Archived
This content is available here strictly for research, reference, and/or recordkeeping and as such it may not be fully accessible. If you work or study at University of Kentucky and would like to request an accessible version, please use the SensusAccess Document Converter.
Location
Lexington, Kentucky
Start Date
5-5-2026 10:30 AM
End Date
5-5-2026 11:00 AM
Description
The environmental and coal combustion residuals (CCR) industries generate vast amounts of information—from groundwater monitoring reports and RCRA documentation to closure plans and analytical data. Managing, interpreting, and communicating this information is a growing challenge for utilities, regulators, and consultants alike. Large Language Models (LLMs), such as OpenAI’s GPT architecture, represent a breakthrough in how organizations can interact with their technical data. These models use deep neural networks trained on billions of words to understand, summarize, and generate language with human-like accuracy. When securely adapted for enterprise use, LLMs can automate routine reporting, extract data from technical documents, generate regulatory narratives, and even provide on-demand insight through conversational interfaces. Because of the vast training data, LLMs provide novel solutions and tap experience from around the world in nano seconds. This presentation explains, in accessible terms, what LLMs are, how they learn and adapt, and the specific ways they can support environmental management and CCR programs. Real-world examples demonstrate how generative AI can enhance compliance efficiency, strengthen data-driven decision-making, and reduce time and cost across environmental reporting workflows. Attendees will gain a foundational understanding of how to responsibly deploy AI within their organizations. AI is already embedded in everything we do on computers. I want to show you practical keys to unlock greater efficacy in our compliance tasks.
Document Type
Presentation
Archival?
Archival
Included in
Energy Systems Commons, Environmental Indicators and Impact Assessment Commons, Environmental Monitoring Commons, Mining Engineering Commons, Oil, Gas, and Energy Commons, Structural Materials Commons, Sustainability Commons
Demystifying Large Language Models: How AI Is Transforming Data, Compliance, and Decision-Making in Coal Ash and Environmental Management
Lexington, Kentucky
The environmental and coal combustion residuals (CCR) industries generate vast amounts of information—from groundwater monitoring reports and RCRA documentation to closure plans and analytical data. Managing, interpreting, and communicating this information is a growing challenge for utilities, regulators, and consultants alike. Large Language Models (LLMs), such as OpenAI’s GPT architecture, represent a breakthrough in how organizations can interact with their technical data. These models use deep neural networks trained on billions of words to understand, summarize, and generate language with human-like accuracy. When securely adapted for enterprise use, LLMs can automate routine reporting, extract data from technical documents, generate regulatory narratives, and even provide on-demand insight through conversational interfaces. Because of the vast training data, LLMs provide novel solutions and tap experience from around the world in nano seconds. This presentation explains, in accessible terms, what LLMs are, how they learn and adapt, and the specific ways they can support environmental management and CCR programs. Real-world examples demonstrate how generative AI can enhance compliance efficiency, strengthen data-driven decision-making, and reduce time and cost across environmental reporting workflows. Attendees will gain a foundational understanding of how to responsibly deploy AI within their organizations. AI is already embedded in everything we do on computers. I want to show you practical keys to unlock greater efficacy in our compliance tasks.
