Detection of hunting pits using airborne laser scanning and deep learning
Forests worldwide contain unique cultural traces of past human land use. Increased pressure on forest ecosystems and intensive modern forest management methods threaten these ancient monuments and cultural remains. In northern Europe, older forests often contain very old traces, such as millennia-ol...
Published in: | Journal of Field Archaeology |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Umeå universitet, Statsvetenskapliga institutionen
2024
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-228297 https://doi.org/10.1080/00934690.2024.2364428 |
id |
ftumeauniv:oai:DiVA.org:umu-228297 |
---|---|
record_format |
openpolar |
spelling |
ftumeauniv:oai:DiVA.org:umu-228297 2024-09-15T18:33:30+00:00 Detection of hunting pits using airborne laser scanning and deep learning Lidberg, William Westphal, Florian Brax, Christoffer Sandström, Camilla Östlund, Lars 2024 application/pdf http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-228297 https://doi.org/10.1080/00934690.2024.2364428 eng eng UmeÃ¥ universitet, Statsvetenskapliga institutionen Swedish University of Agricultural Sciences, UmeÃ¥, Sweden Jönköping University, Jönköping, Sweden Swedish Forest Agency, Jönköping, Sweden Journal of field archaeology, 0093-4690, 2024 orcid:0000-0002-7674-6197 http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-228297 doi:10.1080/00934690.2024.2364428 ISI:001284888800001 Scopus 2-s2.0-85200442419 info:eu-repo/semantics/openAccess Archaeology forest history hunting pits airborne laser scanning artificial intelligence deep learning machine learning Forest Science Skogsvetenskap Other Social Sciences not elsewhere specified Övrig annan samhällsvetenskap Arkeologi Article in journal info:eu-repo/semantics/article text 2024 ftumeauniv https://doi.org/10.1080/00934690.2024.2364428 2024-08-20T23:39:49Z Forests worldwide contain unique cultural traces of past human land use. Increased pressure on forest ecosystems and intensive modern forest management methods threaten these ancient monuments and cultural remains. In northern Europe, older forests often contain very old traces, such as millennia-old hunting pits and indigenous Sami hearths. Investigations have repeatedly found that forest owners often fail to protect these cultural remains and that many are damaged by forestry operations. Current maps of hunting pits are incomplete, and the locations of known pits have poor spatial accuracy. This study investigated whether hunting pits can be automatically mapped using national airborne laser data and deep learning. The best model correctly mapped 70% of all the hunting pits in the test data with an F1 score of 0.76. This model can be implemented across northern Scandinavia and could have an immediate effect on the protection of cultural remains. Article in Journal/Newspaper sami sami Umeå University: Publications (DiVA) Journal of Field Archaeology 1 11 |
institution |
Open Polar |
collection |
Umeå University: Publications (DiVA) |
op_collection_id |
ftumeauniv |
language |
English |
topic |
Archaeology forest history hunting pits airborne laser scanning artificial intelligence deep learning machine learning Forest Science Skogsvetenskap Other Social Sciences not elsewhere specified Övrig annan samhällsvetenskap Arkeologi |
spellingShingle |
Archaeology forest history hunting pits airborne laser scanning artificial intelligence deep learning machine learning Forest Science Skogsvetenskap Other Social Sciences not elsewhere specified Övrig annan samhällsvetenskap Arkeologi Lidberg, William Westphal, Florian Brax, Christoffer Sandström, Camilla Östlund, Lars Detection of hunting pits using airborne laser scanning and deep learning |
topic_facet |
Archaeology forest history hunting pits airborne laser scanning artificial intelligence deep learning machine learning Forest Science Skogsvetenskap Other Social Sciences not elsewhere specified Övrig annan samhällsvetenskap Arkeologi |
description |
Forests worldwide contain unique cultural traces of past human land use. Increased pressure on forest ecosystems and intensive modern forest management methods threaten these ancient monuments and cultural remains. In northern Europe, older forests often contain very old traces, such as millennia-old hunting pits and indigenous Sami hearths. Investigations have repeatedly found that forest owners often fail to protect these cultural remains and that many are damaged by forestry operations. Current maps of hunting pits are incomplete, and the locations of known pits have poor spatial accuracy. This study investigated whether hunting pits can be automatically mapped using national airborne laser data and deep learning. The best model correctly mapped 70% of all the hunting pits in the test data with an F1 score of 0.76. This model can be implemented across northern Scandinavia and could have an immediate effect on the protection of cultural remains. |
format |
Article in Journal/Newspaper |
author |
Lidberg, William Westphal, Florian Brax, Christoffer Sandström, Camilla Östlund, Lars |
author_facet |
Lidberg, William Westphal, Florian Brax, Christoffer Sandström, Camilla Östlund, Lars |
author_sort |
Lidberg, William |
title |
Detection of hunting pits using airborne laser scanning and deep learning |
title_short |
Detection of hunting pits using airborne laser scanning and deep learning |
title_full |
Detection of hunting pits using airborne laser scanning and deep learning |
title_fullStr |
Detection of hunting pits using airborne laser scanning and deep learning |
title_full_unstemmed |
Detection of hunting pits using airborne laser scanning and deep learning |
title_sort |
detection of hunting pits using airborne laser scanning and deep learning |
publisher |
Umeå universitet, Statsvetenskapliga institutionen |
publishDate |
2024 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-228297 https://doi.org/10.1080/00934690.2024.2364428 |
genre |
sami sami |
genre_facet |
sami sami |
op_relation |
Journal of field archaeology, 0093-4690, 2024 orcid:0000-0002-7674-6197 http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-228297 doi:10.1080/00934690.2024.2364428 ISI:001284888800001 Scopus 2-s2.0-85200442419 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1080/00934690.2024.2364428 |
container_title |
Journal of Field Archaeology |
container_start_page |
1 |
op_container_end_page |
11 |
_version_ |
1810475204292378624 |