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.

Heavy rainfall is one of the main causes of the degradation of historic rammed Earth architecture. For this reason, ensuring the conservation thereof entails understanding the factors involved in these risk situations. The purpose of this study is to research three past events in which rainfall caused damage and collapse to historic rammed Earth fortifications in Andalusia in order to analyse whether it is possible to prevent similar situations from occurring in the future.

The three case studies analysed are located in the south of Spain and occurred between 2017 and 2021. The hazard presented by rainfall within this context has been obtained from Art-Risk 3.0 (Registration No. 201999906530090). The vulnerability of the structures has been assessed with the Art-Risk 1 model. To characterise the strength, duration, and intensity of precipitation events, a workflow for the statistical use of GPM and GSMaP satellite resources has been designed, validated, and tested. The strength of the winds has been evaluated from data from ground-based weather stations.

GSMaP precipitation data is very similar to data from ground-based weather stations. Regarding the three risk events analysed, although they occurred in areas with a torrential rainfall hazard, the damage was caused by non-intense rainfall that did not exceed 5 mm/hour. The continuation of the rainfall for several days and the poor state of conservation of the walls seem to be the factors that triggered the collapses that fundamentally affected the restoration mortars.

A workflow applied to vulnerability and hazard analysis is presented, which validates the large-scale use of satellite images for past and present monitoring of heritage structure risk situations due to rain.

We make use of the Volunteered Geographic Information (VGI) data to extract the total extent of the roads using remote sensing images. VGI data is often provided only as vector data represented by lines and not as full extent. Also, high geolocation accuracy is not guaranteed and it is common to observe misalignment with the target road segments by several pixels on the images. In this work, we use the prior information provided by the VGI and extract the full road extent even if there is significant mis-registration between the VGI and the image. The method consists of image segmentation and traversal of multiple agents along available VGI information. First, we perform image segmentation, and then we traverse through the fragmented road segments using autonomous agents to obtain a complete road map in a semi-automatic way once the seed-points are defined. The road center-line in the VGI guides the process and allows us to discover and extract the full extent of the road network based on the image data. The results demonstrate the validity and good performance of the proposed method for road extraction that reflects the actual road width despite the presence of disturbances such as shadows, cars and trees which shows the efficiency of the fusion of the VGI and satellite images.

As stated in the United Nations Global Assessment Report 2022 Concept Note, decision-makers everywhere need data and statistics that are accurate, timely, sufficiently disaggregated, relevant, accessible and easy to use. The purpose of this paper is to demonstrate scalable and replicable methods to advance and integrate the use of earth observation (EO), specifically ongoing efforts within the Group on Earth Observations (GEO) Work Programme and the Committee on Earth Observation Satellites (CEOS) Work Plan, to support risk-informed decision-making, based on documented national and subnational needs and requirements.

Promotion of open data sharing and geospatial technology solutions at national and subnational scales encourages the accelerated implementation of successful EO applications. These solutions may also be linked to specific Sendai Framework for Disaster Risk Reduction (DRR) 2015–2030 Global Targets that provide trusted answers to risk-oriented decision frameworks, as well as critical synergies between the Sendai Framework and the 2030 Agenda for Sustainable Development. This paper provides examples of these efforts in the form of platforms and knowledge hubs that leverage latest developments in analysis ready data and support evidence-based DRR measures.

The climate crisis is forcing countries to face unprecedented frequency and severity of disasters. At the same time, there are growing demands to respond to policy at the national and international level. EOs offer insights and intelligence for evidence-based policy development and decision-making to support key aspects of the Sendai Framework. The GEO DRR Working Group and CEOS Working Group Disasters are ideally placed to help national government agencies, particularly national Sendai focal points to learn more about EOs and understand their role in supporting DRR.

The unique perspective of EOs provide unrealized value to decision-makers addressing DRR. This paper highlights tangible methods and practices that leverage free and open source EO insights that can benefit all DRR practitioners.