Combining Remotely Sensed Optical and Radar Data in kNN-Estimation of Forest Variables
Authors: Holmström H.1; Fransson J.E.S.2
Source: Forest Science, Volume 49, Number 3, June 2003 , pp. 409-418(10)
Abstract:
The use of optical and radar data for estimation of forest variables has been investigated and evaluated by employing the k nearest neighbor (kNN) method. The investigation was performed at a test site located in the south of Sweden consisting mainly of Norway spruce and Scots pine forests with standwise stem volume in the range of 0–430 m3 ha-1. The kNN method imputes weighted reference plot variables to areas to be estimated (target areas), facilitating further use of data in forestry planning models. Remotely sensed multispectral optical data from the SPOT-4 XS satellite and radar data from the airborne CARABAS-II VHF SAR sensor were used, separately and combined, to define weights in the kNN algorithm. The weights were inversely proportional to the image feature distance between the reference plot and the target area. The distance metric was defined using regression models based on the image data sources. Positive impact on the accuracies of stem volume and age estimates was found by combining the two image data sources. Stem volume, at stand level, was estimated with a RMSE of 37 m3 ha-1 (22% of the true mean value) using the combination of optical and radar data, compared to 50 m3 ha-1 (30%) for the best single-sensor case in this study. In conclusion, the results indicate that the accuracy of forest variable estimations was substantially improved by using multisensor data. FOR. SCI. 49(3):409–418.Keywords: Data assessment; forest inventory; imputation; remote sensing; environmental management; forest; forest management; forest resources; forestry; forestry research; forestry science; natural resources; natural resource management
Document Type: Miscellaneous
Affiliations: 1: Ph.D. Department of Forest Resource Management and Geomatics, Section of Forest Resource Analysis, Swedish University of Agricultural Sciences, Umeå, Sweden, SE-901 83, Phone: +46-90-786 59 14; Fax: +46-90-77 81 16 Hampus.Holmstrom@resgeom.slu.se 2: Associate Professor Department of Forest Resource Management and Geomatics, Remote Sensing Laboratory, Swedish University of Agricultural Sciences, Umeå, Sweden, SE-901 83, Phone: +46-90-786 65 54 Johan.Fransson@resgeom.slu.se
