Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.

With the increasing adaptability and complexity of advisory artificial intelligence (AI)-based agents, the topics of explainable AI and human-centered AI are moving close together. Variations in the explanation itself have been widely studied, with some contradictory results. These could be due to users’ individual differences, which have rarely been systematically studied regarding their inhibiting or enabling effect on the fulfillment of explanation objectives (such as trust, understanding, or workload). This paper aims to shed light on the significance of human dimensions (gender, age, trust disposition, need for cognition, affinity for technology, self-efficacy, attitudes, and mind attribution) as well as their interplay with different explanation modes (no, simple, or complex explanation). Participants played the game Deal or No Deal while interacting with an AI-based agent. The agent gave advice to the participants on whether they should accept or reject the deals offered to them. As expected, giving an explanation had a positive influence on the explanation objectives. However, the users’ individual characteristics particularly reinforced the fulfillment of the objectives. The strongest predictor of objective fulfillment was the degree of attribution of human characteristics. The more human characteristics were attributed, the more trust was placed in the agent, advice was more likely to be accepted and understood, and important needs were satisfied during the interaction. Thus, the current work contributes to a better understanding of the design of explanations of an AI-based agent system that takes into account individual characteristics and meets the demand for both explainable and human-centered agent systems.

The Wuertual Reality XR Meeting 2023 was initiated to bring together researchers from many fields who use VR/AR/XR. There was a focus on applied XR and social VR. In this conference band, you can find the abstracts of the two keynotes, the 34 posters and poster pitches, the 29 talks and the four workshops.

This paper deals with the effect of exploiting background knowledge for improving an OMR (Optical Music Recognition) deep learning pipeline for transcribing medieval, monophonic, handwritten music from the 12th–14th century, whose usage has been neglected in the literature. Various types of background knowledge about overlapping notes and text, clefs, graphical connections (neumes) and their implications on the position in staff of the notes were used and evaluated. Moreover, the effect of different encoder/decoder architectures and of different datasets for training a mixed model and for document-specific fine-tuning based on an extended OMR pipeline with an additional post-processing step were evaluated. The use of background models improves all metrics and in particular the melody accuracy rate (mAR), which is based on the insert, delete and replace operations necessary to convert the generated melody into the correct melody. When using a mixed model and evaluating on a different dataset, our best model achieves without fine-tuning and without post-processing a mAR of 90.4%, which is raised by nearly 30% to 93.2% mAR using background knowledge. With additional fine-tuning, the contribution of post-processing is even greater: the basic mAR of 90.5% is raised by more than 50% to 95.8% mAR.

Background: Oro-antral communication (OAC) is a common complication following the extraction of upper molar teeth. The Archer and the Root Sinus (RS) systems can be used to classify impacted teeth in panoramic radiographs. The Archer classes B-D and the Root Sinus classes III, IV have been associated with an increased risk of OAC following tooth extraction in the upper molar region. In our previous study, we found that panoramic radiographs are not reliable for predicting OAC. This study aimed to (1) determine the feasibility of automating the classification (Archer/RS classes) of impacted teeth from panoramic radiographs, (2) determine the distribution of OAC stratified by classification system classes for the purposes of decision tree construction, and (3) determine the feasibility of automating the prediction of OAC utilizing the mentioned classification systems. Methods: We utilized multiple supervised pre-trained machine learning models (VGG16, ResNet50, Inceptionv3, EfficientNet, MobileNetV2), one custom-made convolutional neural network (CNN) model, and a Bag of Visual Words (BoVW) technique to evaluate the performance to predict the clinical classification systems RS and Archer from panoramic radiographs (Aim 1). We then used Chi-square Automatic Interaction Detectors (CHAID) to determine the distribution of OAC stratified by the Archer/RS classes to introduce a decision tree for simple use in clinics (Aim 2). Lastly, we tested the ability of a multilayer perceptron artificial neural network (MLP) and a radial basis function neural network (RBNN) to predict OAC based on the high-risk classes RS III, IV, and Archer B-D (Aim 3). Results: We achieved accuracies of up to 0.771 for EfficientNet and MobileNetV2 when examining the Archer classification. For the AUC, we obtained values of up to 0.902 for our custom-made CNN. In comparison, the detection of the RS classification achieved accuracies of up to 0.792 for the BoVW and an AUC of up to 0.716 for our custom-made CNN. Overall, the Archer classification was detected more reliably than the RS classification when considering all algorithms. CHAID predicted 77.4% correctness for the Archer classification and 81.4% for the RS classification. MLP (AUC: 0.590) and RBNN (AUC: 0.590) for the Archer classification as well as MLP 0.638) and RBNN (0.630) for the RS classification did not show sufficient predictive capability for OAC. Conclusions: The results reveal that impacted teeth can be classified using panoramic radiographs (best AUC: 0.902), and the classification systems can be stratified according to their relationship to OAC (81.4% correct for RS classification). However, the Archer and RS classes did not achieve satisfactory AUCs for predicting OAC (best AUC: 0.638). Additional research is needed to validate the results externally and to develop a reliable risk stratification tool based on the present findings.