BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.cienciaenmexico.com//igisc-2026//speaker//ZGPJCU
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=5SU;BYMONTH=10;UNTIL=20001029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20010930T030000
RRULE:FREQ=YEARLY;BYDAY=5SU;BYMONTH=9;UNTIL=20010930T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20021027T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20000402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20010506T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=5;UNTIL=20010506T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20020407T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20220403T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-igisc-2026-P9T9DN@pretalx.cienciaenmexico.com
DTSTART;TZID=CST:20261112T125000
DTEND;TZID=CST:20261112T130500
DESCRIPTION:Accurate drought prediction in data-scarce urban settings is a 
 challenge with\ndirect implications for water management. This study evalu
 ates whether combining\nground-based drought indices with MODIS and ERA5-L
 and satellite data improves\nRandomForestdrought index reconstruction acro
 ss six meteorological stations in Mex\nico City. Two indices — SPI and S
 PEI — were computed at 3\, 6\, 12\, and 24-month\nscales. Four feature c
 onfigurations and two training strategies were compared: a global\nmodelus
 ingallstationssimultaneously\,andaspatialpoolingapproachthatconcatenates\n
 all station records to increase training sample size from 192 to 1\,152 mo
 nthly obser\nvations. Feature selection (top-30 predictors by importance s
 core) and spatial pooling\nsubstantially improved predictive performance. 
 Average 𝑅2 for SPEI-12 increased from\n0.51 (global model) to 0.82 (poo
 ling)\, and for SPEI-3 from 0.29 to 0.43. The main\nfinding is that in sma
 ll-data contexts\, expanding the training set through spatial pooling\nis 
 more effective than adding satellite predictors alone.
DTSTAMP:20261122T123838Z
LOCATION:Sala Geomática 7
SUMMARY:Satellite-Enhanced Drought Index Reconstruction in Mexico City Usin
 g Random Forest with Spatial Data Pooling - Yunue Garza
URL:https://pretalx.cienciaenmexico.com/igisc-2026/talk/P9T9DN/
END:VEVENT
END:VCALENDAR
