Selection of Sustainable Process and Essential Indicators for Decision Making Using Machine Learning Algorithms

Abstract

Sustainability of processes or systems is generally evaluated with metrics or indicators. When a set of indicators is identified for a particular system of study, it is important to ensure that all the indicators are necessary and sufficient in defining system sustainability. The indicators should be able to distinguish sustainable process options from unsustainable ones. Generally, a large number of indicators are used to characterize a system. While some of the indicators are essential sustainable indicators, they may not be relevant in defining the particular system of interest. It is essential to select the most important indicators from a large set so that reduced set of indicators can enhance the generalized performance of sustainable process selection algorithm. In this paper, we propose the use of machine learning algorithms including k-means clustering for sustainable process selection and support vector machine recursive feature elimination algorithm (SVM-RFE) for relevant indicator identification that is important in sustainable process classification from a group of competing process options. The method is based on weight vector derivatives or generalized error bound sensitivity with respect to each indicator. The proposed method of relevant indicator selection is compared with previous work on important indicator identification using partial least square-variable importance in projection (PLS-VIP) method. We have used two case studies to demonstrate the methodologies. While the PLS-VIP method was successful in identifying indicators that are sufficient for finding relative importance of different process options, SVM-RFE method is useful for identifying indicators that are sufficient in sustainable process classification.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. Brandi HS, dos Santos SF (2016) Introducing measurement science into sustainability systems. Clean Techn Environ Policy 18(2):359–371

    Article  Google Scholar 

  2. Cinar A, Palazoglu A, Kayihan F (2007) Chemical process performance evaluation. CRC press, Boca Raton

    Google Scholar 

  3. El-Halwagi MM (2017) A return on investment metric for incorporating sustainability in process integration and improvement projects. Clean Techn Environ Policy 19(2):611–617

    Article  Google Scholar 

  4. Everitt BS (1993) Cluster analysis, Heinemann Education

  5. Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1–3):389–422

    Article  MATH  Google Scholar 

  6. IChemE (2002) The sustainability metrics, http://www.icheme.org/communities/ subject_groups/sustainability/~/media/Documents/Subject Groups/Sustainability/Newsletters/Sustainability Metrics.ashx Accessed 22 June 2017

  7. Iribarnegaray MA, D’Andrea MLG, Rodriguez-Alvarez MS, Hernández ME, Brannstrom C, Seghezzo L (2015) From indicators to policies: open sustainability assessment in the water and sanitation sector. Sustainability 7(11):14537–14557

    Article  Google Scholar 

  8. Jia X, Li Z, Wang F, Qian Y (2016) Integrated sustainability assessment for chemical processes. Clean Techn Environ Policy 18(5):1295–1306

    Article  Google Scholar 

  9. Mukherjee R, Sengupta D, Sikdar SK (2013) Parsimonious use of indicators for evaluating sustainability systems with multivariate statistical analyses. Clean Techn Environ Policy 15(4):699–706

    Article  Google Scholar 

  10. Olinto AC (2017) Invariance and robustness of the ordered inequality of aggregate sustainability indices by vector space theory. Clean Techn Environ Policy 19(2):587–594

    Article  Google Scholar 

  11. Rakotomamonjy A (2003) Variable selection using SVM-based criteria. J Mach Learn Res 3:1357–1370

    MathSciNet  MATH  Google Scholar 

  12. Saur C, Fava J, Spatari S (2000) Life cycle engineering case study: automotive fender designs. Environ Prog 19(2):72–82

    Article  Google Scholar 

  13. Schwarz J, Beloff B, Beaver E (2002) Use sustainability metrics to guide decision-making. Chem Eng Prog 98(7):58–63

    Google Scholar 

  14. Sengupta D, Mukherjee R, Sikdar SK (2015a) Moving to a decision point in sustainability analysis, Assessing and measuring environmental impact and sustainability. Butterworth-Heinemann, MA, pp 87–129

    Google Scholar 

  15. Sengupta D, Mukherjee R, Sikdar SK (2015b) Environmental sustainability of countries using the UN MDG indicators by multivariate statistical methods. Environ Prog Sustain Energy 34(1):198–206

    Article  Google Scholar 

  16. Sikdar SK (2009) On aggregating multiple indicators into a single metric for sustainability. Clean Techn Environ Policy 11:157–161

    Article  Google Scholar 

  17. Sikdar SK, Sengupta D, Harten P (2012) More on aggregating multiple indicators into a single index for sustainability analyses. Clean Techn Environ Policy 14:765–773

    Article  Google Scholar 

  18. Sikdar SK, Sengupta D, Mukherjee R (2016) Measuring progress towards sustainability: a treatise for engineers. 1st edn., Springer

  19. Sikdar SK, Sengupta D, Mukherjee R (2017) Statistical algorithms for sustainability measurement and decision making. In: Measuring Progress Towards Sustainability. Springer International Publishing, p 153–184

  20. Tan RR, Promentilla MAB (2013) A methodology for augmenting sparse pairwise comparison matrices in AHP: applications to energy systems. Clean Techn Environ Policy 15(4):713–719

    Article  Google Scholar 

  21. Vapnik V (2013) The nature of statistical learning theory. Springer science & business media

  22. Vermeulen I, Block C, Van Caneghem J, Dewulf W, Sikdar S, Vandecasteele C (2012) Sustainability assessment of industrial waste treatment processes. The case of automotive shredder residue. Resour Conserv Recycl 69:17–28

    Article  Google Scholar 

  23. Wold S, Sjöström M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst 58(2):109–130

    Article  Google Scholar 

  24. Yan K, Zhang D (2015) Feature selection and analysis on correlated gas sensor data with recursive feature elimination. Sensors Actuators B Chem 212:353–363

    Article  Google Scholar 

  25. Zhou L, Tokos H, Krajnc D, Yang Y (2012) Sustainability performance evaluation in industry by composite sustainability index. Clean Techn Environ Policy 14:789–803

    Article  Google Scholar 

Download references

Acknowledgements

The author acknowledges benefiting from discussions and insights to process sustainability with Dr. Subhas K. Sikdar, retired from National Risk Management Research Laboratory, US EPA, and Dr. Debalina Sengupta, Gas and Fuels Research Center, Texas A&M University.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Rajib Mukherjee.

Ethics declarations

Conflict of Interest

The author declares that he has no conflict of interest.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mukherjee, R. Selection of Sustainable Process and Essential Indicators for Decision Making Using Machine Learning Algorithms. Process Integr Optim Sustain 1, 153–163 (2017). https://doi.org/10.1007/s41660-017-0011-4

Download citation

Keywords

  • Sustainability indicators
  • Support vector machine-recursive feature elimination (SVM-RFE)
  • K-means clustering
  • Partial least square-variable importance in projection (PLS-VIP)
  • Sustainability footprint