Search results

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.

The main aim of this article is to broaden the notion of strategic intent in public relations. It also develops an understanding of the social value of what can be defined as the first modern health communication campaign in Europe based on strategic intents and the development of modernity.

The study is based on both historical research and empirical material from the Norwegian tuberculosis campaign from 1889 up to 1913, when Norwegian women achieved suffrage. The campaign is analysed in the framework of modernity and social theory. The literature on lobbying and social movements is also used to develop a theoretical framework for the notion of strategic intent.

The study shows that strategic intent can be divided into two layers: (1) the implicit strategic intent is the real purpose behind the communication efforts, whereas (2) the explicit intent is found directly in the communication efforts. The explicit intent may be presented as a solution for the good of society at the right political moment, giving an organisation the possibility to mobilise for long-term social changes, in which could be the implicit intent.

The distinction between explicit and implicit strategic intent broadens our understanding on how to make long-term social changes as well as how social and political changes occur in modern societies. The article also gives a historical account of what is here defined as the first modern health communication campaign in Europe and its social value.

This study illustrates the economic and financial dynamics of the sector, analysing the evolution of the main ratios of profitability and financial structure of 1,559 Italian real estate companies divided into the three macro-regions: North, Centre and South, in the period 2011–2020. In this way, it is also possible to verify the responsiveness to the 2020 pandemic crisis.

The analysis uses descriptive statistics tools and the ANOVA method of analysis of variance, supplemented by the Tukey–Kramer test, to identify significant differences between the three Italian macro-regions.

The study shows the increase in profitability after the 2008 crisis, despite its reverberation in the years 2012–2013. The financial structure of companies improved almost everywhere. The pandemic had modest effects on performance.

In the future, other indices should be considered to gain a more comprehensive view. This is a quantitative study based on financial statements data that neglects other important economic and social factors.

Public policies could use this study for better interventions to support the sector. In addition, internal management can compare their company's performance with the industry average to identify possible improvements.

The research analyses an economic field that employs a large number of people, especially when considering the construction and real estate services covered by this analysis.

The study contributes to the literature by providing a quantitative analysis of industry dynamics, with comparative information that can be deduced from financial statements over the years.