• About

    The vision of salbo.ai is to contribute to a sustainable society by creating data-driven, fact-based decision support, enabling our common assets to last longer and to be utilized more efficiently. With a unique competence in advanced analytics and artificial intelligence applied to transportation, infrastructure, and construction, salbo.ai creates actionable insights from large and small amounts of data.

    I am passionate about extracting valuable insights from data and to bridge the gap between data and business. I believe that artificial intelligence needs hands-on real world knowledge to be efficient - and I aim to combine the best of both worlds.

    I dwell in possibility.

    -- Emily Dickinson

  • Dalarna från Ovan

    Svenson, K., Li, Y., Machucova, Z., and Rönnegård, L., Transportation Research Record: Journal of the Transportation Research Board, 2016, Vol.2589, 51-58.

    National road databases often lack important information for long-term maintenance planning of paved roads. In the Swedish case, latent variables of which there are no recordings in the pavement management systems database are, for example, underlying road construction, subsoil conditions, and amount of heavy traffic measured by the equivalent single-axle load. The mixed proportional hazards model with random effects was used to capture the effect of these latent variables on a road’s risk of needing maintenance. Estimation of random effects makes it possible to identify sections that have shorter or longer lifetimes than could be expected from the observed explanatory variables (traffic load, pavement type, road type, climate zone, road width, speed limit, and bearing capacity restrictions). The results indicate that the mixed proportional hazards model is useful for maintenance planning because the weakest and strongest sections in a road network can be identified. The effect of the latent variables was visualized by plotting the random effect of each section in a map of the road network. In addition, the spatial correlation between road sections was evaluated by fitting the random effects in an intrinsic conditional autoregressive model. The spatial correlation was estimated to explain 17% of the variation in lifetimes of roads that occur because of the latent variables. The Swedish example shows that the mixed proportional hazards and intrinsic conditional autoregressive models are suitable for analyzing the effect of latent variables in national road databases.

    Survival curves

    Svenson, K., Journal of Transportation Engineering, 2014, Vol. 140, No. 11, 04014056.

    Maintenance planning of road pavement requires reliable estimates of roads’ lifetimes. In determining the lifetime of a road, this study combines maintenance activities and road condition measurements. The scope of the paper is to estimate lifetimes of road pavements in Sweden with time-to-event analysis. The model is stratified according to traffic load and includes effects of pavement type, road type, bearing capacity, road width, speed limit, stone size, and climate zone. Among the nine analyzed pavement types, stone mastic had the longest expected lifetime with a hazard ratio (risk of needing maintenance) estimated to be 36% lower than asphalt concrete. Among road types, 2+1 roads had 22% higher hazard ratio than ordinary roads indicating significantly lower lifetimes. Increased speed lowered the lifetime, while increased stone size (up to 20 mm) and increased road width lengthened the lifetime. The results are of importance for life-cycle cost analysis and road management.

    Sensitivity plot

    Nilsson, J-E., Svenson, K., and Haraldsson, M., Part of govermental investigation ''Economic costs of traffic'' (SAMKOST) performed by the Swedish National Road and Transport Research Institute 2014--2016. In review process.

    This paper makes use of state-of-the-art modelling in order to assess the marginal cost for road infrastructure reinvestment based on a large set of data with information about sections of the road network, including their age. Although the modelling is straightforward, it is less so to estimate costs with acceptable quality, primarily since information about heavy vehicles is incomplete. The paper suggests a strategy for identifying major differences in marginal costs across the road network. In a longer perspective this provides a platform for establishing a disaggregate approach for charging heavy vehicles from their use of roads and for channeling heavy traffic to the most modern and robust roads. The analysis also provides strong evidence for not only heavy vehicles but also cars contribute to road quality deterioration. The hypothesis is that this is due to the widespread use of studded tires in countries with regular freeze-thaw cycles.

    Gaussian distributions

    Svenson, K., McRobbie, S., and Alam, M., , International Journal of Pavement Engineering, 2019, Vol 20, No. 4, 458-465.

    Budget restrictions often limit the number of possible maintenance activities in a road network each year. To effectively allocate resources, the rate of road pavement deterioration is of great importance. If two maintenance candidates have an equivalent condition, it is reasonable to maintain the segment with the highest deterioration rate first. To identify such segments, finite mixture models were applied to road condition data from a part of the M4 highway in England. Assuming that data originates from two different normal distributions – defined as a ‘change’ distribution and an ‘unchanged’ distribution – all road segments were classified into one of the groups. Comparisons with known measurement errors and maintenance records showed that segments in the unchanged group had a stationary road condition. Segments classified into the change group showed either a rapid deterioration, improvement in condition because of previous maintenance or unusual measurement errors. Together with additional information from maintenance records, finite mixture models can identify segments with the most rapid deterioration rate, and contribute to more efficient maintenance decisions.


    Feel like doing creative number crunching together?