CoChat
Sign Up
Cited by 49Traffic Prediction and Management TechniquesTraffic control and managementAir Quality Monitoring and Forecasting

Short-term traffic forecasting: an LSTM network for spatial-temporal speed prediction

Open access
Abduljabbar, Rusul, Dia, Hussein, Tsai, Pei-Wei, Liyanage, Sohani·2021·Future Transportation
DOI 10.3390/futuretransp1010003
Open this paper in CoChat — free accountOpen PDF

Abstract

Traffic forecasting remains an active area of research in the transport and data science fields. Decision-makers rely on traffic forecasting models for both policy-making and operational management of transport facilities. The wealth of spatial and temporal real-time data increasingly available from traffic sensors on roads provides a valuable source of information for policymakers. This paper adopts the Long Short-Term Memory (LSTM) recurrent neural network to predict speed by considering both the spatial and temporal characteristics of real-time sensor data. A total of 288,653 real-life traffic measurements were collected from detector stations on the Eastern Freeway in Melbourne/Australia. A comparative performance analysis among different models such as the Recurrent Neural Network (RNN) that has an internal memory that is able to remember its inputs and Deep Learning Backpropagation (DLBP) neural network approaches are also reported. The LSTM results showed average accuracies in the outbound direction ranging between 88 and 99 percent over prediction horizons between 5 and 60 min, and average accuracies between 96 and 98 percent in the inbound direction. The models also showed resilience in accuracies as the prediction horizons increased spatially for distances up to 15 km, providing a remarkable performance compared to other models tested. These results demonstrate the superior performance of LSTM models in capturing the spatial and temporal traffic dynamics, providing decision-makers with robust models to plan and manage transport facilities more effectively.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/futuretransp1010003

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • RNNs and LSTMs are used for time-series data, such as traffic flow prediction or electrical load forecasting.

    “Recurrent neural networks (RNNs) and long short-term memory (LSTM) networks are used for time-series data, such as traffic flow prediction (Abduljabbar et al., 2021) or electrical load forecasting.”

    From Artificial intelligence in civil engineering: emerging applications and opportunities (2025) · cites this paper as Abduljabbar et al., 2021

    Section 2.2 describes RNNs and LSTMs as tools for traffic prediction, and the paper uses an LSTM to forecast traffic speed from temporal sensor data. It does not establish their use for predicting traffic flow specifically; speed and flow are different measures. The citation is attached to the traffic example, not electrical load forecasting. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • ML models leveraging LSTM networks can predict short-term traffic volumes, travel times, and congestion hotspots more accurately than traditional time-series methods.

    “ML models, leveraging techniques such as LSTM networks for spatial-temporal speed prediction (Abduljabbar et al., 2021), can predict short-term traffic volumes, travel times, and congestion hotspots more accurately than traditional time-series methods, as reviewed by Afandizadeh et al. (2024).”

    From Artificial intelligence in civil engineering: emerging applications and opportunities (2025) · cites this paper as Abduljabbar et al., 2021

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 48 references couldn’t be matched to a known paper.

Research works printed but not linked: 2

  1. Nigarnjanagoo, S.; Dia, H. Evaluation of a Dynamic Signal Optimisation Control Model using Traffic Simulation. Special Issue on the Computerisation of Transportation: Sophisticated Systems Incorporating IT in the Mobility of People and Goods. J. Int. Assoc. Traffic Saf. Sci. 2005, 29, 22-30.
  2. Demidov, S., Bonnet, J., Eds.; Nova Science Publishers: Hauppauge, NY, USA, 2005; pp. 29-68.

Cited by

Sorted by citations

Related

Authors
Abduljabbar, R., Dia, H., Tsai, P.-W., & Liyanage, S.
Affiliations
Swinburne University of Technology (AU)
Corresponding author
Abduljabbar, Rusul
ORCID
Venue
Future Transportation
Publisher
MDPI AG
Published
2021-03-30
Volume
1
Issue
1
Pages
21-37
ISSN
2673-7590 (ISSN-L)
DOI
10.3390/futuretransp1010003
OpenAlex
W3141637527
Cited by
49
References
48
Citations by year
2026: 6 · 2025: 19 · 2024: 8 · 2023: 6 · 2022: 6 · 2021: 4
FWCI
2.75
Type
journal article
Language
en
Open access
Licence
Locations
Future Transportation (publishedVersion, cc-by)
Funders
  • Australian Government
  • Swinburne University of Technology
Topics
  • Physical Sciences › Engineering › Building and Construction › Traffic Prediction and Management Techniques
  • Physical Sciences › Engineering › Control and Systems Engineering › Traffic control and management
  • Physical Sciences › Environmental Science › Environmental Engineering › Air Quality Monitoring and Forecasting
Keywords
short-term traffic forecasting, traffic speed prediction, LSTM, recurrent neural networks, prediction horizon

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review