Meteorites provide a unique view into the origin and evolution of the Solar System. Antarctica is the most productive region for recovering meteorites, where these extraterrestrial rocks concentrate at meteorite stranding zones. To date, meteorite-bearing blue ice areas are mostly identified by serendipity and through costly reconnaissance missions. Here, we identify meteorite-rich areas by combining state-of-the-art datasets in a machine learning algorithm and provide continent-wide estimates of the probability to find meteorites at any given location. The resulting set of ca. 600 meteorite stranding zones, with an estimated accuracy of over 80%, reveals the existence of unexplored zones, some of which are located close to research stations. Our analyses suggest that less than 15% of all meteorites at the surface of the Antarctic ice sheet have been recovered to date. The data-driven approach will greatly facilitate the quest to collect the remaining meteorites in a coordinated and cost-effective manner.

<p>Whereas most of the continent of Antarctica is covered by snow, in some areas, blue-colored ice emerges to the surface. In these blue ice areas (BIAs), mass is removed at the surface through ablative processes. This mass removal exposes deeper layers of ice that are normally located closer to the underlying bedrock. As a result, we can find old ice at the surface of BIAs, as well as the material contained within the ice, such as meteorites and terrestrial rocks. BIAs are unique locations for sampling old ice for palaeoclimatic purposes and collecting meteorites (about ⅔ of all meteorites ever retrieved on Earth come from Antarctica BIAs). Hence, a high-quality BIA map is essential for meteorite searches, the quest for the oldest ice, and surface mass balance modeling.</p> <p>Prior efforts to map BIAs across the Antarctic continent using remote sensing are single-sensor based, introducing biases related to temporary snow coverage of the exposed ice, and sensor-dependent conditions such as solar illumination angles, anisotropic reflectance, or cloud coverage. To overcome these challenges, we opt for using multi-sensor observations in a deep learning framework to create a new BIA map. The observations we use are (i) radar backscatter, (ii) surface morphology, (iii) elevation, and (iv) multi-spectral reflectance. The deep learning algorithm consists of the well-established convolutional neural network U-Net, which allows for an efficient training process and inclusion of spatial context. The algorithm outputs a pixel-level prediction of blue ice presence. Moreover, by training multiple, randomly initialized models and rotating and flipping data, we obtain multiple predictions for each pixel. Thanks to this data augmentation at test time, we estimate the variation in the predictions, which we then use as an indication of uncertainty. </p> <p>We use an existing dataset of BIA outlines as reference for training the model. It is known that these existing labels are noisy due to i) large uncertainties related to the use of a single sensor, and ii) biases as a result of applying a threshold that is based on local observations over the entire continent. However, convolutional neural networks, combined with regularization methods like weight decay and batch normalization, can learn from underlying ‘clean’ patterns of noisy labels during initial epochs of training (i.e., at the start of the training process). Here, we demonstrate this noise-eliminating property by assessing the algorithm's performance on noisy pixels that are used for training, where we see that over 80% of these noisy instances are attributed correctly. Furthermore, we optimize the performance of the neural network based on a reduced set of "noise-free", hand-labeled validation data. Last,  we test the performance of our model on hand-labeled test data, therefore having a realistic estimate of the model performance on precise, so far unused data. These tests indicate that it is possible for the neural net to learn how to map blue ice from the noisy data, leading to an improved map of BIAs in Antarctica.</p>

<p>Meteorites provide an unparalleled view on the origin and evolution of the solar system. Antarctica is the most productive region for collecting meteorites, as the visually contrasting meteorites are easily detectable and tend to concentrate at specific areas exposing blue ice. Blue ice areas act as meteorite stranding zones if the flow of the ice sheet and specific geographical and climatological settings combine favorably. Previously, possible meteorite stranding zones were identified by chance or through visual examination of remote sensing data, which limits the discovery of new locations for future meteorite searching campaigns.</p><p>In this study, various state-of-the-art datasets are combined in a machine learning approach to estimate the likeliness of a blue ice area to be a meteorite stranding zone. Input data for a generative classifier consists of ca. 13,000 reprojected meteorite finding locations (positive observations) and 2,000,000 unlabeled observations, for which the presence of meteorites is unknown. Four features have been selected, representing the typical conditions in which meteorites are found: exposure of blue ice (radar backscatter), cold surface conditions and negative surface mass balance (surface temperature and surface slope), and almost stagnant ice flow (surface velocities). With these features, the probability of the presence of meteorites is computed for each unlabeled observation at blue ice areas. These probabilities are computed by evaluating the multidimensional density distributions of the observations on the unlabeled observations and combining these with the prior probabilities of the two classes (positive and unlabeled). As the set of training data does contain only positive and unlabeled observations, the prior probabilities are scaled. The amount of scaling is decided by maximizing the harmonic mean between precision and sensitivity, which are estimated in a cross-validation using negative observations of sites known to be absent of meteorites. In the post-processing, the pixels that likely contain meteorites are clustered, resulting in several hundreds of meteorite stranding zones.</p><p>Results show that the first continent-wide meteorite stranding zone classification is ca. 70-80% accurate (first estimate, based on independent test data). The post-processed results reveal the existence of major unexplored meteorite stranding zones, some of which are in close proximity to existing research stations. The quest to collect the meteorites remaining at the surface of the ice sheet, the number of which is estimated to exceed those already collected to date, will greatly benefit from our newly provided meteorite map.</p>

<p>The vast majority of the Antarctic ice sheet is covered with snow that compacts under its own weight and transforms into ice below the surface. However, in some areas, this typically blue-colored ice is directly exposed at the surface. These so-called "blue ice areas" represent islands of negative surface mass balance through sublimation and/or melt. Moreover, blue ice areas expose old ice that is easily accessible in large quantities at the surface, and some areas contain ice that extends beyond the time scales of classic deep-drilling ice cores.</p><p>Observation and modeling efforts suggest that the location of blue ice areas is related to a specific combination of topographic and meteorological factors. In the literature, these factors are described as (i) enhanced katabatic winds that erode snow, due to an increase of the surface slope or a tunneling effect of topography, (ii) the increased albedo of blue ice (with respect to snow), which enhances ablative processes, and (iii) the presence of nunataks (mountains protruding the ice) that act as barriers to the ice flow upstream, and prevent deposition of blowing snow on the lee side of the mountain. However, it remains largely unknown which role the physical processes play in creating and/or maintaining  blue ice at the surface of the ice sheet.</p><p>Here, we study how a combination of environmental and topographic factors lead to the observation of blue ice. We also quantify the relevance of the single processes and build an interpretable model aiming at not only predicting blue ice presence, but also explaining why it is there. To do so, data is fed into a convolutional neural network, a machine learning algorithm which uses the spatial context of the data to generate a prediction on the presence of blue ice areas. More specifically, we use a U-Net architecture that through convolutions and linked up-convolutions allows to obtain a semantic segmentation (i.e., a pixel-level map) of the input data. Ground reference data is obtained from existing products of blue ice area outlines that are based on multispectral observations. These products contain considerable uncertainties, as (i) the horizontal change from snow to ice is gradual and a single threshold in this transition is not applicable uniformly over the continent, and (ii) the blue ice area extent is known to vary seasonally. Therefore, we train our deep learning model with a loss function with increasing weight towards the center of blue ice areas.</p><p>Our first results indicate that the neural network predicts the location of blue ice relatively well, and that surface elevation data plays an important role in determining the location of blue ice. In our ongoing work, we analyze both the predictions and the neural network itself to quantify which factors posses predictive capacity to explain the location of blue ice. Eventually this information may allow us to answer the simple yet important question of why blue ice areas are located where they are, with potentially important implications for their role as paleoclimate archives and for their evolution under changing climatic conditions.</p>