The cohesion and internal friction angle of loess are important macro-mechanical parameters for evaluating the safety and stability of engineering construction. Traditional laboratory measurement methods are time-consuming and difficult to conduct on-site. This study aims to compare the effectiveness of five Machine Learning (ML) methods, namely Random Forest (RF), Support Vector Machine (SVM), Back Propagation Neural Network (BPNN), BPNN optimized by Particle Swarm Optimization (PSO-BPNN) and BPNN optimized by Genetic Algorithm (GA-BPNN), in predicting the macro-mechanical properties of loess. To this end, the study collected data from 89 undisturbed loess samples and 229 remolded loess samples to construct training and testing datasets, and used three correlation analysis methods to analyze the influence of physical parameters on mechanical properties. The study found that the water content has the most significant impact on the mechanical properties of loess. In terms of prediction ability, SVM performs the best among the ML methods used, and the determination coefficient for cohesion of undisturbed loess reaches 0.857. Although the training data is limited, the prediction performance of BPNN is significantly improved after being optimized by PSO or GA. The research results show that ML provides an effective way to study the complex mechanical behavior of loess.

Assessment of seismic deformations of geosynthetic reinforced soil (GRS) walls in literature has dealt with unsolved challenges, encompassing time-consuming analyses, lack of probabilistic-based analyses, ignored inherent uncertainties of seismic loadings and limited investigated scenarios of these structures, especially for tall walls. Hence, a novel multiple analysis method has been proposed, founded on over 257,400 machine learning simulations (trained with 1582 finite element method analyses) and numerous performance-based fragility curves, to promptly evaluate the seismic vulnerability. The conducted probabilistic parametric study revealed that simultaneously considering several intensity measures for fragility curves is inevitable, preventing engineering judgement bias (up to 52% discrepancies in damage possibilities). Up to 75% contrasts between failure possibilities of 8 and 20 m walls, especially under earthquakes with common intensities (e.g. PGA <= 0.3g), raised serious concerns in the application of height-independent designing methods of GRS walls (e.g. AASHTO Simplified Method). Decreases in deformation possibilities were nearly the same due to increasing reinforcement stiffness (J) (1000 to 2000 kN/m) and reinforcement length to wall height ratio (L/H) (0.8 to 1.5); a decisive superiority of J variations over increasing L/H, as a remedial plan. The proposed methodology privileges engineers to swiftly assess the seismic deformations of multiple GRS walls at the design stage.

Voronoi tessellations are a mathematical concept that appears in many examples in nature, such as the skin of giraffes, dry soil, and vegetable cells. In the context of biomimicry, these tessellations have been used to build impressive structures worldwide that are both aesthetically pleasing and structurally efficient. This paper proposes a methodology based on genetic algorithms (GA) to determine the structural topology of Voronoi flat roofs with tubular steel cross sections and a given boundary. The design variables correspond to the number and position of the Voronoi centers that form the tessellations within the roof, as well as the dimensions of the structural elements. This representation of the design variables creates an unstructured optimization problem. Such characteristic is addressed by an implicit redundant representation of possible solutions, which generates chromosomes with varying numbers of variables. The objective function relates to the weight of the roof, considering constraints raised in technical and constructive issues. The methodology was applied to four different roof boundaries: triangular, pentagonal, square, and rhombic. In general, the results provide optimal aesthetic solutions with a few Voronoi tessellations, based on the algorithm configuration and the multimodal nature of the search space. Convergence analysis indicates the possibility of the algorithm getting stuck in an optimum local and shows the progressive reduction of Voronoi centers. Lastly, it is observed that the maximum displacement constraint leads to the shape of the optimal roof.

Global climate change and permafrost degradation have significantly heightened the risk of geological hazards in high-altitude cold regions, resulting in severe casualties and property damage, particularly in the Qinghai-Tibet Plateau of China. To mitigate the risk of geological disasters, it is crucial to identify the primary disaster-inducing factors. Therefore, to address this issue more effectively, this study proposes a spatiotemporal-scale approach for detecting disaster-inducing factors and investigates the disaster-inducing factors of geological hazards in high-altitude cold regions, using the Kanchenjunga Basin as a case study. As the world's third-highest peak, Kanchenjunga is highly sensitive to climate fluctuations. This study first integrates the frost heave model and multitemporal interferometric synthetic aperture radar techniques to monitor ascending and descending track line-of-sight deformation of the frozen active layer in the study area. Subsequently, the surface parallel flow constrained model is employed to decompose the 3-D time-series deformation of geological hazards in the basin, with remote sensing imagery and field surveys used to identify a total of 94 disaster sites. In parallel, a database of potential conditioning factors is constructed by leveraging Google Earth Engine remote sensing inversion technology and relevant data provided by the China Geological Survey. Finally, by integrating monitoring results with a database of potential geological conditioning factors, the spatiotemporal-scale approach for detecting disaster-inducing factors proposed in this study is applied to investigate the disaster-inducing factors in the Kanchenjunga Basin. The research results highlight that surface temperature is the primary driving factor of geological hazards in the Kanchenjunga Basin. This research helps bridge the data gap in the region and offers critical support for local government decision-making in disaster prevention, risk assessment, and related areas.

Aerosols affect Earth's climate both directly and indirectly, which is the largest uncertainty in the assessment of radiative forcings affecting anthropogenic climate change. The standard Aerosol Robotic Network (AERONET) aerosol products have been widely used for more than 30 years. Currently, there is strong community interest in the possibility of determining aerosol composition directly from remote sensing observations. This work presents the results of applying such a recently developed approach by Li et al. to extended datasets of the directional sky radiances and spectral aerosol optical depth (AOD) measured by AERONET for the retrievals of aerosol components. First, the validation of aerosol optical properties retrieved by this component approach with AERONET standard products shows good agreement. Then, spatiotemporal variations of the obtained aerosol component concentration are characterized globally, especially the absorbing aerosol species (black carbon, brown carbon, and iron oxides) and scattering aerosol species (organic carbon, quartz, and inorganic salts). Finally, we compared the black carbon (BC) and dust column concentration retrievals to the Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2), products in several regions of interest (Amazon zone, Desert, and Taklamakan Desert) for new insights on the quantitative assessment of MERRA-2 aerosol composition products (R = 0.60-0.85 for BC; R = 0.75-0.90 for dust). The new value-added and long-term aerosol composition product globally is available online (https://doi.org/10.6084/ m9.figshare.25415239.v1), which provides important measurements for the improvement and optimization of aerosol modeling to enhance estimation of the aerosol radiative forcing. SIGNIFICANCE STATEMENT: In the assessment of climate change, the uncertainty associated with aerosol radiative forcing is the largest one. The purpose of this study is to provide a new value-added and long-term aerosol composition (including absorbing and scattering aerosol species) inversion dataset derived from Aerosol Robotic Network (AERONET) measurements for characterizing their spatiotemporal variations at global scale. We find some new insights on the quantitative assessment of black carbon and dust column concentration products in the Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2). Our results and aerosol composition inversion dataset will provide robust support for the overall improvement and optimization of aerosol modeling to better understand the aerosol radiative forcing.

Rice is the primary grain crop in China, and the quality of rice is closely related to the external environment, such as soil characteristics, climate, sunshine time, and irrigation water. The high-quality rice-origin area has certain regional limitations. Therefore,the rice can be seen as an apparent geographical marker. There are often some counterfeits or branded famous high-quality rice in the market, which can damage the rice brand, reduce the rice quality guarantee of consumers, and disturb the market stability, so rapid identification technology of rice origin is needed. The rice origin identification models of five sources in Jilin Province (Daan, Gongzhuling, Qianguo, Songyuan and Taoerhe) are done by laser-induced breakdown spectroscopy and machine learning algorithms. The principal component analysis (PCA) algorithm, combined with four machine learning algorithms, Bagged Trees, Weighted KNN, Quadratic SVM, and Coaster Gaussian SVM, has been established. A total of 450 groups of LIBS data are selected. The spectral data of rice LIBS are pretreated with Savitzky-Golay smoothing (SG smoothing) is used for noise reduction and normalisation. The principal component analysis uses the rice LIBS data, which shows that the rice origins had an excellent cluster distribution of clustering spaces. Still, there is spatial overlap in some rice origins. Utilising5x cross-validation, the identification accuracy of rice origins can reachmore than 91.8% by adopting PCA-Bagged Trees, PCA-Weighted KNN, PCA-Quadratic SVM and PCA-Coarse Gaussian SVM, and the recognition accuracy of PCA-Quadratic SVM model is as high as 97.3%. The results show that the combination of LIBS technology and machine learning algorithms can identify rice origin with high precision and high efficiency.

New flood records are being set across the world as precipitation patterns change due to a warming climate. Despite the presence of longstanding water management infrastructure like levees and reservoirs, this rise in flooding has been met with property damage, loss of life, and hundreds of billions in economic impact, suggesting the need for new solutions. In this work, the authors suggest the active management of distributed networks of ponds, wetlands and retention basins that already exist across watersheds for the mitigation of flood damages. As an example of this approach, we investigate optimal control of the gated outlets of 130 such locations within a small watershed using linear programming, genetic algorithms, and particle swarm optimization, with the objective of reducing downstream flow and maximizing basin storage. When compared with passive operation (i.e., no gated outlets) and a uniformly applied active management scheme designed to store water during heavy rainfall, the optimal control techniques (1) reduce the magnitudes of peak flow events by up to 10%, (2) reduce the duration of flood crests for up to several days, and (3) preserve additional storage across the watershed for future rainfall events when compared with active management. Combined, these findings provide both a better understanding of dynamically controlled distributed storage as a flood fighting technique and a springboard for future work aimed at its use for reducing flood impacts.

The epicentral region of earthquakes is typically where liquefaction -related damage takes place. To determine the maximum distance, such as maximum epicentral distance (Re), maximum fault distance (Rf), or maximum hypocentral distance (Rh), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (Re, Rf, or Rh) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short -Term Memory), BiLSTM (Bidirectional Long Short -Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

Biological soil stabilization through Microbial-Induced Calcite Precipitation ( MICP ) demonstrates the potential to be an eco-friendly and sustainable approach to enhance the strength properties of cohesionless granular soils. In this study, based on a comprehensive set of experimental data compiled from literature, the amounts of Precipitated Calcium Carbonate ( PCC ) and Unconfined Compressive Strength ( UCS ) of MICP -treated sands are estimated through hybridizing Artificial Neural Network ( ANN ) and Adaptive Neuro-Fuzzy Inference System ( ANFIS ) models with metaheuristic algorithms. During the data extraction procedure, a total of 70 and 115 datasets are used to predict the PCC and UCS , respectively. Accordingly, five key features of urea concentration ( M u ), calcium chloride ( M cc ), optical density of bacterial suspension ( OD 600 ), pH and total volume of injection per volume of sample ( V t ), are first selected as the inputs of the hybrid models to estimate the amount of calcium carbonate precipitation within the porous structure of MICP -treated granular medium. The experimental data on the PCC along with the basic characteristics of the host sand including mean grain size ( D 50 ), uniformity coefficient ( C u ) and void ratio ( e ), are then adopted as the inputs of the numerical models in the second phase whilst the UCS of bio-mediated sands is set as the output. The performance and accuracy of implemented models are rigorously assessed through analyzing various statistical indices and performance criteria. According to the numerical analysis, the ANN - PSO and ANFIS - PSO hybrid models show the best performance in predicting PCC and UCS of bio-mediated sands, respectively. Using the well-established Gene Expression Programming ( GEP ) algorithm, practical correlations are developed to predict the PCC and UCS values of MICP -mediated soils based on the characteristics of biological binding agents as well as the host material. The Machine Learning ( ML )-based models presented in this study provide engineers with a fruitful framework for the rough and preliminary estimation of the amount of calcite precipitation as well as the UCS of bio-mediated sands in the field prior to stabilization and performing complementary tests.

Featured Application Python application that uses data science and machine learning to estimate the main properties of acid tars. Its main advantage is that determinations for acid tar properties are no longer necessary, thus saving time and money. However, good machine learning estimations are highly dependent on the number and quality of the training data, meaning that the larger and more consistent the training database, the better the estimations.Abstract Hazardous petroleum wastes are an inevitable source of environmental pollution. Leachates from these wastes could contaminate soil and potable water sources and affect human health. The management of acid tars, as a byproduct of refining and petrochemical processes, represented one of the major hazardous waste problems in Romania. Acid tars are hazardous and toxic waste and have the potential to cause pollution and environmental damage. The need for the identification, study, characterization, and subsequently either the treatment, valorization, or elimination of acid tars is determined by the fact that they also have high concentrations of hydrocarbons and heavy metals, toxic for the storage site and its neighboring residential area. When soil contamination with acid tars occurs, sustainable remediation techniques are needed to restore soil quality to a healthy production state. Therefore, it is necessary to ensure a rapid but robust characterization of the degree of contamination with hydrocarbons and heavy metals in acid tars so that appropriate techniques can then be used for treatment/remediation. The first stage in treating these acid tars is to determine its properties. This article presents a software program that uses machine learning to estimate selected properties of acid tars (pH, Total Petroleum Hydrocarbons-TPH, and heavy metals). The program uses the Automatic Machine Learning technique to determine the Machine Learning algorithm that has the lowest estimation error for the given dataset, with respect to the Mean Average Error and Root Mean Squared Error. The chosen algorithm is used further for properties estimation, using the R2 correlation coefficient as a performance criterion. The dataset used for training has 82 experimental points with continuous, unique values containing the coordinates and depth of acid tar samples and their properties. Based on an exhaustive search performed by the authors, a similar study that considers machine learning applications was not found in the literature. Further research is required because the method presented therein can be improved because it is dataset dependent, as is the case with every ML problem.