To fulfil the global sustainable development goals (SDGs), achieving sustainable development is becoming urgent, not least in the transportation sector. In response to this, the sustainability framework Sustainability National Road Administrations (SUNRA) was developed to contribute to improving the sustainability performance of national road administrations across Europe. In the present study, the framework has been tested, applied and further developed to be applicable for target setting and follow-up at the project level at both the Swedish Transport Administration (STA) and at municipal levels. The aim was a framework relevant for investment, re-investments, maintenance and operation projects and also to make it more user applicable. The study also investigated how the framework can contribute to sustainability, identified drivers and barriers for applying the framework and examined whether the framework can be applied and adapted to projects of different complexities. The adaptations and developments were done in collaboration between researchers and practitioners. The results show that the framework could easily be used and adapted for investment, re-investment, maintenance and operation projects in the planning stage, as well as for small municipal establishments, construction or reconstruction of residential areas and frequent maintenance. The framework contributes to increased awareness on sustainability, and it provides a common structure and transparency on how infrastructure project goals/targets are set and fulfilled. The framework can also be applied to follow the fulfilment of the goals/targets and thereby adapt the project to better fulfil the goals. Identified barriers include the lack of obligations and lack of experience in using sustainability frameworks.

The municipal street network acts as a multifunctional asset by providing people, vehicles and public services with a well-functioning infrastructure. To keep it in good condition, optimal maintenance measures are required which would result in an efficient use of taxpayers' money. This paper investigates the street network deterioration processes and the management practices that the municipal administrations have applied in Sweden. The study is based on a survey with Swedish municipalities using questionnaires and complementary interviews. The answers provide insight into a wide range of common pavement distresses and deterioration factors, along with pavement management practices. The study identifies that potholes, surface unevenness and alligator cracking are the most cited challenges, while pavement ageing, heavy traffic and patches are the most noted causes. Similarly, the cold climate and population density are influential factors in pavement deterioration. Allocation of the maintenance and rehabilitation and reconstruction budget is higher in the northern part of the country as well as in densely populated municipalities. Condition data collection and use of commercial Pavement Management Systems (PMS) are limited. Addressing the challenges effectively may be possible through the enhancement of the budget, feasible/clear guidelines from municipal councils/politicians, and reducing the gap between street network administrations and utility service providers.

Machine learning (ML) models are increasingly getting attention in predicting pavement maintenance methods to improve decision-making. This study investigates the use of ML at the municipal level to predict the street pavement condition index (PCI) rating over a 4-year span. Several supervised learning models, namely linear regression (LR), random forest (RF), and neural network (NN), were applied to the visually assessed pavement condition data of Skellefteå municipality, Sweden. Pavement distress, pavement age, and traffic data were used in several combinations to evaluate and compare the performance of the models. The RF model was based on paired variables of pavement age and pavement distress data. The results were comparatively accurate with R2=0.59 and Spearman's coefficient=0.74 for residential streets in the model testing stage. Similarly, for main, collector, and industrial (MCI) streets, the RF model, based on pavement age and traffic variables, performed best with R2=0.79 and Spearman's coefficient=0.88 during the model testing stage. The importance of input variables varies with the level of the model's sophistication and pavement performance goal; however, pavement age is the dominant variable. The prediction models can be useful in effectively managing street networks among municipalities, even those with scarce resources.

Pavement condition prediction is essential for effective street maintenance. Reliable prediction models enable municipalities to anticipate pavement deterioration and plan maintenance proactively. This paper examines the use of machine learning (ML) models to enhance prediction accuracy for municipal streets. Seventy-two models were developed to predict the 2022 pavement condition index (PCI) using Linear Regression (LR), Random Forest (RF) and Neural Network (NN) algorithms. The study data was collected through windshield surveys in 2014, 2018 and 2022 in Skellefteå Municipality, Sweden. The models were trained and tested separately on the 2018 dataset and the combined 2014 and 2018 datasets, incorporating several combinations of variable sets for residential and non-residential (main, collector, and industrial) streets. Additional models were developed for non-residential streets categorized by maintenance treatments to analyse the predictive capability of the models. RF consistently outperformed other models, with the RF (A+D+S) model achieved the highest accuracy for residential streets, with a marginal improvement using the combined dataset. The RF (A+D+S+T) model performed best for non-residential streets and was also the most robust for pavement segments with surface levelling and milling & resurfacing. Among the variables, WDV (Weighted Distress), Status2018 (the PCI rating based on the 2018 assessment), LAR (longitudinal/transverse cracking), A (pavement age), LT (light traffic), and SU (surface unevenness) were the most significant contributors in the best-performing models. These findings provide municipalities with practical guidance for data-driven maintenance, helping to prioritize interventions and optimize resources. The insights also support informed decisions on maintenance frequency and treatment selection to extend pavement service life.

This study uses a sigmoidal model to predict pavement condition index (PCI) ratings over time for residential and non-residential (main, collector and industrial) streets, based on pavement data acquired from Skellefteå Municipality, Sweden. The dataset includes pavement assessments from 2014, 2018, and 2022, collected through the windshield survey method. The model aims to assess pavement degradation patterns over time across different street categories and various maintenance-treated pavement surfaces. Separate best-fit sigmoid parameters and curves were developed for each category and treatment type. While the model underperformed in predicting PCI ratings for residential streets due to utility cuts and inconsistent pavement age, it predicted PCI ratings for non-residential street conditions more accurately, due to their consistent deterioration patterns. The model's performance also varied across different maintenance-treated pavements. Sigmoid best-fit curves for street pavements treated with surface levelling (SL) and special treatments (ST) achieved the highest accuracy, while the sigmoidal curve for model for milling and resurfacing treated surfaces offered a good cost-performance balance. Maintenance of street pavements using the SL method is cost-effective for early pavement deterioration, but traffic patterns should be considered when selecting treatments. Using sigmoid curves can enhance timely, cost-effective maintenance decisions and reduce the need for reconstruction.