11 th International Symposium for GIS and Computer Cartography for Coastal Zones Managementvalidated through final classification maps that will visualize the spatial abundance of SAV in both study areas. Theaccuracy of the distribution will be assessed based on the ground truth data that was collected at the same time theHSI was acquired. Further analysis will look to see if any distinction between species can be detected between theidentified SAV in the environment. Furthermore, the use of the shown endmember extraction methods andgroupings of classes will look towards the potential of better selecting regions of interest (ROI’s) more efficientlyfor large and regional scale classification projects. However, limitations and the uncertainties of the system and itsproducts must be analysed and defined in order to effectively use it in the most valuable manner. The outcome ofthis work-in-progress intends to address these issues and limitations.ConclusionIt has been found that the knowledge base for SAV has significantly improved over the years due to advances inremote sensing technologies, which has made the ability to understand the processes that work within the littoralzone more accessible (Green et al., 2000; Collin et al., 2007). Classification technological advancements haveplayed a large role in this. In the past 20 years, benthic mapping has mainly relied on physical samplings (i.e., grabsand dredges), which are both costly and time consuming, providing only scattered and discrete data within the areasof interest (Collin et al., 2007). With the advent of remote sensing technology like HSI, developing resilient trainingdata for automated classification is achieved by defining the spectral envelope of the classes, signature evaluationwhich checks for similar representation within the data and fed to a decision-making protocol, classifying the databy using various mathematical algorithms (Green et al., 2000). This means minimal field or ground truth data arenecessary, reducing both time and cost investments. The saved time can be more efficiently used for data analysis,rather than being allocated for acquisition or processing.Although not commonly implemented for these types of habitat maps, accuracy assessments ranging from 60% to90% can often be achievable (Green et al., 2000). Therefore, understanding and managing the coastal zone requiresinterdisciplinary studies in both the natural sciences, as well as the technical and statistical aspects of remote sensingtechnology. Through this understanding, SAV can be classified correctly and its workflow and parameters canpotentially be adapted for studying other locations and coastal applications.ReferencesAlberotanza, L., V.E. Brando, G. Ravagnan, and A. Zandonella (1999), “Hyperspectral aerial images. A valuable tool forsubmerged vegetation recognition in the Orbetello Lagoons, Italy”. International Journal of Remote Sensing, 20(3):523–533.Anstee, J.M., A.G. Dekker, V. Brando, N. Pinnel, G. Byrne, P. Daniel, and A. Held (2001), “Hyperspectral imaging for benthicspecies recognition in shallow coastal waters”. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS2001), Sydney, Australia, (6):2513–2515.Bostater, C.R., Jr., T. Ghir, L. Bassetti, C. Hall, E. Reyeier, R. Lowers, K. Holloway-Adkins, and R. Virnstein (2004),“Hyperspectral remote sensing protocol development for submerged aquatic vegetation in shallow waters”. In: C.R. BostaterJr. and R. Santoleri (eds.), Remote Sensing of the Ocean and Sea Ice 2003 (SPIE, 2004), Bellingham, USA, 5233:199–215.Brando, V.E. and A.G. Dekker (2003), “Satellite hyperspectral remote sensing for estimating estuarine and coastal waterquality”. Transactions on Geoscience and Remote Sensing, 41(6):1378–1387.Casal, G., T. Kutser, J.A. Domínguez-Gómez, N. Sánchez-Carnero, and J. Freire (2011), “Mapping benthic macro algalcommunities in the coastal zone using CHRIS-PROBA mode 2 images”. Estuarine, Coastal and Shelf Science, 94(3):281–290.Coleman, J.B., X. Yao, T.R. Jordan, and M. Madden (2011), “Holes in the ocean: Filling voids in bathymetric lidar data”.Computers & Geosciences, 37(4):474–484.Collin, A., A. Cottin, B. Long, P. Kuus, J.H. Clarke, P. Archambault, G. Sohn, et al. (2007), “Statistical classificationmethodology of SHOALS 3000 backscatter to mapping coastal benthic habitats”. In: Geoscience and Remote SensingSymposium (IGARSS 2007), IEEE International: 3178–3181Dekker, A., V. Brando, J. Anstee, H. Botha, Y.J. Park, P. Daniel, and S. Fyfe (2010), “A comparison of spectral measurementmethods for substratum and benthic features in seagrass and coral reef environments”. In A. Goetz (ed.). Art, Science andApplications of Reflectance Spectroscopy Symposium (ASD and IEEE GRS, 2010), Boulder, USA: 1–16.Green, E.P. and A.J. Edwards (2000), Remote Sensing Handbook For Tropical Coastal Management, United NationsEducational, Paris, France, 316p.212
11 th International Symposium for GIS and Computer Cartography for Coastal Zones ManagementJollineau, M.Y. and P.J. Howarth (2008), “Mapping an inland wetland complex using hyperspectral imagery”. InternationalJournal of Remote Sensing, 29(12):3609–3631.Keshava, N. and J.F. Mustard (2002), “Spectral unmixing”. IEEE Signal Processing Magazine, 19(1):44–57.Martínez, P.J., R.M. Pérez, A. Plaza, P.L. Aguilar, M.C. Cantero, and J. Plaza (2006), “Endmember extraction algorithms fromhyperspectral images”. Annals of Geophysics, 49: 93–101.Plaza, A., P. Martinez, R. Perez, and J. Plaza (2004), “A Quantitative and Comparative Analysis of Endmember ExtractionAlgorithms From Hyperspectral Data”. Transactions on Geoscience and Remote Sensing, 42(3):650–663.Rzhanov, Y. and S. Pe’eri (2012), “Pushbroom-Frame Imagery Co-Registration”. Marine Geodesy, 35(2):141–157.Woodroffe, C.D. (2003). Coasts: Form, Process and Evolution, Cambridge University Press, Cambridge, England, 640p.Zulhaidi, H., M. Shafri, A. Suhaili, S. Mansor, R. Sensing, F.O. Branch, W.S. Alam, et al. (2007), “The Performance ofMaximum Likelihood, Spectral Angle Mapper, Neural Network and Decision Tree Classifiers in Hyperspectral ImageAnalysis”. Journal of Computer Science, 3(6):419–423.213
- Page 1 and 2:
CoastGIS Conference 2013: Monitorin
- Page 3 and 4:
Sponsors
- Page 5 and 6:
Steering Committee Secretariat main
- Page 7 and 8:
Santos Basin, BrazilA.F. Romero, R.
- Page 9 and 10:
Coastline development and associate
- Page 11 and 12:
Visual resource management system f
- Page 13 and 14:
11 th International Symposium for G
- Page 15 and 16:
Use of Terrestrial-LiDAR for quanti
- Page 17 and 18:
11 th International Symposium for G
- Page 19 and 20:
11 th International Symposium for G
- Page 21 and 22:
11 th International Symposium for G
- Page 23 and 24:
11 th International Symposium for G
- Page 25 and 26:
Community beach monitoring: utilisi
- Page 27 and 28:
11 th International Symposium for G
- Page 29 and 30:
Data policy implications arising fr
- Page 31 and 32:
11 th International Symposium for G
- Page 33 and 34:
Global ocean observing system for w
- Page 35 and 36:
11 th International Symposium for G
- Page 38 and 39:
11 th International Symposium for G
- Page 40 and 41:
11 th International Symposium for G
- Page 42 and 43:
11 th International Symposium for G
- Page 44 and 45:
11 th International Symposium for G
- Page 46 and 47:
ResultsMetadata11 th International
- Page 48 and 49:
11 th International Symposium for G
- Page 50 and 51:
11 th International Symposium for G
- Page 52 and 53:
Coastal vulnerability index to glob
- Page 54 and 55:
11 th International Symposium for G
- Page 56 and 57:
generating probabilities contours f
- Page 58 and 59:
maps, the most critical conditions
- Page 60 and 61:
11 th International Symposium for G
- Page 62 and 63:
11 th International Symposium for G
- Page 64 and 65:
11 th International Symposium for G
- Page 66 and 67:
11 th International Symposium for G
- Page 68 and 69:
Statistical and spatial toolbox for
- Page 70 and 71:
11 th International Symposium for G
- Page 72 and 73:
Global oceans and marine planning
- Page 74 and 75:
Analysis11 th International Symposi
- Page 76 and 77:
Building scenarios and visualizatio
- Page 78 and 79:
11 th International Symposium for G
- Page 80 and 81:
Using a 3D physics-based visualizat
- Page 82 and 83:
11 th International Symposium for G
- Page 84 and 85:
Documenting situated tsunami risk p
- Page 86 and 87:
11 th International Symposium for G
- Page 88 and 89:
11 th International Symposium for G
- Page 90 and 91:
11 th International Symposium for G
- Page 92 and 93:
SeaSketch11 th International Sympos
- Page 94 and 95:
A structured model to enable coasta
- Page 96 and 97:
11 th International Symposium for G
- Page 98 and 99:
Developing and testing approaches f
- Page 100 and 101:
11 th International Symposium for G
- Page 102 and 103:
A dynamic GIS as an efficient tool
- Page 104 and 105:
11 th International Symposium for G
- Page 106 and 107:
GIS spatio-temporal modeling of hum
- Page 108 and 109:
ResultsCollected data11 th Internat
- Page 110 and 111:
The use of GIS and geospatial techn
- Page 112 and 113:
11 th International Symposium for G
- Page 114 and 115:
Ocean Radar for Monitoring of the C
- Page 116 and 117:
11 th International Symposium for G
- Page 118 and 119:
Geophysical investigations of marin
- Page 120 and 121:
11 th International Symposium for G
- Page 122 and 123:
A semi-supervised learning framewor
- Page 124 and 125:
11 th International Symposium for G
- Page 126 and 127:
Simulation of maritime paths taking
- Page 128 and 129:
11 th International Symposium for G
- Page 130 and 131:
COINAtlantic: Sharing through open
- Page 132 and 133:
11 th International Symposium for G
- Page 134 and 135:
Implementation of the marine data i
- Page 136 and 137:
Perspectives11 th International Sym
- Page 138 and 139:
11 th International Symposium for G
- Page 140 and 141:
11 th International Symposium for G
- Page 142 and 143:
11 th International Symposium for G
- Page 144 and 145:
11 th International Symposium for G
- Page 146 and 147:
11 th International Symposium for G
- Page 148 and 149:
References11 th International Sympo
- Page 150 and 151:
11 th International Symposium for G
- Page 152 and 153:
11 th International Symposium for G
- Page 154 and 155:
11 th International Symposium for G
- Page 156 and 157:
Conclusion11 th International Sympo
- Page 158 and 159:
11 th International Symposium for G
- Page 160 and 161:
11 th International Symposium for G
- Page 162 and 163:
11 th International Symposium for G
- Page 164 and 165:
11 th International Symposium for G
- Page 166 and 167:
11 th International Symposium for G
- Page 168 and 169:
11 th International Symposium for G
- Page 170 and 171:
Tools and best practices for coasta
- Page 172 and 173: 11 th International Symposium for G
- Page 174 and 175: 11 th International Symposium for G
- Page 176 and 177: 11 th International Symposium for G
- Page 178 and 179: Washington Coastal Atlas: creating
- Page 180 and 181: 11 th International Symposium for G
- Page 182 and 183: The African Coastal and Marine Atla
- Page 184 and 185: 11 th International Symposium for G
- Page 186 and 187: 11 th International Symposium for G
- Page 188 and 189: 11 th International Symposium for G
- Page 190 and 191: 11 th International Symposium for G
- Page 192 and 193: 11 th International Symposium for G
- Page 194 and 195: 11 th International Symposium for G
- Page 196 and 197: 11 th International Symposium for G
- Page 198 and 199: Methods11 th International Symposiu
- Page 200 and 201: 11 th International Symposium for G
- Page 202 and 203: Methods11 th International Symposiu
- Page 204 and 205: 11 th International Symposium for G
- Page 206 and 207: 11 th International Symposium for G
- Page 208 and 209: Acknowledgments11 th International
- Page 210 and 211: 11 th International Symposium for G
- Page 212 and 213: 11 th International Symposium for G
- Page 214 and 215: 11 th International Symposium for G
- Page 216 and 217: Long-term continuous observations o
- Page 218 and 219: 11 th International Symposium for G
- Page 220 and 221: Comparing endmember extraction meth
- Page 224 and 225: Integration of scientific data as a
- Page 226 and 227: 11 th International Symposium for G
- Page 228 and 229: 11 th International Symposium for G
- Page 230: Conclusions11 th International Symp