{"corpus_id":252698102,"paper_sha":"83fa808768d2bb1aa25529626673b08c4afc0832","doi":"10.1016/j.biortech.2022.128062","arxiv_id":null,"pmid":36202285,"pmcid":null,"mag_id":null,"dblp_id":null,"acl_id":null,"title":"Interpretable Machine Learning to Model Biomass and Waste Gasification.","year":2022,"publication_date":"2022-10-01","venue":"Bioresource Technology","journal":{"name":"Bioresource technology","pages":"\n          128062\n        ","volume":null},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":["Journal Article"],"s2_fields_of_study":["Medicine","Computer Science","Engineering","Environmental Science"],"reference_count":34,"citation_count":90,"influential_citation_count":3,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Machine learning has been regarded as a promising method to better model thermochemical processes such as gasification. However, their black box nature can limit how much one can trust and learn from the developed models. Here seven different machine learning methods have been adopted to model the gasification of biomass and waste across a wide range of operating conditions. Gradient boosting regression has been found to outperform the other model types with a coefficient of determination (R2) of 0.90 when averaged across ten key gasification outputs. Global and local model interpretability methods have been used to illuminate the developed black box models. The studied models were most strongly influenced by the feedstock's particle size and the type of gasifying agent employed. By combining global and local interpretability methods, the understanding of black box models has been improved. This allows policy makers and investors to make more educated decisions about gasification process design.","claims":[{"public_id":"cl_b2e2fdb8f048ade586fc62419f118778","status":"active","text":"Combining global and local interpretability methods improved understanding of the black box models.","confidence":0.94,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_b2e2fdb8f048ade586fc62419f118778"},{"public_id":"cl_c2362780c88485728fc3bffb9cfdbd92","status":"active","text":"Feedstock particle size and gasifying agent type were the strongest influences on the studied models.","confidence":0.96,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_c2362780c88485728fc3bffb9cfdbd92"},{"public_id":"cl_a034a113c54f6962521abea5653cb30d","status":"active","text":"Global and local interpretability methods were used to illuminate the developed black box models.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_a034a113c54f6962521abea5653cb30d"},{"public_id":"cl_51819d4607e2f3ebf75b53bbff4d36fb","status":"active","text":"Gradient boosting regression outperformed the other model types, achieving an average coefficient of determination of 0.90 across ten key gasification outputs.","confidence":0.99,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_51819d4607e2f3ebf75b53bbff4d36fb"},{"public_id":"cl_1b3ee07f5774f4ef4e2113d5ca791ebc","status":"active","text":"Seven machine learning methods were applied to model biomass and waste gasification across a wide range of operating conditions.","confidence":0.98,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_1b3ee07f5774f4ef4e2113d5ca791ebc"}],"concepts":[{"public_id":"co_163077c334ea62270e11a5f1ac3d07ae","status":"active","name":"global interpretability methods","description":"Interpretability techniques that summarize overall feature influence in a model across the full dataset.","types":["interpretability method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_163077c334ea62270e11a5f1ac3d07ae"},{"public_id":"co_1643dfc4f1372b2d8b8d243665e6ae4f","status":"active","name":"feedstock particle size","description":"The size of the input biomass or waste particles used in gasification.","types":["feature"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1643dfc4f1372b2d8b8d243665e6ae4f"},{"public_id":"co_1a83464c205de73672eda9c78487990d","status":"active","name":"studied models","description":"The machine learning models evaluated for gasification prediction in the abstract.","types":["model"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1a83464c205de73672eda9c78487990d"},{"public_id":"co_340a029bfc9e70b8393c85159f0a571d","status":"active","name":"gasifying agent type","description":"The kind of agent, such as air or steam, used to promote gasification reactions.","types":["feature"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_340a029bfc9e70b8393c85159f0a571d"},{"public_id":"co_445429c442efa4c3ee1e0c97b5e77177","status":"active","name":"machine learning methods","description":"Data-driven modeling approaches used to learn relationships from input-output examples.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_445429c442efa4c3ee1e0c97b5e77177"},{"public_id":"co_4a93ddedcd5f0a8598e3a0b7fc9441cd","status":"active","name":"black box models","description":"Predictive models whose internal decision logic is not directly transparent.","types":["model"],"aliases":["black-box models"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4a93ddedcd5f0a8598e3a0b7fc9441cd"},{"public_id":"co_71417a82168391548901384d617d5f78","status":"active","name":"gradient boosting regression","description":"An ensemble regression method that builds predictive models by sequentially combining weak learners.","types":["method"],"aliases":["GBR"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_71417a82168391548901384d617d5f78"},{"public_id":"co_7f5ec0fc8f44a17529e0d7197c5ff1c2","status":"active","name":"operating conditions","description":"The process settings under which gasification experiments or data were collected.","types":["experimental conditions"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_7f5ec0fc8f44a17529e0d7197c5ff1c2"},{"public_id":"co_934cfba295b2f032664f05b500dc3b70","status":"active","name":"biomass and waste gasification","description":"A thermochemical process that converts biomass and waste into gas products under controlled conditions.","types":["process"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_934cfba295b2f032664f05b500dc3b70"},{"public_id":"co_9662bbf9d5b1d3e1660bd8da0fd69b03","status":"active","name":"coefficient of determination","description":"A statistical metric that measures how well a model explains variance in observed outputs.","types":["metric"],"aliases":["R2","R-squared"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_9662bbf9d5b1d3e1660bd8da0fd69b03"},{"public_id":"co_b0d3b82e080bd2b202e71ebd3efcf77d","status":"active","name":"gasification outputs","description":"Measured outputs or response variables from the gasification process.","types":["outcome variables"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_b0d3b82e080bd2b202e71ebd3efcf77d"},{"public_id":"co_cd1b9bdf37125216eeb8bb8404f3c7f7","status":"active","name":"local interpretability methods","description":"Interpretability techniques that explain individual model predictions or local decision behavior.","types":["interpretability method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_cd1b9bdf37125216eeb8bb8404f3c7f7"}],"external_ids":{"DOI":"10.1016/j.biortech.2022.128062","ArXiv":null,"PubMed":36202285,"PubMedCentral":null,"MAG":null,"DBLP":null,"ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/252698102","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":5},"paper_id":637559,"paper_uid":"cdfa77c4-8c5d-40b5-8c8b-191b130772a3","canonical_identity":{"paper_id":637559,"paper_uid":"cdfa77c4-8c5d-40b5-8c8b-191b130772a3","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/252698102"}