BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.earthmonitor.org//soil-health-now-2026//VQ9JNB
BEGIN:VTIMEZONE
TZID:Europe/Athens
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-soil-health-now-2026-BB3D7A@pretalx.earthmonitor.org
DTSTART;TZID=Europe/Athens:20261207T170000
DTEND;TZID=Europe/Athens:20261207T180000
DESCRIPTION:Grassland systems play a critical role in regulating soil carbo
 n dynamics and delivering essential ecosystem services\, particularly unde
 r the pressures of global climate change. Effective monitoring of soil phy
 sical and chemical properties is therefore critical to support sustainable
  grassland management. However\, conventional laboratory-based analyses ar
 e often costly\, time-consuming\, and difficult to implement at large scal
 es.\nSpectroscopy\, combined with machine learning\, offers a promising al
 ternative by enabling rapid and cost-effective prediction of soil properti
 es. This study evaluates the potential of a commercially available near-in
 frared (NIR) spectrometer\, NeoSpectra\, to support practical soil monitor
 ing in grassland systems. The use of an accessible device aims to simulate
  real-world conditions\, potentially allowing farmers to perform measureme
 nts directly in the field or in simple laboratory settings. NIR spectrosco
 py operates in a wavelength range that is highly sensitive to organic carb
 on and N–H bonds\, which reflects the change of C and N content and maki
 ng it a suitable tool for monitoring grassland soils. The approach integra
 tes spectral data with multiple machine learning models to predict soil ph
 ysical and chemical properties\, with a focus on optimizing model performa
 nce and assessing its robustness under conditions that reflect realistic a
 pplication scenarios. \nThis study highlights the potential of combining N
 IR spectroscopy with machine learning as a scalable tool for soil health m
 onitoring. The approach provides a rapid and accessible method for evaluat
 ing grassland soils and shows potential to support decision-making in sust
 ainable land management under changing environmental conditions.
DTSTAMP:20260825T180317Z
LOCATION:Basement (Foyer)
SUMMARY:Application of Portable NIR Spectroscopy and Machine Learning for S
 oil Health Assessment in Swedish Grassland - Hsiang-Ju Fan
URL:https://pretalx.earthmonitor.org/soil-health-now-2026/talk/BB3D7A/
END:VEVENT
END:VCALENDAR