Anssi Pekkarinen

Estimation of timber volume at the sample plot level by means of image segmentation and Landsat TM imagery

The use of image segments in the feature extraction for the estimation of timber volumes using a Landsat TM image was investigated by applying the k nearest neighbour estimation method (knn) and Finnish National Forest Inventory (NFI) sample plots. The estimates of the volumes by tree species at the plot level were derived by means of the cross-validation technique. Ten nearest neighbours (NNs) were applied in the estimation. Image segments were derived by two different methods: (1) a measurement space-guided clustering followed by the connected component labeling (ISOCCL) and (2) a directed trees algorithm (NG). The segmentations were fine-tuned by means of two different region-merging algorithms. The spectral features were extracted in two ways: from a fixed window (FW) around the field sample plot, and from those pixels within the FW that belonged to the same segment as the sample plot pixel. Window sizes from 1 to 11×11 pixels were tested, and the average of the extracted pixel values was used in the estimation. Features from the ISOCCL-based segments gave the best estimates for the volumes of pine and spruce, as well as for the total volume. Best estimates for the volume of broad-leaved trees were obtained from NG-based segments. Compared to the estimates of the FW approach, the improvements were, however, quite small and relative root mean square errors (RMSEs) remained high. The minimum and maximum improvements of relative RMSEs were 1% and 11.3%, respectively. The NG was considered a more applicable segmentation method for forest inventory purposes at the stand level, even though the ISOCCL gave slightly better estimation results in this study. The use of image segmentation in the stratification of the image material into stand margin and within stand areas could be more suitable for the estimation of forest variables. This is the case especially if only the plot-level field information is available.

Airborne laser scanning and digital stereo imagery measures of forest structure: comparative results and implications to forest mapping and inventory update

Airborne laser scanning (ALS) has demonstrated utility for forestry applications and has renewed interest in other forms of remotely sensed data, especially those that capture three-dimensional (3-D) forest characteristics. One such data source results from the advanced processing of high spatial resolution digital stereo imagery (DSI) to generate 3-D point clouds. From the derived point cloud, a digital surface model and forest vertical information with similarities to ALS can be generated. A key consideration is that when developing forestry related products such as a canopy height model (CHM), a high spatial resolution digital terrain model (DTM), typically from ALS, is required to normalize DSI elevations to heights above ground. In this paper we report on our investigations into the use of DSI-derived vertical information for capturing variations in forest structure and compare these results to those acquired using ALS. An ALS-derived DTM was used to provide the spatially detailed ground surface elevations to normalize DSI-derived heights. Similar metrics were calculated from the vertical information provided by both DSI and ALS. Comparisons revealed that ALS metrics provided a more detailed characterization of the canopy surface including canopy openings. Both DSI and ALS metrics had similar levels of correlation with forest structural attributes (e.g., height, volume, and biomass). DSI-based models predicted height, diameter, basal area, stem volume, and biomass with root mean square (RMS) accuracies of 11.2%, 21.7%, 23.6%, 24.5%, and 23.7%, respectively. The respective accuracies for the ALS-based predictions were 7.8%, 19.1%, 17.8%, 17.9%, and 17.5%. Change detection between ALS-derived CHM (time 1) and DSI-derived CHM (time 2) provided change estimates that demonstrated good agreement (r = 0.71) with two-date, ALS only, change outputs. For the single-layered, even-aged stands under investigation in this study, the DSI-derived vertical information is an appropriate and cost-effective data source for estimating and updating forest information. The accuracy of DSI information is based on a capability to measure the height of the upper canopy envelope with performance analogous to ALS. Forest attributes that are well captured and subsequently modeled from height metrics are best suited to estimation from DSI metrics, whereas ALS is more suitable for capturing stand density. Further investigation is required to better understand the performance of DSI-derived height products in more complex forest environments. Furthermore, the difference in variance captured between ALS and DSI-derived CHM also needs to be better understood in the context of change detection and inventory update considerations.

Image segment-based spectral features in the estimation of timber volume

Plot- and stand-level errors associated with satellite image-based multisource forest inventory (MSFI) applications have been relatively high. The reasons suggested for that are related to the limited spatial resolution of the image material. The introduction of very high spatial resolution (VHR) images to MSFI applications should, therefore, diminish these errors. The use of VHR images is, however, problematic, because pixel-by-pixel analysis methods are no longer applicable. The paper presents an image segment-based approach to the determination of feature extraction and image analysis units. The study was carried out in Southern Finland and employed a spectrally averaged imaging spectrometer (AISA) image and field data gathered from sample plots. A two-phase segmentation method was applied and a large number of segment-based spectral features was extracted and used as input to a feature selection procedure. Forward selection based on an improvement of RMSE was applied. The performance of segment-based features (SF) was compared to that of reference features (RF) extracted from square-shaped windows. The estimation results revealed that even though the applied segmentation method succeeded well in the determination of units of feature extraction and image analysis, the differences between the performance of SF and RF were small and the plot-level estimation errors remained high. The study suggests that large estimation errors are due to the local nature of the field data and may be diminished using data that is representative at the segment level.

Clear-cut Detection in Boreal Forest Aided by Remote Sensing

The study compares the applicability of different remote sensing data and digital change detection methods in detecting clear-cut areas in boreal forest. The methods selected for comparisons are simple and straightforward and thus applicable in practical forestry. The data tested were from Landsat satellite imagery and high-altitude panchromatic aerial orthophotographs. The change detection was based on image differencing. Three different approaches were tested: (1) pixel-by-pixel differencing and segmentation; (2) pixel block-level differencing and thresholding; and (3) presegmentation and unsupervised classification. The study shows that the methods and data sources used are accurate enough for operational detection of clear-cut areas. The study suggests that predelineated segments or pixel blocks should be used for image differencing to decrease the number of misinterpreted small areas. For the same reason the use of a digital forest mask is crucial in operational applications.

Segment-level stand inventory for forest management

The aim of this study was to develop a method for segment-based forest inventory and determine whether segment-level inventories can be used in forest management planning. The study area covered 76 ha located in two different aerial photographs in eastern Finland. The study area was segmented into 220 segments with the aid of aerial photographs and the segment-level forest characteristics were assessed in the field using relascope sample plots and a field computer which displayed the aerial photographs, segment borders and surveyors location on the screen. The segment estimates were calculated as weighted averages of k nearest neighbours (kNN) for the segments and the sample plots. The estimates were tested with a cross-validation technique. The averages and the standard deviations of the spectral values of aerial images extracted for the segments and the sample plots were used in the kNN estimation. The relative root mean square error of the mean volume was 58.1% (bias –6.4%) at the segment level and 57.9% (bias –0.9%) at the sample plot level. The segment-based approach studied here needs further research and improvement before it can be applied to forest management planning.

Modelling and mapping the suitability of European forest formations at 1-km resolution

Proactive forest conservation planning requires spatially accurate information about the potential distribution of tree species. The most cost-efficient way to obtain this information is habitat suitability modelling i.e. predicting the potential distribution of biota as a function of environmental factors. Here, we used the bootstrap-aggregating machine-learning ensemble classifier Random Forest (RF) to derive a 1-km resolution European forest formation suitability map. The statistical model use as inputs more than 6,000 field data forest inventory plots and a large set of environmental variables. The field data plots were classified into different forest formations using the forest category classification scheme of the European Environmental Agency. The ten most dominant forest categories excluding plantations were chosen for the analysis. Model results have an overall accuracy of 76%. Between categories scores were unbalanced and Mesophitic deciduous forests were found to be the least correctly classified forest category. The model’s variable ranking scores are used to discuss relationship between forest category/environmental factors and to gain insight into the model’s limits and strengths for map applicability. The European forest suitability map is now available for further applications in forest conservation and climate change issues.