BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-it-2023//speaker//F3JB3G
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-it-2023-ZGD7RT@talks.staging.osgeo.org
DTSTART;TZID=GMT:20230612T170000
DTEND;TZID=GMT:20230612T171500
DESCRIPTION:West Nile Disease (WND) is one of the most spread zoonosis in I
 taly and Europe caused by a vector-borne virus. In Italy\, the surveillanc
 e for WN and USUTU viruses is focused to early detect the virus circulatio
 n in a territory: it involves equids\, wild and resident birds and mosquit
 oes. \nIn the Italian ecosystem\, peak transmission of WNV to humans typic
 ally occurs between July and September\, coinciding with the summer season
  when mosquitoes are most active and temperatures are highest. To early de
 tect WNV circulation and therefore to reduce the risk of transmission to h
 umans\, wild birds\, corvids\, poultry\, horses\, and mosquitoes are sampl
 ed according to a risk-based ranking of the Italian provinces and WNV infe
 ction are confirmed. Together with field activities it is important to ide
 ntify suitable climatic and environmental conditions for the vectors and v
 irus to spread. The recent and massive availability of Earth Observation (
 EO) data and the continuous development of innovative Machine Learning met
 hods can contribute to automatically identify patterns in big datasets and
  to make highly accurate identification of areas at risk.\nIn this study\,
  the veterinary cases notified in the epidemics 2017-2020 were collected f
 rom the National Information System for Animal Disease Notification (SIMAN
 ) and associated to climatic and environmental variables. EO data were der
 ived from different sources\, downloaded\, mosaicked\, converted to degree
 s (for temperature)\, pre-processed and harmonised: Land Surface Temperatu
 re (LST) Daytime and LST Night-time were derived from the product NASA-MOD
 IS MOD11A2 (8-days temporal resolution\, 250 meters spatial resolution)\; 
 Normalized Difference Vegetation Index (NDVI) dataset was derived from the
  product NASA-MODIS MOD13Q1 (MODIS/Terra Vegetation Indices 16-Day L3 Glob
 al 250 m)\; the Surface Soil Moisture (SSM) was derived from Copernicus - 
 Daily SSM 1-km V1 product. Each eight consecutive images of SSM have been 
 merged to have a unique raster covering the whole Italy\, for a total of 4
 6 images per year. We have then applied a gap filling procedure to replace
  the empty pixels in the datasets\, as the presence of missing values can 
 prevent an accurate and homogeneous (in space and time) prediction. The th
 ree EO datasets have been resampled at the highest available spatial resol
 ution (250 m) using bilinear interpolation method\, and each dataset has m
 aintained its own temporal scale (NDVI: 16 days\; LSTD\, LSTN and SSM: 8 d
 ays).\nApplying a raster-based approach with a time window of 16 days\, we
  investigated the WN virus circulation in relation to the EO variables col
 lected during the 160 days before the infection took place\, with the aim 
 of evaluating the predictive capacity of lagged remotely sensed variables 
 in the identification of areas at risk for WNV circulation in Italy.\n\nAn
  Extreme Gradient Boosting model was trained with data from 2017\, 2018 an
 d 2019 and tested for the 2020 epidemic\, predicting the spatio-temporal W
 NV circulation two weeks in advance with an overall accuracy of 0.86 (sens
 itivity= 0.79\, Specificity = 0.91\, AUC = 0.94). \nThis work lays the bas
 is for an early warning system (16-days ahead) that alert public authoriti
 es when climatic and environmental conditions become favourable to the ons
 et and spread of WNV. This knowledge can be used to define intervention pr
 iorities within national surveillance plans.
DTSTAMP:20260427T163044Z
LOCATION:Sala Videoconferenza @ PoliBa
SUMMARY:Earth Observation Data and Extreme Gradient Boosting Model: innovat
 ive methods predicting West Nile Virus Circulation in Italy - Carla Ippoli
 ti\, Luca Candeloro\, Susanna Tora\, Federica Iapaolo\, Federica Monaco\, 
 Daniela Morelli\, Annamaria Conte
URL:https://talks.staging.osgeo.org/foss4g-it-2023/talk/ZGD7RT/
END:VEVENT
END:VCALENDAR