BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Machine-learning algorithms for mapping LULC of the uMngeni catchm
 ent area\, KwaZulu-Natal
DTSTART;VALUE=DATE-TIME:20240703T060500Z
DTEND;VALUE=DATE-TIME:20240703T062500Z
DTSTAMP;VALUE=DATE-TIME:20260310T182631Z
UID:indico-contribution-2017@events.chpc.ac.za
DESCRIPTION:Speakers: ORLANDO BHUNGENI (University of KwaZulu Natal)\nAbst
 ract: Analysis of land use/land cover (LULC) in the catchment areas is the
  first action toward safeguarding the freshwater resources. The LULC infor
 mation in the watershed has gained popularity in the natural science field
  as it helps water resource managers and environmental health specialists 
 develop natural resource conservation strategies based on available quanti
 tative in-formation. Thus\, remote sensing is the cornerstone in addressin
 g environmental-related issues at the catchment level. In this study\, the
  performance of four machine learning algorithms (MLAs)\, such as Random F
 orests (RF)\, Support Vector Machine (SVM)\, Artificial Neural Networks (A
 NN)\, and Naïve Bayes (NB) was investigated to classify the catchment int
 o nine rele-vant classes of the undulating watershed landscape using Lands
 at 8 Operational Land Imager (L8-OLI) imagery. The assessment of the MLAs 
 were based on the visual inspection of the analyst and the commonly used a
 ssessment metrics\, such as user’s accuracy (UA)\, producers’ accuracy
  (PA)\, overall accuracy (OA)\, and kappa coefficient. The MLAs produced g
 ood results\, where RF (OA= 97.02%\, Kappa= 0.96)\, SVM (OA= 89.74 %\, Kap
 pa= 0.88)\, ANN (OA= 87%\, Kappa= 0.86)\, and NB (OA= 68.64 Kappa= 0.58). 
 The results show the outstanding performance of the RF model over SVM and 
 ANN with a small margin. While NB yielded satisfactory results\, which cou
 ld be primarily influenced by its sensitivity to limited training samples.
  In contrast\, the robust per-formance of RF could be due to an ability to
  classify high-dimensional data with limited train-ing data.\nKeywords: uM
 ngeni River Catchment\; Machine learning\; LULC\; Landsat 8\; Remote sensi
 ng\n\nhttps://events.chpc.ac.za/event/134/contributions/2017/
LOCATION:CSIR ICC ICC-G-Ruby - Ruby Auditorium
URL:https://events.chpc.ac.za/event/134/contributions/2017/
END:VEVENT
END:VCALENDAR