Using fuzzy C-means and local autocorrelation to cluster satellite-inferred burn severity classes
Zachary A. Holden A C and Jeffrey S. Evans BA US Forest Service, 200 East Broadway, Missoula, MT 59807, USA.
B The Nature Conservancy, 117 East Mountain Avenue, Fort Collins, CO 80524, USA. Email: jeffrey_evans@tnc.org
C Corresponding author. Email: zaholden@fs.fed.us
International Journal of Wildland Fire 19(7) 853-860 https://doi.org/10.1071/WF08126
Submitted: 16 July 2008 Accepted: 16 April 2010 Published: 5 November 2010
Abstract
Burn severity classifications derived from multitemporal Landsat Thematic Mapper images and the Normalised Burn Ratio (NBR) are commonly used to assess the post-fire ecological effects of wildfires. Ongoing efforts to retrospectively map historical burn severity require defensible, objective methods of classifying continuous differenced Normalised Burn Ratio (dNBR) data where field data are often unavailable. For three fires, we compare three methods of classifying pre- and post-fire Landsat data: (1) dNBR classification using Composite Burn Index (CBI) field data to assign severity classes; (2) fuzzy C-means classification of a dNBR image; (3) local Getis–Ord statistic (Gi*) output applied to a dNBR image, classified using fuzzy C-means clustering. We then use a Kappa statistic to evaluate the agreement of severity classes assigned to a pixel with its corresponding CBI plot. For two of the three fires, the C-means clustering of the dNBR and the Gi* output performed as well or better than dNBR images classified using CBI data, with strong agreement for moderate- and high-severity classes. These results suggest that clustering of dNBR data may be a suitable approach for classifying burn severity data without field data. This method may also be useful as a tool for rapid post-fire assessments (e.g. Burned Area Emergency Response and Burned Area Reflectance Classification maps), where images must often be classified quickly and subjectively. Further analysis using additional field data and across different vegetation types will be necessary to better understand the importance of localised spatial variability in classifying burn severity data or other remote sensing change-detection analyses.
References
Anselin L (1995) Local indicators of spatial association – LISA. Geographical Analysis 27, 93–115.Bezdek JC (1981) ‘Pattern Recognition with Fuzzy Objective Function Algorithms.’ (Plenum Press: New York)
Bivand R (2008) ‘spdep: Spatial Dependence: Weighting Schemes, Statistics and Models. R Package 0.4–21.’ (R Foundation for Statistical Computing: Vienna, Austria)
Burrough PA, Wilson JP, van Gaans P, Hansen AJ (2001) Fuzzy k-means classification of topoclimatic data as an aid to forest mapping in the Greater Yellowstone Area, USA. Landscape Ecology 16, 523–546.
| Fuzzy k-means classification of topoclimatic data as an aid to forest mapping in the Greater Yellowstone Area, USA.Crossref | GoogleScholarGoogle Scholar |
Cocke AE, Fule PZ, Crouse JE (2005) Comparison of burn severity assessments using Differenced Normalized Burn Ratio and ground data. International Journal of Wildland Fire 14, 189–198.
| Comparison of burn severity assessments using Differenced Normalized Burn Ratio and ground data.Crossref | GoogleScholarGoogle Scholar |
Cohen J (1960) A coefficient of agreement for nominal scales. Educational and Psychological Measurement 20, 37–46.
| A coefficient of agreement for nominal scales.Crossref | GoogleScholarGoogle Scholar |
Eidenshink JC, Schwind B, Brewer K, Zhu Z-L, Quayle B, Howard S (2007) A project for monitoring trends in burn severity. Fire Ecology 3, 3–21.
| A project for monitoring trends in burn severity.Crossref | GoogleScholarGoogle Scholar |
Getis A, Ord JK (1992) The analysis of spatial association by use of distance statistics. Geographical Analysis 24, 189–206.
Getis A, Ord JK (1996) Local spatial statistics: an overview. In ‘Spatial Analysis: Modeling in a GIS Environment’. (Eds P Longley, M Batty) pp. 261–278. (Wiley: New York)
Hartigan JA, Wong MA (1979) A C-means clustering algorithm. Applied Statistics 28, 100–108.
| A C-means clustering algorithm.Crossref | GoogleScholarGoogle Scholar |
Jain TB, Pilliod D, Graham RC (2004) Tongue-tied. Wildfire 4, 22–26.
Jelinski DE, Wu J (1996) The Modifiable Areal Unit Problem and implications for landscape ecology. Landscape Ecology 11, 129–140.
| The Modifiable Areal Unit Problem and implications for landscape ecology.Crossref | GoogleScholarGoogle Scholar |
Key CH, Benson NC (2006) Landscape Assessment (LA). In ‘FIREMON: Fire Effects Monitoring and Inventory System’. (Eds DC Lutes, RE Keane, JF Caratti, CH Key, NC Benson, S Sutherland, LJ Gangli) USDA Forest Service, Rocky Mountain Research Station, General Technical Report RMRS-GTR-164-CD. (Fort Collins, CO)
Kokaly RF, Rockwell BW, Haire SL, King TV (2007) Characterization of post-fire surface cover, soils and burn severity at the Cerro Grande fire, New Mexico, using hyperspectral and multispectral remote sensing. Remote Sensing of Environment 106, 305–325.
| Characterization of post-fire surface cover, soils and burn severity at the Cerro Grande fire, New Mexico, using hyperspectral and multispectral remote sensing.Crossref | GoogleScholarGoogle Scholar |
Lentile LB, Holden ZA, Smith AM, Falkowski MJ, Hudak AT, Morgan P, Lewis S, Gessler PE, Benson NC (2006) Remote sensing techniques to assess active fire characteristics and post-fire effects. International Journal of Wildland Fire 15, 319–345.
| Remote sensing techniques to assess active fire characteristics and post-fire effects.Crossref | GoogleScholarGoogle Scholar |
Lentile LB, Morgan P, Hardy C, Hudak A, Means R, Ottmar R, Robichaud P, Sutherland E, Way F, Lewis S (2007) Lessons learned from rapid response research on wildland fires. Fire Management Today Winter 2007, 24–31.
Lewin-Koh N, Bivand R (2008) ‘maptools: Tools for Reading and Handling Spatial Objects. R Package Version 0.7–7.’ (R Foundation for Statistical Computing: Vienna, Austria)
Odeh IOA, McBratney AB, Chittleborough DJ (1992) Soil pattern recognition with fuzzy C-means clustering algorithms. Soil Science Society of America Journal 56, 505–516.
| Soil pattern recognition with fuzzy C-means clustering algorithms.Crossref | GoogleScholarGoogle Scholar |
Openshaw
Pal N, Bezdek JC, Hathaway RJ (1996) Sequential competitive learning and the fuzzy C-means clustering algorithms. Neural Networks 9, 787–796.
| Sequential competitive learning and the fuzzy C-means clustering algorithms.Crossref | GoogleScholarGoogle Scholar | 12662563PubMed |
R Development Core Team (2008) ‘R: A language and environment for statistical computing.’ (R Foundation for Statistical Computing: Vienna, Austria) Available at http://www.R-project.org [Verified 30 August 2010]
Roubens M (1982) Fuzzy clustering algorithms and their cluster validity. European Journal of Operational Research 10, 294–301.
| Fuzzy clustering algorithms and their cluster validity.Crossref | GoogleScholarGoogle Scholar |
Scrucca L (2005) Clustering multivariate spatial data based on local measures of spatial autocorrelation. Quaderni del Dipartimento di Economia, Finanza e Statistica 20, 1–11. Available at http://www.ec.unipg.it/DEFS/uploads/spatcluster.pdf [Verified 30 August 2010]
van Wagtendonk JW, Root RR, Key CH (2004) Comparison of AVIRIS and Landsat ETM+ detection capabilities for burn severity. Remote Sensing of Environment 92, 397–408.
| Comparison of AVIRIS and Landsat ETM+ detection capabilities for burn severity.Crossref | GoogleScholarGoogle Scholar |
Visser H, de Nijs T (2006) The Map Comparison Kit. Environmental Modelling & Software 21, 346–358.
| The Map Comparison Kit.Crossref | GoogleScholarGoogle Scholar |
Wulder M, Boots B (1998) Local spatial autocorrelation characteristics of remotely sensed imagery assessed with the Getis Statistic. International Journal of Remote Sensing 19, 2223–2231.
| Local spatial autocorrelation characteristics of remotely sensed imagery assessed with the Getis Statistic.Crossref | GoogleScholarGoogle Scholar |
