Street-Frontage-Net: urban image classification using deep convolutional neural networks

ABSTRACT

Quantifying aspects of urban design on a massive scale is crucial to help develop a deeper understanding of urban designs elements that contribute to the success of a public space. In this study, we further develop the Street-Frontage-Net (SFN), a convolutional neural network (CNN) that can successfully evaluate the quality of street frontage as either being active (frontage containing windows and doors) or blank (frontage containing walls, fences and garages). Small-scale studies have indicated that the more active the frontage, the livelier and safer a street feels. However, collecting the city-level data necessary to evaluate street frontage quality is costly. The SFN model uses a deep CNN to classify the frontage of a street. This study expands on the previous research via five experiments. We find robust results in classifying frontage quality for an out-of-sample test set that achieves an accuracy of up to 92.0%. We also find active frontages in a neighbourhood has a significant link with increased house prices. Lastly, we find that active frontage is associated with more scenicness compared to blank frontage. While further research is needed, the results indicate the great potential for using deep learning methods in geographic information extraction and urban design.     

From solid to granular gases: the steady state for granular materials

This paper aims at extending the well‐known critical state concept, associated with quasi‐static conditions, by accounting for the role played by the strain rate when focusing on the steady, simple shear flow of a dry assembly of identical, inelastic, soft spheres. An additional state variable for the system, the granular temperature, is accounted for. The granular temperature is related to the particle velocity fluctuations and measures the agitation of the system. This state variable, as is in the context of kinetic theories of granular gases, is assumed to govern the response of the material at large strain rates and low concentrations. The stresses of the system are associated with enduring, frictional contacts among particles involved in force chains and nearly instantaneous collisions. When the first mechanism prevails, the material behaves like a solid, and constitutive models of soil mechanics hold, whereas when inelastic collisions dominate, the material flows like a granular gas, and kinetic theories apply. Considering a pressure‐imposed flow, at large values of the normal stress and small values of the shear rate, the theory predicts a nonmonotonic shear rate dependence of the stress ratio at the steady state, which is likely to govern the evolution of landslides. Copyright © 2013 John Wiley & Sons, Ltd.     

A visco‐elasto‐plastic model for granular materials under simple shear conditions

The numerical simulation of rapid landslides is quite complex mainly because constitutive models capable of simulating the mechanical behaviour of granular materials in the pre‐collapse and post‐collapse regimes are still missing. The goal of this paper is to introduce a constitutive model capable of capturing the response of dry granular flows from quasi‐static to dynamic conditions, in particular when the material experiences a sort of solid‐to‐fluid phase transition. An ideal assembly of identical spheres under simple shear conditions is considered. In the constitutive model, void ratio and granular temperature have been chosen as state variables, and both shear and normal stresses are computed as the sum of two contributions: the quasi‐static one and the collisional one. The former is determined by using a perfect elasto‐plastic model including the critical state concept, while the latter is derived from the kinetic theory of granular gases. The evolution of the granular temperature, fundamentally governing the material phase transition, is obtained by imposing the kinetic fluctuating energy balance. The constitutive relationship has been integrated, under both constant pressure and constant volume conditions, and the influence of shear strain rate, initial void ratio and normal pressure on the mechanical response has been investigated. Copyright © 2015 John Wiley & Sons, Ltd.     

Evidence of a shallow magma intrusion beneath the NE Rift system of Mt. Etna during 2013

Continuous GPS (CGPS) data, collected at Mt. Etna between April 2012 and October 2013, clearly define inflation/deflation processes typically observed before/after an eruption onset. During the inflationary process from May to October 2013, a particular deformation pattern localised in the upper North Eastern sector of the volcano suggests that a magma intrusion had occurred a few km away from the axis of the summit craters, beneath the NE Rift system. This is the first time that this pattern has been recorded by CGPS data at Mt. Etna. We believe that this inflation process might have taken place periodically at Mt. Etna and might be associated with the intrusion of batches of magma that are separate from the main feeding system. We provide a model to explain this unusual behaviour and the eruptive regime of this rift zone, which is characterised by long periods of quiescence followed by often dangerous eruptions in which vents can open at low elevation and thus threaten the villages in this sector of the volcano.     

Multivariate return period for different types of flooding in city of Monza,Italy

Natural Hazards - The return period is a probabilistic criterion used to measure and communicate the random occurrence of geophysical events such as floods in risk assessment studies. Since an...     

A Carnian 40Ar/39Ar age for the Paasselkä impact structure (SE Finland)—An update

A recrystallized band of pale feldspathic impact melt in a gneissic impact breccia from the approximately 10 km Paasselkä impact structure in southeast Finland was dated via ⁴⁰Ar/³⁹Ar step‐heating. The newly obtained plateau age of 228.7 ± 1.8 (2.2) Ma (2σ) (MSWD = 0.32; p = 0.93) is equal to the previously published pseudoplateau age of 228.7 ± 3.0 (3.4) (2σ) for the impact event. According to the current international chronostratigraphic chart and using the most recent published suggestions for the K decay constants, a Carnian (Late Triassic) age for the Paasselkä impact structure of 231.0 ± 1.8 (2.2) Ma (2σ) is calculated and considered the most precise and accurate age for this impact structure. The new plateau age for Paasselkä confirms the previous dating result but is, based on its internal statistics, much more compelling.     

Toward reduction of artifacts in fused images

Most fusion satellite image methodologies at pixel-level introduce false spatial details, i.e. artifacts, in the resulting fused images. In many cases, these artifacts appears because image fusion methods do not consider the differences in roughness or textural characteristics between different land covers. They only consider the digital values associated with single pixels. This effect increases as the spatial resolution image increases. To minimize this problem, we propose a new paradigm based on local measurements of the fractal dimension (FD). Fractal dimension maps (FDMs) are generated for each of the source images (panchromatic and each band of the multi-spectral images) with the box-counting algorithm and by applying a windowing process. The average of source image FDMs, previously indexed between 0 and 1, has been used for discrimination of different land covers present in satellite images. This paradigm has been applied through the fusion methodology based on the discrete wavelet transform (DWT), using the à trous algorithm (WAT). Two different scenes registered by optical sensors on board FORMOSAT-2 and IKONOS satellites were used to study the behaviour of the proposed methodology. The implementation of this approach, using the WAT method, allows adapting the fusion process to the roughness and shape of the regions present in the image to be fused. This improves the quality of the fused images and their classification results when compared with the original WAT method.