Identification of Black Reef Shipwreck Sites Using AI and Satellite Multispectral Imagery

Karamitrou, Alexandra; Sturt, Fraser; Bogiatzis, Petros

doi:10.3390/rs15082030

Cited by 2 publications

(1 citation statement)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Projects applying ML approaches to satellite imagery or LiDAR data likewise report a lack of high-quality, well-annotated training data, often due to cost and time constraints (Albrecht et al, 2019;Argyrou and Agapiou, 2022;Canedo et al, 2023;Casini et al, 2021;Gallwey et al, 2019;Kadhim and Abed, 2023;Karamitrou et al, 2022Karamitrou et al, , 2023Lambers et al, 2019;Ofli et al, 2016;Sech et al, 2023;Verschoof-van der Vaart and Landauer, 2021). Transfer learning based on pre-trained models is sometimes proposed as solution to the problem of limited training data, as well as related problems like small dataset size (Casini et al, 2021(Casini et al, , 2022Character et al, 2021;Gallwey et al, 2019;Sech et al, 2023;Xiong et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Validating predictions of burial mounds with field data: the promise and reality of machine learning

Sobotkova,

Kristensen-McLachlan,

Mallon

et al. 2024

View full text Add to dashboard Cite

PurposeThis 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.Design/methodology/approachAutomated 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.FindingsValidation 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.Research limitations/implicationsOur 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.Practical implicationsImproving 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.Social implicationsOur 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.Originality/valueUnlike 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.

show abstract

Section: Introductionmentioning

confidence: 99%

Validating predictions of burial mounds with field data: the promise and reality of machine learning

Sobotkova,

Kristensen-McLachlan,

Mallon

et al. 2024

View full text Add to dashboard Cite

show abstract

Research on the Influencing Factors of AUV Hovering Control in Null-Speed State

Wang,

Jiang,

Wan

et al. 2024

JMSE

View full text Add to dashboard Cite

Intelligent underwater vehicles hover by way of a hovering control system. To provide design inputs and maneuver guidance, this study focused on the characteristics of intelligent underwater vehicles during hovering control with the propulsion system shut down, established a mathematical model of hovering control and determined injection and drainage functions based on optimal control theory. From analysis simulation experiments, the influence laws of control parameters, control timing and rate of injection and drainage control upon hovering control were deduced. It is proposed that, at the time of control parameter selection, the continuous injection and drainage rate at each time should be reduced as far as possible to relieve the demand on the volume of the reservoir when the requirement of depth control accuracy has been satisfied. In addition, the injection and drainage control should initiate when depth changes exceed 0.5 m. Suggestions are included on the minimum injection and drainage rate required for different initial disturbances. The proposed suggestions guide the design of hovering control systems and hovering control over intelligent underwater vehicles.

show abstract

Identification of Black Reef Shipwreck Sites Using AI and Satellite Multispectral Imagery

Cited by 2 publications

References 63 publications

Validating predictions of burial mounds with field data: the promise and reality of machine learning

Validating predictions of burial mounds with field data: the promise and reality of machine learning

Research on the Influencing Factors of AUV Hovering Control in Null-Speed State

Contact Info

Product

Resources

About