Richard J. Murphy

Learn More
Short rotation coppice (SRC) willow is currently emerging as an important dedicated lignocellulosic energy crop in the UK. However, investigation into the variation between species and genotypes in their suitability for liquid transport biofuel processing has been limited. To address this, four traits relevant to biofuel processing (composition, enzymatic(More)
—A new method is presented which combines a deterministic analytical method and a probabilistic measure to classify rock types on the basis of their hyperspectral curve shape. This method is a supervised learning algorithm using Gaussian Processes (GPs) and the Observation Angle Dependent (OAD) covariance function. The OAD covariance function makes use of(More)
Intertidal ecosystems have primarily been studied using field-based sampling; remote sensing offers the ability to collect data over large areas in a snapshot of time that could complement field-based sampling methods by extrapolating them into the wider spatial and temporal context. Conventional remote sensing tools (such as satellite and aircraft imaging)(More)
BACKGROUND Short rotation coppice willow is a potential lignocellulosic feedstock in the United Kingdom and elsewhere; however, research on optimising willow specifically for bioethanol production has started developing only recently. We have used the feedstock Salix viminalis × Salix schwerinii cultivar 'Olof' in a three-month pot experiment with the aim(More)
UNLABELLED BACKGROUND The recalcitrance of lignocellulosic cell wall biomass to deconstruction varies greatly in angiosperms, yet the source of this variation remains unclear. Here, in eight genotypes of short rotation coppice willow (Salix sp.) variability of the reaction wood (RW) response and the impact of this variation on cell wall recalcitrance to(More)
—Hyperspectral data acquired from field-based platforms present new challenges for their analysis, particularly for complex vertical surfaces exposed to large changes in the geometry and intensity of illumination. The use of hyperspectral data to map rock types on a vertical mine face is demonstrated, with a view to providing real-time information for(More)
This paper investigates the performance of machine learning methods for classifying rock types from hyperspectral data. The main objective is to test the impact on classification error rate of calibrating the model's output into class probability estimates. The base classifiers included in this study are: boosted decision trees, support vector machines and(More)
BACKGROUND The European Union has made it a strategic objective to develop its biofuels market in order to minimize greenhouse gas (GHG) emissions, to help mitigate climate change and to address energy insecurity within the transport sector. Despite targets set at national and supranational levels, lignocellulosic bioethanol production has yet to be widely(More)
The use of hyperspectral data is limited, in part, by increased spectral noise, particularly at the extremes of the wavelength ranges sensed by scanners. We apply Gaussian Processes (GPs) as a preprocessing step prior to extracting mineralogical information from the image using automated feature extraction. GPs are a probabilistic machine learning technique(More)