Estimating defoliation in boreal coniferous forests by combining Landsat TM, aerial photographs and field data

Abstract

Multitemporal Landsat TM images, panchromatic high altitude aerial photographs and field sample plots of the Finnish national forest inventory (NFI) were used for estimating defoliation in boreal coniferous forests. Satellite images were used for spectral information, aerial photographs for textural features and the NFI sample plots were utilized as reference data of defoliation. A distance weighted k-nearest neighbor classification was applied in the estimation. The defoliation was estimated as a function of distance between the spectral and textural responses of pixels in the inventory area and pixels corresponding to the reference data. Two different spatial scales, plot and stand levels, were examined. The plot level examination was implemented both as single date estimation and estimation of defoliation change. In the plot level, the producer’s accuracy of the three change classes was 26 and 56% overall (Kappa 0.12) for plot and stand levels. When the estimation was done with the changed sample plots only, the accuracy was 61% (Kappa 0.34). The results of the corresponding plot level single date estimation were slightly poorer. The stand level examination was done only with single date estimation. Using the NFI sample plots as reference data, defoliation was estimated for each test stand and compared to the field assessment. When three defoliation classes (none, slight and severe) were applied, the overall accuracy for the test stands was 42% (Kappa 0.11) and with two classes (no defoliation and defoliation) the accuracy was 58% (Kappa 0.15). The most useful variables for estimating defoliation were TM channels 4 and 5.