vegetation classification on prathong island, phang nga , thailand

25
Vegetation classification on Prathong Island, Phang Nga, Thailand Naiyana Srichai & Chanida Suwanprasit Faculty of Technology and Environment, Prince of Songkla University, Phuket Campus APAN 33 rd Meeting 13-17 February 2012

Upload: vaughan

Post on 24-Jan-2016

46 views

Category:

Documents


0 download

DESCRIPTION

Vegetation classification on Prathong Island, Phang Nga , Thailand. Naiyana Srichai & Chanida Suwanprasit Faculty of Technology and Environment, Prince of Songkla University, Phuket Campus. APAN 33 rd Meeting 13-17 February 2012. Introduction. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

Vegetation classification on Prathong Island, Phang Nga, Thailand

Naiyana Srichai & Chanida Suwanprasit

Faculty of Technology and Environment, Prince of Songkla University, Phuket Campus

APAN 33rd Meeting 13-17 February 2012

Page 2: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

2

•vegetation type study date back to the Nineteenth Century : ecologists, plant geographers, vegetation scientists

•three major determinants of vegetation-competition, stress and disturbance (Grime, 1974)

Introduction

Page 3: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

Objectives

•To classify vegetation on Prathong Island, Phang Nga province, southern Thailand

3

Page 4: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

Study area: Prathong Island, Phang Nga THAILAND

7th biggest island 1.5 km off the coastSize : width 9.7 kmlength 15.4 kmArea : 92 sq.km

Unseen Thailand 2002 deer,

hornbill, adjutant stork, green turtle, dugong

4

Page 5: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

5

Wild orchids

79 spp.

Local plants

96 spp.

Local vegetables

65 spp.

Source: Dept.of Marine and Coastal Resources, 2005

Page 6: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

6

11 Mammals spp.

86 Reptiles spp.

137 Birds

> 20 Freshwater animals

Source: Dept.of Marine and Coastal Resources, 2005

Page 7: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

7

Koh Ra

Koh Prathong

Source: Dept.of Marine and Coastal Resources, 2005

Koh Ra19 households109 people

Tong Dab village49 households272 people

Tha Paeyow123 households409 people

Pak Jok87 households134 people

Page 8: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

8

Koh Ra and Prathong Size 71,000 Rais or 92 sq.km

Mangrove 32% (green)

Beach forest 7% (orange)

Swamp forest 13% (pink)

Tropical forest 13% (Koh Ra,purple)

Grassland 8% (yellow)

Beach 26 km (orange)Seagrass 4,550 Rais (blue)

Coral 43 Rais (lighter green)

Source: Dept.of Marine and Coastal Resources, 2005

Page 9: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

9

Swamp forest Grassland

Beach forestMangrove forest

Page 10: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

10

Tsunami 26 Dec. 2004Area affected : 18.55 % (6.25% agricultural,92.88% others)

Page 11: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

11

Vegetation change after Tsunami

Fragile landSalt tolerant tree invasion Casuarina equisetifolia

Page 12: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

12

Data set: THEOS Multispectral Achieved on 19 Jan 2009 Spatial Resolution 15 m

Spectral Band Wavelength (m)

Band 0 (Blue) 0.45-0.52

Band 1 (Green) 0.53-0.60

Band 2 (Red) 0.62-0.69

Band 3 (NIR) 0.77-0.90

Page 13: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

13

THEOS Spectral bands

Band 0 (Blue) Band 1 (Green) Band 2 (Red) Band 3 (NIR)

Page 14: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

14

Classes

• Grassland• Beach forest• Mangrove forest• Wetland (swamp forest)• Water• Other

THEOS image 2009

Image Classification

Maximum Likelihood (MLC)

Support Vector Machines (SVMs)

Pre-image processing

Vegetation Mapping

Process Outline

Page 15: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

15

Support Vector Machines•SVMs : a supervised classifier, which

requires training samples but SVMs are not relatively sensitive to training sample size (works with limited quantity and quality).

•The SVM-based approach used a recursive procedure to generate prior probability estimates for known and unknown classes by adapting the Bayesian minimum-error decision rule (Mountrakis,et.at. 2011; Fauvel 2008).

Page 16: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

16

Support vector machines (SVMs) : numerousapplications in remote sensing . 108 relevant papers, published in 2007-2010. (G.Mountrakis, Jungho Im, C.Ogole, 2011)

Page 17: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

17

Unsupervised Classification:• K-Mean• 10 Classes

Page 18: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

18

ROI Separability

Classes Grassland

Beach Forest

Mangrove

Forest

Swamp forest

Sand Water

Grassland - 1.982 2.000 1.610 1.959 2.000Beach Forest - 1.766 1.881 2.000 2.000

Mangrove Forest - 1.996 2.000 2.000

Swamp Forest - 1.648 1.997

Sand - 2.000

Water -

Page 19: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

19

Classification Results

GrasslandSwamp ForestBeach ForestMangrove ForestSandWaterOther

MLC SVMs

Page 20: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

20

MLC SVMsRGB(0,1,2)

Page 21: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

21

Class Confusion Matrix

ClassMLC SVMs

Prod. Acc. (%) User Acc. (%) Prod. Acc. (%) User Acc. (%)

Grassland 98.68 100.00 96.71 100.00

Beach Forest 97.26 97.06 100.00 97.14

Mangrove Forest 97.20 100.00 99.15 99.39

Swamp 46.55 56.84 61.21 83.53

Water 97.58 70.35 97.58 82.31

Sand 98.21 100.00 99.40 98.82

Over all Accuracy 94.29 % (Kappa Co. = 0.921) 96.72 % (Kappa Co.= 0.954)

Page 22: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

22

Conclusions

•SVM classifier compared to the more conventional maximum likelihood approach gave slightly better accuracy using THEOS image for class : swamp forest of Prathong Island.

Page 23: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

23

Acknowledgement• Geo-Informatics

and Space Technology Development Agency (Public Organization)

• UniNet

• Prince of Songkla University, Phuket campus

Page 24: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

24

References:• Department of Marine and Coastal Resources. 2005.

Strategies for sustainable development of Koh Ra and Koh Prathong with people participation. Unpublished report.

• Fauvel, M.,  Benediktsson, J.A.,  Chanussot, J., Sveinsson, J.R.. 2008. Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles.  Geoscience and Remote Sensing, 46 (11), 3804 - 3814 

• Giorgos Mountrakis, Jungho Im, Caesar Ogole. 2011. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66, 247–259.

• Grime, J.P. 1974. Vegetation classification by reference to strategies. Nature, 250 (5461), 26-31.

Page 25: Vegetation classification on  Prathong Island,  Phang Nga ,  Thailand

25

Kob Khun Ka : Thank You