Demand prediction for urban air mobility using deep learning

Faheem Ahmed; Muhammad Ali Memon; Khairan Rajab; Hani Alshahrani; Mohamed Elmagzoub Abdalla; Adel Rajab; Raymond Houe; Asadullah Shaikh

doi:10.7717/peerj-cs.1946

Demand prediction for urban air mobility using deep learning

PeerJ Comput Sci. 2024 Apr 5:10:e1946. doi: 10.7717/peerj-cs.1946. eCollection 2024.

Authors

Faheem Ahmed¹, Muhammad Ali Memon¹, Khairan Rajab², Hani Alshahrani², Mohamed Elmagzoub Abdalla³, Adel Rajab², Raymond Houe⁴, Asadullah Shaikh⁵

Affiliations

¹ Department of Information Technology, University of Sindh, Jamshoro, Sindh, Pakistan.
² Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran, Saudi Arabia.
³ Department of Network and Communication Engineering, College of Computer Science and Information Systems, Najran University, Najran, Najran, Saudi Arabia.
⁴ INP-ENIT, Univeristy of Tolouse, Tarbes, France.
⁵ Department of Information Systems College of Computer Science and Information Systems, Najran University, Najran, Saudi Arabia.

Abstract

Urban air mobility, also known as UAM, is currently being researched in a variety of metropolitan regions throughout the world as a potential new mode of transport for travelling shorter distances inside a territory. In this article, we investigate whether or not the market can back the necessary financial commitments to deploy UAM. A challenge in defining and addressing a critical phase of such guidance is called a demand forecast problem. To achieve this goal, a deep learning model for forecasting temporal data is proposed. This model is used to find and study the scientific issues involved. A benchmark dataset of 150,000 records was used for this purpose. Our experiments used different state-of-the-art DL models: LSTM, GRU, and Transformer for UAM demand prediction. The transformer showed a high performance with an RMSE of 0.64, allowing decision-makers to analyze the feasibility and viability of their investments.

Keywords: Deep learning; Demand of mobility; Prediction; Temporal data; Urban air mobility.

Grants and funding

The authors received funding from the Deanship of Scientific Research at Najran University for this research through a grant (NU/RG/SERC/12/35) under the Research Groups Funding program at Najran University, Kingdom of Saudi Arabia. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.