Abstract
The process life-cycle assessment (LCA) method has a crucial problem such that the LCA system boundary is freely decided by LCA practitioners, which consequently leads to truncation error and underestimation of life-cycle emission. This paper focuses on clustering methods (eigenvalue decomposition of the normalized Laplacian matrix and nonnegative matrix factorization of the normalized affinity matrix) which are useful in determining the LCA system boundary and investigates the instability of the clustering methods. The results indicate that, in cases involving a relatively small number of K-means repetitions (approximately 10), choosing the nonnegative matrix factorization method over the eigenvalue decomposition method yields smaller values of “normalized cut” value N cut (an indicator showing the goodness of network partitions), the benchmark indicating optimal cluster assignment. On the other hand, for a larger number of K-means repetitions (100 or more), neither method is universally superior to the other.
Similar content being viewed by others
References
Ben-David S, von Luxburg U (2008) Relating clustering stability to properties of cluster boundaries. In: Proceedings of the 21st annual conference on learning theory (COLT), pp 379–390
Ben-David S, Pál D, Simon HU (2007) Stability of k-means clustering. Lect Notes Comput Sci 4539:20–34
Ding C, He X, Simon HD (2005) On the equivalence of nonnegative matrix factorization and spectral clustering. In: Proceedings of SIAM international conference on data mining (SDM’05), pp 606–610
Ding C, Li T, Jordan MI (2008) Nonnegative matrix factorization for combinatorial optimization: spectral clustering, graph matching, and clique finding. In: Proceedings of 2008 eighth IEEE international conference on data mining, pp 183–192
Donath WE, Hofmann AJ (1973) Lower bounds for the partitioning of graphs. IBM J Res Dev 17:420–425
Fiedler M (1973) Algebraic connectivity of graphs. Czechoslovak Math J 23:298–305
Fukuyama H, Yoshida Y, Managi S (2011) Modal choice between air and rail: a social efficiency benchmarking analysis that considers CO2 emissions. Environ Econ Policy Stud 13(2):89–102
Heijungs R (1994) A generic method for the identification of options for cleaner products. Ecol Econ 10(1):69–81
Joshi S (1999) Product environmental life-cycle assessment using input-output techniques. J Ind Ecol 3:95–120
Kagawa S, Okamoto S, Suh S, Kondo Y, Nansai K (2013a) Finding environmentally important industry clusters: multiway cut approach using nonnegative matrix factorization. Soc Netw 35:423–438
Kagawa S, Suh S, Kondo Y, Nansai K (2013b) Identifying environmentally important supply chain clusters in the automobile industry. Econ Syst Res 25:265–286
Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401:788–791
Lee DD, Seung HS (2001) Algorithms for non-negative matrix factorization. In: Dietterich TG, Tresp V (eds) Advances in neural information processing systems, vol 13, The MIT Press, Cambridge
Lenzen M (2001) Errors in conventional and input-output-based life-cycle inventories. J Ind Ecol 4:127–148
Lenzen M, Crawford R (2009) The path exchange method for hybrid LCA. Environ Sci Technol 43:8251–8256
Nansai K, Moriguchi Y (2012) Embodied energy and emission intensity data for Japan using input–output tables (3EID): for 2005 IO table, CGER, National Institute for Environmental Studies, Japan. http://www.cger.nies.go.jp/publications/report/d031/index.html
Shao L, Chen GQ (2013) Water footprint assessment for wastewater treatment: method, indicator and application. Environ Sci Technol 47:7787–7794
Shao L, Chen GQ, Chen ZM, Guo S, Han MY, Zhang B, Hayat T, Alsaedi A, Ahmad B (2014) Systems accounting for energy consumption and carbon emission by building. Commun Nonlinear Sci Numer Simul 19:1859–1873
Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22:888–905
Strømman AH, Peters GP, Hertwich EG (2009) Approaches to correct for double counting in tiered hybrid life cycle inventories. J Clean Prod 17(2):248–254
Suh S, Huppes G (2005) Methods for life cycle inventory of a product. J Clean Prod 13:687–697
Suh S, Nakamura S (2007) Five years in the area of input-output and hybrid LCA. Int J Life Cycle Assess 12(6):351–352
Suh S, Lenzen M, Treloar G, Hondo H, Horvath A, Huppes G, Jolliet O, Klann U, Krewitt W, Moriguchi Y, Munksgaard J, Norris G (2004) System boundary selection for life cycle inventories. Environ Sci Technol 38(3):657–664
von Luxburg U (2007) A tutorial on spectral clustering. Stat Comput 17:395–416
von Luxburg U (2010) Clustering stability: an overview. Found Trends Mach Learn 2:235–274
von Luxburg U, Belkin M, Bousquet O (2008) Consistency of spectral clustering. Ann Stat 36:555–586
Xia XH, Huang GT, Chen GQ, Zhang B, Chen ZM, Yang Q (2011) Energy security, efficiency and carbon emission of Chinese industry. Energy Policy 39:3520–3528
Zhang Z, Jordan MI (2008) Multiway spectral clustering: a margin-based perspective. Stat Sci 23:383–403
Zhang B, Chen GQ, Xia XH, Li SC, Chen ZM, Ji X (2012) Environmental emissions by Chinese industry: energy-based unifying assessment. Energy Policy 45:490–501
Acknowledgments
An early version of this paper was prepared for the 24th Pan Pacific Association of Input–Output Studies, Nagoya, October 2013. I gratefully appreciate helpful comments received from Shunsuke Mori (Tokyo University of Science), Hiroshi Taguchi (Central Research Institute of Electric Power Industry), and Yuko Oshita (Kobe University) at the conference. In addition, I would like to express my gratitude to Shigemi Kagawa (Kyushu University) and Keiichiro Kanemoto (Kyushu University) for their penetrating opinions. I also want to express appreciation for the helpful comments and suggestions from the anonymous reviewer and the editor. This research has been supported by a Grant-in-Aid for Research Fellowship (No. 25·7261) of the Japan Society for the Promotion of Science.
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
See Table 2.
About this article
Cite this article
Okamoto, S. Analyzing instability of industrial clustering techniques. Environ Econ Policy Stud 17, 389–406 (2015). https://doi.org/10.1007/s10018-014-0086-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10018-014-0086-x