GEOINFORMATICS TECHNOLOGY INTEGRATION FOR OPTIMUM FOREST AND LAND COVER CLASSIFICATION AND ABOVE GROUND BIOMASS ESTIMATION
Keywords:
CART model, AGB estimation model, forest and land cover classification, geoinformatics technologyAbstract
Image classification is a prerequisite for remote sensing applications, such as thematic mapping, environment monitoring, and forest management. The main objectives of the study were (1) to classify forest and land cover using the optimum classification and regression trees (CART) model and (2) to estimate the above ground biomass (AGB) of forest types and plantations with the optimum AGB estimation model. The research methodology consisted of 3 main components: (1) data collection and preparation, (2) the optimum CART model development for forest and land cover classification, and (3) the optimum AGB estimation model development. From the results, an optimum CART model was developed using 10 independent variables consisting of blue, red, near infra-red (NIR), shortwave infra-red (SWIR)-1, SWIR-2, simple ratio (SR), normalized difference water index (NDWI), wetness, elevation, and slope. The classified forest and land cover map provided strong agreement between the classified and the ground reference information with an overall accuracy of 91.18% and a kappa hat coefficient of 89.06%. Meanwhile, for the AGB estimation models, a simple linear model of dense dry evergreen forest (DDEF) with NIR provided a normalized root mean square error (NRMSE) of 0.2449 and coefficient of determination (R2) of 0.94 while the exponential model of moderate dry evergreen forest (MDEF) with the forest canopy density (FCD) provided a NRMSE of 0.5097 and R2 of 0.82. Likewise, the simple linear model of mixed deciduous forest (MDF) with a normalized difference vegetation index (NDVI) provided a NRMSE of 1.0835 and R2 of 0.85, while the logarithm model of forest plantation (FPT) with the FCD provided a NRMSE of 0.8039 and (R2) of 0.75. In conclusion, it can be concluded that geoinformatics technology, particularly remote sensing and GIS, can be efficiently used as tools to classify forest and land cover with a CART model and to estimate the AGB of forest type and plantation with simple linear and non-linear regression analysis.
References
Optimum Forest and Land Cover Classification and Above Ground Biomass Estimation
Birth, G.S. and McVey, G. (1968). Measuring the color of growing turf with a reflectance spectrophotometer. Agron. J., 60:640-643
Bittencourt, H.R. and Clarke, R.T. (2003). Use of classification and regression trees (CART) to classify remotely sensed digital images. Proceedings of the 2003 IEEE International Geoscience and Remote Sensing Symposium; July 21-25, 2003; Toulouse, France, p. 3,751-3,753.
Bombelli, A., Henry, M., Castaldi, S., Adu-Bredu, S., Arneth, A., de Grandcourt, A.D., Grieco, E., Kutsch, W.L., Lehsten, V., Rasile, A., Reichstein, M., Tansey, K., Weber, U., and Valentini, R. (2009). An outlook on the Sub-Saharan Africa carbon balance. Biogeosciences, 6:2193-2205.
Broge, N.H. and Leblane, E. (2000). Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sens. Environ., 76:156-172.
Chailangka, P. (2010). Above ground biomass estimation of Eucalyptus plantation using remotely sensed data: Case study Nakhon Ratchasima province, [M.Sc. thesis]. School of Remote Sensing, Institute of Science, Suranaree University of Technology, Nakhon Ratchasima, Thailand, 82p.
Chaudhary, A.K., Acharya, A.K., and Khanal, S. (2016). Forest type mapping using object-based classification method in Kapilvastu district, Nepal. Nepal Journal of Forestry, 26(1):38-44.
Chen, J.M., Pavlic, G., Brown, L., Cihlar, J., Leblanc, S.G., White, H.P., Hall, R.J., Peddle, D.R., King, D.J., Trofymow, J.A., Swift, E., van der Sanden, J., and Pellikka, P.K. (2002). Derivation and validation of Canada-wide coarse-resolution leaf area index maps using high-resolution satellite imagery and ground measurements. Remote Sens. Environ., 80:165-184.
Colombo, R., Bellingeri, D., Fasolini, D., and Marino, C.M. (2003). Retrieval of leaf area index in different vegetation types using high satellite data. Remote Sens. Environ., 86:120-131.
Crist, E.P. and Kauth, R.J. (1986). The Tasseled Cap de-mystified. Photogramm. Eng. Rem. S., 52(1):81-86.
Deering, D.W., Rouse, J.W., Haas, R.H., and Schell, J.A. (1975). Measuring forage production of grazing units from Landsat MSS data. Proceedings of the 10th International Symposium on Remote Sensing of Environment; October 6-10, 1975; Ann Arbor, MI, USA, p. 1169-1178.
Diloksumpun, S., Visaratana, T., Panuthai, S., Ladpala, P., Janmahasatien, S., and Sumran, S. (2005). Carbon cycling in the Sakaerat dry evergreen and the Maeklong mixed deciduous forests. Proceedings of the Climate Change in Forestry, Potential of Forests in Support of the Kyoto Protocol Annual Conference; August 4-5, 2005; Bangkok, Thailand, p. 77-94.
Domrongsutsiri, V. (2001). Application of remote sensing for estimating leaf area index and above-ground forest biomass at Phu Kradung National Park, Changwat Loei, [MSc. thesis]. Major Field Forest Management, Department of Forest Management, Kasetsart University, Bangkok, Thailand, 153p.
Epron, D., Marsden, C., M’Bou, A., Saint-Andre, L., Annunzio, R., and Nouvellon, Y. (2009). Soil carbon dynamics following afforestation of a tropical savannah with Eucalyptus in Congo. Plant Soil, 323:309-322.
Fitzpatrick-Lins, K. (1981). Comparison of sampling procedures and data analysis for a land-use and land-cover map. Photogramm. Eng. Rem. S., 55 (4):475-478.
Gao, B.C. (1996). NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens. Environ., 58:257-266.
Ghose, M.K., Pradhan, R., and Ghose, S.S. (2010). Decision tree classification of remotely sensed satellite data using spectral separability matrix. International Journal of Advanced Computer Science and Applications, 1(5):93-101.
Gomez, C., Wulder, M.A., Montes, F., and Delgado, J.A. (2012). Modeling forest structural parameters in the Mediterranean pines of central Spain using Quickbird-2 imagery and classification and regression tree analysis (CART). Remote Sens., 4(1):135-159.
Gordon, L. (2013). Using classification and regression trees (CART) in SAS enterprise miner for applications in public health. Proceeding of SAS Global Forum 2013 Conference; April 28 - May 1, 2013; San Francisco, USA.
Herold, N.D., Koeln, G., and Cunnigham., D. (2003). Mapping impervious surfaces and forest canopy using classification and regression tree (CART) analysis. Proceedings of the 2003 ASPRS Annual Conference “Technology: Converging at the Top of the World”; May 5-9, 2003; Anchorage, AK, USA, 7p.
Htun, N.Z., Mizoue, N., and Yoshida, S. (2011). Classifying tropical deciduous vegetation: a comparison of multiple approaches in Popa Mountain Park, Myanmar. Int. J. Remote Sens., 32(24):8935-8948.
Huete, A.R. (1988). A soil-adjusted vegetation index (SAVI). Remote Sens. Environ., 25:295-309.
Huete, A.R. and Liu, H.Q. (1994). An error and sensitivity analysis of the atmospheric and soil-correcting variants of the NDVI for the MODIS-EOS. IEEE T. Geosci. Remote, 32(4):897-905.
Kantirach, A. (2002). Application of remote sensing data on forest area classification and forest biomass estimation in Huai Tubtun-Huai Samran Wildlife Sanctuary, Surin Province, [MSc. thesis]. Major Field Forest Management, Department of Forest Management, Kasetsart University, Bangkok, Thailand, 138p.
Kushwaha, S.P.S. (2008). Geoinformatics - technology and applications. The Zoological Survey of India, 14(1&2):1-13.
Kutintara, U. (1999). Ecology: Fundamental Basics in Forestry. Department of Forest Biology, Faculty of Forestry, Kasetsart University, Bangkok, Thailand, 566p.
Labrecque, S., Fournier, R.A., Luther, J.E., and Piercey, D. (2006). A comparison of four methods to map biomass from Landsat-TM and inventory data in western Newfoundland. Forest Ecol. Manag., 226:129-144.
Lawrence, R.L. and Wright, A. (2001). Rule-based classification systems using classification and regression tree (CART) analysis. Photogramm. Eng. Rem. S., 67(10):1137-1142.
Li, Y., Yan, L., and Liu, J. (2009). Remote sensing image classification development in the past decade. Proceedings of the 6th International Symposium on Multispectral Image Processing and Pattern Recognition; October 30-November 1, 2009; Yichang, China, p. 74941D1-74941D6.
Lunetta, R.S., Ediriwickrema, J., Johnson, D.M., Lyon, J.G., and Mckerrow, A. (2002). Impacts of vegetation dynamics on the identification of land-cover change in biologically complex community in North Carolina, USA. Remote Sens. Environ., 82:258-270.
Mcfeeters, S.K. (1996). The use of normalized difference water index (NDWI) in the delineation of open water features. Int. J. Remote Sens., 17:1425-1432.
Meresa, E. (2015). Applications of geoinformatics technology in land use land cover change detection using multi-temporal satellite images: the case of Mariamdehan Tabia, Tigray Region, Northern Ethiopia. J. Environ. Earth Sci., 5(5):53-59.
Morgan, J. (2014). Report of the classification and regression tree analysis. Department of Health Policy and Management, School of Public Health, No.1. 15p. Available from: www.bu.edu. Accessed date: 17 March 2018.
Muukkonen, P. and Heiskanen, J. (2007). Biomass estimation over a large area based on stand-wise forest inventory data and ASTER and MODIS satellite data: a possibility to verify carbon inventories. Remote Sens. Environ., 107(4):617-624.
Nuanurai, N. (2005). Comparison of leaf area index, above-ground biomass and carbon sequestration of forest ecosystems by forest inventory and remote sensing at Kaeng Krachan National Park, Thailand, [MSc. thesis]. Department of Biology, Faculty of Science, Chulalongkorn University, Bangkok, Thailand, 195p.
Ogawa, H., Yoda, K., Ogino, K., and Kira, T. (1965). Comparative ecological studies on three main type of forest vegetation in Thailand. II. Plant biomass. Nature and Life in Southeast Asia, 4:49-80.
Poulain, M., Peña, M., Schmidt, A., Schmidt, H., and Schulte, A. (2012), Above ground biomass estimation in intervened and non-intervened Nothofagus pumilio forests using remotely sensed data. Int. J. Remote Sens., 33(12):3816-3833.
Qian, Y., Zhou, W., Yan, J., Li, W., and Han, L. (2015). Comparing machine learning classifiers for object-based land cover classification using very high resolution imagery. Remote Sens., 7(1):153-168.
Rikimaru, A., Roy, P.S., and Miyatake, S. (2002). Tropical forest cover density mapping. Trop. Ecol., 43(1):39-47.
Rouse, J.W., Haas, R.H., Schell, J.A., and Deering, D.W. (1974). Monitoring vegetation system in the Great Plains with ERTS. Proceeding of the 3rd Earth Resource Technology Satellite (ERTS) Symposium; December 10-14, 1973; Washington, DC, USA, p. 48-62.
Sricharienchot, A. (2014). Forest inventory method for the spatial estimation of forest biomass based on geoinformatics at Huai Lan sub-watershed, Ngao district, Lampang province, [MSc. thesis]. Major Field Forest Resource Management, Department of Forest Management, Kasetsart University, Bangkok, Thailand, 101p.
Stehman, S.V. (2000). Practical implications of design-based sampling for thematic map accuracy assessment. Remote Sens. Environ., 72:35-45.
Stehman, S.V. (2001). Statistical rigor and practical utility in thematic map accuracy assessment. Photogramm. Eng. Rem. S., 67:727-734.
Terakunpisut, J., Gajaseni, N., and Ruankawe, N. (2007). Carbon sequestration potential in aboveground biomass of Thong Pha Phum National Forest, Thailand. Appl. Ecol. Env. Res., 5(2):93-102.
Timofeev, R. (2004). Classification and regression trees (CART) theory and applications, [MSc. thesis]. Center of Applied Statistics and Economic, Humboldt University, Berlin, Germany, 39p.
Trephattanasuwan, P., Diloksumpun, S., Staporn, D., and Rattanakaew, J. (2010). Carbon storage in biomass of some tree species planted at the Pu Parn Royal Development Study Centre, Sakon Nakhon Province. Department of National Park, Wildlife and Plant Conservation. Bangkok, Thailand.
Tsutsumi, T., Nishitani, Y., and Kirimura, Y. (1983). On the effects of soil fertility on the rate and the nutrient element concentration of litterfall in a forest. Japanese Journal of Ecology, 33:313-322.
UNFCCC (United Nations Framework Convention on Climate Change). (2008). Decision 2/CP.13: Reducing emissions from deforestation in developing countries: approaches to stimulate action. FCCC/CP/2007/6/Add.1. Bonn: UNFCCC.
USGS (United States Geological Survey). (2016). Landsat 8 data users handbook. Available from: https://landsat.usgs.gov/sites/default/files/documents/Landsat8DataUsersHandbook.pdf. Accessed date: Apr 26, 2018.
Viriyabuncha, C., Peawsa-ad, K., and Janmahasatien, S. (2005). Assessment of the potentiality of re-afforestation activities in climate change mitigation. Proceedings of the Climate Change in Forestry, Potential of Forests in Support of the Kyoto Protocol Annual Conference; August 4-5, 2005; Bangkok, Thailand, p. 119-136.
Virrantaus, K. and Haggren, H. (2000). Curriculum of geoinformatics-integration of remote sensing and geographical information technology. International Archives of Photogrammetry and Remote Sensing. B6:288-294.
Walker, S., Pearson, T., Munishi, P., and Petrova, S. (2008). Carbon market opportunities for the forestry sector of Africa. Proceedings of the 16th Session of the African Forestry and Wildlife Commission; February 17-24, 2008; Khartoum, Sudan, 44p.
Weih, R.C.Jr. and Riggan, N.D.Jr. (2010). Object-based classification vs. Pixel-based classification: Comparative importance of multi-resolution imagery. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVII-4/C7.
