Search

Signals used for Earth observation, when travelling through the atmosphere, are sensitive to refractivity; especially high spatio-temporal variations of water vapor are difficult to model and correct. Remaining unmodeled tropospheric delays deteriorate the positioning solution and therefore limit the accuracy of sensing and navigation applications. These delays are usually computed with empirical models based on ground meteorological parameters (pressure, temperature and water vapor partial pressure). However, existing models are not accurate enough for high-precision applications such as GNSS, where in consequence the so-called zenith total delay (ZTD) has to be estimated together with other unknown parameters (coordinates etc.). For decades, the Institute of Geodesy and Photogrammetry at ETH Zurich has been studying collocation methods for the modeling of tropospheric delays using meteorological parameters, successfully interpolating pointwise or integral atmospheric observations. Meanwhile, machine learning has become a widely used and valuable alternative, when big datasets are available for the training process. Indeed, we have already successfully predicted ZTDs based on meteorological parameters with an accuracy of 1–2 cm for locations (GNSS stations) already used in the training phase. However, difficulties arise to predict delays at new locations. In this work, we take a step forward in investigating the combination of machine learning algorithms and physical models used in a collocation approach to derive atmospheric delay fields at a very high resolution. Thus, without processing any GNSS data we can predict tropospheric delay fields everywhere in the area of investigation. In this paper, we firstly describe the designed architecture of the neural network, secondly, the combination of least-squares collocation and artificial neural networks for high-resolution prediction of tropospheric delays. We benefit from the complementary characteristics of these algorithms. While machine learning is capable of successfully predicting the variation of time series for given points, empirical models based on collocation are well suited for describing spatial variations within the area of investigation. Finally, we report the achieved performance for the entire territory of Switzerland (1–2 cm in terms of RMS), showing that the synergic combination of these algorithms can overcome the individual drawbacks of each method and provide more accurate delay estimates than either method individually. Datasets of 11 years, covering the territory of Switzerland, consisting of GNSS ZTDs from 72 permanent AGNES/COGEAR (swisstopo, ETHZ) stations and meteorological data from MeteoSwiss were used for this research. • Machine learning to predict time series of GNSS tropospheric delays. • The prediction of tropospheric delays at new locations is difficult. • Least-squares collocation can successfully interpolate in space tropospheric delays. • Combination of machine learning and collocation (physical models) methods. • High-resolutions spatio-temporal tropospheric fields. [ABSTRACT FROM AUTHOR]

Machine learning (ML) models, especially deep neural networks, are increasingly being used for the analysis of medical images and as a supporting tool for clinical decision-making. In this study, we propose an artificial intelligence system to facilitate dental decision-making for the removal of mandibular third molars (M3M) based on 2-dimensional orthopantograms and the risk assessment of such a procedure. A total of 4,516 panoramic radiographic images collected at the Center of Dental Medicine at the University of Zurich, Switzerland, were used for training the ML model. After image preparation and preprocessing, a spatially dependent U-Net was employed to detect and retrieve the region of the M3M and inferior alveolar nerve (IAN). Image patches identified to contain a M3M were automatically processed by a deep neural network for the classification of M3M superimposition over the IAN (task 1) and M3M root development (task 2). A control evaluation set of 120 images, collected from a different data source than the training data and labeled by 5 dental practitioners, was leveraged to reliably evaluate model performance. By 10-fold cross-validation, we achieved accuracy values of 0.94 and 0.93 for the M3M–IAN superimposition task and the M3M root development task, respectively, and accuracies of 0.9 and 0.87 when evaluated on the control data set, using a ResNet-101 trained in a semisupervised fashion. Matthew's correlation coefficient values of 0.82 and 0.75 for task 1 and task 2, evaluated on the control data set, indicate robust generalization of our model. Depending on the different label combinations of task 1 and task 2, we propose a diagnostic table that suggests whether additional imaging via 3-dimensional cone beam tomography is advisable. Ultimately, computer-aided decision-making tools benefit clinical practice by enabling efficient and risk-reduced decision-making and by supporting less experienced practitioners before the surgical removal of the M3M. [ABSTRACT FROM AUTHOR]

• Bottom-up approach for predicting near-optimal building retrofit solutions. • Artificial neural networks ensure scalability for large-scale retrofit analysis. • Retrofit model for residential buildings of various climatic regions. • Trade-off between accuracy, computational cost, and ease of application. • Near-optimal retrofit solutions for residential buildings in Geneva municipality. Coordinated large scale building retrofit is one of the most effective approaches not only to reduce the environmental footprint of existing buildings but also to assure that climate goals can be met. Existing bottom-up retrofit approaches become infeasible or lack in terms of accuracy and/or computational cost especially when the scale of application increases in size. Hence, the aim of this paper is to propose and develop a bottom-up approach for large-scale building retrofit with the use of a scalable building-level surrogate retrofit model. To ensure scalability and generalization to large areas, we use artificial neural networks. The developed approach consists of a set of artificial neural networks trained on building archetypes, aiming to predict near-optimal building retrofit solutions for all residential buildings in Switzerland. This is achieved with a small set of inputs, and within a short run time. In order to validate the developed approach, we compare it with a conventional mixed building simulation and optimization approach. The surrogate model computes near-optimal building retrofit solutions, with an average coefficient of determination of 0.91 and an average f1 score of 0.89. To illustrate the advantages of this model, we perform a large-scale retrofit analysis of a case study in Geneva municipality. Such a surrogate model is capable of providing insights into the overall retrofit potential of large areas and thus shall support reaching energy emission reduction targets of existing residential buildings. [ABSTRACT FROM AUTHOR]