Analysis of classification accuracy for pre-filtered multichannel remote sensing data

Noise is one of the main factors degrading the quality of original multichannel remote sensing data and its presence influences classification efficiency, object detection, etc. Thus, pre-filtering is often used to remove noise and improve the solving of final tasks of multichannel remote sensing. Recent studies indicate that a classical model of additive noise is not adequate enough for images formed by modern multichannel sensors operating in visible and infrared bands. However, this fact is often ignored by researchers designing noise removal methods and algorithms. Because of this, we focus on the classification of multichannel remote sensing images in the case of signal-dependent noise present in component images. Three approaches to filtering of multichannel images for the considered noise model are analysed, all based on discrete cosine transform in blocks. The study is carried out not only in terms of conventional efficiency metrics used in filtering (MSE) but also in terms of multichannel data classification accuracy (probability of correct classification, confusion matrix). The proposed classification system combines the pre-processing stage where a DCT-based filter processes the blocks of the multichannel remote sensing image and the classification stage. Two modern classifiers are employed, radial basis function neural network and support vector machines. Simulations are carried out for three-channel image of Landsat TM sensor. Different cases of learning are considered: using noise-free samples of the test multichannel image, the noisy multichannel image and the pre-filtered one. It is shown that the use of the pre-filtered image for training produces better classification in comparison to the case of learning for the noisy image. It is demonstrated that the best results for both groups of quantitative criteria are provided if a proposed 3D discrete cosine transform filter equipped by variance stabilizing transform is applied. The classification results obtained for data pre-filtered in different ways are in agreement for both considered classifiers. Comparison of classifier performance is carried out as well. The radial basis neural network classifier is less sensitive to noise in original images, but after pre-filtering the performance of both classifiers is approximately the same.

Status, trends and drivers of kelp forests in Europe: an expert assessment

A comprehensive expert consultation was conducted in order to assess the status, trends and the most important drivers of change in the abundance and geographical distribution of kelp forests in European waters. This consultation included an on-line questionnaire, results from a workshop and data provided by a selected group of experts working on kelp forest mapping and eco-evolutionary research. Differences in status and trends according to geographical areas, species identity and small-scale variations within the same habitat where shown by assembling and mapping kelp distribution and trend data. Significant data gaps for some geographical regions, like the Mediterranean and the southern Iberian Peninsula, were also identified. The data used for this study confirmed a general trend with decreasing abundance of some native kelp species at their southern distributional range limits and increasing abundance in other parts of their distribution (Saccharina latissima and Saccorhiza polyschides). The expansion of the introduced species Undaria pinnatifida was also registered. Drivers of observed changes in kelp forests distribution and abundance were assessed using experts’ opinions. Multiple possible drivers were identified, including global warming, sea urchin grazing, harvesting, pollutionand fishing pressure, and their impact varied between geographical areas. Overall, the results highlight major threats for these ecosystems but also opportunities for conservation. Major requirements to ensure adequate protection of coastal kelp ecosystems along European coastlines are discussed, based on the local to regional gaps detected in the study.

Status, trends and drivers of kelp forests in Europe: an expert assessment

A comprehensive expert consultation was conducted in order to assess the status, trends and the most important drivers of change in the abundance and geographical distribution of kelp forests in European waters. This consultation included an on-line questionnaire, results from a workshop and data provided by a selected group of experts working on kelp forest mapping and eco-evolutionary research. Differences in status and trends according to geographical areas, species identity and small-scale variations within the same habitat where shown by assembling and mapping kelp distribution and trend data. Significant data gaps for some geographical regions, like the Mediterranean and the southern Iberian Peninsula, were also identified. The data used for this study confirmed a general trend with decreasing abundance of some native kelp species at their southern distributional range limits and increasing abundance in other parts of their distribution (Saccharina latissima and Saccorhiza polyschides). The expansion of the introduced species Undaria pinnatifida was also registered. Drivers of observed changes in kelp forests distribution and abundance were assessed using experts’ opinions. Multiple possible drivers were identified, including global warming, sea urchin grazing, harvesting, pollutionand fishing pressure, and their impact varied between geographical areas. Overall, the results highlight major threats for these ecosystems but also opportunities for conservation. Major requirements to ensure adequate protection of coastal kelp ecosystems along European coastlines are discussed, based on the local to regional gaps detected in the study.