BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2026//speaker//SR3W37
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-juliacon-2026-8RGCRS@pretalx.com
DTSTART;TZID=CET:20260812T114500
DTEND;TZID=CET:20260812T120000
DESCRIPTION:Spatial machine learning has become increasingly crucial for en
 vironmental prediction tasks. Yet\, current workflows in R and Python face
  challenges when scaling to high‑resolution\, national‑level mapping a
 nd when integrating modern uncertainty‑aware methods. In this talk\, I p
 resent a new Julia‑based spatial machine learning framework for digital 
 soil mapping\, focusing on national soil organic carbon (SOC) prediction i
 n Estonia. The approach combines Random Forest models\, stacked meta‑lea
 rning\, and conformal prediction through the MLJ ecosystem\, while develop
 ing an integration port to Julia of the IGEO7 discrete global grid system 
 (DGGS) to impose a hierarchical spatial structure.\nThis approach targets 
 persistent issues in spatial ML\, such as autocorrelation\, multi‑scale 
 dependencies\, and computational efficiency. It implements DGGS‑based mu
 lti‑resolution covariate aggregation\, spatially aware cross‑validatio
 n\, Shapley values\, and area‑of‑applicability (AOA) assessment using 
 the Dissimilarity Index method. Initial results demonstrate improved spati
 al fidelity\, scalable high-resolution prediction\, and more transparent c
 ommunication of uncertainty.\nThis work showcases how Julia’s speed and 
 composability enable a modern\, reproducible\, and scalable approach to sp
 atial machine learning in comparison to what conventional Python/R workflo
 ws currently offer.
DTSTAMP:20260502T094002Z
LOCATION:Room 3
SUMMARY:Spatial Machine Learning for Digital Soil Mapping - Alexander Kmoch
URL:https://pretalx.com/juliacon-2026/talk/8RGCRS/
END:VEVENT
END:VCALENDAR