Skip Navigation Links.
Journal of Geosciences and Geomatics. 2017, 5(5), 243-250
DOI: 10.12691/JGG-5-5-3
Original Research

Testing the Potential Application of Simulated Multispectral Data in Discriminating Tree Species in Taita Hills

Samuel Nthuni1, , Faith Karanja1, Petri Pellikka2 and Mika Siljander2

1University of Nairobi, Department of Geospatial and Space Technology, Nairobi, Kenya

2University of Helsinki, Department of Geosciences and Geography, Helsinki, Finland

Pub. Date: September 28, 2017
Full Text PDF

Cite this paper

Samuel Nthuni, Faith Karanja, Petri Pellikka and Mika Siljander. Testing the Potential Application of Simulated Multispectral Data in Discriminating Tree Species in Taita Hills. Journal of Geosciences and Geomatics. 2017; 5(5):243-250. doi: 10.12691/JGG-5-5-3

Abstract

Hyperspectral data is gaining tremendous popularity in mapping tree species in the recent past. This is due to its ability to distinguish between individual tree species. However, its cost is prohibitive especially for developing economies. This paper focuses on the possibility of using the recently launched free optical sensors for mapping tree species in the Ngangao Forest of Taita Hills in Kenya. The AISA Eagle hyperspectral data was used to 10 tree species (six indigenous and four exotic species). The hyperspectral data reflectance was then used to derive Worldview 2 and Sentinel 2 data. A total 2504 training sites were used for the classification AISA Eagle data. The same training sites were used for the classification of the Worldview 2 and Sentinel 2 but after downscaling due to coarse resolution of the two sensors resulting into 638 and 23 training sites respectively. Spectral angle mapper, neural network and support vector machine classification algorithms were tested in this study. The three algorithms resulted into accuracies 49.24%, 79.47% and 80.15% respectively for the AISA Eagle data. However, only neural network algorithm was able to classify Worldview 2 and Sentinel 2 images resulting into overall accuracies of 56.43% and 47.22% with Kappa coefficient of 0.48 and 0.33 respectively.

Keywords

AISA Eagle, hyperspectral data, Worldview 2, Sentinel 2, tree species, Ngangao forest

Copyright

Creative CommonsThis work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References

[1]  Abraham, A, Artificial neural networks. In: Handbook of measuring system design. John Wiley & Sons, London, 2005, 901-908.
 
[2]  Asner, G.P., and Martin, R.E, “Contrasting leaf chemical traits in tropical lianas and trees: implications for future forest composition”, Ecology Letters, 15, 1001-1007, Jun.2012.
 
[3]  Becker, B.L., Lusch, D.P., and Qi, J, “A classification-based assessment of the optimal spectral and spatial resolutions for Great Lakes coastal wetland imagery,” Remote Sensing of Environment, 108. 111-120. May.2007.
 
[4]  Benedetto, J.J. and Czaja, W, Dimension Reduction and Remote Sensing Using Modern Harmonic Analysis, in: Freeden, W., Nashed, M.Z., Sonar, T. (Eds.), Handbook of Geomathematics. Springer Berlin, Heidelberg, 2013, 1-22.
 
[5]  Beniwal, S. and Arora, J, “Classification and feature selection techniques in data mining,” International journal of engineering research & technology (IJERT) 1(6). Aug. 2012.
 
[6]  Chi, M. and Bruzzone, L, “Semisupervised classification of hyperspectral images by SVMs optimized in the primal,” IEEE Transactions on Geoscience and Remote Sensing, 45(6). 1870-1880. Jun.2007.
 
[7]  Cho, M.A., Mathieu, R., Asner, G.P., Naidoo, L., van Aardt, J., Ramoelo, A., Debba, P., Wessels, K., Main, R., Smit, I.P.J. and Erasmus, B, “Mapping tree species composition in South African savannas using an integrated airborne spectral and LiDAR system,” Remote Sensing of Environment, 125. 214-226. Oct.2012.
 
[8]  Chu, C., Hsu, A.-L., Chou, K.-H., Bandettini, P., Lin, C. and Initiative, A.D.N, “Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images,” Neuroimage, 60(1). 59-70. Mar.2012.
 
[9]  Clark, M.L., Aide, T.M., Grau, H.R. and Riner, G, “A scalable approach to mapping annual land cover at 250 m using MODIS time series data: A case study in the Dry Chaco ecoregion of South America,” Remote Sensing of Environment, 114(11). 2816-2832. Nov.2010.
 
[10]  Clasen, A., Somers, B., Pipkins, K., Tits, L., Segl, K., Brell, M., Kleinschmit, B., Spengler, D., Lausch, A. and Förster, M, “Spectral Unmixing of Forest Crown Components at Close Range, Airborne and Simulated Sentinel-2 and EnMAP Spectral Imaging Scale,” Remote Sensing, 7(11). 15361-15387. Nov.2015.
 
[11]  Colgan, M.S., Baldeck, C.A., Féret, J.-B. and Asner, G.P, “Mapping savanna tree species at ecosystem scales using support vector machine classification and BRDF correction on airborne hyperspectral and LiDAR data,” Remote Sensing, 4(11). 3462-3480. Nov.2012.
 
[12]  Dalponte, M., Bruzzone, L. and Gianelle, D, “Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data,” Remote Sensing of Environment 123. 258-270. Aug.2012.
 
[13]  Denghui, Z. and Le, Y, “Support vector machine based classification for hyperspectral remote sensing images after minimum noise fraction rotation transformation, in Internet Computing & Information Services (ICICIS), 2011 International Conference, IEEE, 132-135. 17-18. Sept.2011.
 
[14]  Ferwerda, G., Girardin, S.E., Kullberg, B.-J., Le Bourhis, L., De Jong, D.J., Langenberg, D.M., Van Crevel, R., Adema, G.J., Ottenhoff, T.H. and Van der Meer, J.W, “NOD2 and toll-like receptors are nonredundant recognition systems of Mycobacterium tuberculosis,” PLoS Pathog, 1(34). e34. Nov.2005.
 
[15]  Hedley, J., Roelfsema, C., Koetz, B. and Phinn, S, “Capability of the Sentinel 2 mission for tropical coral reef mapping and coral bleaching detection,” Remote Sensing of Environment, 120. 145-155. May.2012.
 
[16]  Immitzer, M., Atzberger, C. and Koukal, T, “Tree species classification with random forest using very high spatial resolution 8-band WorldView-2 satellite data,” Remote Sensing, 4(9). 2661-2693. Sep.2012.
 
[17]  Immitzer, M., Vuolo, F. and Atzberger, C, “First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe,” Remote Sensing, 8. 166. Feb.2016.
 
[18]  Latif, Z.A., Zamri, I. and Omar, H, “Determination of tree species using Worldview-2 data,” in Signal Processing and Its Applications (CSPA), 2012 IEEE 8th International Colloquium, IEEE, 383-387. 23-25 Mar.2012.
 
[19]  Makori, D.M., Fombong, A.T., Abdel-Rahman, E.M., Nkoba, K., Ongus, J., Irungu, J., Mosomtai, G., Makau, S., Mutanga, O., Odindi, J., Raina, S., Landmann, T, “Predicting Spatial Distribution of Key Honeybee Pests in Kenya Using Remotely Sensed and Bioclimatic Variables: Key Honeybee Pests Distribution Models,” ISPRS International Journal of Geo-Information, 6. 66. Feb.2017.
 
[20]  Mantero, P., Moser, G. and Serpico, S.B, “Partially supervised classification of remote sensing images through SVM-based probability density estimation,” IEEE Transactions on Geoscience and Remote Sensing, 43(3). 559-570. Feb.2005.
 
[21]  McCloy, K.R. and Bøcher, P.K, “Optimizing image resolution to maximize the accuracy of hard classification,” Photogrammetric Engineering & Remote Sensing, 73(8). 893-903. Aug.2007.
 
[22]  Mitchell, J.J., Glenn, N.F., Sankey, T.T., Derryberry, D.R., Germino, M.J, “Remote sensing of sagebrush canopy nitrogen,” Remote Sensing of Environment, 124. 217-223. Sep.2012.
 
[23]  Mumby, P.J. and Edwards, A.J, “Mapping marine environments with IKONOS imagery: enhanced spatial resolution can deliver greater thematic accuracy,” Remote sensing of Environment, 82(2-3). 248-257. Oct.2002.
 
[24]  Nguyen, M.Q., Atkinson, P.M. and Lewis, H.G, “Superresolution mapping using a Hopfield neural network with fused images,” IEEE Transactions on Geoscience and Remote Sensing, 44(3), 736-749. Mar.2006.
 
[25]  Numata, I., Thenkabail, P.S., Lyon, J.G. and Huete, A, Characterization on pastures using field and imaging spectrometers. Hyperspectral remote sensing of vegetation, CRC Press, Florida, 2011, 207-226.
 
[26]  Omar, H, “Commercial timber tree species identification using multispectral Worldview2 data,” Digital Globe® 8Bands Research Challenge, 2-13. Jan.2010.
 
[27]  Omoro, L.M., Pellikka, P.K., Rogers, P.C, “Tree species diversity, richness, and similarity between exotic and indigenous forests in the cloud forests of Eastern Arc Mountains, Taita Hills, Kenya,” Journal of Forestry Research, 21. 255-264. Sep.2010.
 
[28]  Padwick, C., Deskevich, M., Pacifici, F., Smallwood, S, WorldView-2 pan-sharpening, in Proceedings of the ASPRS 2010 Annual Conference, ASPRS, 26-30 Apr.2010.
 
[29]  Pellikka, P.K.E., Clark, B.J.F., Sirviö, T. and Masalin, K, Environmental change monitoring applying satellite and airborne remote sensing data in the Taita Hills, Kenya. In Proceedings of the International Conference on Remote Sensing and Geoinformation Processing in the Assessment and Monitoring of Land Degradation and Desertification in Trier Germany, 7-9 Sep. 2005, CD-Rom publication, no page numbers.
 
[30]  Pellikka, P.K.E., Lötjönen, M., Siljander, M. and Lens, L. “Airborne remote sensing of spatiotemporal change (1955-2004) in indigenous and exotic forest cover in the Taita Hills, Kenya,” International Journal of Applied Earth Observation and Geoinformation, 11, 221-232. Feb.2009.
 
[31]  Rodríguez-Castañeda, G., Hof, A.R., Jansson, R. and Harding, L.E, “Predicting the Fate of Biodiversity Using Species’ Distribution Models: Enhancing Model Comparability and Repeatability,” PLoS ONE, 7(9). Sep.2012. e44402.
 
[32]  Rogers, P.C., O’Connell, B., Mwang’ombe, J., Madoffe, S. and Hertel, G, “Forest health monitoring in the Ngangao forest, Taita Hills, Kenya: a five year assessment of change,” Journal of East African Natural History, 97. 3-17. 2008.
 
[33]  Sarhrouni, El., Hammouch, A. and Aboutajdine, D, “Dimensionality reduction and classification feature using mutual information applied to hyperspectral images: a filter strategy based algorithm,” Applied Mathematical Sciences, 6(102). 5085-5095. 2012.
 
[34]  Schmidt, K.S. and Skidmore, A.K, “Spectral discrimination of vegetation types in a coastal wetland,” Remote Sensing of Environment, 85(1). 92-108. Apr.2003.
 
[35]  Stratoulias, D., Balzter, H., Sykioti, O., Zlinszky, A., Tóth, V.R., 2015. “Evaluating Sentinel-2 for Lakeshore Habitat Mapping Based on Airborne Hyperspectral Data,” Sensors, 15(9). 22956-22969. Sep.2015.
 
[36]  Thulin, S., Hill, M.J., Held, A., Jones, S. and Woodgate, P, “Hyperspectral determination of feed quality constituents in temperate pastures: Effect of processing methods on predictive relationships from partial least squares regression,” International Journal of Applied Earth Observation and Geoinformation, 19. 322-334. Oct.2012.
 
[37]  User Guides - Sentinel-2 MSI - Sentinel Online [WWW Document], n.d. URL https://sentinel.esa.int/web/sentinel/user-guides/sentinel-2-msi (accessed 5.1.17).
 
[38]  Veganzones, M.A., Simoes, M., Licciardi, G., Yokoya, N., Bioucas-Dias, J.M. and Chanussot, J, “Hyperspectral super-resolution of locally low rank images from complementary multisource data,” IEEE Transactions on Image Processing, 25(1). 274-288. Jan.2016.
 
[39]  Wang, S. and Wang, C, “Research on dimension reduction method for hyperspectral remote sensing image based on global mixture coordination factor analysis,” The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 40. 159-167. Jun.2015.
 
[40]  Wu, H. and Li, Z.-L, “Scale issues in remote sensing: A review on analysis, processing and modeling,” Sensors, 9. 1768-1793. Mar.2009.
 
[41]  Yanqin, T., Ping, G. and Lyu, M.R, “Comparative Studies on Feature Extraction Methods for Multispectral Remote Sensing Image In Classification Systems, Man and Cybernetics, 2005 IEEE International Conference. IEEE, 1275-1279.
 
[42]  Yegnanarayana, B, Artificial neural networks. Prentice Hall of India, New Delhi, 2006 [E-book] Available: PHI Learning Pvt. Ltd.
 
[43]  Yin, J., Wang, Y. and Hu, J, “A new dimensionality reduction algorithm for hyperspectral image using evolutionary strategy,” IEEE Transactions on Industrial Informatics, 8(4), 935-943. Nov.2012.
 
[44]  Zhang, J., Wu, J. and Zhou, L, “Deriving vegetation leaf water content from spectrophotometric data with orthogonal signal correction-partial least square regression,” International journal of remote sensing, 32(22). 7557-7574. Aug.2011.
 
[45]  Zhang, Y., Atkinson, P.M., Ling, F., Wang, Q., Li, X., Shi, L. and Du, Y, “Spectral-Spatial Adaptive Area-to-Point Regression Kriging for MODIS Image Downscaling,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(5). 1883-1896. May.2017.