Map stone walls

Map stone walls in New England

A community project to map New England's old stone walls. A model suggests where they are, and people confirm them.

Open the map
New England shaded by the density of suggested stone walls.

How it works

  1. Laser scans show the ground

    Under the trees, an old wall is a thin raised ridge.

  2. A model suggests walls

    It learned from walls people traced by hand, and it makes mistakes.

  3. People confirm them

    A line becomes a wall on the map once someone has seen it and a reviewer agrees.

Existing stone wall maps

Made by others. This project is not affiliated with them.

Research

Stone walls and LiDAR

  1. Johnson, K. M. and Ouimet, W. B. (2014). Rediscovering the lost archaeological landscape of southern New England using airborne light detection and ranging (LiDAR). Journal of Archaeological Science 43, 9-20. doi.org/10.1016/j.jas.2013.12.004
  2. Johnson, K. M. and Ouimet, W. B. (2016). Physical properties and spatial controls of stone walls in the northeastern USA: Implications for Anthropocene studies of 17th to early 20th century agriculture. Anthropocene 15, 22-36. doi.org/10.1016/j.ancene.2016.07.001
  3. Johnson, K. M. and Ouimet, W. B. (2021). Reconstructing historical forest cover and land use dynamics in the northeastern United States using geospatial analysis and airborne LiDAR. Annals of the American Association of Geographers 111(6), 1656-1678. doi.org/10.1080/24694452.2020.1856640
  4. Johnson, K. M., Ouimet, W. B., Dow, S. and Haverfield, C. (2021). Estimating historically cleared and forested land in Massachusetts, USA, using airborne LiDAR and archival records. Remote Sensing 13(21), 4318. doi.org/10.3390/rs13214318
  5. Suh, J. W. and Ouimet, W. (2023). Mapping stone walls in Northeastern USA using deep learning and LiDAR data. GIScience & Remote Sensing 60(1), 2196117. doi.org/10.1080/15481603.2023.2196117
  6. Suh, J. W., Ouimet, W. B. and Dow, S. (2023). Reconstructing and identifying historic land use in northeastern United States using anthropogenic landforms and deep learning. Applied Geography 161, 103121. doi.org/10.1016/j.apgeog.2023.103121
  7. Trotter, E. F. L., Fernandes, A. C. M., Fibæk, C. S. and Keßler, C. (2022). Machine learning for automatic detection of historic stone walls using LiDAR data. International Journal of Remote Sensing 43(6), 2185-2211. doi.org/10.1080/01431161.2022.2057206
  8. Thorson, R. M. (2002). Stone by Stone: The Magnificent History in New England's Stone Walls. Walker & Company, New York.

The model

A U-Net with a ResNet-34 encoder reads hillshade, slope, local relief and sky-view factor images made from the elevation data.

  1. Ronneberger, O., Fischer, P. and Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Lecture Notes in Computer Science 9351, 234-241. doi.org/10.1007/978-3-319-24574-4_28
  2. He, K., Zhang, X., Ren, S. and Sun, J. (2016). Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770-778. doi.org/10.1109/CVPR.2016.90
  3. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K. and Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 248-255. doi.org/10.1109/CVPR.2009.5206848
  4. Iakubovskii, P. (2019). Segmentation Models Pytorch. Software, GitHub. github.com/qubvel-org/segmentation_models.pytorch
  5. Zakšek, K., Oštir, K. and Kokalj, Ž. (2011). Sky-view factor as a relief visualization technique. Remote Sensing 3(2), 398-415. doi.org/10.3390/rs3020398
  6. Hesse, R. (2010). LiDAR-derived local relief models: a new tool for archaeological prospection. Archaeological Prospection 17(2), 67-72. doi.org/10.1002/arp.374

Data