Semantic Segmentation of Archaeological Features on Public Lands
Case Study of Historical Cotton Terraces within the Piedmont National Wildlife Refuge, Georgia, USA
Bibliographic Data
| ID | 13085187 |
|---|---|
| Authors | Claudine Gravel-Miguel (0000-0003-1324-7937, New Mexico Consortium, corresponding author), Grant Snitker (0000-0003-3548-2241, New Mexico Consortium), Jayde Hirniak (0000-0001-6491-8097, Arizona State University), Katherine Peck (0009-0008-4068-2591, New Mexico Consortium), Alex Fetterhoff (New Mexico Consortium) |
| Year | 2025 |
| Volume | 13 |
| Issue | 2 |
| Pages | 291-314 |
| Publication date | 2025-05-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Advances in Archaeological Practice (JOURNAL) |
| Journal identifiers | ISSN: 2326-3768 • E-ISSN: 2326-3768 |
| Publisher | Cambridge University Press (CUP) (PUBLISHER) |
| DOI | 10.1017/aap.2025.1 |
| OpenAlex | W7082382243 |
| Language | EN |
| Citations received | 4 |
| References cited | 46 |
The logistics, costs, and capacity needed to complete extensive archaeological pedestrian surveys to inventory cultural resources present challenges to public land managers. To address these issues, we developed a workflow combining lidar-derived imagery and deep learning (DL) models tailored for cultural resource management (CRM) programs on public lands. It combines Python scripts that fine-tune models to recognize archaeological features in lidar-derived imagery with denoising QGIS steps that improve the predictions’ performance and applicability. We present this workflow through an applied case study focused on detecting historic agricultural terraces in the Piedmont National Wildlife Refuge, Georgia, USA. For this project, we fine-tuned pretrained U-Net models to teach them to recognize agricultural terraces in imagery, identified the parameter settings that led to the highest recall for detecting terraces, and used those settings to train models on incremental dataset sizes, which allowed us to identify the minimum training size necessary to obtain satisfying models. Results present effective models that can detect most terraces even when trained on small datasets. This study provides a robust methodology that requires basic proficiencies in Python coding but expands DL applications in federal CRM by advancing methods in lidar and machine learning for archaeological inventorying, monitoring, and preservation
Cultural heritage · Land use · Public use · Python (programming language · Satellite imagery · Scripting language · Segmentation · Workflow · Electrical and Electromagnetic Research · Geochemistry and Geologic Mapping · Geological Modeling and Analysis
A Computer Vision Survey of the Northern San Juan
The Importance of Fit-for-Purpose Evaluation for Computer Vision in Archaeology
Using Simulated Training Data to Locate Archaeological Sites with Machine Learning
Deep Learning–Based Detection of Ancient Agricultural Terraces Using Multisensor Data Fusion
Faster R-CNN
Why Not a Single Image? Combining Visualizations to Facilitate Fieldwork and On-Screen Mapping
The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation
Mask R-CNN
ImageNet Large Scale Visual Recognition Challenge
Sky-View Factor as a Relief Visualization Technique
Array programming with NumPy
You Only Look Once
Uncovering archaeological landscapes at Angkor using lidar
Welcome to the Tidyverse
Combining Deep Learning and Location-Based Ranking for Large-Scale Archaeological Prospection of LiDAR Data from The Netherlands
Combined Detection and Segmentation of Archeological Structures from LiDAR Data Using a Deep Learning Approach
Implementing State-of-the-Art Deep Learning Approaches for Archaeological Object Detection in Remotely-Sensed Data
Learning to Look at LiDAR
An approach to the automatic surveying of prehistoric barrows through LiDAR
When Computers Dream of Charcoal
High‐resolution airborne Light Detection and Ranging data, ethics and archaeology
Using deep neural networks on airborne laser scanning data
LiDAR‐derived Local Relief Models – a new tool for archaeological prospection
Automated large‐scale mapping and analysis of relict charcoal hearths in Connecticut (USA) using a Deep Learning Yolov4 framework
A Comparison of Visualization Techniques for Models Created from Airborne Laser Scanned Data
Investigating ancient agricultural field systems in Sweden from airborne Lidar data by using convolutional neural network
Deep learning reveals extent of Archaic Native American shell-ring building practices
Airborne LiDAR, archaeology, and the ancient Maya landscape at Caracol, Belize
Airborne lidar survey of irrigated agricultural landscapes
Agricultural potential and actualized development in Hawai’i
Automated feature extraction for prospection and analysis of monumental earthworks from aerial LiDAR in the Kingdom of Tonga
| Unique citing works | 4 |
|---|---|
| Citations per year | 4 |
| Citation span | 2026 - 2026 (1) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 2 |