Neural network modelling of planform geometry of headland-bay beaches

The shoreline of beaches in the lee of coastal salients or man-made structures, usually known as headland-bay beaches, has a distinctive curvature; wave fronts curve as a result of wave diffraction at the headland and in turn cause the shoreline to bend. The ensuing curved planform is of great interest both as a peculiar landform and in the context of engineering projects in which it is necessary to predict how a coastal structure will affect the sandy shoreline in its lee. A number of empirical models have been put forward, each based on a specific equation. A novel approach, based on the application of artificial neural networks, is presented in this work. Unlike the conventional method, no particular equation of the planform is embedded in the model. Instead, it is the model itself that learns about the problem from a series of examples of headland-bay beaches (the training set) and thereafter applies this self-acquired knowledge to other cases (the test set) for validation. Twenty-three headland-bay beaches from around the world were selected, of which sixteen and seven make up the training and test sets, respectively. As there is no well-developed theory for deciding upon the most convenient neural network architecture to deal with a particular data set, an experimental study was conducted in which ten different architectures with one and two hidden neuron layers and five training algorithms – 50 different options combining network architecture and training algorithm – were compared. Each of these options was implemented, trained and tested in order to find the best-performing approach for modelling the planform of headland-bay beaches. Finally, the selected neural network model was compared with a state-of-the-art planform model and was shown to outperform it.     

Linking Tarim Basin sea retreat (west China) and Asian aridification in the late Eocene

The Tarim Basin in western China formed the easternmost margin of a shallow epicontinental sea that extended across Eurasia and was well connected to the western Tethys during the Paleogene. Climate modelling studies suggest that the westward retreat of this sea from Central Asia may have been as important as the Tibetan Plateau uplift in forcing aridification and monsoon intensification in the Asian continental interior due to the redistribution of the land‐sea thermal contrast. However, testing of this hypothesis is hindered by poor constraints on the timing and precise palaeogeographic dynamics of the retreat. Here, we present an improved integrated bio‐ and magnetostratigraphic chronological framework of the previously studied marine to continental transition in the southwest Tarim Basin along the Pamir and West Kunlun Shan, allowing us to better constrain its timing, cause and palaeoenvironmental impact. The sea retreat is assigned a latest Lutetian–earliest Bartonian age (ca. 41 Ma; correlation of the last marine sediments to calcareous nannofossil Zone CP14 and correlation of the first continental red beds to the base of magnetochron C18r). Higher up in the continental deposits, a major hiatus includes the Eocene–Oligocene transition (ca. 34 Ma). This suggests the Tarim Basin was hydrologically connected to the Tethyan marine Realm until at least the earliest Oligocene and had not yet been closed by uplift of the Pamir–Kunlun orogenic system. The westward sea retreat at ca. 41 Ma and the disconformity at the Eocene–Oligocene transition are both time‐equivalent with reported Asian aridification steps, suggesting that, consistent with climate modelling results, the sea acted as an important moisture source for the Asian continental interior.     

Airborne radar and in-situ observations of a shallow stratus with drizzle

Observations were made of a shallow stratus of upslope origin using an aircraft equipped with insitu probes and with a vertically-pointing radar of 3-mm wavelength. A cloud layer of 300 m thickness was found below the inversion; an additional layer of 100 m thickness was located within the inversion. The coldest temperature within the cloud was -2°C and the cloud contained no ice particles. Drizzle drops up to 180 Am were present in both cloud layers.The observations reveal precipitation and air motion structures of approximately 1 km horizontal dimensions. The origin of this organization appears to be weak convection. In addition, mixing played an important role in forming the cloud droplet and drizzle drop size distributions.