Dams play a vital role in securing water and electricity supplies for households and industry, and they contribute significantly to flood protection. Regular monitoring of dam deformations holds fundamental socio-economic and ecological importance. Traditionally, this has relied on time-consuming in situ techniques that offer either high spatial or temporal resolution. Persistent Scatterer Interferometry (PSI) addresses these limitations, enabling high-resolution monitoring in both domains. Sensors such as TerraSAR-X (TSX) and Sentinel-1 (S-1) have proven effective for deformation analysis with millimeter accuracy. Combining TSX and S-1 datasets enhances monitoring capabilities by leveraging the high spatial resolution of TSX with the broad coverage of S-1. This improves monitoring by increasing PS point density, reducing revisit intervals, and facilitating the detection of environmental deformation drivers. This study aims to investigate two objectives: first, we evaluate the benefits of a spatially and temporally densified PS time series derived from TSX and S-1 data for detecting radial deformations in individual dam segments. To support this, we developed the TSX2StaMPS toolbox, integrated into the updated snap2stamps workflow for generating single-master interferogram stacks using TSX data. Second, we identify deformation drivers using water level and temperature as exogenous variables. The five-year study period (2017–2022) was conducted on a gravity dam in North Rhine-Westphalia, Germany, which was divided into logically connected segments. The results were compared to in situ data obtained from pendulum measurements. Linear models demonstrated a fair agreement between the combined time series and the pendulum data ($R^2$ = 0.5; MAE = 2.3 mm). Temperature was identified as the primary long-term driver of periodic deformations of the gravity dam. Following the filling of the reservoir, the variance in the PS data increased from 0.9 mm to 3.9 mm in RMSE, suggesting that water level changes are more responsible for short-term variations in the SAR signal. Upon full impoundment, the mean deformation amplitude decreased by approximately 1.7 mm toward the downstream side of the dam, which was attributed to the higher water pressure. The last five meters of water level rise resulted in higher feature importance due to interaction effects with temperature. The study concludes that integrating multiple PS datasets for dam monitoring is beneficial particularly for dams where few PS points can be identified using one sensor or where pendulum systems are not installed. Identifying the drivers of deformation is feasible and can be incorporated into existing monitoring frameworks.

Deformation monitoring is a critical task for dam operators to guarantee safe operation. Given an increasing number of extreme weather events caused by climate change, the precise prediction of dam deformations has become increasingly important. Traditionally, multiple linear regression models have been employed, utilizing in situ data from pendulum systems or trigonometric measurements. These methods sometimes suffer from sparse data, which typically represent deformations only at specific points on the dam, if such data are available at all. Technical advances in multi-temporal synthetic aperture radar interferometry (MT-InSAR), particularly Persistent Scatterer Interferometry (PSI), address these limitations by enabling monitoring in high spatial and temporal resolution, capturing dam deformations with millimeter precision, and providing extensive spatial coverage. This study advances traditional methods of dam monitoring by employing data-driven techniques and integrating Sentinel-1 C-band Persistent Scatterer (PS) time series alongside in situ data. Through a comprehensive evaluation of advanced data-driven approaches, we demonstrated considerable improvements in predicting dam deformations and evaluating their drivers. The analysis provided evidence for the following insights: First, the accuracy of current modeling approaches can be greatly improved by utilizing advanced feature engineering and data-driven model selection. The prediction performance of the pendulum data was improved by utilizing data-driven algorithms, reducing the mean absolute error from 0.51 mm in the baseline model (R² = 0.92) to as low as 0.05 mm using the full model search space (R² = 0.99). Although the model accuracy for the PS datasets (MAE_max: 0.81 mm) was about one order of magnitude lower than that for pendulum data, the mean absolute errors could be reduced by up to 0.25 mm. Second, by incorporating freely available PS time series into deformation prediction, dams can be monitored in higher spatial resolution, making PSI a valuable tool for dam operators. This requires adequate dataset filtering to eliminate noisy PS points. Third, extended representations of water level and temperature, including interaction effects, can improve model accuracy and reduce prediction errors. With these insights, we recommend incorporating the proposed methodology into the monitoring program of gravity dams to enhance the accuracy in predicting their expected deformations.

A substantial body of research has focused on developing systems that assist medical professionals during labor-intensive early screening processes, many based on convolutional deep-learning architectures. Recently, multiple studies explored the application of so-called self-attention mechanisms in the vision domain. These studies often report empirical improvements over fully convolutional approaches on various datasets and tasks. To evaluate this trend for medical imaging, we extend two widely adopted convolutional architectures with different self-attention variants on two different medical datasets. With this, we aim to specifically evaluate the possible advantages of additional self-attention. We compare our models with similarly sized convolutional and attention-based baselines and evaluate performance gains statistically. Additionally, we investigate how including such layers changes the features learned by these models during the training. Following a hyperparameter search, and contrary to our expectations, we observe no significant improvement in balanced accuracy over fully convolutional models. We also find that important features, such as dermoscopic structures in skin lesion images, are still not learned by employing self-attention. Finally, analyzing local explanations, we confirm biased feature usage. We conclude that merely incorporating attention is insufficient to surpass the performance of existing fully convolutional methods.

Causal discovery from time series data encompasses many existing solutions, including those based on deep learning techniques. However, these methods typically do not endorse one of the most prevalent paradigms in deep learning: End-to-end learning. To address this gap, we explore what we call Causal Pretraining. A methodology that aims to learn a direct mapping from multivariate time series to the underlying causal graphs in a supervised manner. Our empirical findings suggest that causal discovery in a supervised manner is possible, assuming that the training and test time series samples share most of their dynamics. More importantly, we found evidence that the performance of Causal Pretraining can increase with data and model size, even if the additional data do not share the same dynamics. Further, we provide examples where causal discovery for real-world data with causally pretrained neural networks is possible within limits. We argue that this hints at the possibility of a foundation model for causal discovery.

Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model. This behavior is especially problematic in critical areas such as autonomous driving or medical decision-making. In these scenarios, new data is often expensive and hard to come by. In this work, we present a method based on change penalization that takes a pre-trained model and adapts the weights to mitigate a previously detected bias. We achieve this by tuning a zero-initialized copy of a frozen pre-trained network. Our method needs very few, in extreme cases only a single, examples that contradict the bias to increase performance. Additionally, we propose an early stopping criterion to modify baselines and reduce overfitting. We evaluate our approach on a well-known bias in skin lesion classification and three other datasets from the domain shift literature. We find that our approach works especially well with very few images. Simple fine-tuning combined with our early stopping also leads to performance benefits for a larger number of tuning samples.

Causal discovery, or identifying causal relationships from observational data, is a notoriously challenging task, with numerous methods proposed to tackle it. Despite this, in-the-wild evaluation of these methods is still lacking, as works frequently rely on synthetic data evaluation and sparse real-world examples under critical theoretical assumptions. Real-world causal structures, however, are often complex, making it hard to decide on a proper causal discovery strategy. To bridge this gap, we introduce CausalRivers, the largest in-the-wild causal discovery benchmarking kit for time-series data to date. CausalRivers features an extensive dataset on river discharge that covers the eastern German territory (666 measurement stations) and the state of Bavaria (494 measurement stations). It spans the years 2019 to 2023 with a 15-minute temporal resolution. Further, we provide additional data from a flood around the Elbe River, as an event with a pronounced distributional shift. Leveraging multiple sources of information and time-series meta-data, we constructed two distinct causal ground truth graphs (Bavaria and eastern Germany). These graphs can be sampled to generate thousands of subgraphs to benchmark causal discovery across diverse and challenging settings. To demonstrate the utility of CausalRivers, we evaluate several causal discovery approaches through a set of experiments to identify areas for improvement. CausalRivers has the potential to facilitate robust evaluations and comparisons of causal discovery methods. Besides this primary purpose, we also expect that this dataset will be relevant for connected areas of research, such as time-series forecasting and anomaly detection. Based on this, we hope to push benchmark-driven method development that fosters advanced techniques for causal discovery, as is the case for many other areas of machine learning.