Combining Deep Learning and Location-Based Ranking for Large-Scale Archaeological Prospection of LiDAR Data from The Netherlands

Combining Deep Learning and Location-Based Ranking for Large-Scale Archaeological Prospection of LiDAR Data from The Netherlands. Verschoof-van der Vaart, W. B., Lambers, K., Kowalczyk, W., & Bourgeois, Q. P. ISPRS International Journal of Geo-Information, 9(5):293, May, 2020.

Paper doi abstract bibtex

This paper presents WODAN2.0, a workﬂow using Deep Learning for the automated detection of multiple archaeological object classes in LiDAR data from the Netherlands. WODAN2.0 is developed to rapidly and systematically map archaeology in large and complex datasets. To investigate its practical value, a large, random test dataset—next to a small, non-random dataset—was developed, which better represents the real-world situation of scarce archaeological objects in different types of complex terrain. To reduce the number of false positives caused by speciﬁc regions in the research area, a novel approach has been developed and implemented called Location-Based Ranking. Experiments show that WODAN2.0 has a performance of circa 70% for barrows and Celtic ﬁelds on the small, non-random testing dataset, while the performance on the large, random testing dataset is lower: circa 50% for barrows, circa 46% for Celtic ﬁelds, and circa 18% for charcoal kilns. The results show that the introduction of Location-Based Ranking and bagging leads to an improvement in performance varying between 17% and 35%. However, WODAN2.0 does not reach or exceed general human performance, when compared to the results of a citizen science project conducted in the same research area.

@article{verschoof-van_der_vaart_combining_2020,
	title = {Combining {Deep} {Learning} and {Location}-{Based} {Ranking} for {Large}-{Scale} {Archaeological} {Prospection} of {LiDAR} {Data} from {The} {Netherlands}},
	volume = {9},
	issn = {2220-9964},
	url = {https://www.mdpi.com/2220-9964/9/5/293},
	doi = {10.3390/ijgi9050293},
	abstract = {This paper presents WODAN2.0, a workﬂow using Deep Learning for the automated detection of multiple archaeological object classes in LiDAR data from the Netherlands. WODAN2.0 is developed to rapidly and systematically map archaeology in large and complex datasets. To investigate its practical value, a large, random test dataset—next to a small, non-random dataset—was developed, which better represents the real-world situation of scarce archaeological objects in different types of complex terrain. To reduce the number of false positives caused by speciﬁc regions in the research area, a novel approach has been developed and implemented called Location-Based Ranking. Experiments show that WODAN2.0 has a performance of circa 70\% for barrows and Celtic ﬁelds on the small, non-random testing dataset, while the performance on the large, random testing dataset is lower: circa 50\% for barrows, circa 46\% for Celtic ﬁelds, and circa 18\% for charcoal kilns. The results show that the introduction of Location-Based Ranking and bagging leads to an improvement in performance varying between 17\% and 35\%. However, WODAN2.0 does not reach or exceed general human performance, when compared to the results of a citizen science project conducted in the same research area.},
	language = {en},
	number = {5},
	urldate = {2020-05-07},
	journal = {ISPRS International Journal of Geo-Information},
	author = {Verschoof-van der Vaart, Wouter B. and Lambers, Karsten and Kowalczyk, Wojtek and Bourgeois, Quentin P.J.},
	month = may,
	year = {2020},
	pages = {293},
}

Downloads: 0

{"_id":"fXovGsajuKLxEbChq","bibbaseid":"verschoofvandervaart-lambers-kowalczyk-bourgeois-combiningdeeplearningandlocationbasedrankingforlargescalearchaeologicalprospectionoflidardatafromthenetherlands-2020","author_short":["Verschoof-van der Vaart, W. B.","Lambers, K.","Kowalczyk, W.","Bourgeois, Q. P."],"bibdata":{"bibtype":"article","type":"article","title":"Combining Deep Learning and Location-Based Ranking for Large-Scale Archaeological Prospection of LiDAR Data from The Netherlands","volume":"9","issn":"2220-9964","url":"https://www.mdpi.com/2220-9964/9/5/293","doi":"10.3390/ijgi9050293","abstract":"This paper presents WODAN2.0, a workﬂow using Deep Learning for the automated detection of multiple archaeological object classes in LiDAR data from the Netherlands. WODAN2.0 is developed to rapidly and systematically map archaeology in large and complex datasets. To investigate its practical value, a large, random test dataset—next to a small, non-random dataset—was developed, which better represents the real-world situation of scarce archaeological objects in different types of complex terrain. To reduce the number of false positives caused by speciﬁc regions in the research area, a novel approach has been developed and implemented called Location-Based Ranking. Experiments show that WODAN2.0 has a performance of circa 70% for barrows and Celtic ﬁelds on the small, non-random testing dataset, while the performance on the large, random testing dataset is lower: circa 50% for barrows, circa 46% for Celtic ﬁelds, and circa 18% for charcoal kilns. The results show that the introduction of Location-Based Ranking and bagging leads to an improvement in performance varying between 17% and 35%. However, WODAN2.0 does not reach or exceed general human performance, when compared to the results of a citizen science project conducted in the same research area.","language":"en","number":"5","urldate":"2020-05-07","journal":"ISPRS International Journal of Geo-Information","author":[{"propositions":["Verschoof-van","der"],"lastnames":["Vaart"],"firstnames":["Wouter","B."],"suffixes":[]},{"propositions":[],"lastnames":["Lambers"],"firstnames":["Karsten"],"suffixes":[]},{"propositions":[],"lastnames":["Kowalczyk"],"firstnames":["Wojtek"],"suffixes":[]},{"propositions":[],"lastnames":["Bourgeois"],"firstnames":["Quentin","P.J."],"suffixes":[]}],"month":"May","year":"2020","pages":"293","bibtex":"@article{verschoof-van_der_vaart_combining_2020,\n\ttitle = {Combining {Deep} {Learning} and {Location}-{Based} {Ranking} for {Large}-{Scale} {Archaeological} {Prospection} of {LiDAR} {Data} from {The} {Netherlands}},\n\tvolume = {9},\n\tissn = {2220-9964},\n\turl = {https://www.mdpi.com/2220-9964/9/5/293},\n\tdoi = {10.3390/ijgi9050293},\n\tabstract = {This paper presents WODAN2.0, a workﬂow using Deep Learning for the automated detection of multiple archaeological object classes in LiDAR data from the Netherlands. WODAN2.0 is developed to rapidly and systematically map archaeology in large and complex datasets. To investigate its practical value, a large, random test dataset—next to a small, non-random dataset—was developed, which better represents the real-world situation of scarce archaeological objects in different types of complex terrain. To reduce the number of false positives caused by speciﬁc regions in the research area, a novel approach has been developed and implemented called Location-Based Ranking. Experiments show that WODAN2.0 has a performance of circa 70\\% for barrows and Celtic ﬁelds on the small, non-random testing dataset, while the performance on the large, random testing dataset is lower: circa 50\\% for barrows, circa 46\\% for Celtic ﬁelds, and circa 18\\% for charcoal kilns. The results show that the introduction of Location-Based Ranking and bagging leads to an improvement in performance varying between 17\\% and 35\\%. However, WODAN2.0 does not reach or exceed general human performance, when compared to the results of a citizen science project conducted in the same research area.},\n\tlanguage = {en},\n\tnumber = {5},\n\turldate = {2020-05-07},\n\tjournal = {ISPRS International Journal of Geo-Information},\n\tauthor = {Verschoof-van der Vaart, Wouter B. and Lambers, Karsten and Kowalczyk, Wojtek and Bourgeois, Quentin P.J.},\n\tmonth = may,\n\tyear = {2020},\n\tpages = {293},\n}\n\n","author_short":["Verschoof-van der Vaart, W. B.","Lambers, K.","Kowalczyk, W.","Bourgeois, Q. P."],"key":"verschoof-van_der_vaart_combining_2020","id":"verschoof-van_der_vaart_combining_2020","bibbaseid":"verschoofvandervaart-lambers-kowalczyk-bourgeois-combiningdeeplearningandlocationbasedrankingforlargescalearchaeologicalprospectionoflidardatafromthenetherlands-2020","role":"author","urls":{"Paper":"https://www.mdpi.com/2220-9964/9/5/293"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/users/2028754/collections/VXAKQXJD/items?key=PNAHX6guuiHtbx4zjvbou2Cb&format=bibtex&limit=100","dataSources":["fRbZ2u4aKxiW4QZaZ"],"keywords":[],"search_terms":["combining","deep","learning","location","based","ranking","large","scale","archaeological","prospection","lidar","data","netherlands","verschoof-van der vaart","lambers","kowalczyk","bourgeois"],"title":"Combining Deep Learning and Location-Based Ranking for Large-Scale Archaeological Prospection of LiDAR Data from The Netherlands","year":2020}