This paper adopts two modeling tools, namely, multiple linear regression (MLR) and artificial neural networks (ANNs), to predict the concentrations of heavy metals (zinc, boron, and manganese) in surface waters of the Oued Inaouen watershed flowing towards Inaouen, using a set of physical-chemical parameters. XLStat was employed to perform multiple linear and nonlinear regressions, and Statista 10 was chosen to construct neural networks for modeling and prediction. The effectiveness of the ANN- and MLR-based stochastic models was assessed by the determination coefficient (R²), the sum squared error (SSE) and a review of fit graphs. The results demonstrate the value of ANNs for prediction modeling. Drawing on supervised learning and back propagation, the ANN-based prediction models adopt an architecture of [18-15-1] for zinc, [18-11-1] for manganese, and [18-8-1] for boron, and perform effectively with a single cached layer. It was found that the MLR-based prediction models are substantially less accurate than those based on the ANNs. In addition, the physical-chemical parameters being investigated are nonlinearly correlated with the levels of heavy metals in the surface waters of the Oued Inaouen watershed flowing towards Inaouen.

The primary way to design building structures refers to the stationary loads specified by the governing laws. However, the load pattern does not guarantee the appropriateness of the seismic design. To make matters worse, old or ancient structures are traditionally reinforced for gravitational loads. This study reveals that the traditional reinforcement, in most cases, harms the seismic performance of buildings. The authors introduced the approach of most computer programs for seismic design, along with their limitations. Then, the ancient Roman approach was explained, and the reasons for the survival of many of these ancient structures were exposed thoroughly. After that, classical advices were summarized briefly for good seismic design of structures and reinforcement. Finally, a few classical mistakes were identified in reinforcement design.

In view of the limitations of traditional InSAR technology in selecting stable target point for orbit refining and surface subsidence inversion in complicated mining area, this paper proposes a time-series InSAR mining area subsidence monitoring method based on the fusion of multi threshold targets. On the basis of the traditional technology, the deviation threshold parameters, the regional window threshold parameters and the coherence threshold parameters are set to extract the relatively stable target points on the ground. Applying this method and traditional InSAR method to practical cases, the monitoring results of surface subsidence in the study area are obtained and verified. The results show that: (1) there are three mining subsidence areas in the mining area, the maximum annual average subsidence rate is -156 mm/a, and the maximum subsidence is -376 mm. Compared with the optical image data, the location of the mining subsidence area is consistent with the mining work area of the coal mine; (2) The absolute average difference of subsidence in the mining area using the two methods shall not exceed 12 mm. It shows that the InSAR method of fusing multi threshold targets can not only effectively overcome the limitations of traditional InSAR, but also ensure high accuracy, and has more advantages in the monitoring of surface subsidence in mining areas.

This work completes the thorough petrophysical interpretation of 46 wells, as well as a technical feasibility analysis. Even though the acoustic logging was of very poor quality, work was done to get it ready for use in creating synthetic seismograms that accurately represented the section. The sle.28 Karagie Severny, which was drilled in 2012 and has significantly better GIS quality, was used to control this operation. Through a dynamic analysis, the shooting system's (footprint) influence on the distribution of the amplitudes at the Karagie Severny site was not eliminated during data processing, but it was removed during the re-processing. As a result, the findings for Karagie Severny should be taken with a grain of salt because the initial data's quality was not considered when choosing the sites for the suggested wells. However, the seismic facies analysis in two forms—classical and cluster—showed the presence of at least three primary facies complexes, which are reflected in both formed, with a more precise distribution in accordance with cluster analysis.

The overuse of natural resources by humanity in recent decades has resulted in noticeable changes environment quality. Global environmental research is particularly interested in the topics of land use change and land cover. The Republic of Serbia has a diverse spectrum of landforms, with agricultural use taking up the largest portions, followed by forestry, water, and building land. Significant anthropogenic pressures (such as mining, deforestation, urbanization, and uncontrolled land use, among other things) have harmed Serbia's natural resources over the past two decades. This study examines the causes of specific trends in land-use change in Serbia, utilizing the CORINE Land Cover (CLC) database to track temporal and spatial changes in the major categories of land use and land cover from 1990 to 2018. The authors explained that focusing on the rational use of natural resources is the only way to promote sustainable development, legal alignment with EU law, and prompt adoption of harmonized laws and planning documents across all sectors.

The development of railways brings many positive externalities, such as the expansion of built environment, the growth of feeder roads, the rise of passenger mobility, and the creation of economic opportunities for locals. In the meantime, the railway transport system exerts some negative externalities on environmental sustainability, which intensifies climate change. This paper assesses the negative externalities of railway transport through the changing dynamics of the normalized difference vegetation index (NDVI) and fractional vegetation cover (FVC). The spatial regression model was calibrated to understand the degree of these externalities. In addition, a prediction model was constructed based on machine learning techniques like cellular automata and Markov chain. The study reveals that the development of railway stations in Tripura, India has significant negative externalities on the environment.

Due to a number of circumstances, grain depots will emit exhaust gases that are harmful to the environment and the health of the surrounding population in addition to being complex in composition and challenging to manage. In order to cope with environmental exhaust gases, this work integrates microbial spray filtering with an exhaust gas treatment equipment. The authors ran simulations of the mixture of exhaust gases and the microbial solution using COMSOL Multiphysics at various pipe diameters, initial nozzle distances, nozzle number, and nozzle intervals. The findings indicate that the pipe diameter should be 300mm, the starting nozzle distance should be 290mm, there should be five nozzles, and the nozzle interval should be 200mm to obtain the optimal mixing of exhaust gases and the microbial solution. The study offers a useful guide for microbial deodorization.