Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Capítulo o parte de un libro (BookPart)

‘Linking megaliths’. A computational approach to the study of movement and mobility in the megalithic complex of Galicia (Northwest of the Iberian Peninsula)

  • Carrero Pazos, Miguel
  • White, Devin A.
In this paper we study the spatial relation of more than 3,000 mounds with the natural movement through the landscape in Galicia (NW Spain). We adopt a computational approach by creating three geospatial models of pedestrian transportation networks in a GIS environment which comprised the creation of almost 19 billion routes in the whole region, taking into consideration as the mobility factors the slope, rivers, and land cover. In a second step, we generated an aggregate viewshed map using a regularly-spaced grid of observers across the region, in order to see if the megaliths are located in areas of high visual prominence. Finally, spatial statistical analyses were applied to see if the sites are situated near places that would naturally channel pedestrian movement at local and regional scales, and areas with high visibility. The results point out a clear spatial relation of the megalithic monuments with the movement through the landscape, a trend that might be common to the Atlantic façade of Europe. We argue that this relation could be interpreted as a way of connecting the daily lived human landscapes and long-distance routes which not only physically connected the communities but also enabled the expansion of funerary ideas through terrestrial routes.
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Hybrid MSRM-based deep learning and multitemporal sentinel 2-based machine learning algorithm detects near 10k archaeological tumuli in North-Western Iberia

  • Berganzo Besga, Iban
  • Orengo, Hector A.
  • Lumbreras, Felipe
  • Carrero Pazos, Miguel
  • Fonte, João
  • Vilas Estévez, Benito
This paper presents an algorithm for large-scale automatic detection of burial mounds, one of the most common types of archaeological sites globally, using LiDAR and multispectral satellite data. Although previous attempts were able to detect a good proportion of the known mounds in a given area, they still presented high numbers of false positives and low precision values. Our proposed approach combines random forest for soil classification using multitemporal multispectral Sentinel-2 data and a deep learning model using YOLOv3 on LiDAR data previously pre-processed using a multi–scale relief model. The resulting algorithm significantly improves previous attempts with a detection rate of 89.5%, an average precision of 66.75%, a recall value of 0.64 and a precision of 0.97, which allowed, with a small set of training data, the detection of 10,527 burial mounds over an area of near 30,000 km2, the largest in which such an approach has ever been applied. The open code and platforms employed to develop the algorithm allow this method to be applied anywhere LiDAR data or high-resolution digital terrain models are available., Ministerio de Ciencia e Innovación, España | Ref. RYC-2016-19637, Ministerio de Ciencia e Innovación, España | Ref. BOSSS TIN2017-89723-P, European Commission | Ref. H2020, n. 886793, European Commission | Ref. H2020, n. 794048, Fundación BBVA | Ref. Ayuda a Equipos de Investigación Científica