AI-Powered Automation of NEPA Categorical Exclusions for Historic Districts and Federal Landmarks: An Integrated Multi-Agency Framework for Intelligent Permitting
Keywords:
NEPA compliance, categorical exclusion, AI automation, retrieval-augmented generation, computer vision, multi-agency integration, intelligent permitting, historic preservation, 5G deployment, regulatory knowledge graphAbstract
NEPA categorical exclusion compliance for infrastructure projects in historic districts requires cross-referencing more than 30 federal agency CE catalogs, initiating NHPA Section 106 consultations with State Historic Preservation Offices, and generating legally defensible documentation, a workflow that currently consumes 15 to 30 days per site and costs telecommunications carriers $3,000 to $8,000 per application, based on the author's primary research projections in telecommunications program management. No integrated AI framework currently addresses this multi-agency determination challenge at scale. This paper proposes a multi-modal platform that resolves CE determination through retrieval-augmented generation (RAG) over a structured regulatory knowledge graph, transformer-based computer vision analysis of geospatial imagery and construction drawings, parallel federal API orchestration across 15 or more databases, and large language model (LLM)-driven generation of agency-specific compliance documentation. A tiered processing architecture targets Tier 1 CE determination in under two hours for standard cases, while a human-in-the-loop override design with immutable audit traceability maintains the legal defensibility standard required for operational deployment. Applied to U.S. 5G small cell programs, where NEPA/Section 106 compliance represents one of the documented bottlenecks on infrastructure deployment velocity, the framework addresses a compliance challenge that has resisted automation to date, with broader applicability to electric utilities, transportation agencies, and federal facility operators.
Downloads
References
U.S. Government, "National Environmental Policy Act of 1969 (Public Law 91-190)," Enacted July 4, 2025. Available: https://www.govinfo.gov/content/pkg/COMPS-10352/pdf/COMPS-10352.pdf
National Park Service, "National Historic Preservation Act of 1966." Available: https://www.nps.gov/subjects/archeology/national-historic-preservation-act.htm
Office of NEPA Policy and Compliance, "40 CFR 1500-1508: CEQ Regulations for Implementing the Procedural Provisions of NEPA," 2005. Available: https://www.energy.gov/nepa/articles/40-cfr-1500-1508-ceq-regulations-implementing-procedural-provisions-nepa-ceq-1978
Federal Communications Commission, "Environmental Rules, 47 CFR Sections 1.1301-1.1319," 2001. Available: https://docs.fcc.gov/public/attachments/FCC-01-319A1.pdf
Advisory Council on Historic Preservation, "Section 106 Regulations, 36 CFR Part 800." Available: https://www.achp.gov/digital-library-section-106-landing/section-106-regulations
P. Lewis et al., "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks," NeurIPS 33 (2020): 9459-9474. Available: https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html
T. Saren, "Using AI in NEPA Review: Legal Challenges and Judicial Scrutiny," Environmental Law Reporter (2025). Available: https://www.elr.info/sites/default/files/files-general/55.UsingAIinNEPAReview_0.pdf
Federal Communications Commission, "FCC Facilitates Wireless Infrastructure Deployment for 5G," 33 FCC Rcd 9088 (14), 2018. Available: https://www.fcc.gov/document/fcc-facilitates-wireless-infrastructure-deployment-5g
Congressional Research Service, "U.S. Army Corps of Engineers: FY2024 Appropriations," 2023. Available: https://www.congress.gov/crs_external_products/IF/PDF/IF12370/IF12370.3.pdf
H. Naveed et al., "A Comprehensive Overview of Large Language Models," ACM Trans. Intell. Syst. Technol. 16, no. 5 (2025): 1-72. Available: https://dl.acm.org/doi/full/10.1145/3744746
Y. Gao et al., "Retrieval-Augmented Generation for Large Language Models: A Survey," arXiv:2312.10997 (2023). Available: https://arxiv.org/abs/2312.10997
A. Vaswani et al., "Attention Is All You Need," NeurIPS 30 (2017). Available: https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html
J. Wei et al., "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models," NeurIPS 35 (2022): 24824-24837. Available: https://proceedings.neurips.cc/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html
X. Ma, G. Fang, and X. Wang, "LLM-Pruner: On the Structural Pruning of Large Language Models," NeurIPS 36 (2023): 21702-21720. Available: https://proceedings.neurips.cc/paper_files/paper/2023/hash/44956951349095f74492a5471128a7e0-Abstract-Conference.html
I. Chalkidis et al., "LEGAL-BERT: The Muppets Straight Out of Law School," Findings of EMNLP 2020, pp. 2898-2904. Available: https://aclanthology.org/2020.findings-emnlp.261/
N. Carion et al., "End-to-End Object Detection with Transformers," ECCV 2020, pp. 213-229. Available: https://link.springer.com/chapter/10.1007/978-3-030-58452-8_13
T. Brown et al., "Language Models Are Few-Shot Learners," NeurIPS 33 (2020): 1877-1901. Available: https://proceedings.neurips.cc/paper_files/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
D. Edge et al., "From Local to Global: A Graph RAG Approach to Query-Focused Summarization," arXiv:2404.16130 (2024). Available: https://arxiv.org/abs/2404.16130
National Conference of State Historic Preservation Officers, "Section 106," NCSHPO, 1966. Available: https://ncshpo.org/resources/section-106/
R. Bommasani et al., "On the Opportunities and Risks of Foundation Models," arXiv:2108.07258 (2021). Available: https://arxiv.org/abs/2108.07258
U.S. Fish & Wildlife Service, "IPaC: Information for Planning and Consultation," Accessed: 2026. Available: https://www.fws.gov/service/information-planning-and-consultation
National Park Service, "IRMA Data Store REST API Documentation," Accessed: Jun. 2026. Available: https://irmaservices.nps.gov/datastore/v8/documentation/datastore-api.html
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
