Over the past decade there have been considerable increases in both the quantity of remotely sensed data available and the use of neural networks. These increases have largely taken place in ...parallel, and it is only recently that several researchers have begun to apply neural networks to remotely sensed data. This paper introduces this special issue which is concerned specifically with the use of neural networks in remote sensing. The feed-forward back-propagation multi-layer perceptron (MLP) is the type of neural network most commonly encountered in remote sensing and is used in many of the papers in this special issue. The basic structure of the MLP algorithm is described in some detail while some other types of neural network are mentioned. The most common applications of neural networks in remote sensing are considered, particularly those concerned with the classification of land and clouds, and recent developments in these areas are described. Finally, the application of neural networks to multi-source data and fuzzy classification are considered.
A new framework is presented for an automated approach to identify possible internal wave packets in synthetic aperture radar (SAR) images as a means to infer primary information about the internal ...waves. An operational version of this framework is expected to be useful to both oceanographers and modellers for analysing the importance of internal waves for the mixing required to warm and advect deep-sea water to the surface. The framework is based on a combination of techniques using wavelets, edge discrimination, edge linking and edge parallelism analysis. Six satellite images of the Eastern Atlantic have been used to demonstrate and test the framework. The determination of the type of signature and the wavelength of the internal wave has been demonstrated and the accuracy of the approach is assessed.
Harnessing High-Altitude Solar Power Aglietti, G.S.; Redi, S.; Tatnall, A.R. ...
IEEE transactions on energy conversion,
06/2009, Letnik:
24, Številka:
2
Journal Article
Recenzirano
Odprti dostop
As an intermediate solution between Glaser's satellite solar power (SSP) and ground-based photovoltaic (PV) panels, this paper examines the collection of solar energy using a high-altitude aerostatic ...platform. A procedure to calculate the irradiance in the medium/high troposphere, based on experimental data, is described. The results show that here a PV system could collect about four to six times the energy collected by a typical U.K.-based ground installation, and between one-third and half of the total energy the same system would collect if supported by a geostationary satellite (SSP). The concept of the aerostat for solar power generation is then briefly described together with the equations that link its main engineering parameters/variables. A preliminary sizing of a facility stationed at 6 km altitude and its costing, based on realistic values of the input engineering parameters, is then presented.
► A test rig was developed to measure microyield in materials subject to random vibration. ► Tests were performed on two materials, one metallic and one non-metallic. ► The metallic sample showed ...significant residual strain in the presence of a small non-symmetry in loading. ► The residual strain was predicted with reasonable accuracy using an FEA model solved in the time domain using nonlinear kinematic hardening.
High precision stable structures are potentially vulnerable to dimensional instability induced by exposure to random vibration. There appears to have been little work in the literature to understand or mitigate structural dimensional instability induced by random vibration. To gain more insight into this issue, a novel test was recently developed to assess the plastic strain response in the 10−5 to 10−6 range for structural materials subjected to specific random vibration loads. The test was based on a four-point bending configuration with an applied random base excitation. Two types of material were tested – an Al alloy and a CFRP. This paper presents the test setup and results in detail. The Al alloy samples were found to grow slightly in length during testing, due to a small non-symmetry in the applied load. An FEA model of the test setup was solved in the time domain for a sequence of cyclic loads whose amplitude was based on their probability of exceedance in the random environment. This model, using nonlinear kinematic hardening, was able to predict the residual strain response observed during testing with good accuracy. The main implication of this finding is that ultra stable structures subject to random vibration should be assembled in the most strain-free state possible to avoid loss of dimensional stability due to cyclic hardening.
A bio-optical model coupled with the radiative transfer model Hydrolight was used to create 18,000 synthetic ocean colour spectra corresponding to open ocean and coastal waters. The bio-optical model ...took into account the optical properties of the three oceanic constituents, chlorophyll-a, suspended non-chlorophyllous particles and coloured dissolved organic matter (CDOM) as well as of normal seawater. The resulting spectra were input into multilayer perceptron neural network algorithms with the aim of computing the original concentrations of chlorophyll-a, non-chlorophyllous particles and CDOM initially input into the bio-optical model. The process of training the neural networks is essential for the accuracy of the inversion the neural net performs on the coupled bio-optical and radiative transfer models. The objective of this paper is to investigate the performance difference of a neural network trained with untransformed as opposed to logarithmically transformed data.
High resolution satellite imaging is considered as the outstanding applicant to extract the Earth’s surface information. Extraction of a feature of an image is very difficult due to having to find ...the appropriate image segmentation techniques and combine different methods to detect the Region of Interest (ROI) most effectively. This paper proposes techniques to classify objects in the satellite image by using image processing methods on high-resolution satellite images. The systems to identify the ROI focus on forests, urban and agriculture areas. The proposed system is based on histograms of the image to classify objects using thresholding. The thresholding is performed by considering the behaviour of the histogram mapping to a particular region in the satellite image. The proposed model is based on histogram segmentation and morphology techniques. There are five main steps supporting each other; Histogram classification, Histogram segmentation, Morphological dilation, Morphological fill image area and holes and ROI management. The methods to detect the ROI of the satellite images based on histogram classification have been studied, implemented and tested. The algorithm is be able to detect the area of forests, urban and agriculture separately. The image segmentation methods can detect the ROI and reduce the size of the original image by discarding the unnecessary parts.
The radiative transfer model Hydrolight was used to produce 18 000 artificial reflectance spectra representing case 1 and case 2 water conditions. Remote sensing reflectances were generated at the ...MERIS wavebands 412, 442, 490, 510, 560, 620, 665 and 682 nm from randomly generated triplet combinations of chlorophyll a, non-chlorophyllous particles and coloured dissolved organic matter concentrations. These spectra were used to train multilayer perceptron neural network algorithms to perform the inversion from input reflectances to these three optically active substances. A method is proposed that establishes the neural network output error sensitivity towards changes in the individual input reflectance channels. From the output error produced for each reflectance change, a hypothesis about the importance of each band can be made. Results suggest a strong weight associated to the 620 nm band for the estimation of all three substances.
Artificial radiance sets were used as inputs to Multi-layer Perceptron and multilinear regression algorithms to study their retrieval capabilities for optically active constituents in sea water. The ...radiative transfer model Hydrolight was used to produce 18,000 artificial reflectance spectra representing various case 1 and case 2 water conditions. The remote sensing reflectances were generated at the Medium Resolution Imaging Spectrometer (MERIS) wavebands 412, 442, 490, 510, 560, 620, 665 and 682 nm from randomly generated triplet combinations of chlorophyll a, non-chlorophyllous particles and CDOM (Coloured Dissolved Organic Matter) concentrations. These reflectances were contaminated with different noise terms, before they were used to assess the performance of multilayer perceptron and multilinear regression algorithms. The potential of both algorithms for retrieving optically active constituents was demonstrated with the neural network showing more accurate results for case 2 scenarios.