Utilizing advanced language models to identify industrial symbiosis opportunities within the circular economy: Capabilities and challenges

Abstract

PurposeThe aim of this study is to investigate the application of advanced language models, particularly ChatGPT-4, in identifying and utilizing industrial symbiosis opportunities within the circular economy. It examines how the model can aid in promoting sustainable industrial practices by processing data from the MAESTRI project database, which includes various symbiotic relationships, as well as randomly selected waste codes not included in the database. The research involves structured queries related to industrial symbiosis, circular economy, waste codes and potential opportunities. By assessing the model's accuracy in response generation, the study seeks to uncover both the capabilities and limitations of the language model in resource efficiency and waste reduction, emphasizing the need for ongoing refinement and expert oversight.Design/methodology/approachThe study adopts a mixed-methods approach, combining qualitative and quantitative analyses to explore the potential of ChatGPT-4 in identifying industrial symbiosis opportunities. Data from the EU-funded MAESTRI project database, which includes existing symbiotic relationships, as well as randomly selected waste codes not included in the database, are used as the primary sources. The language model is queried with structured questions on industrial symbiosis, circular economy and specific waste codes utilizing the model's advanced functions such as file upload. Responses are evaluated by comparing them with the MAESTRI database and official European Waste Catalogue (EWC) codes.FindingsThe study finds that ChatGPT-4 possesses a solid understanding of fundamental concepts related to industrial symbiosis and the circular economy. However, it encounters challenges in accurately describing EWC codes, with a notable portion of descriptions found to be incorrect. Despite these inaccuracies, the model shows potential in suggesting symbiotic opportunities, although its effectiveness is limited. Interestingly, the study reveals that the model can occasionally identify correct symbiotic relationships even with initial inaccuracies. These findings highlight the need for expert oversight and further development of the language model to improve its utility in complex, regulated fields like industrial symbiosis.Originality/valueThis study's originality lies in its exploration of advanced language models, particularly ChatGPT-4, for identifying industrial symbiosis opportunities within the circular economy framework. Unlike previous research, which primarily focuses on specific sectors and AI's role in general resource efficiency, this study specifically examines the capabilities and limitations of the language model in handling specialized and regulated information, such as EWC codes across various sectors. It employs a novel approach by comparing AI-generated responses with an established symbiosis database, which is comprehensive and spans all sectors rather than being limited to a single industry, as well as with randomly selected waste codes not included in the database. The study contributes to understanding how AI tools can support sustainable industrial practices, emphasizing the importance of refining these models for practical applications in environmental and industrial contexts.