via PLOS One, 5 Nov 2018: A cool new Open Access paper by Klassen et al. using machine learning to create a predictive chronology of Angkorian temples based on the architectural features and artifacts found at a site.
Archaeologists often need to date and group artifact types to discern typologies, chronologies, and classifications. For over a century, statisticians have been using classification and clustering techniques to infer patterns in data that can be defined by algorithms. In the case of archaeology, linear regression algorithms are often used to chronologically date features and sites, and pattern recognition is used to develop typologies and classifications. However, archaeological data is often expensive to collect, and analyses are often limited by poor sample sizes and datasets. Here we show that recent advances in computation allow archaeologists to use machine learning based on much of the same statistical theory to address more complex problems using increased computing power and larger and incomplete datasets. This paper approaches the problem of predicting the chronology of archaeological sites through a case study of medieval temples in Angkor, Cambodia. For this study, we have a large dataset of temples with known architectural elements and artifacts; however, less than ten percent of the sample of temples have known dates, and much of the attribute data is incomplete. Our results suggest that the algorithms can predict dates for temples from 821–1150 CE with a 49-66-year average absolute error. We find that this method surpasses traditional supervised and unsupervised statistical approaches for under-specified portions of the dataset and is a promising new method for anthropological inquiry.
Source: Semi-supervised machine learning approaches for predicting the chronology of archaeological sites: A case study of temples from medieval Angkor, Cambodia
via PhysOrg, 10 October 2018: A new Open Access paper in PLOS One indicates that the ‘brief’ 10th century Khmer capital of Koh Ker may not have been so brief after all.
Source: Tegan et al., PLOS ONE. https://doi.org/10.1371/journal.pone.0203962
The classic account of the ancient city of Koh Ker is one of a briefly-occupied and abruptly-abandoned region, but in reality, the area may have been occupied for several centuries beyond what is traditionally acknowledged, according to a study published October 10, 2018 in the open-access journal PLOS ONE by Tegan Hall of the University of Sydney, Australia and colleagues.
Koh Ker was part of the Khmer kingdom during the Angkor period in what is now Cambodia. For a mere two decades in the tenth century CE, the city served as royal capital, and it has long been proposed that after the royal seat moved back to Angkor, the city and its surroundings were abandoned. In this study, Hall and colleagues tested this theory by analyzing charcoal and pollen remains in sediment cores spanning several centuries in three Koh Ker localities, including the moat of the main central temple. From these data, they inferred a long history of fluctuations in fire regimes and vegetation which are highly indicative of patterns of human occupation and land use over time.
Source: City of Koh Ker was occupied for centuries longer than previously thought
Re-evaluating the occupation history of Koh Ker, Cambodia, during the Angkor period: A palaeo-ecological approach | PLOS One
This story broke a couple of weeks ago, but I’ve been behind posts because of the recent 13th conference of the European Association of Southeast Asian Archaeologists in Berlin. A study in PLoS ONE suggests that the Indonesian hobbits suffer from cretinism rather than being an altogether new species of hominid, by comparing the bones of homo floresiensis, normal humans, chimpanzees and cretins.
Post-Cranial Skeletons of Hypothyroid Cretins Show a Similar Anatomical Mosaic as Homo floresiensis
PLoS ONE, 2010
‘Hobbit’ Was an Iodine-Deficient Human, Not Another Species, New Study Suggests
Science Daily, 28 September 2010