En el siguiente artículo analizamos uno de los más modernos instrumentos de documentación gráfica del patrimonio, el láser escáner. Aunque profundizaremos en todos aquellos aspectos técnicos, logísticos y de método relativos a su empleo, nos centraremos en su efectiva aplicabilidad dentro del campo de la Arqueología de la Arquitectura, incidiendo en aquellas capacidades diagnósticas que pueden ayudar al estratígrafo a determinar la secuencia evolutiva de un edificio. Tomaremos como base nuestra experiencia en

RESUMENLa propuesta que se hace en este artículo parte del convencimiento de que existen ciertos métodos de análisis en arqueología que podrían mejorar notablemente si incorporaran las técnicas cuantitativas; uno de esos métodos es sin duda el de la lectura estratigráfica de alzados. A lo largo de estas líneas expondremos cual es nuestro bagaje al respecto, haciendo un breve recorrido que, si bien partirá de los primeros experimentos más intuitivos, se centrará prioritariamente en nuestros últimos ensayos de carácter matemático-estadístico. En el texto se apreciará cómo estamos experimentando con métodos de captura masiva de información geométrica que después, mediante programación, sometemos a una minería de datos basada en el empleo de algoritmos propios de las técnicas de análisis multivariante. Aportamos finalmente nuestra reflexión sobre un futuro en el que prevemos que la lectura estratigráfica de alzados alcanzará un grado de automatización muy próximo a los sistemas expertos y la inteligencia artificial. ABSTRACTThe proposal made in this article is based on the conviction that there are certain methods of analysis in archaeology that could be significantly improved i f t hey incorporated quantitative t echniques; o ne o f those methods is undoubtedly that of the stratigraphic reading of elevations. In the course of this document, our background in this regard will be explained, by means of a brief summary. Although the starting point will be based on the initial more intuitive experiments, it will focus primarily on our latest mathematical-statistical trials. The text will identify how we are experimenting with methods of massive capture of geometric information, which through programming is later subjected to data mining, based on the use of multivariate analysis techniques with proprietary algorithms. Finally, we reflect on the future in which we envisage that the stratigraphic reading of elevations will reach a degree of automation very close to expert systems and artificial intelligence.

The presence of artificial intelligence in our lives is increasing and being applied to fields such as medicine, engineering, telecommunications, remote sensing and 3D visualization. Nevertheless, it has never been used for the stratigraphic study of historical buildings. Thus far, archaeologists and architects, the experts in archaeology of architecture, have led this research. The method consisted of visually—and, consequently, subjectively—identifying certain evidence regarding the elevations of such buildings that could be a consequence of the passage of time. In this article, we would like to present the results from one of the research projects pursued by our group, in which we automated the stratigraphic study of some historic buildings using multivariate statistic techniques. To this end, we first measured the building using surveying techniques to create a 3D model, and then, we broke down every stone into qualitative and quantitative variables. To identify the stratigraphic features on the walls, we applied machine learning by conducting different predictive and descriptive analyses. The predictive analyses were used to rule out any blocks of stone with different characteristics, such as rough stones, joint ashlars, and voussoirs of arches; these are irregularities that probably show building processes and whose identification is crucial in ascertaining the structural evolution of the building. In supervised learning, we experimented with decision trees and random forest—and although the results were good in all cases, we ultimately opted to implement the predictive model obtained using the last one. While identifying the evidence on the walls, it was also very important to identify different continuity solutions or interfaces present on them, because although these are elements without materiality, they are of great value in terms of timescale, because they delimit different strata and allow us to deduce the relationship between them.

El presente artículo está pensado para ofrecer una panorámica general de diversas metodologías que, respetando la perspectiva estratigráfica inherente a la Arqueología de la Arquitectura, se han ensayado en las últimas dos décadas con el fin de ampliar el horizonte de aplicabilidad de la disciplina, desde el ámbito habitual de trabajo que es el edificio singular, para llegar al paisaje antropizado. Prácticamente todas las experiencias de las que se habla han sido desarrolladas por el Grupo de Investigación en Patrimonio Construido de la UPV/EHU en el ámbito territorial del municipio de Vitoria-Gasteiz.