Along with the increase in global pollution, every part of the urban system, including facilities for the transport of people and goods, is becoming increasingly interesting for the study. The first serious research into the impact of railway traffic on the environment appeared after the year 2000. So far, there have been few studies, the main shortcoming of which is a lack of understanding about pollutant migration. With this in mind, in this paper, an investigation and control of the railway track with regard to the presence, content and migration paths of heavy metals was provided. For the research purposes, X-ray fluorescence spectrometry and optical emission spectrometry with induced coupled plasma were used. It was found that the maximum allowable values were exceeded for cadmium, cobalt, copper, zinc, nickel, vanadium, barium, chromium and iron. In the course of determining the amount of these elements in the railway track, there was also evidence of significant metal infiltration into the lower layers. This indicated the ability of heavy metals to migrate, even through mechanically compacted soil. Detailed knowledge of these issues is of huge importance, which enables the selection of adequate techniques to prevent the migration of heavy metals into the lower layers of the ground and the surrounding soil, among which the elements of Low Impact Development technology stand out in recent years, which could find a very wide and effective application in railway engineering.

A number of current studies have revealed that during regular railway operations, different kinds of heavy metals accumulate on the track and in the railway body. Cadmium stands out among pollutants, both in terms of the amount of excess and in terms of the severe harm it causes to human life and health. In the first place, the study discusses existing methodologies for detecting the presence of heavy metals in soil on the railway body or in the surrounding areas. Following current procedures, the results of individual study were discussed and compared to those of other researchers. The individual study was done considering a section along a railway in service, which verified that cadmium was present on the railroad. In addition, various sources and origins of cadmium were analyzed considering the railway transportation. All the presented researches imposed an urgent need to establish effective remediation measures against the harmful impact of cadmium.

One of the basic assignments of modern society is preserving the quality of freshwater resources, especially drinking water. Line facilities potentially pose a higher risk to the environment due to the large length of the extension and the diversity of the environment they may affect. Storm water drained from railway could pollute the surrounding land besides railway track. Based on the data from available research, it has been determined that heavy metals (iron, copper, zinc, manganese and chromium), polycyclic aromatic hydrocarbons (PAHs) and herbicides stand out in significant quantities from substances hazardous to the environment. This paper proposes the solutions using some self-sustainable techniques, based on the analysis railway drainage needs. The proposals that have been made refer to the open-air railway and railway station.

Maintaining the geometric quality of railway tracks is essential for safe and efficient operations. This study examines the prediction of the Track Quality Index (TQI) using Multiple Linear Regression (MLR) and Random Forest (RF) models, based on inspection data from the mountainous Kolashin–Podgorica railway section. Data collected from 2017 to 2022 were used for model development, while 2024 data served as an independent validation set. The primary contribution is a high-resolution analysis of 20-m homogeneous track units across multiple years, combined with independent validation. The dataset includes precise measurements segmented into 20-m units, covering infrastructure, geometric, operational, and maintenance variables. Model variables were selected for their relevance to track quality and data completeness. Both models were trained on scaled input data and evaluated using the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). The RF model outperformed MLR, achieving a higher R² (0.69 versus 0.57) and an MAE approximately 15% lower. Furthermore, the RF model identified severe localized degradation trends and demonstrated robust screening capability, achieving 86.4% sensitivity in detecting high-risk track segments requiring urgent intervention. These findings highlight the effectiveness of ensemble machine learning methods in reducing prediction errors and enabling proactive, data-driven track maintenance in complex railway networks. This methodology allows railway engineers to identify segments most susceptible to rapid deterioration, supporting more precise scheduling of tamping, renewals, or other targeted interventions. Model outputs can assist managers in prioritizing maintenance activities, optimizing resource allocation, and minimizing unexpected failures, thereby enhancing safety and cost efficiency in daily operations. However, the study is limited by its focus on a single railway corridor and a relatively short observation period with few maintenance events, which may restrict the generalizability of the findings to other lines or maintenance regimes.

In modern railway systems, maintaining a high track quality is a key prerequisite for safe and efficient railway traffic operations. The Track Quality Index (TQI) serves as a quantitative indicator reflecting the technical and geometric properties of the track, forming the foundation for maintenance planning and intervention activities. This paper presents a comparative analysis of several TQI calculation methods to determine their advantages, limitations, and applicability across various contexts of railway infrastructure. The research evaluates three widely used methods for determining the track quality index: the Polish quality indicator (J), the multi-parameter unified index, and the percentage-based index. For the purpose of this analysis, all three methods were applied to a specific 5-kilometer railway section, utilizing available track geometry measurement data (longitudinal profile, gauge, alignment, and twist). The results demonstrate that while all three approaches show a high correlation in the overall assessment, they exhibit varying sensitivity to specific types of defects. The weighted-factor method (unified index) allows for a more precise identification of critical track locations, whereas the standard deviation-based approach is easier to apply and interpret but proves less informative in complex geometric deformation scenarios. The statistical approach provides a solid foundation for automated analysis, though it requires precise calibration of threshold values according to national or operator standards. The study concludes that there is no universally superior method for calculating the track quality index; rather, the selection of an appropriate methodology should depend on specific infrastructure management goals, data availability, and the required balance between accuracy and simplicity. The combined use of multiple methods is recommended for long-term planning, alongside the future development of a hybrid index that integrates the strengths of existing approaches for real-time track condition assessment.

Maintaining the geometric quality of railway tracks is essential for ensuring the safety and efficiency of railway operations. This study presents a comparative analysis of Multiple Linear Regression (MLR) and Random Forest (RF) models for predicting the Track Quality Index (TQI), based on historical inspection data collected from the mountainous Kolašin–Podgorica railway section between 2017 and 2022, with data from 2024 reserved for independent validation. The dataset includes high-resolution measurements divided into 20-meter homogeneous units, incorporating infrastructure, geometric, operational, and maintenance-related variables. Both models were trained on scaled input features, and their performance was evaluated using the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE). The results demonstrate that the machine learning approach significantly outperformed the statistical baseline; the RF model achieved a higher goodness-of-fit (R2 = 0.69 vs. 0.57) and reduced the average prediction error (MAE) by approximately 15% compared to the MLR model. Furthermore, RF exhibited superior stability in capturing severe localized degradation trends. These findings highlight the potential of ensemble machine learning methods to mitigate large prediction errors and enhance data-driven, proactive track maintenance planning in geometrically complex railway networks.