Estimation of aboveground tree carbon stock using SPOT-HRG data (a case study: Darabkola forests)

Abstract

Forests are among the most important carbon sinks on earth. However, their complex structure and vast areas preclude accurate estimation of forest carbon stocks. Data sets from forest monitoring using advanced satellite imagery are now used in international policy agreements. Data sets enable tracking of emissions of CO₂ into the atmosphere caused by deforestation and other types of land-use changes. The aim of this study is to determine the capability of SPOT-HRG Satellite data to estimate aboveground carbon stock in a district of Darabkola research and training forest, Iran. Preprocessing to eliminate or reduce geometric error and atmospheric error were performed on the images. Using cluster sampling, 165 sample plots were taken. Of 165 plots, 81 were in natural habitats, and 84 were in forest plantations. Following the collection of ground data, biomass and carbon stocks were quantified for the sample plots on a per hectare basis. Nonparametric regression models such as support vector regression were used for modeling purposes with different kernels including linear, sigmoid, polynomial, and radial basis function. The results showed that a third-degree polynomial was the best model for the entire studied areas having an root mean square error, bias and accuracy, respectively, of 38.41, 5.31, and 62.2; 42.77, 16.58, and 57.3% for the best polynomial for natural forest; and 44.71, 2.31, and 64.3% for afforestation. Overall, these results indicate that SPOT-HRG satellite data and support vector machines are useful for estimating aboveground carbon stock.

Keywords

Aboveground carbon stock / Support vector machine / SPOT-HRG / Darabkola

References

[1] Amini J, Sumantyo JT. Employing a method on SAR and optical images for forest biomass estimation. IEEE Trans Geosci Remote Sens, 2009, 47: 4020-4026.

[2] Anonymous (2005) Darabkola Forest Management. Organization of Forest and Range and Watershed Management, Islamic Republic of Iran, pp 350

[3] Bray M, Han D. Identification of support vector machines for runoff modeling. Journal of Hydroinfor, 2004, 6(4): 265-280.

[4] Brown S. Estimating biomass and biomass change of tropical forests, 1997, Roma: FAO Forest Resources Assessment Publication 55

[5] Brown S (1997b) Estimating biomass and biomass change of tropical forests: a Primer. (FAO Forestry Paper—134). Reprinted with corrections 1997.Produced by: Forestry Department. http://www.fao.org/docrep/w4095e/w4095e00.htm

[6] Cai YD, Liu XJ, Xu X, Zhou GP. Support vector machines for predicting protein structural class. Bioinformatics, 2001, 2: 3.

[7] Castillo-Santiago MA, Ricker M, De Jong BHJ. Estimation of tropical forest structure from SPOT-5 satellite images. Int J Remote Sens, 2010, 31: 2767-2782.

[8] Chen WJ, Blain D, Li JH, Keohler K, Fraser R, Zhang Y. Biomass measurements and relationships with Landsat-7/ETM + and JERS-1/SAR data over Canada’s western sub-arctic and low arctic. Int J Remote Sens, 2009, 30: 2355-2376.

[9] Cortez P, Morsis A (2007) A data mining approach to predict forest fires using meteorological data. In: Neves J, Santos MF, Machado JM (eds.) Proceedings of the EPIA 2007—Portuguese conference on artificial intelligence, Guimarães, Portugal Heidelberg: Springer, pp 512–523

[10] Dong J, Wang L, Xu S, Zhao R. Comparison of four models on forest above ground biomass estimation based on remote sensing. Geo Infor Resour Manag Sustain Ecosyst, 2013, 398: 253-263.

[11] Du CJ, Sun DW. Shape extraction and classification of pizza base using computer vision. J Food Eng, 2004, 64: 489-496.

[12] Durbha SS, King RL, Younan NH. Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer. Remote Sens Environ, 2007, 107: 348-361.

[13] Dutta S, Datta A, Das Chakladar N, Pal SL, Mukhopadhyay S, Sen S. Detection of tool condition from the turned surface images using accurate grey level co-occurrence technique. Precis Eng, 2012, 36: 458-466.

[14] Eckert S. Improved forest biomass and carbon estimations using texture measures from worldview-2 satellite data. Remote Sens, 2012, 4: 810-829.

[15] Eckert S, Rakoto Ratsomba H, Rakotondrasoa LO, Rajoelison LG, Ehrensperger A. Deforestation and forest degradation monitoring and assessment of biomass and carbon stock of lowland rainforest in the Analjirofo region, Madagascar. For Ecol Manag, 2010, 262: 1996-2007.

[16] FAO (1997) Estimating biomass and biomass change of tropical forests: a primer. FAO Forestry Paaper, p 134

[17] Furey TS, Cristianini N, Duffy N, Bednarski DW, Schummer M, Haussler D. Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics, 2000, 16(10): 906-914.

[18] Gao X, Huete AR, Ni W, Miura T. Optical-biophysical relationships of vegetation spectra without background contamination. Remote Sens Environ, 2000, 74: 609-620.

[19] Gao JB, Gunn SR, Harris CJ. SVM regression through variational methods and its sequential implementation. Neurocomputing, 2003, 55: 151-167.

[20] Geo BG. NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens Environ, 1996, 58: 257-266.

[21] Gibbs HK, Brown S, Niles JO, Foley JA. Monitoring and estimating tropical forest carbon stocks: making REDD a reality. Environ Res Lett, 2007, 2(4): 1-13.

[22] Goel NS, Qin W. Influences of canopy architecture on relationships between various vegetation indices LAI and FPAR: a computer simulation. Remote Sens, 1994, 10: 309-347.

[23] Goetz SJ, Baccini A, Laporte NT, Johns T, Walker W, Kellndorfer J. Mapping and monitoring carbon stocks with satellite observations: a comparison of methods. Carbon Balance Manag, 2009, 4(2): 1-7.

[24] Gualtieri JA, Cromp RF. Support vector machines for hyperspectral remote sensing classification. Proc SPIE, 1998, 3584: 221-232.

[25] Hansen EH, Gobakken T, Solberg S, Kangas A, Ene L, Mauya E, Næsset E. Relative efficiency of ALS and InSAR for biomass estimation in a Tanzanian rainforest. Remote Sens, 2015, 7: 9865-9885.

[26] Hsu CW, Chang CC, Lin CJ (2010) A practical guide to support vector classification (Taipei: Department of Computer Science, National Taiwan University). http://www.csie.ntu.edu.tw/~cjlin

[27] IPCC (2000) Nakićenović N, Swart R (eds) Special report on emissions scenarios: a special report of Working Group III of the intergovernmental panel on climate change (book), Cambridge University Press

[28] Intergovernmental Panel on Climate Change (IPCC). The physical science basis: working group I contribution to the fourth assessment report of the IPCC, 2007, Cambridge: Cambridge University Press 996

[29] Kajisa T, Murakami T, Mizoue N, Top N, Shigejiro Y. Object-based forest biomass estimation using Landsat ETM + in Kampong Thom Province, Cambodia. For Res, 2009, 14: 203-211.

[30] Li M. Estimation and analysis of forest biomass in northest forest region using remote sensing technology. Estimation of canopy-average surface-specific leaf area using Landsat TM data, 2010, Harbin: Northoest Forestry University.

[31] Liu Q, Yang L, Liu Q, Li J. Review of forest above ground biomass inversion methods based on remote sensing technology. J Remote Sens, 2015, 19: 62-74.

[32] Mattera D, Haykin S (1999) Support vector machines for dynamic reconstruction of a chaotic system. In: Scho¨lkopf B, Burges J, Smola A (eds) Advances in kernel methods: support vector machine. Cambridge, MA, MIT Press, pp 211–241

[33] Mitchard ETA, Asstchi SS, Woodhouse IH, Nangendo G, Ribeiro NS, Williams M. Using satellite radar backscatter to predict above-ground woody biomass: a consistent relationship across four different African landscapes. Geophys Res Lett, 2009, 36: 1-6.

[34] Mukherjee S, Osuna E, Girosi. F (1997) Nonlinear prediction of chaotic time series using support vector machines. In Proceeding of the 1997 IEEE workshop, pp 511–520

[35] Mustakim M, Buono A, Hermadi I. Performance comparison nSSION and artificial neural network for prediction of oil palm production. J Comput Sci Inf, 2016, 9(1): 1-8.

[36] Pavlidis P, Wapinski I, Noble WS. Support vector machine classification on the web. Bioinformatics, 2004, 20(4): 586-587.

[37] Perales FJ, Campilho AJC, Blanca NP, Sanfeliu A (eds) (2003) Pattern recognition and image analysis. In: Lecture notes in computer science, Berlin, Germany Springer-verlag Berlin Heidelberg, pp 134–141

[38] Pontil M, Mukherjee S, Girosi F (1998) On the noise model of support vector machine regression. In Proceedings of the 11th international conference on algorithmic learning theory, Institute of Technology Cambridge, Massachusetts, USA pp 316–324

[39] Ranta E, Rita H, Kouki J. Biometria, 1991, Tilastotiedettä ekologeille. Helsinki: Yliopistopaino 569

[40] Roujean JL, Breon FM. Estimating PAR absorbed by vegetation from bidirectional reflectance measurement. Remote Sens Environ, 1995, 51: 375-384.

[41] Rouse JW, Haas RH, Schell JA, Deering DW (1973) Monitoring vegetation systems in the Great Plains with ERTS. In: Third earth resources technology satellite-1 symposium. Washington: published by NASA, vol 1, pp 309–317

[42] Rousu J, Flander L, Suutarinen M, Autio K, Kontkanen P, Rantanen A. Novel computational tools in bakery process data analysis: a comparative study. J Food Eng, 2003, 57(1): 45-56.

[43] Shataee Sh, kalbi S, Fallah A. Forest attribute imputation using machine-learning methods and ASTER data: comparison of k-NN, SVR and random forest. Regression algorithms. Int J Remote Sens, 2012, 33(19): 6254-6280.

[44] Sironen S, Kangas A, Maltamo M. Comparison of different non-parametric growth imputation methods in the presence of dependent observations. Forestry, 2010, 83: 39-51.

[45] Sivapragasam C, Liong SY, Pasha MFK. Rainfall and runoff forecasting with SSA–SVM approach. Journal of Hydroinf, 2001, 3: 141-152.

[46] Sohrabi H, Hosseini SM, Zobeiri M. Assessment the forest volume stocks by the use of aerial texture indexes. Iran J For Poplar Res, 2010, 18(2): 297-306.

[47] Steininger MK. Satellite estimation of tropical secondary forest above-ground biomass: data from Brazil and Bolivia. Int J Remote Sens, 2000, 21: 1139-1157.

[48] Todd SW, Hoffer RM, Milchunas DG. Biomass estimation on grazed and ungrazed rangelands using spectral indices. Int J Remote Sens, 1998, 19: 427-438.

[49] Tucker CJ. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens Environ, 1979, 8: 127-150.

[50] Tuominen S, Pekkarinen A. Performance of different spectral and textural aerial photograph features in multi-source forest inventory. Remote Sens Environ, 2005, 94: 256-268.

[51] Vapnik V. The nature of statistical learning theory, 1995, New York: Springer 768

[52] Vicharnakorn P, Shrestha RP, Nagai M, Salam AP, Kiratiprayoon S. Carbon stock assessment using remote sensing and forest inventory data in Savannakhet, Lao PDR. Remote Sens, 2014, 6: 5452-5479.

[53] Walton JT. Subpixel urban land cover estimation: comparing cubist, random forests, and support vector regression. Photogramm Eng Remote Sens, 2008, 74(10): 1213-1222.

[54] Wang Y, Wang J, Du W, Wang C, Liang Y, Zhou C, Huang L (2009) Immune particle swarm optimization for support vector regression on forest fire prediction. In: Yu W He H, Zhang N(eds) Advances in neural networks, ISNN 2009, Part II, LNCS 5552, Berlin: Springer, pp 382–390

[55] Wijaya A, Liesenberg V, Gloaguen R. Retrieval of forest attributes in complex successional forest of Central Indonesia: modeling and estimation of bitemporal data. For Ecol Manag, 2010, 259: 2315-2326.

[56] Wulder MA, LeDrew EF, Franklin SE, Lavigne MB. Aerial image texture information in the estimation of northern deciduous and mixed wood forest leaf area index (LAI). Remote Sens Environ, 1998, 64: 64-76.

[57] Zhou X, Hemstrom MA (2009) Estimating aboveground tree biomass on forest land in the Pacific Northwest: a comparison of approaches. Publication series: Research Paper, Department of Agriculture, Forest Service, Pacific Northwest Research Station, p18

[58] Zien A, Rätsch G, Mika S, Schölkopf B, Lengauer T, Müller KR. Engineering support vector machine kernels that recognize translation initiation sites. Bioinformatics, 2000, 16(9): 799-807.