Large Language Model-assisted EIA screening
A case study using GPT
Bibliographic Data
| ID | 21153705 |
|---|---|
| Authors | Dirk Cilliers (0000-0001-9777-0463, North-West University, corresponding author), Alex Bond (0000-0002-3809-5805, North-West University), Francois Retief (0000-0001-7164-9593, North-West University), Reece Alberts (0000-0001-6840-4405, North-West University), Claudine Roos (0000-0002-6290-6129, North-West University) |
| Year | 2025 |
| Volume | 43 |
| Issue | 4 |
| Pages | 267-277 |
| Publication date | 2025-07-04 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Impact Assessment and Project Appraisal (JOURNAL) |
| Journal identifiers | ISSN: 1461-5517 • E-ISSN: 1471-5465 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/14615517.2025.2523628 |
| OpenAlex | W4412041535 |
| Language | EN |
| Citations received | 4 |
| References cited | 27 |
Large Language Models (LLMs) have developed rapidly in recent years and are increasingly used for tasks involving the interpretation of human language expressed in text. As many EIA systems rely on EIA screening approaches that are based on the interpretation of descriptive thresholds contained in lists of text, LLMs might hold value for automating aspects of the EIA screening stage. This paper investigates the feasibility of using a customised Generative Pre-trained Transformer (GPT) model (a specific type of LLM) as an EIA screening tool. Three versions of a GPT-based screener were developed through an iterative process and tested against 20 real-world EIA cases involving activities regulated by two listing notices under South African law (GNR 983 and GNR 984). The iterative improvement of the model – from GPTv1 through GPTv3—demonstrated improvements in correctly identifying applicable activities that would be triggered. However, the models were not without challenges and specifically struggled with large-scale and highly complicated development proposals involving multiple triggers. The results demonstrate the potential value of GPTs but also highlight the importance of human oversight and the need for iterative refinement tailored to specific contexts
Environmental planning · Computer Science · Environmental and Social Impact Assessments · Environmental Science
Improving quality
Using an Artificial intelligence chatbot to critically review the scientific literature on the use of Artificial intelligence in Environmental Impact Assessment
Simulations of EIA screening across jurisdictions
A critical appraisal of EIA screening practice in EU Member States
Environmental assessment simplification in Botswana – is it fit for purpose
Screening for environmental impact assessment projects in England
ChatGPT and the future of impact assessment
Land take and the effectiveness of project screening in Environmental Impact Assessment
The validity of spatial data-based EIA screening decisions
| Citations per year | 4 |
|---|---|
| Citation span | 2025 - 2026 (2) |
| Highly cited | No |