AccScience Publishing / AJWEP / Volume 21 / Issue 5 / DOI: 10.3233/AJW240062
RESEARCH ARTICLE

Comparisons of Different Cluster Analysis Methods with Application to Mizoram Rainfall Data

L. Thangmawia4 Lalpawimawha 1 Vanlalhriatsaka 1 * Anupam Kumar1 Thanhmingliana 2 R. Zoramthanga1 Mukesh Ranjan1 Denghmingliani 4 L.P. Duhawma4 Zothanpuia 3
Show Less
1 Department of Statistics, Pachhunga University College University, Aizawl, Mizoram
2 Department of Chemistry, Pachhunga University College University, Aizawl, Mizoram
3 Department of Biotechnology, Pachhunga University College University, Aizawl, Mizoram
4 Department of Mathematics, Pachhunga University College University, Aizawl, Mizoram
AJWEP 2024, 21(5), 73–83; https://doi.org/10.3233/AJW240062
Submitted: 8 March 2024 | Revised: 18 April 2024 | Accepted: 18 April 2024 | Published: 7 September 2024
© 2024 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

Analysing rainfall patterns in Mizoram from 1998 to 2017 reveals diverse trends. The highest average rainfall occurred in 2004, reaching 292.8 mm, while 2014 marked the lowest at 151.77 mm. Siaha District experienced the highest average rainfall (3020.2 mm), while Champhai District had the lowest (1663 mm). In 2017, the Kendall method showed correlations between temperature and relative humidity, rainfall and relative humidity, but not between rainfall and temperature. Cluster analysis, a technique partitioning datasets into cohesive groups, was applied to Mizoram’s district-wise rainfall data using single, complete, and average linkage methods. The Single Linkage Method formed one large cluster with under 26% similarity and the shortest distances between data points. The complete linkage method divided districts into two clusters with under 26% similarity and maximal inter-cluster distance. The Average Linkage Method merged all districts into one cluster with under 26% similarity and minimised inter-cluster distances. Comparing the techniques, Single and Complete Linkage Methods proved most effective for Mizoram’s district-wise rainfall data. With only eight districts, forming additional clusters remained limited. This analysis highlights the significance of rainfall patterns in agricultural ecosystems and the utility of statistical methodologies like cluster analysis in understanding long-term trends.

Keywords
Mizoram
rainfall
dendrogram
cluster analysis
References

Alam, M.S. and S. Paul (2020). A comparative analysis of  clustering algorithms to identify the homogeneous rainfall gauge stations of Bangladesh. J Appl Stat, 47: 1460-1481.  https://doi.org/10.1080/02664763.2019.1675606

Gadgil, S. and R. Narayana Iyengar (1980). Cluster analysis  of rainfall stations of the Indian peninsula. Quarterly  Journal of the Royal Meteorological Society, 106: 873- 886. https://doi.org/10.1002/qj.49710645016

Gupta, S.C. and V.K. Kapoor (2002). Fundamentals of  mathematical statistics : A modern approach. Sultan  Chand.

Lallianthanga, R.K., n.d. Climate Profile of Mizoram.

Lin, F.R., Wu, N.J. and T.K. Tsay (2017). Applications of  cluster analysis and pattern recognition for typhoon hourly  rainfall forecast. Advances in Meteorology, 2017(2): 1-17.  https://doi.org/10.1155/2017/5019646

Machiwal, D., Kumar, S., Meena, H.M., Santra, P., Singh,  R.K. and D.V. Singh (2019). Clustering of rainfall stations  and distinguishing influential factors using PCA and  HCA techniques over the western dry region of India. Meteorological Applications 26: 300-311. https://doi. org/10.1002/met.1763

Meteorological Data of Mizoram 2017. P R E F A C E,  n.d. Directorate of Economics & Statistics, Planning &  Programme Implementation. Department Government of  Mizoram

Michaelides, S.C., Pattichis, C.S. and G. Kleovoulou (2001).  Classification of rainfall variability by using artificial  neural networks. International Journal of Climatology,  21: 1401-1414. https://doi.org/10.1002/joc.702

Muñozmu˜muñoz-Díaz, D. and F.S. Rodrigo (2004). Spatiotemporal patterns of seasonal rainfall in Spain (1912- 2000) using cluster and principal component analysis:  Comparison. Annales Geophysicae, 22(5): 1435-1448.

Nasseri, M. and B. Zahraie (2011). Application of simple  clustering on space-time mapping of mean monthly rainfall  pattern. International Journal of Climatology, 31: 732-741.  https://doi.org/10.1002/joc.2109

Pansera, W. and B.M. Gomes (2005). Clustering rainfall  stations aiming regional frequency analysis. Journal of  Food Agriculture and Environment, 11(2): 877-885.

Santos, C.A.G., Neto, R.M.B., da Silva, R.M. and S.G.F.  Costa (2019). Cluster analysis applied to spatiotemporal  variability of monthly precipitation over Paraíba state  using tropical rainfall measuring mission (TRMM) data. Remote Sens (Basel), 11(6): 637. https://doi.org/10.3390/ rs11060637

Teodoro, P.E., de Oliveira-Júnior, J.F., da Cunha, E.R.,  Correa, C.C.G., Torres, F.E., Bacani, V.M., Gois, G. and  L.P. Ribeiro (2016). Cluster analysis applied to the spatial  and temporal variability of monthly rainfall in Mato  Grosso do Sul State, Brazil. Meteorology and Atmospheric  Physics, 128: 197–209. https://doi.org/10.1007/s00703- 015-0408-y

Yashwant, S. and S.L. Sananse (2007). Comparisons of  different methods of cluster analysis with application to  rainfall data. International Journal of Innovative Research  in Science, Engineering and Technology. 4(11): 10861- 10872. https://doi.org/10.15680/IJIRSET.2015.0411087

Share
Back to top
Asian Journal of Water, Environment and Pollution, Electronic ISSN: 1875-8568 Print ISSN: 0972-9860, Published by AccScience Publishing