   
      
   "Most studies are applying machine learning to just a very small part   
   of the entire lifecycle of BDM," Yao says. "Our argument is that if   
   you really want to incorporate sustainability into development of this   
   material, we need to consider the entire lifecycle of the materials, from   
   how they are generated to their potential environmental impact. We believe   
   machine learning has the potential to support sustainability-informed   
   design for biomass-derived materials."  Wang said the study has led to   
   further research on data gaps in machine learning on biomass-derived   
   materials.   
      
   "We found a future direction that people have not yet explored in terms   
   of sustainability assessments for BDM. There needs to be a full pathway   
   prediction to enhance our understanding of how various factors regarding   
   BDM interact and contribute to sustainability," she says.   
      
       * RELATED_TOPICS   
             o Plants_&_Animals   
                   # Ecology_Research # Agriculture_and_Food # Soil_Types #   
                   Animal_Learning_and_Intelligence   
             o Earth_&_Climate   
                   # Sustainability # Environmental_Awareness #   
                   Energy_and_the_Environment # Environmental_Issues   
       * RELATED_TERMS   
             o Biomass o Overfishing o Hydrogen_vehicle o   
             Smoulder o Biomass_(ecology) o Renewable_energy o   
             Computational_neuroscience o Carbon_dioxide_sink   
      
   ==========================================================================   
   Story Source: Materials provided by Yale_University. Note: Content may   
   be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Hannah Szu-Han Wang, Yuan Yao. Machine learning for sustainable   
         development and applications of biomass and biomass-derived   
         carbonaceous materials in water and agricultural systems: A   
         review. Resources, Conservation and Recycling, 2023; 190: 106847   
         DOI: 10.1016/ j.resconrec.2022.106847   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/03/230307174307.htm   
      
   --- up 1 year, 1 week, 1 day, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 226/30 227/114 229/111   
   SEEN-BY: 229/112 113 307 317 400 426 428 470 664 700 292/854 298/25   
   SEEN-BY: 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426