BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Sediment core analysis using artificial intelligence - Gianluca Ca
 rlini
DTSTART:20230721T170000Z
DTEND:20230721T173000Z
UID:TALK203500@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Subsurface stratigraphic modeling is crucial for a variety of 
 environmental\, societal\, and economic challenges. However\, the need for
  specific sedimentological skills in sediment core analysis may constitute
  a limitation. Methods based on Machine Learning and Deep Learning can pla
 y a central role in automatizing this time-consuming procedure. In this wo
 rk\, using a robust dataset of high-resolution digital images from continu
 ous sediment cores of Holocene age that reflect a wide spectrum of contine
 ntal to shallow-marine depositional environments\, we outline a novel deep
 -learning-based approach to perform automatic semantic segmentation direct
 ly on core images\, leveraging the power of state-of-the-art convolutional
  neural networks. To optimize the interpretation process and maximize scie
 ntific value\, we use six sedimentary facies associations as target classe
 s in lieu of ineffective classification methods based uniquely on litholog
 y. We propose an automated model that can rapidly characterize sediment co
 res\, allowing immediate guidance for stratigraphic correlation and subsur
 face reconstructions.
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR