Machine learning for accelerating 2D flood models: Potential and challenges

Two-dimensional hydrodynamic models numerically solve full Shallow Water Equations (SWEs). Despite their high accuracy, these models have long simulation run times and therefore are of limited use for exploratory or real-time flood predictions. We investigated the possibility of improving flood modelling speed using Machine Learning (ML). We propose a new method that replaces the computationally expensive parts of the hydrodynamic models with simple and efficient data-driven approximations. Our hypothesis is that by integrating ML with physics-based numerical methods, we can achieve improved generalization performance: that is, the trained model for one case study can be used in other studies without the need for new training. We tested two ML approaches: for the first, we integrated curve fitting, and, for the second, artificial neural networks (ANN) with a finite volume scheme to solve the local inertial approximation of the SWEs. The data-driven models approximated the Momentum Equation, which explicitly solved the time derivative of flow rates. Water depths were then updated by applying a water balance equation. We also tested two different training datasets: the simulated dataset, generated from the results of hydrodynamic model, and the random dataset, generated by directly solving the momentum equation on randomly sampled input data. Various combinations of input features, for example, water slope and depth, were explored. The proposed models were trained in a small hypothetical case and tested in a different hypothetical and in two real case studies. Results showed that the curve-fitting method can be implemented successfully, given sufficient training and input data. The ANN model trained with a random dataset was substantially more accurate than that of the model trained with the simulated dataset. However, it was not successful in the real case studies. The curve-fitting method resulted in better generalization performance and increased the simulation speed of the local inertial model by 23%. Future research should test the performance of ML in terms of an increase in stable time step size and approximation of the full SWEs.     

A risk‐based life cycle cost strategy for optimal design and evaluation of control methods for nonlinear structures

The lack of direct correspondence between control objectives and hazard risks over the lifetime of systems is a key shortcoming of current control techniques. This along with the inability to objectively analyze the benefits and costs of control solutions compared with conventional methods has hindered widespread application of control systems in seismic regions. To address these gaps, this paper offers 2 new contributions. First, it introduces risk‐based life cycle–cost (LCC) optimal control algorithms, where LCC is incorporated as the performance objective in the control design. Two strategies called risk‐based linear quadratic regulator and unconstrained risk‐based regulator are subsequently proposed. The considered costs include the initial cost of the structure and control system, LCC of maintenance, and probabilistically derived estimates of seismic‐induced repair costs and losses associated with downtime, injuries, and casualties throughout the life of the structure. This risk‐based framework accounts for uncertainties in both system properties and hazard excitations and uses outcrossing rate theory to estimate fragilities for various damage states. The second contribution of this work is a risk‐based probabilistic framework for LCC analysis of existing and proposed control strategies. The proposed control designs are applied to the nonlinear model of a 4‐story building subjected to seismic excitations. Results show that these control methods reduce the LCC of the structure significantly compared with the status quo option (benefits of up to $1 351 000). The advancements offered in this paper enhance the cost‐effectiveness of control systems and objectively showcase their benefits for risk‐informed decision making.     

Reconstructing Regional Ionospheric Electron Density: A Combined Spherical Slepian Function and Empirical Orthogonal Function Approach

The computerized ionospheric tomography is a method for imaging the Earth’s ionosphere using a sounding technique and computing the slant total electron content (STEC) values from data of the global positioning system (GPS). The most common approach for ionospheric tomography is the voxel-based model, in which (1) the ionosphere is divided into voxels, (2) the STEC is then measured along (many) satellite signal paths, and finally (3) an inversion procedure is applied to reconstruct the electron density distribution of the ionosphere. In this study, a computationally efficient approach is introduced, which improves the inversion procedure of step 3. Our proposed method combines the empirical orthogonal function and the spherical Slepian base functions to describe the vertical and horizontal distribution of electron density, respectively. Thus, it can be applied on regional and global case studies. Numerical application is demonstrated using the ground-based GPS data over South America. Our results are validated against ionospheric tomography obtained from the constellation observing system for meteorology, ionosphere, and climate (COSMIC) observations and the global ionosphere map estimated by international centers, as well as by comparison with STEC derived from independent GPS stations. Using the proposed approach, we find that while using 30 GPS measurements in South America, one can achieve comparable accuracy with those from COSMIC data within the reported accuracy (1 × 10¹¹ el/cm³) of the product. Comparisons with real observations of two GPS stations indicate an absolute difference is less than 2 TECU (where 1 total electron content unit, TECU, is 10¹⁶ electrons/m²).     

In Situ Biotreatment of TBA with Recirculation/Oxygenation

The potential for in situ biodegradation of tert‐butyl alcohol (TBA) by creation of aerobic conditions in the subsurface with recirculating well pairs was investigated in two field studies conducted at Vandenberg Air Force Base. In the first experiment, a single recirculating well pair with bromide tracer and oxygen amendment successfully delivered oxygen to the subsurface for 42 d. TBA concentrations were reduced from approximately 500 μg/L to below the detection limit within the treatment zone and the treated water was detected in a monitoring transect several meters downgradient. In the second experiment, a site‐calibrated model was used to design a double recirculating well pair with oxygen amendment, which successfully delivered oxygen to the subsurface for 291 d and also decreased TBA concentrations to below the detection limit. Methylibium petroleiphilum strain PM1, a known TBA‐degrading bacterium, was detectable at the study site but addition of oxygen had little impact on the already low baseline population densities, suggesting that there was not enough carbon within the groundwater plume to support significant new growth in the PM1 population. Given favorable hydrogeologic and geochemical conditions, the use of recirculating well pairs to introduce dissolved oxygen into the subsurface is a viable method to stimulate in situ biodegradation of TBA or other aerobically degradable aquifer contaminants.     

Machine learning-based thermal anomalies detection from MODIS LST associated with the Mw 7.7 Awaran,Pakistan earthquake

Natural Hazards - Satellite based thermal anomaly occurs as a substantial precursor for strong earthquakes, as the need for earthquake precursor detection has very important for impending main...     

Experimental and numerical investigation for energy dissipation of supercritical flow in sudden contractions

Dealing with kinetic energy is one of the most important problems in hydraulic structures, and this energy can damage downstream structures. This study aims to study energy dissipation of supercritical water flow passing through a sudden contraction. The experiments were conducted on a sudden contraction with 15 cm width. A 30 cm wide flume was installed. The relative contraction ranged from 8.9 to 9.7, where relative contraction refers to the ratio of contraction width to initial flow depth. The Froude value in the investigation varied from 2 to 7. The contraction width of numerical simulation was 5~15 cm, the relative contraction was 8.9~12.42, and the Froude value ranged from 8.9~12.42. In order to simulate turbulence, the k-ε RNG model was harnessed. The experimental and numerical results demonstrate that the energy dissipation increases with the increase of Froude value. Also, with the sudden contraction, the rate of relative depreciation of energy is increased due to the increase in backwater profile and downstream flow depth. The experimentation verifies the numerical results with a correlation coefficient of 0.99 and the root mean square error is 0.02.     

Vibration screening by trench barriers,a review

This paper provides a review of various investigations concerned with vibration isolation using trench barriers and factors affecting their performance, also extracts design recommendations, because there is no exact conclusion of researches in this field. Vibrations induced by different sources can be seriously harmful to structures and occupants. Geometrical parameters, soil characteristics, and filling material properties can affect a barrier’s performance. Investigators have applied analytical approach, finite element, boundary element, experimental, and field studies to identify relevant factors. Various geometrical parameters affecting trench’s isolation level were examined, among which depth of trench was found to be the most important, but in most cases, the width of the trench and source-barrier distance have a low effect. Shear-wave velocity ratio of filling material and surrounding soil has the most significant role of all material properties. Using high-energy-absorbing materials can lead to better isolation. The majority of studies consider soil and filling material’s behavior to be elastic, so changes in loading amplitude have no effect on vibration reduction. Finally, among special cases in vibration isolation by trenches, non-rectangular and multiple ones found to be economically satisfying and well-isolating barriers.     

Is there a role for potential supervised injection facilities in Victoria,British Columbia,Canada?

Supervised injection facilities (SIFs) are medical facilities where injection drug users can inject their illicit drugs under the supervision of nurses and doctors. Currently, there is only one legal SIF in operation in North America and it has been operating in Vancouver, British Columbia for over a decade. The purpose of this study is to determine whether the current facility needs to be expanded to other locations in British Columbia, Canada. We employ mathematical modeling to estimate the number of new human immunodeficiency virus (HIV) and hepatitis C infections prevented based on the available secondary data. Additionally, we also estimate the number of prevented overdose deaths attributable to the SIF. With very conservative estimates, it is predicted that establishing two SIFs locations outside Vancouver in British Columbia’s capital city, Victoria, is cost-effective, with a benefit-cost ratio of 1.25:1. It appears that expanding SIFs to Victoria could offer significant savings for local health care institutions.     

利用支持向量分类(SVC)估算断层深度和特征选择(英文)

地下断层深度的估算是重力解释难题之一,我们试利用支持向量分类(SVC)法进行计算。使用正演和非线性反演技术,通过相关误错使检测地下断层深度成为可能。但必要有一个深度初始猜测值,而且这猜测值通常不是由重力资料得。本文我们介绍以SVC作为利用重力数据估算断层深度的一种手段。在这项研究中,我们假设一种地下断层深度可归为一种类型,SVC作为一个分类算法。为了有效地利用此SVC算法,我们基于一个正确的特征选择算法去选择正确的深度特征。本次研究中我们建立了一套基于不同深度地下断层的合成重力剖面训练集,用以训练用于计算实际的地下断层深度的SVC代码。然后用其它合成重力剖面训练集测试我们训练的SVC代码,同时也用实际资料验证了我们的训练SVC代码。     

Evaluation of Carcinogenic Risk Due to Accidental Ingestion of PAHs in Contaminated Soils

Polycyclic aromatic hydrocarbons (PAHs) are types of hazardous contaminants, which their ingestion could cause severe consequences on human health. Leakages from storage tanks, underground pipelines, and evaporation ponds are the main sources of soil and groundwater contaminations at the Tehran Oil Refinery area (TOR site), located in south of Tehran, Iran. In this study, soil samples were collected from different locations at and adjacent to a polluted stream in the south of the refinery. The samples were analyzed for two hazardous PAH compounds, namely benzo[a]anthracene and acenaphthene. The clean up levels due to the accidental ingestion of contaminated soils at the site were also investigated in accordance to the U.S.EPA guidelines. Comparing the soil analysis results indicated that the benzo[a]anthracene concentrations in the samples varied from 53 to 299 mg/kg, which were higher than the clean up level of 1.17 mg/kg. Thus, soil remediation is required for this contaminant. The acenaphthene analysis results denoted that the average concentration of this contaminant was below the clean up level of 116.67 mg/kg, indicating that no treatment for this contaminant is necessary at the TOR site. Also, because the slope of the ground extends to the south of the stream, which stimulates the migration of the contaminants in this direction due to advection and dispersion mechanisms, the average of benzo[a]anthracene concentrations in south samples was higher than north samples (i.e., C_avg(S) = 160 ppm, C_avg(N) = 113 ppm). Various treatment techniques such as thermal desorption, soil vapor extraction (SVE), and solidification/stabilization (S/S) were investigated for this site. Due to moderate to high plasticity and relatively low permeability of the soil and low volatility of benzo[a]anthracene, however S/S method is recommended as a practical approach for the remediation of the soil at the site.