Estimation and Mapping Forest Attributes Using “k Nearest Neighbor” Method on IRS-P6 LISS III Satellite Image Data

Journal Title: Ecologia Balkanica - Year 2015, Vol 7, Issue 1

Abstract

 In this study, we explored the utility of k Nearest Neighbor (kNN) algorithm to integrate IRS-P6 LISS III satellite imagery data and ground inventory data for application in forest attributes (DBH, trees height, volume, basal area, density and forest cover type) estimation and mapping. The ground inventory data was based on a systematic-random sampling grid and the numbers of sampling plots were 408 circular plots in a plantation in Guilan province, north of Iran. We concluded that kNN method was useful tool for mapping at a fine accuracy between 80% and 93.94%. Values of k between 5 and 8 seemed appropriate. The best distance metrics were found Euclidean, Fuzzy and Mahalanobis. Results showed that kNN was accurate enough for practical applicability for mapping forest areas.

Authors and Affiliations

Roya Abedi, Amir Bonyad

Keywords

Related Articles

Shell Size of the Freshwater Snail Physella acuta (Draparnaud, 1805) Collected from Water Vegetation: A Case Study from South-East Bulgaria

The specimens of the freshwater snail Physella acuta collected from Southeastern part of Bulgaria during the cold period as a whole were with mean shell height of 5.7 mm. During spring and summer it was more than twice l...

Eco-Biological Characteristics of Medicinal Plants in the Protected Area “Nahodishte Na Blatno Kokiche”, Gradina Village, Parvomay (Bulgaria)

In the present work we investigated medicinal plants of the flora of the protected area “Nahodishte na blatno kokiche” the village of Gradina, Parvomay Municipality. Eco-biological characterization of the plants was done...

On the fruit consumption of Eurasian Badger (Meles meles) (Mammalia: Mustelidae) during the autumn season in Sredna Gora Mountains (Bulgaria)

This case study was carried out at one badgers family territory by a single collection (11.11.2002, north of Stara Zagora City, near Tabashka River) of faeces from the animal latrine sites. Total of 1361 individual food...

Hydrobiological Investigation of the Activated Sludge from Sequencing Batch Reactors of WWTP–Hisarya

The operations of the relatively new wastewater treatment plant of Hisarya, Bulgaria were evaluated in the present paper. The bacterial diversity of activated sludge from aeration basins of cyclic type (SBR-method) durin...

Assessing the Heavy Metal Content in Forest Dormouse (Dryomys nitedula Pallas, 1778) from an Agricultural Region in Bulgaria

The heavy metals load in the forest dormouse (Dryomys nitedula), inhabiting in forest shelter belts in the agricultural region was assessed. The concentrations of Cd, Co, Cu, Ni, Pb and Zn (expressed in mg/kg of dry tiss...

Download PDF file
  • EP ID EP158696
  • DOI -
  • Views 175
  • Downloads 0

How To Cite

Roya Abedi, Amir Bonyad (2015). Estimation and Mapping Forest Attributes Using “k Nearest Neighbor” Method on IRS-P6 LISS III Satellite Image Data. Ecologia Balkanica, 7(1), 93-102. https://europub.co.uk/articles/-A-158696