Digital repository of Slovenian research organisations

Search the repository
A+ | A- | Help | SLO | ENG

Query: search in
search in
search in
search in

Options:
  Reset


Query: "keywords" (forecasting) .

1 - 3 / 3
First pagePrevious page1Next pageLast page
1.
Models for forecasting the traffic flow within the city of Ljubljana
Gašper Petelin, Rok Hribar, Gregor Papa, 2023, original scientific article

Abstract: Efficient traffic management is essential in modern urban areas. The development of intelligent traffic flow prediction systems can help to reduce travel times and maximize road capacity utilization. However, accurately modeling complex spatiotemporal dependencies can be a difficult task, especially when real-time data collection is not possible. This study aims to tackle this challenge by proposing a solution that incorporates extensive feature engineering to combine historical traffic patterns with covariates such as weather data and public holidays. The proposed approach is assessed using a new real-world data set of traffic patterns collected in Ljubljana, Slovenia. The constructed models are evaluated for their accuracy and hyperparameter sensitivity, providing insights into their performance. By providing practical solutions for real-world scenarios, the proposed approach offers an effective means to improve traffic flow prediction without relying on real-time data.
Keywords: traffic modeling, time-series forecasting, traffic-count data set, machine learning, model comparison
Published in DiRROS: 28.09.2023; Views: 320; Downloads: 134
.pdf Full text (5,05 MB)
This document has many files! More...

2.
Combining an occurrence model and a quantitative model for the prediction of the sanitary felling of Norway spruce because of bark beetles
Maarten De Groot, Nikica Ogris, 2022, original scientific article

Abstract: The European spruce bark beetle (Ips typographus L.) is an eruptive forest pest that has caused a great deal of damage in the last decades because of increasing climatic extremes. In order to effectively manage outbreaks of this pest, it is important to predict where they will occur in the future. In this study we developed a predictive model of the sanitary felling of Norway spruce (Picea abies (L.) H. Karst.) because of bark beetles. We used a time series of sanitary felling because of bark beetles from 1996 to 2020 in Slovenia. For the explanatory variables, we used soil, site, climate, geographic, and tree damage data from the previous year. The model showed that sanitary felling is negatively correlated with slope, soil depth, soil cation exchange capacity, and Standard Precipitation Index (less sanitary felling in wet years). On the other hand, soil base saturation percentage, temperature, sanitary felling because of bark beetles from the previous year, sanitary felling because of other abiotic factors from the previous year, and the amount of spruce were positively correlated with the sanitary felling of Norway spruce due to bark beetles. The model had an R2 of 0.38. A prediction was performed for 2021 combining an occurrence model and a quantitative model. The model can be used to predict the amount of sanitary felling of Norway spruce due to bark beetles and to refine the risk map for the next year, which can be used for forest management planning and economic loss predictions.
Keywords: sanitary felling, prediction, Ips typographus, Picea abies, Slovenia, forecasting, insect outbreak forest pest
Published in DiRROS: 21.02.2022; Views: 642; Downloads: 527
.pdf Full text (1,24 MB)
This document has many files! More...

3.
A comparison of models for forecasting the residential natural gas demand of an urban area
Rok Hribar, Primož Potočnik, Jurij Šilc, Gregor Papa, 2019, original scientific article

Abstract: Forecasting the residential natural gas demand for large groups of buildings is extremely important for efficient logistics in the energy sector. In this paper different forecast models for residential natural gas demand of an urban area were implemented and compared. The models forecast gas demand with hourly resolution up to 60 h into the future. The model forecasts are based on past temperatures, forecasted temperatures and time variables, which include markers for holidays and other occasional events. The models were trained and tested on gas-consumption data gathered in the city of Ljubljana, Slovenia. Machine-learning models were considered, such as linear regression, kernel machine and artificial neural network. Additionally, empirical models were developed based on data analysis. Two most accurate models were found to be recurrent neural network and linear regression model. In realistic setting such trained models can be used in conjunction with a weather-forecasting service to generate forecasts for future gas demand.
Keywords: demand forecasting, buildings, energy modeling, forecast accuracy, machine learning
Published in DiRROS: 15.03.2019; Views: 2275; Downloads: 1072
.pdf Full text (968,06 KB)
Search done in 0.13 sec.
Back to top