Quantifying the spatiotemporal dynamics in subsurface hydrological flows over a long time window usually employs a network of monitoring wells. However, such observations are often spatially sparse with potential temporal gaps due to poor quality or instrument failure. In this study, we explore the ability of recurrent neural networks to fill gaps in a spatially distributed time-series dataset. We use a well network that monitors the dynamic and heterogeneous hydrologic exchanges between the Columbia River and its adjacent groundwater aquifer at the U.S. Department of Energy's Hanford site. This 10-year-long dataset contains hourly temperature, specific conductance, and groundwater table elevation measurements from 42 wells with gaps of various lengths. We employ a long short-term memory (LSTM) model to capture the temporal variations in the observed system behaviors needed for gap filling. The performance of the LSTM-based gap-filling method was evaluated against a traditional autoregressive integrated moving average (ARIMA) method in terms of error statistics and accuracy in capturing the temporal patterns of river corridor wells with various dynamics signatures. Our study demonstrates that the ARIMA models yield better average error statistics, although they tend to have larger errors during time windows with abrupt changes or high-frequency (daily and subdaily) variations. The LSTM-based models excel in capturing both high-frequency and low-frequency (monthly and seasonal) dynamics. However, the inclusion of high-frequency fluctuations may also lead to overly dynamic predictions in time windows that lack such fluctuations. The LSTM can take advantage of the spatial information from neighboring wells to improve the gap-filling accuracy, especially for long gaps in system states that vary at subdaily scales. While LSTM models require substantial training data and have limited extrapolation power beyond the conditions represented in the training data, they afford great flexibility to account for the spatial correlations, temporal correlations, and nonlinearity in data without a priori assumptions. Thus, LSTMs provide effective alternatives to fill in data gaps in spatially distributed time-series observations characterized by multiple dominant frequencies of variability, which are essential for advancing our understanding of dynamic complex systems.

Chicken-pathogenicEscherichia coliis severely endangering the poultry industry in China and worldwide, and antibiotic therapy is facing an increasing problem of antibiotic resistance. Bacteriophages can kill bacteria with no known activity in human or animal cells, making them an attractive alternative to antibiotics. In this study, we present the characteristics of a novel virulent bacteriophage, Bp7, specifically infecting pathogenic multidrug-resistantE. coli. Phage Bp7 was isolated from chicken feces. Bp7 belongs to the familyMyoviridae, possessing an elongated icosahedral head and contractile sheathed tail. It has a 168-kb double-stranded DNA genome. For larger yields, its optimal multiplicity of infection (MOI) to infectE. coliwas about 0.001. The latent period was 10 to 15 min, and the burst size was 90 PFU/infected cell. It was stable both at pH 5.0 to 10.0 and at 40°C or 50°C for at least 1 h. Bp7 could infect 46% of pathogenic clinicalE. colistrains. Bp7 harbored 791 open reading frames (ORFs) and 263 possible genes. Among the 263 genes, 199 possessed amino acid sequence identities with ORFs of phage T4, 62 had identities with other T4-like phages, and only one lacked any database match. The genome of Bp7 manifested obvious division and rearrangement compared to phages T4, JS98, and IME08. Bp7 is a new member of the “T4-like” genus, familyMyoviridae. Its wide host range, strong cell-killing activity, and high stability to pH make it an alternative to antimicrobials for controlling drug-resistantE. coliin chickens.

In this study, we isolated a lytic Pseudomonas aeruginosa phage (vB_PaeP_ASP23) from the sewage of a mink farm, characterized its complete genome and analyzed the function of its putative lysin and holin. Morphological characterization and genome annotation showed that phage ASP23 belonged to the Krylovirinae family genus Phikmvvirus, and it had a latent period of 10 min and a burst size of 140 pfu/infected cell. In minks challenged with P. aeruginosa, phage ASP23 significantly reduced bacterial counts in the liver, lung, and blood. The whole-genome sequencing showed that its genome was a 42,735-bp linear and double-stranded DNA (dsDNA), with a G + C content of 62.15%. Its genome contained 54 predicted open reading frames (ORFs), 25 of which had known functions. The lysin of phage ASP23 (LysASP), in combination with EDTA, showed high lytic activity against P. aeruginosa L64. The holin of phage ASP23 was synthesized by M13 phage display technology, to produce recombinant phages (HolASP). Though HolASP exhibited a narrow lytic spectrum, it was effective against Staphylococcus aureus and Bacillus subtilis. However, these two bacteria were insensitive to LysASP. The findings highlight the potential of phage ASP23 to be used in the development of new antibacterial agents.

Detection and timely identification of power system disturbances are essential for situation awareness and reliable electricity grid operation. Because records of actual events in the system are limited, ensemble simulation-based events are needed to provide adequate data for building event-detection models through deep learning; e.g., a convolutional neural network (CNN). An ensemble numerical simulation-based training data set have been generated through dynamic simulations performed on the Polish system with various types of faults in different locations. Such data augmentation is proven to be able to provide adequate data for deep learning. The synchronous generators’ frequency signals are used and encoded into images for developing and evaluating CNN models for classification of fault types and locations. With a time-domain stacked image set as the benchmark, two different time-series encoding approaches, i.e., wavelet decomposition-based frequency-domain stacking and polar coordinate system-based Gramian Angular Field (GAF) stacking, are also adopted to evaluate and compare the CNN model performance and applicability. The various encoding approaches are suitable for different fault types and spatial zonation. With optimized settings of the developed CNN models, the classification and localization accuracies can go beyond 84 and 91%, respectively.