BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.geoinfo-lab.org//foss4g-asia-2024//LCCEZL
BEGIN:VTIMEZONE
TZID:+07
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:+07
TZOFFSETFROM:+0700
TZOFFSETTO:+0700
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-asia-2024-UUUPDK@talks.geoinfo-lab.org
DTSTART;TZID=+07:20241217T101500
DTEND;TZID=+07:20241217T103000
DESCRIPTION:Species Distribution Modeling (SDM) is a statistical methodolog
 y used to predict the spatial and temporal distribution of species based o
 n environmental conditions that are conducive to their survival and reprod
 uction. This modeling approach leverages spatially explicit species occurr
 ence records alongside various environmental covariates\, including climat
 e\, terrain\, and land cover\, as input variables\, with the aim of quanti
 fying and mapping species-environment interactions. SDM has become a criti
 cal tool in ecological research and conservation biology for understanding
  and predicting species distribution patterns. A range of machine learning
  and deep learning techniques can be employed in SDM\, such as Logistic Re
 gression (LR)\, Random Forest (RF)\, Multilayer Perceptron (MLP)\, Convolu
 tional Neural Network (CNN)\, and Generative Adversarial Network-CNN (GAN-
 CNN). Despite the availability of these techniques\, there is a lack of a 
 comprehensive application that integrates these algorithms for species dis
 tribution modeling. To address this gap\, this paper introduces a new tool
 \, kari-sdm\, which enables users to perform SDM utilizing a variety of te
 chniques. Kari-sdm supports LR\, RF\, MLP\, CNN\, and GAN-CNN algorithms\,
  all based on open-source frameworks PyTorch and scikit-learn. Additionall
 y\, it facilitates all necessary preprocessing steps\, from data collectio
 n\, cleaning\, transformation\, spatial preprocessing\, and environmental 
 variable selection\, to data splitting. The tool also provides functions f
 or model evaluation\, result visualization\, and cross-validation. The pri
 mary goal of kari-sdm is to assist ecologists in modeling species distribu
 tions\, interpreting results\, and developing informed conservation and ma
 nagement strategies.
DTSTAMP:20260416T212143Z
LOCATION:Room34-1104
SUMMARY:kari-sdm: Advanced Species Distribution Modeling using PyTorch and 
 scikit-learn - Lee\, Jeongho\, Byeong-Hyeok Yu\, Chunghyeon Oh\, Soodong L
 ee\, Cho Bonggyo
URL:https://talks.geoinfo-lab.org/foss4g-asia-2024/talk/UUUPDK/
END:VEVENT
END:VCALENDAR