A Hybrid Clustering Method for Burnt Area Mapping of Forests
A Hybrid Clustering Method for Burnt Area Mapping of Forests |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-11 |
||
| Year of Publication : 2023 | ||
| Author : Keerti Kulkarni |
||
| DOI : 10.14445/22315381/IJETT-V71I11P221 | ||
How to Cite?
Keerti Kulkarni, "A Hybrid Clustering Method for Burnt Area Mapping of Forests," International Journal of Engineering Trends and Technology, vol. 71, no. 11, pp. 201-207, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I11P221
Abstract
Mapping the burnt forest areas presents a major challenge since it is impossible to collect the ground information (labelled data) for the supervised classification. In such cases, unsupervised classification techniques, which do not require any prior knowledge of the geographic area, can be used. This work maps the burnt areas of the forests of Bandipura forests in Karnataka (also known as Rajiv Gandhi National Park) using remotely sensed images obtained from LANDSAT-8. Part of the forests were destroyed in the forest fires of February 2019. Unsupervised k-means clustering algorithm is used to map the forest area. After that, the burnt areas are mapped using a hybrid approach comprising the Normalized Burn Ratio (NBR) and the Normalized Difference Water Index (NDWI). Additionally, the severity of the burns is also mapped using the threshold values in the difference Normalized Burn Ratio (dNBR). It was found that around 15,000 acres of forested land were lost due to forest fires.
Keywords
Forest Mapping, k-means clustering, Normalized Burn Ratio, Difference Normalized Burn Ratio, Unsupervised Learning.
References
[1] D.P. Malik, and Sunil Dhanda, “Status, Trends and Demand for Forest Products in India,” 12th World Forestry Congress, Quebec City, Canada, 2003.
[Google Scholar] [Publisher Link]
[2] R.K. Sharma et al., “Study of Forest Fires in Sikkim Himalayas, India Using Remote Sensing and GIS Techniques,” Climate Change in Sikkim–Patterns, Impacts and Initiatives, pp. 233-244, 2012.
[Google Scholar] [Publisher Link]
[3] M.S. Negi, and Atul Kumar, “Assessment of Increasing Threat of Forest Fires in Uttarakhand, Using Remote Sensing and GIS Techniques,” Global Journal of Advanced Research, vol. 3, no. 6, pp. 457-468, 2016.
[Google Scholar] [Publisher Link]
[4] Mark A. Cochrane, and William F. Laurance, “Fire as a Large-Scale Edge Effect in Amazonian Forests,” Journal of Tropical Ecology, vol. 18, pp. 311-325, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Tomohiro Shiraishi, Ryuichi Hirata, and Takashi Hirano, “New Inventories of Global Carbon Dioxide Emissions through Biomass Burning in 2001-2020,” Remote Sensing, vol. 13, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Lisa-Jen Ferrato, and K. Wayne Forsythe, “Comparing Hyperspectral and Multispectral Imagery for Land Classification of the Lower Don River, Toronto,” Journal of Geography and Geology, vol. 5, no. 1, pp. 92-107, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[7] T. Toutin, “Geometric Processing of Remote Sensing Images: Models, Algorithms and Methods,” International Journal of Remote Sensing, vol. 25, no. 10, pp. 1893-1924, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[8] D. Lu, and Q. Weng, “A Survey of Image Classification Methods and Techniques for Improving Classification Performance,” International Journal of Remote Sensing, vol. 28, no. 5, pp. 823-870, 2007.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Tapas Ray et al., “Impact of Forest Fire Frequency on Tree Diversity and Species Regeneration in Tropical Dry Deciduous Forest of Panna Tiger Reserve, Madhya Pradesh, India,” Journal of Sustainable Forestry, vol. 40, no. 5, pp. 831-845, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] George P. Petropoulos, Charalambos Kontoes, and Iphigenia Keramitsoglou, “Burnt Area Delineation from a Uni-Temporal Perspective Based on Landsat TM Imagery Classification Using Support Vector Machines,” International Journal of Applied Earth Observation and Geoinformation, vol. 13, no. 1, pp. 70-80, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Rubén Ramo et al., “A Data Mining Approach for Global Burned Area Mapping,” International Journal of Applied Earth Observation and Geoinformation, vol. 73, pp. 39-51, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Ruiliang Pu, and Peng Gong, “Determination of Burnt Scars Using Logistic Regression and Neural Network Techniques from a Single Post-Fire Landsat 7 ETM+ Image,” Photogrammetric Engineering and Remote Sensing, vol. 70, no. 7, pp. 841-850, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[13] M. Pal, “Random Forest Classifier for Remote Sensing Classification,” International Journal of Remote Sensing, vol. 26, no. 1, pp. 217- 222, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Matteo Sali et al., “A Burned Area Mapping Algorithm for Sentinel-2 Data Based on Approximate Reasoning and Region Growing,” Remote Sensing, vol. 13, no. 11, pp. 1-27, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[15] K.V. Suresh Babu, A. Roy, and R. Aggarwal, “Mapping of Forest Fire Burned Severity Using the Sentinel Datasets,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 469-474, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Abhinav Chandel et al., “Evaluating Methods to Map Burned Area at 30-Meter Resolution in Forests and Agricultural Areas of Central India,” Frontiers in Forests and Global Change, vol. 5, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Justin Epting, David Verbyla, and Brian Sorbel, “Evaluation of Remotely Sensed Indices for Assessing Burn Severity in Interior Alaska using Landsat TM and ETM+,” Remote Sensing of Environment, vol. 96, no. 3, pp. 328-339, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Louis Giglio, Wilfrid Schroeder, and Christopher O. Justice, “The Collection 6 MODIS Active Fire Detection Algorithm and Fire Products,” Remote Sensing of Environment, vol. 178, pp. 31-41, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] V.S. Kalaranjini et al., “Burnt Area Detection using SAR Data – A Case Study of May, 2020 Uttarakand Forest fire,” Proceedings of the 2020 IEEE India Geoscience and Remote Sensing Symposium, IEEE, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Alistair M.S. Smith et al., “Testing the Potential of Multi-Spectral Remote Sensing for Retrospectively Estimating Fire Severity in African Savannahs,” Remote Sensing of Environment, vol. 97, no. 1, pp. 92-115, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Jan W. van Wagtendonk, Ralph R. Root, and Carl H. Key, “Comparison of AVIRIS and Landsat ETM+ Detection Capabilities for Burn Severity,” Remote Sensing of Environment, vol. 92, no. 3, pp. 397-408, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Natasha M. Robinson et al., “Refuges for Birds in Fire-Prone Landscapes: The Influence of Fire Severity and Fire History on the Distribution of Forest Birds,” Forest Ecology and Management, vol. 318, pp. 110-121, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Sapana B. Chavan, C. Sudhakar Reddy, and K. Kameswara Rao, “Conservation Priority Hotspot for Forests of Nirmal District, Telangana Using Geospatial Techniques: A Case Study,” SSRG International Journal of Geoinformatics and Geological Science, vol. 5, no. 2, pp. 1-7, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Jon E. Keeley, “Fire Intensity, Fire Severity and Burn Severity: A Brief Review and Suggested Usage,” International Journal of Wildland Fire, vol. 18, no. 1, pp. 116-126, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Shubhaswi Ananth et al., “Mapping of Burnt Area and Burnt Severity Using Landsat 8 Images: A Case Study of Bandipur Forest Fire Region of Karnataka State India,” IEEE Recent Advances in Geoscience and Remote Sensing: Technologies, Standards and Applications, pp. 146-147, 2019.
[CrossRef] [Google Scholar] [Publisher Link]