Search

Robust and accurate flood hazard maps are essential for early warning systems and flood risk management. Although physically based models are effective in estimating pluvial flooding, the computational burden makes them difficult to use for real-time flood prediction. In contrast, data-driven models can provide faster flood predictions if trained offline. While most studies have focused on predicting maximum water depth, in this study, we predict pixel-wise water depth maps for entire catchments at a lead time of 2 h. To that end, we propose a deep learning approach that uses a sequence encoding network with temporal self-attention. We also adapt the popular hydrological performance metric Nash–Sutcliffe efficiency (NSE) as our loss function. We test the effectiveness and generalizability of our method using a new dataset called SwissFlood, which consists of 100 catchments and 1500 rainfall events extracted from real observations in Switzerland. Our method produces 2 m spatial resolution flood maps with absolute error as low as 27 cm for water depth exceeding 1 m. [ABSTRACT FROM AUTHOR]

For many safety-related applications such as hazard mapping or road management, well documented avalanche events are crucial. Nowadays, despite research into different directions, the available data is mostly restricted to isolated locations where it is collected by observers in the field. Webcams are getting more frequent in the Alps and beyond, capturing numerous avalanche prone slopes several times a day. To complement the knowledge about avalanche occurrences, we propose to make use of this webcam imagery for avalanche mapping. For humans, avalanches are relatively easy to identify, but the manual mapping of their outlines is time intensive. Therefore, we propose to support the mapping of avalanches in images with a learned segmentation model. In interactive avalanche segmentation (IAS), a user collaborates with a deep learning model to segment the avalanche outlines, taking advantage of human expert knowledge while keeping the effort low thanks to the model's ability to delineate avalanches. The human corrections to the prediction in the form of positive clicks on the avalanche or negative clicks on the background result in avalanche outlines of good quality with little effort. Relying on IAS, we extract avalanches from the images in a flexible and efficient manner, resulting in a 90 % time saving compared to conventional manual mapping. If mounted in a stable position, the camera can be georeferenced with a mono-photogrammetry tool, allowing for exact geolocation of the avalanche outlines and subsequent use in geographical information systems (GIS). In this way all avalanches mapped in an image can be imported into a designated database, making them available for the relevant safety-related applications. For imagery, we rely on current and archive data from webcams that cover the Dischma valley near Davos, Switzerland and capture an image every 30 minutes during daytime since the winter 2019. Our model and the associated mapping pipeline represent an important step forward towards continuous and precise avalanche documentation, complementing existing databases and thereby providing a better base for safety-critical decisions and planning in avalanche-prone mountain regions. [ABSTRACT FROM AUTHOR]

The spatial and temporal distribution of Alpine snow is a sensitive gauge of environmental change. While understanding past snow dynamics is essential for reconstructing past climate and forecasting future trends, reliable snowpack data prior to the instrumental record are scarce. We present a novel pairing of cosmogenic paleothermometry and luminescence photochronometry which constrain the temperature and insolation history of bedrock outcrops at the Gotthard Pass, Switzerland, over the last ∼15,000 years. By coupling these results with cosmogenic 14C‐10Be chronology and modern in situ rock thermometry, we infer a ∼70‐day reduction of snowpack at the topographic mid‐slope. Our data indicate stable environmental conditions throughout the Holocene, followed by a 6.6 ± 2.9°C increase of ground surface temperature, coeval with an order‐of‐magnitude or more increase in ground surface insolation. Bracketing the onset of these changes between 1504 and 1807 CE, our findings tie the snowpack decline with the onset of human industrialization. Plain Language Summary: The extent of snow cover is shrinking in high elevation mountain environments due to climate change. However, it is challenging to determine when snow cover began to change because humans have only been monitoring snow cover for several decades, and snow cover has appeared to shrink over this entire time. We used two new geologic records of ground temperature and light exposure—both of which are impacted by the duration and amount of snow cover—to assess when snow cover began to change in the Gotthard Pass in Switzerland. We found that the middle slopes of the pass began experiencing snow cover loss three centuries ago, well before historical monitoring of snow cover in this region. This record of prolonged snow cover loss matters for the informed management of mountain water sources, rock and snow avalanche risk, and ecosystem change. Key Points: We present a novel data set of cosmogenic paleothermometry and luminescence photochronometry at the Gotthard Pass, SwitzerlandStable Holocene environmental conditions are followed by increases in ground temperature and insolation caused by snow cover declineThese environmental changes began between 1504 and 1807 CE, tying the observed snowpack decline with the onset of human industrialization [ABSTRACT FROM AUTHOR]

Consistent estimates of avalanche size are crucial for communicating not only among avalanche practitioners but also between avalanche forecasters and the public, for instance in public avalanche forecasts. Moreover, applications such as risk management and numerical avalanche simulations rely on accurately mapped outlines of past avalanche events. Since there is not a widely applicable and objective way to measure avalanche size or to determine the outlines of an avalanche, we need to rely on human estimations. Therefore, knowing about the reliability of avalanche size estimates and avalanche outlines is essential as errors will impact applications relying on this kind of data. In the first of three user studies, we investigate the reliability in avalanche size estimates by comparing estimates for 10 avalanches made by 170 avalanche professionals working in Europe or North America. In the other two studies, both completed as pilot studies, we explore reliability in the mappings of six avalanches from oblique photographs from 10 participants and the mappings of avalanches visible on 2.9 km 2 of remotely sensed imagery in four different spatial resolutions from 5 participants. We observed an average agreement of 66 % in the most frequently given avalanche size, while agreement with the avalanche size considered "correct" was 74 %. Moreover, European avalanche practitioners rated avalanches significantly larger for 8 out of 10 avalanches, compared to North Americans. Assuming that participants are equally competent in the estimation of avalanche size, we calculated a score describing the factor required to obtain the observed agreement rate between any two size estimates. This factor was 0.72 in our dataset. It can be regarded as the certainty related to a size estimate by an individual and thus provides an indication of the reliability of a label. For the outlines mapped from oblique photographs, we noted a mean overlapping proportion of 52 % for any two avalanche mappings and 60 % compared to a reference mapping. The outlines mapped from remotely sensed imagery had a mean overlapping proportion of 46 % (image resolution of 2 m) to 68 % (25 cm) between any two mappings and 64 % (2 m) to 80 % (25 cm) when compared to the reference. The presented findings demonstrate that the reliability of size estimates and of mapped avalanche outlines is limited. As these data are often used as reference data or even ground truth to validate further applications, the identified limitations and uncertainties may influence results and should be considered. [ABSTRACT FROM AUTHOR]

Historical maps depict past states of the Earth's surface and make it possible to trace the natural or anthropogenic evolution of geographic objects back through time. However, the state of the depicted reality is not the only source of change: maps of varying age can differ in terms of graphical design, and also in terms of storage conditions, physical ageing of pigments, and the scanning process for digitization. Consequently, a computer vision system learned from a specific (source) map series will often not generalize well to older or newer (target) maps, calling for domain adaptation. In the present paper we examine – to our knowledge for the first time – domain adaptation for segmenting historical maps. We argue that for geo-spatial data like maps, which are geo-localized by definition, the spatial co-occurrence of geographical objects provides a supervision signal for domain adaptation. Since only a subset of all mapped objects co-occur, and even those are not perfectly aligned due to both real topographic changes and variations in map generalization/production, they only provide weak supervision — still they can bring a substantial benefit over completely unsupervised domain adaptation methods. The core of our proposed method is a novel self-supervised co-occurrence network that detects co-occurring objects across maps (specifically, domains) with a novel loss function that allows for object changes and spatial misalignment. Experiments show that, for the task of segmenting hydrological objects such as rivers, lakes and wetlands, our system significantly outperforms two state-of-art baselines, even with limited supervision (e.g., 5%). The source code is publicly available at https://github.com/sian-wusidi/spatialcooccurrence. [ABSTRACT FROM AUTHOR]

We propose a probabilistic deep learning approach for the prediction of maximum water depth hazard maps at high spatial resolutions, which assigns well-calibrated uncertainty estimates to every predicted water depth. Efficient, accurate, and trustworthy methods for urban flood management have become increasingly important due to higher rainfall intensity caused by climate change, the expansion of cities, and changes in land use. While physically based flood models can provide reliable forecasts for water depth at every location of a catchment, their high computational burden is hindering their application to large urban areas at high spatial resolution. While deep learning models have been used to address this issue, a disadvantage is that they are often perceived as "black-box" models and are overconfident about their predictions, therefore decreasing their reliability. Our deep learning model learns the underlying phenomena a priori from simulated hydrodynamic data, obviating the need for manual parameter setting for every new rainfall event at test time. The only inputs needed at the test time are a rainfall forecast and parameters of the terrain such as a digital elevation model to predict the maximum water depth with uncertainty estimates for complete rainfall events. We validate the accuracy and generalisation capabilities of our approach through experiments on a dataset consisting of catchments within Switzerland and Portugal and 18 rainfall patterns. Our method produces flood hazard maps at 1 m resolution and achieves mean absolute errors as low as 21 cm for extreme flood cases with water above 1 m. Most importantly, we demonstrate that our approach is able to provide an uncertainty estimate for every water depth within the predicted hazard map, thus increasing the model's trustworthiness during flooding events. [ABSTRACT FROM AUTHOR]

Spatially dense and continuous information on avalanche occurrences is crucial for numerous safety-related applications such as avalanche warning, hazard zoning, hazard mitigation measures, forestry, risk management and numerical simulations. This information is today still collected in a non-systematic way by observers in the field. Current research has explored the application of remote sensing technology to fill this information gap by providing spatially continuous information on avalanche occurrences over large regions. Previous investigations have confirmed the high potential of avalanche mapping from remotely sensed imagery to complement existing databases. Currently, the bottleneck for fast data provision from optical data is the time-consuming manual mapping. In our study we deploy a slightly adapted DeepLabV3+, a state-of-the-art deep learning model, to automatically identify and map avalanches in SPOT 6/7 imagery from 24 January 2018 and 16 January 2019. We relied on 24 778 manually annotated avalanche polygons split into geographically disjointed regions for training, validating and testing. Additionally, we investigate generalization ability by testing our best model configuration on SPOT 6/7 data from 6 January 2018 and comparing it to avalanches we manually annotated for that purpose. To assess the quality of the model results, we investigate the probability of detection (POD), the positive predictive value (PPV) and the F1 score. Additionally, we assessed the reproducibility of manually annotated avalanches in a small subset of our data. We achieved an average POD of 0.610, PPV of 0.668 and an F1 score of 0.625 in our test areas and found an F1 score in the same range for avalanche outlines annotated by different experts. Our model and approach are an important step towards a fast and comprehensive documentation of avalanche periods from optical satellite imagery in the future, complementing existing avalanche databases. This will have a large impact on safety-related applications, making mountain regions safer. [ABSTRACT FROM AUTHOR]

We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM [16] and GRU [10] while being more robust against vanishing or exploding gradients. Stacking recurrent units into deep architectures suffers from two major limitations: (i) many recurrent cells (e.g., LSTMs) are costly in terms of parameters and computation resources; and (ii) deep RNNs are prone to vanishing or exploding gradients during training. We investigate the training of multi-layer RNNs and examine the magnitude of the gradients as they propagate through the network in the ”vertical” direction. We show that, depending on the structure of the basic recurrent unit, the gradients are systematically attenuated or amplified. Based on our analysis we design a new type of gated cell that better preserves gradient magnitude. We validate our design on a large number of sequence modelling tasks and demonstrate that the proposed STAR cell allows to build and train deeper recurrent architectures, ultimately leading to improved performance while being computationally more efficient. [ABSTRACT FROM AUTHOR]