Deep Data Example: Zbiva, Early Medieval Data Set for the Eastern Alps (original) (raw)
Related papers
Think big about data: Archaeology and the Big Data challenge
2015
Usually defined as high volume, high velocity, and/or high variety data, Big Data permit us to learn things that we could not comprehend using smaller amounts of data, thanks to the empowerment provided by software, hardware and algorithms. This requires a novel archaeological approach: to use a lot of data; to accept messiness; to move from causation to correlation. Do the imperfections of archaeological data preclude this approach? Or are archaeological data perfect because they are messy and difficult to structure? Normally archaeology deals with the complexity of large datasets, fragmentary data, data from a variety of sources and disciplines, rarely in the same format or scale. If so, is archaeology ready to work more with data-driven research, to accept predictive and probabilistic techniques? Big Data inform, rather than explain, they expose patterns for archaeological interpretation, they are a resource and a tool: data mining, text mining, data visualisations, quantitative methods, image processing etc. can help us to understand complex archaeological information. Nonetheless, however seductive Big Data appear, we cannot ignore the problems, such as the risk of considering that data = truth, and intellectual property and ethical issues. Rather, we must adopt this technology with an appreciation of its power but also of its limitations.
Archaeologists, like other scientists, are experiencing a dataflood in their discipline, fueled by a surge in computing power and devices that enable the creation, collection, storage and transfer of an increasingly complex (and large) amount of data, such as remotely sensed imagery from a multitude of sources. In this paper, we pose the preliminary question if this increasing availability of information actually needs new computerized techniques, and Artificial Intelligence methods, to make new and deeper understanding into archaeological problems. Simply said, while it is a fact that Deep Learning (DL) has become prevalent as a type of machine learning design inspired by the way humans learn, and utilized to perform automatic actions people might describe as intelligent, we want to anticipate, here, a discussion around the subject whether machines, trained following this procedure, can extrapolate, from archaeological data, concepts and meaning in the same way that humans would do. Even prior to getting to technical results, we will start our reflection with a very basic concept: Is a collection of satellite images with notable archaeological sites informative enough to instruct a DL machine to discover new archaeological sites, as well as other potential locations of interest? Further, what if similar results could be reached with less intelligent machines that learn by having people manually program them with rules? Finally: If with barrier of meaning we refer to the extent to which humanlike understanding can be achieved by a machine, where should be posed that barrier in the archaeological data science?
BIG DATA IN LANDSCAPE ARCHAEOLOGICAL PROSPECTION
While traditionally archaeological research has mainly been focused on individual cultural heritage monuments or distinct archaeological sites, the Austrian based Ludwig Boltzmann Institute for Archaeological Prospection and Virtual Archaeology goes beyond the limitations of discrete sites in order to understand their archaeological context. This is achieved by investigating the space in-between the sites, studying entire archaeological landscapes from the level of individual postholes to the mapping of numerous square kilometres. This large-scale, high-resolution, multi-method prospection approach leads to enormous digital datasets counting many terabytes of data that until recently were technically not manageable. Novel programs and methods of data management had to be developed for data acquisition, processing and archaeological interpretation, in order to permit the extraction of the desired information from the very big amount of data. The analysis of the generated datasets is conducted with the help of semi-automatic algorithms within complex three-, or even four-dimensional geographical information systems. The outcome of landscape archaeological prospection surveys is visually communicated to the scientific community as well as to the general public and stakeholders. In many cases, a visualization of the scientific result and archaeological interpretations can be a powerful and suitable tool to illustrate and communicate even complex contexts to a wide audience. This paper briefly presents the great potential offered by a combination of large-scale non-invasive archaeological prospection methods and standardized workflows for the integration of big data, its interpretation and visualization. The proposed approach provides a context for buried archaeology across entire archaeological landscapes, changing our understanding of known monuments. We address the overcome and remaining challenges with the help of examples taken from outstanding landscape archaeological prospection case studies. Resumen: Aunque tradicionalmente la investigación arqueológica ha estado fundamentalmente centrada en monumentos y yacimientos arqueológicos de forma individual, el Ludwig Boltzmann Institute for Archaeological Prospection and Virtual Archaeology (Austria) va más allá de los límites de yacimientos particulares con el objetivo de entender su contexto arqueológico. Esto es conseguido mediante la investigación del espacio entre yacimientos y estudiando paisajes arqueológicos completos yendo desde un hoyo de poste hasta el mapeado de varios kilómetros cuadrados. El enfoque de prospección multi-metodológico a gran escala y de alta resolución conduce hacia un enorme conjunto de datos digital que incluye varios Terabytes de información los cuales no habían podido ser manipulados hasta hace poco debido a limitaciones tecnológicas. Por consiguiente, nuevos programas y métodos de gestión de datos han sido diseñados para la adquisición y procesado de datos así como interpretación arqueológica para así permitir la extracción de la información deseada desde estos enormes bancos de datos. El análisis de estos conjuntos de datos generados es llevado a cabo a través de análisis de sistemas de información geográfica tridimensionales e incluso cuatridimensionales. El resultado de la prospección de paisajes arqueológicos es transferido de forma visual a la comunididad científica así como al gran público e interesados en la materia. En muchos casos una visualización de los resultados científicos e interpretaciones arqueológicas puede ser una herramienta más poderosa y adecuada para ilustrar y comunicar contextos arqueológicos complejos a un público mayor. Este artículo presenta de forma breve el gran potencial ofrecido por la combinación de métodos de prospección arqueológica de gran resolución a gran escala y unos flujos de trabajo estandarizados para integración, interpretación y visualización de datos. La estrategía propuesta proporciona un contexto para restos arqueológicos enmarcados en paisajes arqueológicos que viene a cambiar nuestra This work is licensed under a Creative Commons 4.0 International License (CC BY-NC-ND 4.0) EDITORIAL UNIVERSITAT POLITÈCNICA DE VALÈNCIA forma de entender monumentos ya conocidos. Pretendemos también superar los desafios que quedan con la ayuda de ejemplos sacados de excepcionales paisajes arqueológicos que son nuestros estudios de caso a prospectar. Palabras clave: big data, gran escala, alta resolución, métodos no-invasivos, prospección arqueológica, métodos geofísicos en superficie, arqueología virtual, interpretación de datos, arqueología del paisaje, preservación, difusión.
The Barrier of meaning in archaeological data science
ArXiv, 2021
Archaeologists, like other scientists, are experiencing a dataflood in their discipline, fueled by a surge in computing power and devices that enable the creation, collection, storage and transfer of an increasingly complex (and large) amount of data, such as remotely sensed imagery from a multitude of sources. In this paper, we pose the preliminary question if this increasing availability of information actually needs new computerized techniques, and Artificial Intelligence methods, to make new and deeper understanding into archaeological problems. Simply said, while it is a fact that Deep Learning (DL) has become prevalent as a type of machine learning design inspired by the way humans learn, and utilized to perform automatic actions people might describe as intelligent, we want to anticipate, here, a discussion around the subject whether machines, trained following this procedure, can extrapolate, from archaeological data, concepts and meaning in the same way that humans would do...
Big Archaeological Data. The ArchAIDE project approach
Conferenza GARR_17 Selected papers. The Data way to science, Venezia, 15-17 novembre 2017, 2018
Digitisation has changed archaeology deeply and has increased exponentially the amount of data that could be processed, but it does not by itself involve datafication, which is the act of transforming something (objects, processes, etc.) into a quantified format, so they can be tabulated and analysed. Datafication fits a Big Data approach and promises to go significantly beyond digitisation. To datafy archaeology would mean to produce a flow of data starting from the data produced by the archaeological practice, for instance, locations, interactions and relations between finds and sites. The ArchAIDE project goes exactly in this direction. ArchAIDE is a H2020 funded project (2016-2019) that will realise a tool for recognising archaeological potsherds; a web-based real-time data visualization to generate new understanding; an open archive to allow the archival and re-use of ar-chaeological data. This process would move archaeology towards data-driven research and Big Data.
The challenges of digging data
Proceedings of the 13th ACM/IEEE-CS joint conference on Digital libraries - JCDL '13, 2013
Field archaeology only recently developed centralized systems for data curation, management, and reuse. Data documentation guidelines, standards, and ontologies have yet to see wide adoption in this discipline. Moreover, repository practices have focused on supporting data collection, deposit, discovery, and access more than data reuse. In this paper we examine the needs of archaeological data reusers, particularly the context they need to understand, verify, and trust data others collect during field studies. We then apply our findings to the existing work on standards development. We find that archaeologists place the most importance on data collection procedures, but the reputation and scholarly affiliation of the archaeologists who conducted the original field studies, the wording and structure of the documentation created during field work, and the repository where the data are housed also inform reuse. While guidelines, standards, and ontologies address some aspects of the context data reusers need, they provide less guidance on others, especially those related to research design. We argue repositories need to address these missing dimensions of context to better support data reuse in archaeology.
The Zbiva Web Application: a tool for Early Medieval archaeology of the Eastern Alps
THE ARIADNE IMPACT, 2019
Zbiva’ is a research database for the archaeology of the eastern Alps and its surrounding regions in the Early Middle Ages. Its inception in the early 1980s was deeply rooted in the scientific research context of the time. In 2016 the database front-end was migrated to the ‘Zbiva web application’ based on an open source Arches 3.0 platform. Zbiva is a GIS-enabled web application focused on catering to the needs of highly invested researchers. Some of the most important design ideas for the application were informed either by the ARIADNE User Needs report or by discussion with many collaborators within the ARIADNE consortium. The design maxim for Zbiva was to focus on highly motivated and invested users. This was only possible because Zbiva’s data top level data search is ‘outsourced’ to the ARIADNE portal. KEYWORDS: Early Medieval archaeology; Eastern Alps; web application; database
Expedite and upscale: large area archaeological survey in the age of big data and machine learning
2021
Archaeology is something of a magpie discipline, with a track record of appropriating approaches, theory, and techniques from other fields that has helped, for example, to drive the 'digital revolution' in archaeological practice. Digital documentation, 3D datasets and complex analyses are now routine practice rather than revolutionary, but it is one thing that such methods are widespread, and quite another for their implications to be fully explored. Archaeologists at Historic Environment Scotland (HES) are exploring these implications for their workflows, recognising that sometimes assimilation of new technology or practice can happen organically, but also that sometimes a more fundamental reassessment is required of how we do what we do.
Geospatial Big Data and archaeology: Prospects and problems too great to ignore
Journal of Archaeological Science, 2017
As spatial technology has evolved and become integrated in to archaeology, we face a new set of challenges posed by the sheer size and complexity of data we use and produce. In this paper I discuss the prospects and problems of Geospatial Big Data (GBD) e broadly defined as data sets with locational information that exceed the capacity of widely available hardware, software, and/or human resources. While the datasets we create today remain within available resources, we nonetheless face the same challenges as many other fields that use and create GBD, especially in apprehensions over data quality and privacy. After reviewing the kinds of archaeological geospatial data currently available I discuss the near future of GBD in writing culture histories, making decisions, and visualizing the past. I use a case study from New Zealand to argue for the value of taking a data quantity-in-use approach to GBD and requiring applications of GBD in archaeology be regularly accompanied by a Standalone Quality Report.