When Computers Dream of Charcoal

Abstract

This research employs machine learning (Mask Region-Based Convolutional Neural Networks [Mask R-CNN]) and cluster analysis (Density-based spatial clustering of applications with noise [DBSCAN]) to identify more than 20,000 relict charcoal hearths (RCHs) organized in large “fields” within and around State Game Lands (SGLs) in Pennsylvania. This research has two important threads that we hope will advance the archaeological study of landscapes. The first is the significant historical impact of charcoal production, a poorly understood industry of the late eighteenth to early twentieth century, on the historic and present landscape of the United States. Although this research focuses on charcoal production in Pennsylvania, it has broad application for both identifying and contextualizing historical charcoal production throughout the world and for better understanding modern charcoal production. The second thread is the use of open data, open source, and open access tools to conduct this analysis, as well as the open publication of the resultant data. Not only does this research demonstrate the significance of open access tools and data but the open publication of our code as well as our data allow others to replicate our work, to tweak our code and protocols for their own work, and reuse our results.

Automated large‐scale mapping and analysis of relict charcoal hearths in Connecticut (USA) using a Deep Learning YOLOv4 framework

“…With the ever‐increasing reliance of archaeologists on remotely sensed data (Opitz & Herrmann, 2018)—with some even advocating for remote sensing as the primary source for archaeological prospection of large areas (Banaszek et al, 2018)—the usability of automated mapping approaches for large‐scale archaeological survey becomes ever more important and necessitates investigation (Lambers et al, 2019). However, up‐to‐now, the application of automated methods is generally limited to relatively small test areas, although a trend towards covering larger areas can be observed (e.g., Berganzo‐Besga et al, 2021; Carter et al, 2021; Suh et al, 2021). Even though, questions concerning the reliability and transferability of these methods for large spatial scales remain (Cowley et al, 2020; Kermit et al, 2018; Verschoof‐van der Vaart & Landauer, 2022).…”

“…Previous research in an effort to automatically detect RCHs has relied on various methods including Template Matching (Schneider et al, 2015;Trier & Pilø, 2012) and Geographic Object-Based Image Analysis (Witharana et al, 2018), whereas more recently, Machine Learning approaches are being developed and utilized (Anderson, 2019;Bonhage et al, 2021;Carter et al, 2021;Davis & Lundin, 2021;Kazimi et al, 2020Kazimi et al, , 2019Oliveira et al, 2021;Suh et al, 2021;Trier et al, 2021Trier et al, , 2018 (Guo et al, 2016)-that learn to generalize from a large set of labelled examples, rather than relying on a human operator to set parameters or formulate rules. To date, these automated methods are mainly tested in an experimental setting but have yet to be applied in various contexts or on a large (e.g., regional or national) scale (Verschoof-van der Vaart et al, 2020; but see for instance Berganzo-Besga et al, 2021;Orengo et al, 2020), with this being the aim of previous initiatives (Trier et al, 2019).…”

“…Previous research in an effort to automatically detect RCHs has relied on various methods including Template Matching (Schneider et al, 2015; Trier & Pilø, 2012) and Geographic Object‐Based Image Analysis (Witharana et al, 2018), whereas more recently, Machine Learning approaches are being developed and utilized (Anderson, 2019; Bonhage et al, 2021; Carter et al, 2021; Davis & Lundin, 2021; Kazimi et al, 2020, 2019; Oliveira et al, 2021; Suh et al, 2021; Trier et al, 2021, 2018; Verschoof‐van der Vaart et al, 2020). Deep Learning (LeCun et al, 2015), a subfield of Machine Learning, predominantly employs Convolutional Neural Networks (CNNs)—hierarchically structured algorithms that generally consist of a (image) feature extractor and classifier (Guo et al, 2016)—that learn to generalize from a large set of labelled examples, rather than relying on a human operator to set parameters or formulate rules.…”

EvaluatingMaskR‐CNN models to extract terracing across oceanic high islands: A case study from Sāmoa

“…Given the shared morphological characteristics of most terraces, we are confident that this model will be applicable to other places within and outside Oceania. Further, we demonstrate, building on prior research (e.g., Bonhage et al, 2021;Carter et al, 2021;Dolejš et al, 2020)…”

“…Such palimpsests can also provide estimates of which locations of a landscape were most frequently and intensively occupied over time, as well as those areas where habitation or other activities were sporadic or avoided (Freeman et al 2016;Ladefoged et al 2011;Sugiyama et al 2021). Documentation of feature locations, and the nature of features across space, is also a first step in generating robust models of settlement and demographic change (Carter et al 2021;Klassen et al 2021;Ladefoged et al 2011) as well as in tracking archaeological preservation and stewardship (Sugiyama et al 2021).…”