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.

What are the local impacts of energy systems on marine ecosystem services: a systematic map protocol

Background: Increasing concentrations of atmospheric greenhouse gases (GHG) and its impact on the climate has resulted in many international governments committing to reduce their GHG emissions. The UK, for example, has committed to reducing its carbon emissions by 80% by 2050. Suggested ways of reaching such a target are to increase dependency on offshore wind, offshore gas and nuclear. It is not clear, however, how the construction, operation and decommissioning of these energy systems will impact marine ecosystem services, i.e. the services obtained by people from the natural environment such as food provisioning, climate regulation and cultural inspiration. Research on ecosystem service impacts associated with offshore energy technologies is still in its infancy. The objective of this review is to bolster the evidence base by firstly, recording and describing the impacts of energy technologies at the marine ecosystems and human level in a consistent and transparent way; secondly, to translate these ecosystem and human impacts into ecosystem service impacts by using a framework to ensure consistency and comparability. The output of this process will be an objective synthesis of ecosystem service impacts comprehensive enough to cover different types of energy under the same analysis and to assist in informing how the provision of ecosystem services will change under different energy provisioning scenarios. Methods: Relevant studies will be sourced using publication databases and selected using a set of selection criteria including the identification of: (i) relevant subject populations such as marine and coastal species, marine habitat types and the general public; (ii) relevant exposure types including offshore wind farms, offshore oil and gas platforms and offshore structures connected with nuclear; (iii) relevant outcomes including changes in species structure and diversity; changes in benthic, demersal and pelagic habitats; and changes in cultural services. The impacts will be synthesised and described using a systematic map. To translate these findings into ecosystem service impacts, the Common International Classification of Ecosystem Services (CICES) and Millennium Ecosystem Assessment (MEA) frameworks are used and a detailed description of the steps taken provided to ensure transparency and replicability.