Start-up and shut-down (SUSD) events in proton exchange membrane fuel cells (PEMFCs) are a major source of cathode degradation, causing a loss of electrochemical surface area (ECSA) and carbon corrosion. Our study reveals that also the anode suffers significant damage during SUSD, dominated by the loss of ECSA, induced by potential cycling between ≈0 and ≈1 V upon the passage of H 2 /air fronts. Furthermore, we demonstrate the analogy of SUSD-induced anode degradation and that originating from quasi-square wave potential cycling between 0.05 and 1.05 V RHE . The performance penalties arising from a decrease of the kinetics of the hydrogen oxidation reaction (HOR) and growing H 2 mass-transport resistances are measured via H 2 -pump experiments. The thus projected anode voltage losses for low anode Pt loadings (25 μg Pt cm −2 ) predict HOR kinetic losses of ≈40 mV at 80 • C and 3 A cm −2 for aged anode catalyst layers, suggesting that anode degradation by SUSD could be a significant durability issue in future PEMFC systems with ultra-low Pt loadings and with more stable cathode catalyst carbon supports. Moreover, SUSD-induced H 2 mass-transport related overpotentials were identified and attributed to carbon corrosion, indicated by a thinning of the anode catalyst layer upon aging.

Deep learning has been used successfully in computer vision problems, e.g. image classification, target detection and many more. We use deep learning in conjunction with ArcGIS to implement a model with advanced convolutional neural networks (CNN) for lithological mapping in the Mount Isa region (Australia). The area is ideal for spectral remote sensing as there is only sparse vegetation and besides freely available Sentinel-2 and ASTER data, several geophysical datasets are available from exploration campaigns. By fusing the data and thus covering a wide spectral range as well as capturing geophysical properties of rocks, we aim at improving classification accuracies and support geological mapping. We also evaluate the performance of the sensors on their own compared to a joint use as the Sentinel-2 satellites are relatively new and as of now there exist only few studies for geological applications. We developed an end-to-end deep learning model using Keras and Tensorflow that consists of several convolutional, pooling and deconvolutional layers. Our model was inspired by the family of U-Net architectures, where low-level feature maps (encoders) are concatenated with high-level ones (decoders), which enables precise localization. This type of network architecture was especially designed to effectively solve pixel-wise classification problems, which is appropriate for lithological classification. We spatially resampled and fused the multi-sensor remote sensing data with different bands and geophysical data into image cubes as input for our model. Pre-processing was done in ArcGIS and the final, fine-tuned model was imported into a toolbox to be used on further scenes directly in the GIS environment. The tool classifies each pixel of the multiband imagery into different types of rocks according to a defined probability threshold. Results highlight the power of using Sentinel-2 in conjunction with ASTER data with accuracies of 75% in comparison to only 70% and 73% for ASTER or Sentinel-2 data alone. These results are similar but examining the different classes shows that there are significant improvements for classes such as dolerite or carbonate sediments that are not that widely distributed in the area. Adding geophysical datasets reduced accuracies to 60%, probably due to an order of magnitude difference in spatial resolution. In comparison, Random Forest (RF) and Support Vector Machines (SVMs) that were trained on the same data only achieve accuracies of 46 % and 36 % respectively. Most insecurity is due to labelling errors and labels with mixed lithologies. However, results show that the U-Net model is a powerful alternative to other classifiers for medium-resolution multispectral data.

No abstract

No abstract

No abstract