Modelling silvicultural thinning using unsupervised machine learning: Evidence from Pterocarpus santalinus trial plots of Odisha, India
Ključne riječi:
K-means clustering, Hierarchical clustering, Pterocarpus santalinus, Silvicultural thinning, Silhouette score, Caliński–Harabasz indexSažetak
Silvicultural thinning is essential for regulating stand density, yet conventional prescriptions rely on fixed rules and subjective judgment that may not fully account for stand heterogeneity. This study applies unsupervised machine learning to support silvicultural thinning decisions in Pterocarpus santalinus trial plots across Odisha, India. Tree-level girth and height data from six plots were analysed using k-means and hierarchical clustering to classify trees for retention or felling. Across all six plots, k-means produced better-separated clusters than hierarchical clustering, with higher silhouette scores (0.53–0.62 versus 0.46–0.61) and higher Caliński–Harabasz index values (approximately 538–2504 versus 200–2334). The clustering approach offers an objective, reproducible, and quantitative framework for characterising intra-stand variability that can complement traditional rule-based thinning and support more consistent, data-informed silvicultural management.
Reference
Abbas, S., Wong, M. S., Wu, J., Shahzad, N., & Muhammad Irteza, S. 2020. Approaches of satellite remote sensing for the assessment of above-ground biomass across tropical forests: Pan-tropical to national scales. Remote Sensing, 12(20): 3351. doi: 10.3390/rs12203351.
Banskota, A., Kayastha, N., Falkowski, M. J., Wulder, M. A., Froese, R. E., & White, J. C. 2014. Forest monitoring using Landsat time series data: A review. Canadian Journal of Remote Sensing, 40(5): 362–384. doi: 10.1080/07038992.2014.987376.
Blanco, J. A., Ameztegui, A., & Rodríguez, F. 2020. Modelling forest ecosystems: a crossroad between scales, techniques and applications. Ecological Modelling, 425: 109030. doi: 10.1016/j.ecolmodel.2020.109030.
Cattaneo, N., Puliti, S., Fischer, C., & Astrup, R. 2024. Estimating wood quality attributes from dense airborne LiDAR point clouds. Forest Ecosystems, 11: 100184. doi: 10.1016/j.fecs.2024.100184.
Goodbody, T. R., Coops, N. C., & White, J. C. 2019. Digital aerial photogrammetry for updating area-based forest inventories: A review of opportunities, challenges, and future directions. Current Forestry Reports, 5(2): 55–75. doi: 10.1007/s40725-019-00087-2.
Hanewinkel, M., Cullmann, D. A., Schelhaas, M. J., Nabuurs, G. J., & Zimmermann, N. E. 2013. Climate change may cause severe loss in the economic value of European forest land. Nature Climate Change, 3(3): 203–207. doi: 10.1038/nclimate1687.
Hota, A. 2024. Heterogeneity in biomass production and net primary productivity of Pterocarpus santalinus L.f. in Odisha [Master's thesis]. Odisha University of Agriculture and Technology. https://krishikosh.egranth.ac.in/handle/1/5810231713.
Köppen, W. 1936. Das geographische System der Klimate. In Handbuch der Klimatologie (Vol. 1, Part C). Gebrüder Borntraeger, Berlin.
Maxwell, A. E., Warner, T. A., & Fang, F. 2018. Implementation of machine-learning classification in remote sensing: An applied review. International Journal of Remote Sensing, 39(9): 2784–2817. doi: 10.1080/01431161.2018.1433343.
McAdam, E. 2015. Using remote sensing and process-based growth modelling to predict forest productivity across Western Oregon [M.Sc. thesis]. Oregon State University.
Mosin, V., Aguilar, R., Platonov, A., Vasiliev, A., Kedrov, A., & Ivanov, A. 2019. Remote sensing and machine learning for tree detection and classification in forestry applications. In Image and Signal Processing for Remote Sensing XXV (Vol. 11155, pp. 130–141). SPIE. doi: 10.1117/12.2531820.
Pommerening, A., & Grabarnik, P. 2019. Theories and concepts in individual-based forest management. In Individual-based Methods in Forest Ecology and Management (pp. 51–97). Springer International Publishing, Cham. doi: 10.1007/978-3-030-24528-3_3.
R Core Team. 2024. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/.
Seidl, R., Thom, D., Kautz, M., Martin-Benito, D., Peltoniemi, M., Vacchiano, G., … Reyer, C. P. 2017. Forest disturbances under climate change. Nature Climate Change, 7(6): 395–402. doi: 10.1038/nclimate3303.
Stupariu, M. S., Cushman, S. A., Pleşoianu, A. I., Pătru-Stupariu, I., & Fuerst, C. 2022. Machine learning in landscape ecological analysis: a review of recent approaches. Landscape Ecology, 37(5): 1227–1250. doi: 10.1007/s10980-021-01366-9.
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. 2021. Understanding deep learning (still) requires rethinking generalization. Communications of the ACM, 64(3): 107–115. doi: 10.1145/3446776.
Zhou, L., Pan, S., Wang, J., & Vasilakos, A. V. 2017. Machine learning on big data: Opportunities and challenges. Neurocomputing, 237: 350–361. doi: 10.1016/j.neucom.2017.01.026.
Preuzimanja
Objavljeno
Broj časopisa
Rubrika
Licenca
Authors who publish with this journal agree to the following terms:- Authors grant the journal right of first publication, with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) following the publication by the journal, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
