{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/132801"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/132801","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Domain-specific adaptation of large language models and integration with knowledge graph analytics for enhanced bridge maintenance decision making","abstract":"Bridges are critical components of transportation infrastructure, ensuring mobility and economic connectivity. However, a large portion of U.S. bridges are in poor condition, raising significant safety and maintenance challenges. According to the 2025 ASCE Infrastructure Report Card, 42% of U.S. bridges are over 50 years old and 6.8% are in poor condition, with an estimated $191 billion in bridge-related system rehabilitation needs. Despite extensive data collection efforts by transportation agencies, existing data-driven models for bridge condition assessment and maintenance decision making remain limited. Most models rely primarily on abstract data from single sources, such as the National Bridge Inventory (NBI), which lacks the rich contextual information contained in textual inspection reports, images, and other heterogeneous data sources. Consequently, these models struggle to leverage the full potential of the available multimodal data to support accurate condition assessment, deterioration prediction, and cost-effective maintenance strategies. To address these limitations, a novel large language model (LLM)-based analytics framework for bridge data integration and enhanced maintenance decision support is proposed. The proposed framework is composed of six primary components: (1) an LLM-based semantic information extraction method for extracting information entities that describe bridge conditions and maintenance actions from bridge textual reports; (2) a low-rank adaptation (LoRA)-based finetuning method to efficiently adapt pretrained LLMs to the bridge domain; (3) an LLM-based semantic relation extraction method for extracting semantic relations from bridge reports to link the extracted, yet isolated, information entities in the form of a bridge knowledge graph; (4) an LLM-based data augmentation method to mitigate training data scarcity and enable advanced encoding of high-dimensional datasets; (5) a vector encoding-based multimodal data linking method to link diverse inspection data types (e.g., text, images) across multiple sources; and (6) an LLM-based method that integrates knowledge-enriched prompts, retrieval-augmented generation (RAG), reinforcement learning from human feedback, and the bridge knowledge graph to support bridge maintenance decision-making, including automated analysis of bridge conditions and generation of context-aware maintenance plans. The experimental results demonstrated the promise of the proposed framework. Overall, this research provides a novel, multimodal bridge analytics framework that advances automated condition assessment, improves maintenance decision support, and demonstrates the potential of LLM-based methods to transform data-driven bridge management.","abstract_html":"Bridges are critical components of transportation infrastructure, ensuring mobility and economic connectivity. However, a large portion of U.S. bridges are in poor condition, raising significant safety and maintenance challenges. According to the 2025 ASCE Infrastructure Report Card, 42% of U.S. bridges are over 50 years old and 6.8% are in poor condition, with an estimated $191 billion in bridge-related system rehabilitation needs. Despite extensive data collection efforts by transportation agencies, existing data-driven models for bridge condition assessment and maintenance decision making remain limited. Most models rely primarily on abstract data from single sources, such as the National Bridge Inventory (NBI), which lacks the rich contextual information contained in textual inspection reports, images, and other heterogeneous data sources. Consequently, these models struggle to leverage the full potential of the available multimodal data to support accurate condition assessment, deterioration prediction, and cost-effective maintenance strategies. To address these limitations, a novel large language model (LLM)-based analytics framework for bridge data integration and enhanced maintenance decision support is proposed. The proposed framework is composed of six primary components: (1) an LLM-based semantic information extraction method for extracting information entities that describe bridge conditions and maintenance actions from bridge textual reports; (2) a low-rank adaptation (LoRA)-based finetuning method to efficiently adapt pretrained LLMs to the bridge domain; (3) an LLM-based semantic relation extraction method for extracting semantic relations from bridge reports to link the extracted, yet isolated, information entities in the form of a bridge knowledge graph; (4) an LLM-based data augmentation method to mitigate training data scarcity and enable advanced encoding of high-dimensional datasets; (5) a vector encoding-based multimodal data linking method to link diverse inspection data types (e.g., text, images) across multiple sources; and (6) an LLM-based method that integrates knowledge-enriched prompts, retrieval-augmented generation (RAG), reinforcement learning from human feedback, and the bridge knowledge graph to support bridge maintenance decision-making, including automated analysis of bridge conditions and generation of context-aware maintenance plans. The experimental results demonstrated the promise of the proposed framework. Overall, this research provides a novel, multimodal bridge analytics framework that advances automated condition assessment, improves maintenance decision support, and demonstrates the potential of LLM-based methods to transform data-driven bridge management.","abstract_has_math":false,"creators":["Chen, Qiyang"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Civil Engineering","degree_department":null,"school":null,"contributors":["El-Gohary, Nora","El-Rayes, Khaled","Golparvar-Fard, Mani","Zhai, ChengXiang","Jebelli, Houtan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12","date_published":"2025-12","updated_at":"2026-07-22T22:25:07Z","subjects":["large language model","bridge maintenance decision making","information extraction, data-driven","finetuning"],"languages":["en"],"rights":["Copyright 2025 Qiyang Chen"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/132801","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["El-Gohary, Nora","El-Rayes, Khaled","Golparvar-Fard, Mani","Zhai, ChengXiang","Jebelli, Houtan"]},{"key":"dc:creator","label":"Author","values":["Chen, Qiyang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12","2025-12-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Civil Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["large language model","bridge maintenance decision making","information extraction, data-driven","finetuning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Qiyang Chen"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/132801"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Bridges are critical components of transportation infrastructure, ensuring mobility and economic connectivity. However, a large portion of U.S. bridges are in poor condition, raising significant safety and maintenance challenges. According to the 2025 ASCE Infrastructure Report Card, 42% of U.S. bridges are over 50 years old and 6.8% are in poor condition, with an estimated $191 billion in bridge-related system rehabilitation needs. Despite extensive data collection efforts by transportation agencies, existing data-driven models for bridge condition assessment and maintenance decision making remain limited. Most models rely primarily on abstract data from single sources, such as the National Bridge Inventory (NBI), which lacks the rich contextual information contained in textual inspection reports, images, and other heterogeneous data sources. Consequently, these models struggle to leverage the full potential of the available multimodal data to support accurate condition assessment, deterioration prediction, and cost-effective maintenance strategies. To address these limitations, a novel large language model (LLM)-based analytics framework for bridge data integration and enhanced maintenance decision support is proposed. The proposed framework is composed of six primary components: (1) an LLM-based semantic information extraction method for extracting information entities that describe bridge conditions and maintenance actions from bridge textual reports; (2) a low-rank adaptation (LoRA)-based finetuning method to efficiently adapt pretrained LLMs to the bridge domain; (3) an LLM-based semantic relation extraction method for extracting semantic relations from bridge reports to link the extracted, yet isolated, information entities in the form of a bridge knowledge graph; (4) an LLM-based data augmentation method to mitigate training data scarcity and enable advanced encoding of high-dimensional datasets; (5) a vector encoding-based multimodal data linking method to link diverse inspection data types (e.g., text, images) across multiple sources; and (6) an LLM-based method that integrates knowledge-enriched prompts, retrieval-augmented generation (RAG), reinforcement learning from human feedback, and the bridge knowledge graph to support bridge maintenance decision-making, including automated analysis of bridge conditions and generation of context-aware maintenance plans. The experimental results demonstrated the promise of the proposed framework. Overall, this research provides a novel, multimodal bridge analytics framework that advances automated condition assessment, improves maintenance decision support, and demonstrates the potential of LLM-based methods to transform data-driven bridge management.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-12-01","The student, Qiyang Chen, accepted the attached license on 2025-12-05 at 11:08.","The student, Qiyang Chen, submitted this Dissertation for approval on 2025-12-05 at 11:09.","This Dissertation was approved for publication on 2025-12-05 at 16:08.","DSpace SAF Submission Ingestion Package generated from Vireo submission #23073 on 2026-02-19 at 20:10:03"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Domain-specific adaptation of large language models and integration with knowledge graph analytics for enhanced bridge maintenance decision making"]}]}],"canonical_facts":{"dc:contributor":["El-Gohary, Nora","El-Rayes, Khaled","Golparvar-Fard, Mani","Zhai, ChengXiang","Jebelli, Houtan"],"dc:creator":["Chen, Qiyang"],"dc:date":["2025-12","2025-12-05"],"dc:description":["Bridges are critical components of transportation infrastructure, ensuring mobility and economic connectivity. However, a large portion of U.S. bridges are in poor condition, raising significant safety and maintenance challenges. According to the 2025 ASCE Infrastructure Report Card, 42% of U.S. bridges are over 50 years old and 6.8% are in poor condition, with an estimated $191 billion in bridge-related system rehabilitation needs. Despite extensive data collection efforts by transportation agencies, existing data-driven models for bridge condition assessment and maintenance decision making remain limited. Most models rely primarily on abstract data from single sources, such as the National Bridge Inventory (NBI), which lacks the rich contextual information contained in textual inspection reports, images, and other heterogeneous data sources. Consequently, these models struggle to leverage the full potential of the available multimodal data to support accurate condition assessment, deterioration prediction, and cost-effective maintenance strategies. To address these limitations, a novel large language model (LLM)-based analytics framework for bridge data integration and enhanced maintenance decision support is proposed. The proposed framework is composed of six primary components: (1) an LLM-based semantic information extraction method for extracting information entities that describe bridge conditions and maintenance actions from bridge textual reports; (2) a low-rank adaptation (LoRA)-based finetuning method to efficiently adapt pretrained LLMs to the bridge domain; (3) an LLM-based semantic relation extraction method for extracting semantic relations from bridge reports to link the extracted, yet isolated, information entities in the form of a bridge knowledge graph; (4) an LLM-based data augmentation method to mitigate training data scarcity and enable advanced encoding of high-dimensional datasets; (5) a vector encoding-based multimodal data linking method to link diverse inspection data types (e.g., text, images) across multiple sources; and (6) an LLM-based method that integrates knowledge-enriched prompts, retrieval-augmented generation (RAG), reinforcement learning from human feedback, and the bridge knowledge graph to support bridge maintenance decision-making, including automated analysis of bridge conditions and generation of context-aware maintenance plans. The experimental results demonstrated the promise of the proposed framework. Overall, this research provides a novel, multimodal bridge analytics framework that advances automated condition assessment, improves maintenance decision support, and demonstrates the potential of LLM-based methods to transform data-driven bridge management.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-12-01","The student, Qiyang Chen, accepted the attached license on 2025-12-05 at 11:08.","The student, Qiyang Chen, submitted this Dissertation for approval on 2025-12-05 at 11:09.","This Dissertation was approved for publication on 2025-12-05 at 16:08.","DSpace SAF Submission Ingestion Package generated from Vireo submission #23073 on 2026-02-19 at 20:10:03"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/132801"],"dc:language":["en"],"dc:rights":["Copyright 2025 Qiyang Chen"],"dc:subject":["large language model","bridge maintenance decision making","information extraction, data-driven","finetuning"],"dc:title":["Domain-specific adaptation of large language models and integration with knowledge graph analytics for enhanced bridge maintenance decision making"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Civil Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:07Z"}