The ability to identify similar sandstones to a given sample is important where the provenance of the sample is unknown or the quarry of origin is no longer in operation. In the case of building stones from heritage buildings in protected areas, it may be mandatory. Here, a proof of concept for an automated similarity measure is presented by means of a convolutional autoencoder that is able to extract features from a sample thin section and use these features to identify the most similar sample in an existing image library. The approach considers only the shape of the pore space between grains, as, if the pore space alone contains enough information to distinguish between samples, the required image pre-processing and training of a model is greatly simplified. The trained model is able to predict correctly the progenitor quarry of a thin section, from an eight-class dataset of Scottish sandstones, with an accuracy of 47.9%. This prototype, although insufficient for commercial purposes, forms a benchmark for future models against which improvements can be assessed and some of which are suggested.Thematic collection: This article is part of the Digitization and Digitalization in engineering geology and hydrogeology collection available at: https://www.lyellcollection.org/cc/digitization-and-digitalization-in-engineering-geology-and-hydrogeology

pity that the high standard of management and execution of structural work on the site that is evident elsewhere has not been achieved in Britain. 44.Much of what has been said above obviously relates to steelwork as a structural medium, commonly so in large-scale plants, but it applies equally to concrete structures, which in many applications are eminently satisfactory. In all cases the aesthetics of the structural outline are already becoming a constant demand on the engineer. Yet only a limited number of structural engineers have a flair for good proportions, and it might reasonably be that this should be part of a structural engineer's training, for it cannot always with advantage be separately handled by the architect.The Paper, which was received on 18 January, 1961, is accompanied by nine photographs, from some of which the half-tone page plates have been prepared. DiscussionMr R. M. Wynne-Edwards (Managing Director, Constructors, John Brown Ltd), agreeing that the architect-engineer was a splendid ideal but no longer practicable, said that those who aspired to climb high in their professions ought to keep their minds broad enough and their visions wide enough to comprehend what the other skills were trying to do and to make use of them all. It was true, for example, that the building of a nuclear power station was an extremely complex matter. The same was obviously true of more mundane buildings such as hospitals which were 50% mechanical engineering.46. Much more use could be made of models. For example, a three-dimensional model could show every floor of a hospital and how the services fitted in. Such models were not clad but showed the interiors of the buildings and on a model it should be possible to pull out any floor and re-arrange it. The Building Research Station WaS developing techniques in the use of models, and much planning could be done more quickly from such models than from drawings. 47. Thought should continuously be given to the subject of what required homing.h4r Atkins had mentioned the Fine Art Commission. There was no reason why the Fine Art Commission should not be broad-minded enough to see a structure as it Saw a bridge-in its simple functional form. It should be unnecessary to put it in a box. Refineries, for example, were spread over large areas of ground largely because of the danger of fire but also because the industries concerned were always adding to them.But reheries were almost entirely unclad. Architects) observed that whereas Mr Lobb's Paper covered the wide or human aspect of the subject, Mr Atkin's Paper had been far more down-to-earth and practical in detail. These two aspects showed the significant difference between the architect's and the engineer's approaches. Obviously, those aspects were not in conflict but were complementary. Nowadays there was rightly much talk about collaboration, but these could be no return to that wonderful person who used to combine the functions of architect and engineer. The comple-ities were far too great for that, and the main aim m...