Hazardous waste from metal processing industries increases heavy metal contamination in ecosystems, threatening environmental health and regional sustainability. This study suggests a resilient and human-centered environmental monitoring approach that incorporates machine learning and decision analytics to address these challenges in line with Industry 5.0's goals. By utilising a PRINCIPAL COMPONENT REGRESSION (PCR)-based predictive model, the approach addresses variability in environmental data, predicting levels of heavy metals like lead, zinc, nickel, arsenic, and cadmium, frequently beyond regulatory thresholds. The suggested PCR-based model outperforms conventional models by lowering mean absolute error (MAE) to 2.9339, mean absolute percentage error (MAPE) to 0.0358, and nearly the same mean square error (MSE). This study introduces a more interpretable and computationally efficient alternative to existing predictive models by introducing a novel integration of PCR with machine learning for environmental monitoring. By predicting and optimising environmental outcomes, validation against test datasets confirmed its ability to optimise impurity control. After process adjustments, the average concentrations of lead, nickel, and cadmium were reduced from 13.23 to 11.26 mg/L, 2.83 to 2.70 mg/L, and 2.15 to 1.88 mg/L, respectively. This research supports sustainability, resilience, and decisionmaking aligned with Industry 5.0, offering scalable solutions and insights for global industries.HighlightsChemical plants' environmental risk is evaluated using a machine learning algorithmFor better monitoring, the PCR method forecasts process variables and interactionsIt identifies the key factors that affect the environmental risks in soil and waterAs a result, the local ecosystem's levels of toxic metals have notably decreasedInsights for managing environmental risks aligned with Industry 5.0 principles

There is a significant variability of salinity level in sensitive marine clays (SMC), which will produce an important impact on the development of mechanical characteristics in stabilized SMC. The influences of salt content (NaCl salt: 3, 10, and 20 g/L) on mechanical properties evolution of cement-stabilized SMC under different curing time (1, 7, 28, 60, and 90 days) have been experimentally investigated and modeled. The results indicate that the strength and modulus increase constantly with time but the time rates decrease. Meanwhile, the apparent improvement of strength and modulus at early age (up to 7 days) is observed. Higher NaCl content can bring a larger strength gain to stabilized SMC after same curing time and the enhancing effect of high salt contents (10 and 20 g/L) becomes more obvious with the extension of curing time. Whereas, the enhancing effect of high NaCl content on modulus is limited compared with strength. Further improvement provided by excessive NaCl salt (20 g/L) is not as effective. In addition, the predictive models have been established to quantitatively evaluate the evolution of mechanical properties in stabilized SMC with different NaCl contents. The capability of developed models has been demonstrated through the good agreement between simulated and experimental results.

Global warming accelerates permafrost degradation, compromising the reliability of critical infrastructure relied upon by over five million people daily. Additionally, permafrost thaw releases substantial methane emissions due to the thawing of swamps, further amplifying global warming and climate change and thus posing a significant threat to more than eight billion people worldwide. To mitigate this growing risk, policymakers and stakeholders need accurate predictions of permafrost thaw progression. Comprehensive physics-based permafrost models often require complex, location-specific fine-tuning, making them impractical for widespread use. Although simpler models with fewer input parameters offer convenience, they generally lack accuracy. Purely data-driven models also face limitations due to the spatial and temporal sparsity of observational data. This work develops a physics-informed machine learning framework to predict permafrost thaw rates. By integrating a physics-based model into machine learning, the framework significantly enhances the feature set, enabling models to train on higher-quality data. This approach improves permafrost thaw rate predictions, supporting more reliable decision-making for construction and infrastructure maintenance in permafrost-vulnerable regions, with a forecast horizon spanning several decades.

Management of perennial weeds has become increasingly difficult with the reduction of herbicide use. Creeping perennials accumulate reserves in specialized belowground organs from which they regenerate new plants after a disturbance. Through tool selection, tillage operations could be optimized to reduce perennial-weed reserves and limit regeneration. In the present study, the effect of five tools on the fragmentation of the creeping roots of Cirsium arvense (L.) Scop. (Canada thistle), a major perennial weed in arable crops, were analysed. A field trial was set up to measure the lengths of the root fragments left after tillage. Five tools were tested: mouldboard ploughing, rotary harrow, disc harrow, rigid-tine cultivator and goose-foot cultivator. Fragment-length distribution varied according to the tool: rotary harrow left the smallest (3.7 cm on average) and least variable fragment lengths, mouldboard ploughing the longest (12.7 cm) and most variable ones. The other tools produced intermediate-sized fragments (8-10 cm). Based on these results and literature, a model was proposed to predict perennial-weed regeneration probability from storage-organ fragments after one tillage run. The effects of six factors, which were agronomic (tillage tool), environmental (soil conditions and temperature) and biological (storage-organ fragment diameter, maximal belowground-shoot length and pre-tillage storage-organ distribution), were tested through a sensitivity analysis. According to the model, the probability of fragment regeneration success is lower for the rotary harrow than for the mouldboard plough. The most important drivers of fragment regeneration success were the biological traits: fragment diameter and maximal belowground-shoot length per unit fragment biomass. The present model should be complemented to predict the effect of tillage on perennial-weed regrowth and help improving non-chemical weed-management strategies. To achieve this, further research is needed on plant regrowth potential from storage organs and their architecture in the soil.

Concrete structures in saline soil regions are prone to degradation due to chloride and sulfate erosion, compounded by the concurrent infiuences of drying, high and low temperatures, and freeze-thaw cycles. This study establishes a simulation test system for complex saline soil environments, integrating findings from real-world environmental investigations. The investigation focused on the degradation mechanism of concrete under the combined impacts of dry-wet and high-low temperature cycles, coupled with composite salt erosion. Additionally, the impacts of water-cement ratio, fiy ash content, and basalt fiber content on concrete's mechanical properties and ion erosion resistance were analyzed. The alterations in the internal pore structure of corroded concrete were examined through nuclear magnetic resonance (NMR) technology. Utilizing the XGBoost algorithm, a predictive model for chloride and sulfate ion concentrations in concrete, under the combined infiuence of dry-wet and high-low temperature cycles, coupled with composite salt erosion, was developed. The findings reveal that the rate of concrete deterioration is gradually accelerating under the combined erosion to dry-wet cycles, high-low temperature cycles, and composite salt. Optimal fiy ash and basalt fiber dosages for corrosion resistance are determined to be 10% and 0.10%, respectively. During advanced erosion stages, concrete porosity, capillary and macropore volume fractions increase, while gel pore volume fraction declines significantly. The XGBoost-based chloride and sulfate concentration prediction model demonstrates strong agreement with experimental measurements, yielding correlation indices of R2 = 0.98 and 0.97, respectively. Interpretation results obtained using SHAP from the machine learning model align with experimental outcomes.

Resilient modulus (Mr) is a fundamental mechanical property vital for assessing the resistance of pavement structures to cyclic vertical loads. It has played a pivotal role in pavement design and has been instrumental in predicting pavement responses and fatigue life. The Mr of subgrade soil is affected by a multitude of factors, including stress, moisture, and temperature conditions, all of which interact to define the response of the soil. This research investigated the effect of complex climatic conditions on Mr with a particular focus on areas experiencing significant seasonal changes in snowy cold regions like Hokkaido, Japan. Previous studies have proposed predictive models for Mr, incorporating the concept of matric suction, to account for moisture conditions. However, these models have rarely considered suction hysteresis in the soil-water characteristic curve (SWCC) or the effects of wheel loading on frost-susceptible subgrade soil during different seasons. In this study, a series of Mr tests were conducted on two types of subgrade soil under various climatic and wheel loading conditions. The test results promise to enhance our understanding of the complex interplay of climatic and stress conditions on Mr of standard sand and frost susceptible subgrade soil along different drying and wetting paths, particularly in regions with significant seasonal variations.

In seismic regions both in Iran and around the world, subterranean gas pipelines inevitably extend through highrisk areas prone to seismic landslides. The seismic landslide-pipe failure mechanism constitutes a continuum geomechanical challenge influenced by factors such as sliding mass configuration, pipe positioning relative to potential slope failure surfaces, and seismic input characteristics. In this study, response of steel pipeline buried in sand under seismic landslide action is analyzed by finite difference models using an advanced soil constitutive model. The numerical model is first validated based on the shaking table test results and then several dynamic analyses are performed using the selected records of the Iranian ground motions database. The outcomes of the dynamic analysis demonstrate that Arias Intensity (Ia) can be identified as an optimal intensity measure (IM) for predicting the seismic response of a slope-pipe system in terms of maximum pipe deflection, axial strain, and shear stress. Predictive models are then developed based on the optimal IM for estimating the pipe deflection, axial strain, and shear stress subjected to a seismic landslide. These proposed predictive models offer valuable insights for assessing the response of buried pipelines to seismic landslides in Iran within the framework of performance-based earthquake engineering.

A new numerical-based fragility relation for cast iron (CI) pipelines with lead-caulked joints subjected to seismic body-wave propagation is proposed in this article. Two-dimensional 1600-m-length finite element models for pipelines buried in sand are developed in OpenSees. Parametric analysis is performed to investigate the influence of various parameters on the damage estimates of the buried pipelines. Numerical analyses are conducted to estimate the repair rates (RR) for CI pipelines subjected to wave propagation. The predictive model for RR is thus developed based on the numerical results and the Gaussian Process Regression approach. The model developed employs four predictor variables, namely, the peak particle velocity and wave propagation velocity along axial direction, the maximum soil shear force per unit length, and the outer diameter of pipelines, exhibiting desirable performance in terms of predictive efficiency and generalization. The performance of the developed relation is compared to several existing fragility relations. The new fragility relation can be used to estimate RR for CI pipelines with lead-caulked joints with outer diameters ranging from 169 to 1554 mm subjected to seismic body-wave propagation.

Foundation settlement is a common problem in civil engineering. In the case of un-even settlement, it can lead to structural deformation and damage, which seriously affects the safety and reliability of the project. Therefore, the influence of adjusting the stiffness of the foundation on un-even settlement was analyzed through finite element analysis to effectively solve un-even settlement. By simulating the settlement of soil under different foundation stiffness and load conditions, the influence of foundation stiffness adjustment on soil deformation and settlement distribution was analyzed, and its impact on structural safety was evaluated. These studies confirmed that thickened layers could effectively solve the un-even settlement. Within the range of 0.2 to 1.0 meters, the difference in thickness was the greatest. The adjustment of differential settlement by layer thickness was phased and decreased with increasing thickness. Adjusting the stiffness of the foundation could effectively solve un-even settlement, reduce differences in soil settlement, and improve the overall stability and safety of the structure. These results have important guiding significance for the design of foundation and the solution of un-even settlement problems in engineering practice and provide certain reference and basis for further research.

This paper takes the representative buried structure in permafrost regions, a transmission line tower foundation, as the research object. An inverse prediction is conducted in a scaled-down experimental system mimicking actual heat conduction of the frozen ground in a tower foundation. In permafrost regions, global warming and the heat transfer through the buried structures bring significantly adverse thermal effects on the stability of the infrastructures. In modeling the thermal effects, it has been a challenge to determine the ground surface boundary condition and heat source strength from the buried structures due to the complex climate and environmental conditions. In this work, based on the improved model predictive inverse method with an adaptive strategy, an inverse scheme is successfully implemented to simultaneously identify the time-varying surface temperature and the time-space-dependent heat source representing the buried structures. In this scheme, an adaptive time-varying predictive model is established by the rolling update of the sensitivity response coefficients according to the predicted temperature field to overcome the influence of nonlinear characteristics in the heat transfer process. The inverse method is verified by simulation and experimental data. According to the experimental inversion results, the reconstructed temperature distribution efficiently predicts the thermal state evolution of the permafrost foundation under seasonal freezing and thawing. It is found that, under the experimental conditions, the intensified thawing and freezing are significantly severe, e.g., the increased area ratio of active layer thickness is as high as 28% after building a tower, and the depth of permafrost table ranges from about 14 mm to about 38 mm, which could be detrimental to the stability and safety of the tower foundation. This study will provide valuable guidance for risk assessments or optimizing the design and maintenance of the real tower foundation and similar buried structures.