BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computational and machine learning methods to investigate the comp
 lex human-environment interaction. From the Mediterranean to the Andes - M
 aria Elena Castiello\, Institute of Archaeological Sciences\, University o
 f Bern
DTSTART:20230605T150000Z
DTEND:20230605T163000Z
UID:TALK200680@talks.cam.ac.uk
CONTACT:Simon Carrignon
DESCRIPTION:Investigating the interaction of people with their environment
 \, how humans shaped and transformed it in the long-durée\, has long been
  a trajectory in archaeology. Moreover\, thanks to computational methods a
 nd machine learning techniques nowadays widely adopted and developed in ar
 chaeology\, the possibilities to explore\, interrogate and disentangle arc
 haeological information in order to simulate and better understand the pas
 t\, have significantly increased.\n\nThe aim of this talk is to give an ov
 erview of the multiple and infinite uses of computational approaches and m
 achine learning techniques in archaeology. Synthesising data and results f
 rom projects carried out in the past years\, and drawing upon different ma
 terials\, several case studies ranging from the Mediterranean\, Asia and S
 outh America\, will be presented.\n\nOn the one hand\, the integrated use 
 of multi proxy and machine learning methods in a paleo-ecological and pale
 o-climatic framework analysing the dynamics of the first\, small-scale Neo
 lithic farming societies facing climate constraints in the Mediterranean\,
  and on the other the complementary methodological application of a multi-
 agents based model to simulate Neolithic hunting strategies within and aro
 und the desert kites structures in Saudi Arabia will be tackled. Finally\,
  the talk will summit on the on-going research project – ADArchaeoSA –
  in South America\, to explore the most cutting edge solutions to analyse 
 complex patterns of pre-Inca landscape occupation and transformation in th
 e Andean highlands\, by relying on deep-learning based site detection work
 flows.\n\nIt will be argued here how these methods have become increasingl
 y valuable and needed in the discipline for describing and navigating the 
 challenges of past and present questions of human-environment complexity\,
  developing multi-proxy modelling approaches\, working towards data reprod
 ucibility and accessibility\, and dealing with bias and uncertainty.\n
LOCATION:McDonald Institute Seminar Room\, Department of Archaeology\, Dow
 ning Site
END:VEVENT
END:VCALENDAR