Comparison of data mining and allometric model in estimation of tree biomass

BMC Bioinformatics

Carlos R. Sanquetta¹  Jaime Wojciechowski¹  Ana P. Dalla Corte¹  Alexandre Behling¹  Sylvio Péllico Netto¹  Aurélio L. Rodrigues¹  Mateus N. I. Sanquetta¹ 

[1] Forest Science Department, Federal University of Paraná, 900 Lothário Meissner Avenue, Curitiba, Paraná, Brazil

关键词: Modeling;    Instance;    Forests;    Carbon;    Accuracy;   

Others  :  1230254
DOI  :  10.1186/s12859-015-0662-5

 received in 2014-08-14, accepted in 2015-07-03,  发布年份 2015

【 摘 要 】

Background

The traditional method used to estimate tree biomass is allometry. In this method, models are tested and equations fitted by regression usually applying ordinary least squares, though other analogous methods are also used for this purpose. Due to the nature of tree biomass data, the assumptions of regression are not always accomplished, bringing uncertainties to the inferences. This article demonstrates that the Data Mining (DM) technique can be used as an alternative to traditional regression approach to estimate tree biomass in the Atlantic Forest, providing better results than allometry, and demonstrating simplicity, versatility and flexibility to apply to a wide range of conditions.

Results

Various DM approaches were examined regarding distance, number of neighbors and weighting, by using 180 trees coming from environmental restoration plantations in the Atlantic Forest biome. The best results were attained using the Chebishev distance, 1/d weighting and 5 neighbors. Increasing number of neighbors did not improve estimates. We also analyze the effect of the size of data set and number of variables in the results. The complete data set and the maximum number of predicting variables provided the best fitting. We compare DM to Schumacher-Hall model and the results showed a gain of up to 16.5 % in reduction of the standard error of estimate.

Conclusion

It was concluded that Data Mining can provide accurate estimates of tree biomass and can be successfully used for this purpose in environmental restoration plantations in the Atlantic Forest. This technique provides lower standard error of estimate than the Schumacher-Hall model and has the advantage of not requiring some statistical assumptions as do the regression models. Flexibility, versatility and simplicity are attributes of DM that corroborates its great potential for similar applications.

【 授权许可】

   
2015 Sanquetta et al.

【 图 表 】

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

【 参考文献 】

• [1]Dixon RK, Brown S, Houghton RA, Solomon AM, Trexler MC, Wisniewski J. Carbon pools and flux of global forest ecosystems. Science. 1994; 263:185-90.
• [2]Global forest resources assessment. Food and Agriculture Organization of the United Nations, Rome; 2010.
• [3]Laurance WF, Nascimento HEM, Laurance SG, Andrade A, Ewers RM, Harms KA et al.. Habitat fragmentation, variable edge effects, and the landscape-divergence hypothesis. PLoS One. 2007; 2:e.1017.
• [4]Laurance WF, Camargo JL, Luizão RC, Laurance SG, Pimm SL, Bruna EM. The fate of Amazonian forest fragments: a 32-year investigation. Conserv Biol. 2011; 144:56-67.
• [5]Shukla J, Nobre CA, Sellers P. Amazon deforestation and climate change. Science. 1990; 247:1322-5.
• [6]Houghton J. Global warming. Rep Prog Phys. 2005; 68:1343-403.
• [7]Kindermann EG, McCallum I, Fritz S, Obersteiner MA. Global forest growing stock, biomass and carbon map based on FAO statistics. Silva Fennica. 2008; 42:387-96.
• [8]Mandal RA, Yadav BKV, Yadav KK, Dutta IC, Haque SM. Development of allometric equation for biomass estimation of eucalyptus camaldulensis: a study from Sagarnath Forest, Nepal. Int J Biodiv Ecosyst. 2013; 1:1-7.
• [9]Alam K, Nizami SM. Assessing biomass expansion factor of Birch Tree Betula utilis D. DON. Open J Forestry. 2014; 4:181-90.
• [10]Kurz WA, Beukem SJ, Apps MJ. Estimation of root biomass and dynamics for the carbon budget model of the Canadian forest sector. Can J For Res. 1996; 26:1973-9.
• [11]Levy P, Hale S, Nicoll B. Biomass expansion factors and root: shoot ratios for coniferous tree species in Great Britain. Forestry. 2004; 77:421-30.
• [12]Sanquetta CR, Corte APD, Silva F. Biomass expansion factor and root-to-shoot ratio for Pinus in Brazil. Carbon Balance Manag. 2011; 6:1-8. BioMed Central Full Text
• [13]Petrokofsky G, Kanamaru H, Achard F, Goetz SJ, Joosten H, Holmgren P et al.. Comparison of methods for measuring and assessing carbon stocks and carbon stock changes in terrestrial carbon pools. How do the accuracy and precision of current methods compare? A systematic review protocol. Environmental Evidence. 2012; 1:1-22. BioMed Central Full Text
• [14]Osborne J, Waters E. Four assumptions of multiple regression that researchers should always test. Pract Assessment Res Evaluation. 2002; 8(2):1-8.
• [15]Tan P, Steinbach M, Kumar V. Introduction to data mining. Stanford University Press, Stanford; 2009.
• [16]Mithal VA, Garg S, Boriah M, Steinbach V, Kumar C, Potter SK et al.. Monitoramento da cobertura florestal global usando mineração de dados. ACM Trans Intell Syst Technol. 2011; 2:24-36.
• [17]Albert MK, Kibler D, Aha DW. Instance-based learning algorithms. Mach Learn. 1991; 6:37-66.
• [18]Bradzil PB, Soares C, Costa JP. Ranking learning algorithms: using IBL anda Meta-Learning on accuracy and time results. Mach Learn. 2003; 50:251-77.
• [19]Sanquetta CR, Wojciechowski J, Corte APD, Rodrigues AL, Maas GCB. On the use of data mining for estimating carbon storage in the trees. Carbon Balance Manag. 2013; 8(6):1-9.
• [20]Dean W. A ferro e fogo: a história e a devastação da Mata Atlântica brasileira. Companhia das Letras, São Paulo; 1995.
• [21]Martins SV, Sartori M, Raposo Filho FR, Simoneli M, Dadalto G, Pereira ML et al.. Potencial de regeneração natural de florestas nativas nas diferentes regiões do Estado do Espírito Santo. CEDAGRO, Vitória; 2014.
• [22]Martins SV. Recuperação de áreas degradadas: ações em áreas de preservação permanente, voçorocas, taludes rodoviários e de mineração. Aprenda Fácil Editora, Viçosa; 2013.
• [23]Manual de Restauração Florestal: Um Instrumento de Apoio à Adequação Ambiental de Propriedades Rurais do Pará. The Nature Conservancy, Belém; 2013.
• [24]Vieira SA, Alves LF, Aidar M, Araújo LS, Baker T, Batista JLF et al.. Estimation of biomass and carbon stocks: the case of the Atlantic Forest. Biota Neotrop. 2008; 8:21-9.
• [25]Brown S. Estimating biomass and biomass change of tropical forests: a primer. FAO, Rome; 1997.
• [26]Machado SA, Figueiredo Filho A. Dendrometria. Published by the authors, Curitiba; 2003.
• [27]Cole TC, Ewel JJ. Allometric equations for four valuable tropical tree species. For Ecol Manage. 2006; 229:351-60.
• [28]Tiepolo G, Calmon M, Ferretti AR. Measuring and monitoring carbon stocks at the Guaraqueçaba climate action project, Paraná, Brazil. In: Proceedings of the International Symposium of Forest carbon sequestration and monitoring: 2002. Taiwan Forestry Research Institute, Taipei; 2002: p.98-115.
• [29]Rolim SG, Jesus RM, Nascimento HEM, Couto HTZ, Chambers JQ. Biomass change in Atlantic tropical moist forest: The ENSO effect in permanent sample plots over a 22-year period. Oecologia. 2005; 142:238-46.
• [30]Alves LF, Vieira SA, Scaranello MA, Camargo PB, Santos FAM, Joly CA et al.. Forest structure and live aboveground biomass variation along an elevational gradient of tropical Atlantic moist forest (Brazil). For Ecol Manage. 2010; 260:679-91.
• [31]Lindner A, Sattler D. Biomass estimations in forests of different disturbance history in the Atlantic Forest of Rio de Janeiro, Brazil. New Forests. 2011; 43:287-301.
• [32]Miranda DLC, Melo ACG, Sanquetta CR. Equações alométricas para estimativa de biomassa e carbono em árvores de reflorestamentos de restauração. Rev Árvore. 2011; 35:679-89.
• [33]Nogueira LR, Engel VL, Parrotta JA, Melo ACG, Re DS. Allometric equations for estimating tree biomass in restored mixed-species Atlantic Forest stands. Biota Neotrop. 2014; 14(2):1-9.
• [34]Chave J, Andalo C, Brown S, Cairns M, Chambers J, Eamus D et al.. Tree allometry and improved estimation of carbon stocks and balance in tropical forests. Oecologia. 2005; 145:87-99.
• [35]Mascaro J, Litton CM, Hughes RF, Uowolo A, Schnitzer SA. Minimizing bias in biomass allometry: model selection and log-transformation of data. Biotropica. 2011; 43(6):649-53.
• [36]Gujarati DN, Porter DC. Econometria básica. Bookman, Porto Alegre; 2009.
• [37]White HA. Heteroskedasticity consistente covariance matrix estimator and a direct test of heteroskedasticity. Econometrica. 1980; 48:817-38.
• [38]Maddala GS. Introduction to Econometrics. Prentice Hall, Englewood Cliffs; 2001.
• [39]Xiao X, White EP, Hooten MB, Durham SL. On the use of log-transformation vs. nonlinear regression for analyzing biological power laws. Ecology. 2011; 92(10):1887-94.
• [40]Sanquetta CR, Balbinot R. Metodologias para determinação de biomassa florestal. In: As Florestas e o Carbono. Sanquetta CR, Watzlawick LF, Balbinot R, Ziliotto MAB, Gomes FS, editors. Imprensa Universitária da UFPR, Curitiba; 2002: p.77-92.
• [41]Zhou G, Xiaojun X, Huaqiang D, Hongli G, Yongjun S, Yufeng Z. Estimating Moso bamboo forest attributes using the k Nearest Neighbors technique and satellite imagery. Photogramm Eng Remote Sens. 2011; 77(11):1123-31.
• [42]McRoberts RE. Diagnostic tools for nearest neighbors techniques when used with satellite imagery. Remote Sens Environ. 2009; 113(3):489-99.
• [43]Akaike H. Information theory as an extension of the maximum likelihood principle. In: Proceedings of the Second International Symposium on Information Theory 1973; Baltimore. Petrov BN, Csaki F, editors. Akademiai Kiado, Hungary; 1973: p.267-81.
• [44]Schwarz G. Estimating the dimensional of a model. Ann Stat. 1978; 6:461-4.
• [45]Burnham KP, Anderson DR. Model selection and multimodel inference: a practical information-theoretic approach. Springer, New York; 2002.