Accurately characterizing clouds and their shadows is a long-standing problem in the Earth Observation community. Recent works showcase the necessity to improve cloud detection methods for imagery acquired by the Sentinel-2 satellites. However, the lack of consensus and transparency in existing reference datasets hampers the benchmarking of current cloud detection methods. Exploiting the analysis-ready data offered by the Copernicus program, we created CloudSEN12, a new multi-temporal global dataset to foster research in cloud and cloud shadow detection. CloudSEN12 has 49,400 image patches, including (1) Sentinel-2 level-1C and level-2A multi-spectral data, (2) Sentinel-1 synthetic aperture radar data, (3) auxiliary remote sensing products, (4) different hand-crafted annotations to label the presence of thick and thin clouds and cloud shadows, and (5) the results from eight state-of-the-art cloud detection algorithms. At present, CloudSEN12 exceeds all previous efforts in terms of annotation richness, scene variability, geographic distribution, metadata complexity, quality control, and number of samples. The dataset is made publicly available at https://cloudsen12.github.io/.

Blood flow into the kidneys through the renal artery determines the systemic blood pressure which is regulated by the baroreceptors in the kidneys. When the baroreceptors sense decreases in local fluid pressure they stimulate the renin-angiotensin aldosterone (RAA) system, which increases systemic blood pressure by constricting blood vessels throughout the body. An aneurysm in the renal artery leads to high systemic blood pressure in most patients with this condition, but the mechanisms by which the pressure increase occurs are not well understood. One explanation of the pressure increase could be a drop in local fluid pressure near the aneurysm itself causing the RAA system to “correct” this low pressure by systemically increasing the blood pressure. The ongoing work reported here has focused on a model renal artery network with and without an aneurysm by simulating the flow with computational fluid dynamics (CFD) software. The fluid for the simulations was meant to mimic blood in terms of density and viscosity for shear stresses where Non-Newtonian flow effects should not be a concern. Flow into the renal artery was at a Reynolds number of almost 700, to mimic the flow rate in the renal artery. The simulations were performed to determine the difference in pressure between an inlet to the renal network and the exits from the network. These results indicate that the pressure difference through the network differed by less than 10 Pa comparing networks with and without saccular aneurysm. The pressure change that would trigger the RAA system is nearly 1000 Pa. So we conclude that the effect of changing the geometry with only a saccular aneurysm is not responsible for triggering the RAA system alone. Other effects that could lead to triggering of the RAA system are discussed as well as our initial construction of a system to perform validation experiments of our CFD results.