Exploring the best sequence LSTM modeling architecture for flood prediction

Neural Computing and Applications - Accurate and efficient models for rainfall–runoff (RR) simulations are crucial for flood risk management. Recently, the success of the recurrent neural...     

Stimulating the anaerobic biodegradation of explosives by the addition of hydrogen or electron donors that produce hydrogen

The anaerobic biodegradation of hexahydro-1,3,5-trinitro-1,3,5-triazine (RDX), octahydro-1,3,5,7-tetranitro-1,3,5,7-tetrazocine (HMX), and 2,4,6-trinitrotoluene (TNT) by a methanogenic mixed culture was investigated. Microcosms containing a basal medium and the mixed culture were amended with ethanol, propylene glycol (PG), butyrate or hydrogen gas as the electron donor and a mixture of TNT (50 microM), RDX (25 microM), and HMX (8 microM). After 29 days TNT and RDX were completely transformed to unidentified endproducts in the bottles amended with ethanol, hydrogen, or PG, while 53%, 40%, and 22% of the HMX was transformed, respectively. There was no loss of RDX or HMX in the electron donor unamended control bottles. The ethanol and PG were transformed to near stoichiometric amounts of acetate and propionate, suggesting the immediate electron donor supporting the transformation of the explosives was the H2 evolved during the metabolism of the parent substrate. Our findings suggest that the addition of H2 or electron donors that produce H2 may be a useful strategy for enhancing the anaerobic biodegradation of explosives in contaminated groundwater and soils.     

Morphology-based approaches for detecting stream channels from ALSM data

To map the Earth's surface at remarkable resolution, Airborne Laser Swath Mapping (ALSM) instrument technology and subsequent algorithms have been used over the last several years. Since forested watersheds have commonly been problematic to study with remote sensing techniques, the ability of ALSM technology to densely sample ground elevations beneath forest canopies is especially considerable. Stream network detection from digital elevation models (DEMs) is a key role in modelling spatially distributed hydrological processes. To detect stream channels, we have developed two approaches. The first approach is based on an encoding of mathematical morphological operators. In the second approach, a composition of geodesic top-hat and bot-hat operations of different sizes is used in order to build a morphological profile (P _M) that records the image structural information. The two proposed methods perform well in terms of detection results and classification accuracies. The second approach is more general than the first, but it also requires training and more computation.     

Accelerating Machine-Learning Algorithms on FPGAs using Pattern-Based Decomposition

Machine-learning algorithms are employed in a wide variety of applications to extract useful information from data sets, and many are known to suffer from super-linear increases in computational time with increasing data size and number of signals being processed (data dimension). Certain principal machine-learning algorithms are commonly found embedded in larger detection, estimation, or classification operations. Three such principal algorithms are the Parzen window-based, non-parametric estimation of Probability Density Functions (PDFs), K-means clustering and correlation. Because they form an integral part of numerous machine-learning applications, fast and efficient execution of these algorithms is extremely desirable. FPGA-based reconfigurable computing (RC) has been successfully used to accelerate computationally intensive problems in a wide variety of scientific domains to achieve speedup over traditional software implementations. However, this potential benefit is quite often not fully realized because creating efficient FPGA designs is generally carried out in a laborious, case-specific manner requiring a great amount of redundant time and effort. In this paper, an approach using pattern-based decomposition for algorithm acceleration on FPGAs is proposed that offers significant increases in productivity via design reusability. Using this approach, we design, analyze, and implement a multi-dimensional PDF estimation algorithm using Gaussian kernels on FPGAs. First, the algorithm’s amenability to a hardware paradigm and expected speedups are predicted. After implementation, actual speedup and performance metrics are compared to the predictions, showing speedup on the order of 20× over a 3.2 GHz processor. Multi-core architectures are developed to further improve performance by scaling the design. Portability of the hardware design across multiple FPGA platforms is also analyzed. After implementing the PDF algorithm, the value of pattern-based decomposition to support reuse is demonstrated by rapid development of the K-means and correlation algorithms.     

Strategies for stationary and portable fuel cell markets

In the future, hydrogen-based stationary and portable fuel cell systems can help supply some or all of the power demanded with additional advantages of higher reliability, lower emissions, independence from the general grid, and cogeneration capability. In order to understand how to prepare the future for this technology, this paper describes a thorough investigation of past alternative stationary and portable power projects in order for an assessment of the opportunities for stationary and portable fuel cell markets, as well as interactions with transportation hydrogen systems. The lessons learned from the programs are used to establish best practices and recommendations for a hydrogen strategy that addresses opportunities for hydrogen in power generation systems, as well as to make recommendations for market transformation within the hydrogen fuel cell industry.     

A Performance Comparison of Continuous and Discontinuous Finite Element Shallow Water Models

We present a comparative study of two finite element shallow water equation (SWE) models: a generalized wave continuity equation based continuous Galerkin (CG) model—an approach used by several existing SWE models—and a recently developed discontinuous Galerkin (DG) model. While DG methods are known to possess a number of favorable properties, such as local mass conservation, one commonly cited disadvantage is the larger number of degrees of freedom associated with the methods, which naturally translates into a greater computational cost compared to CG methods. However, in a series of numerical tests, we demonstrate that the DG SWE model is generally more efficient than the CG model (i) in terms of achieving a specified error level for a given computational cost and (ii) on large-scale parallel machines because of the inherently local structure of the method. Both models are verified on a series of analytic test cases and validated on a field-scale application.     

Tungsten Lamps as an Affordable Light Source for Testing of Photovoltaic Cells

An improved Tungsten light source system for photovoltaic cell testing made from low-cost, commercially available materials is presented as an alternative to standard expensive testing equipment. In this work, spectral correction of the Tungsten light source is achieved by increasing the color temperature to ??5200 K using inexpensive commercially available filters. Spectral measurements of the enhanced light source reveal that a better spectrum match towards the solar spectrum is achieved than what has been previously demonstrated. Specifically, the improved solar spectrum match is achieved by substantial filtering of the infrared range. The proposed setup is used to evaluate the performance of both silicon and organic based photovoltaic cells.     

Ecological Restoration of Novel Lake Districts: New Approaches for New Landscapes

Mine void pit lakes often contain water of poor quality with potential for environmental harm that may dwarf other mine closure environmental issues in terms of severity, scope, and longevity. This is particularly so when many pit lakes occur close together and thus form a new “lake district” landscape. Pit lakes that can be developed into healthy lake or wetland ecosystems as a beneficial end use provide opportunities for the mining industry to fulfil commitments to sustainability. Clearly articulated restoration goals and a strategic closure plan are necessary to ensure pit lake restoration toward a new, yet regionally-relevant, aquatic ecosystem, which can achieve sustainability as an out-of-kind environmental offset. Such an approach must also consider obstacles to development of a self-sustaining aquatic ecosystem, such as water quality and ecological requirements. We recommend integration of pit lakes into their catchments as a landscape restoration planning exercise with clearly-identified roles and objectives for each new lake habitat and its surrounds.     

Use of the lognormal distribution for the coefficients of friction and wear

To predict the reliability of a system, an engineer might allocate a distribution to each input. This raises a question: how to select the correct distribution? Siddall put forward an evolutionary approach that was intended to utilise both the understanding of the engineer and available data. However, this method requires a subjective initial distribution based on the engineer's understanding of the variable or parameter. If the engineer's understanding is limited, the initial distribution will be misrepresentative of the actual distribution, and application of the method will likely fail. To provide some assistance, the coefficients of friction and wear are considered here. Basic tribology theory, dimensional issues and the central limit theorem are used to argue that the distribution for each of the coefficients will typically be like a lognormal distribution. Empirical evidence from other sources is cited to lend support to this argument. It is concluded that the distributions for the coefficients of friction and wear would typically be lognormal in nature. It is therefore recommended that the engineer, without data or evidence to suggest differently, should allocate a lognormal distribution to the coefficients of friction and wear.     

Effect of various heat treatments on plasminogen activation in bovine milk during refrigerated storage

Plasmin and plasminogen‐derived plasmin activities were measured in heated milk with and without the addition of plasminogen activator, before and after storage at 4 °C for 96 h. The effect of a free sulfhydryl group donor, β‐lactoglobulin or cysteine, on plasminogen activation was investigated in a model system and milk. Heating milk to 75 °C enhanced plasminogen activation that was marked by a considerable increase in plasmin activity. Heating at 85 and 90 °C caused a significant decrease in plasmin and plasminogen‐derived plasmin activities. However, after storage, significant plasmin levels were restored because of the activation of remaining unfolded plasminogen. Both β‐lactoglobulin and cysteine significantly decreased plasmin and plasminogen‐derived plasmin activities in a model system. While endogenous β‐lactoglobulin was not sufficient to completely eliminate plasminogen activation in milk, cysteine addition prior to pasteurisation significantly decreased plasmin and plasminogen‐derived plasmin activities. Results highlighted the importance of the remaining plasminogen in heated milk systems.