Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network

Dockless electric scooters (e-scooter) have emerged as a green alternative to automobiles and a solution to the first- and last-mile problems. Demand anticipation, or being able to accurately predict spatiotemporal demand of e-scooter usage, is one supply–demand balancing strategy. In this paper, we...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Santi Phithakkitnukooon, Karn Patanukhom, Merkebe Getachew Demissie
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/25383b616feb4c89bd22128ffb8532f0
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:25383b616feb4c89bd22128ffb8532f0
record_format dspace
spelling oai:doaj.org-article:25383b616feb4c89bd22128ffb8532f02021-11-25T17:53:09ZPredicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network10.3390/ijgi101107732220-9964https://doaj.org/article/25383b616feb4c89bd22128ffb8532f02021-11-01T00:00:00Zhttps://www.mdpi.com/2220-9964/10/11/773https://doaj.org/toc/2220-9964Dockless electric scooters (e-scooter) have emerged as a green alternative to automobiles and a solution to the first- and last-mile problems. Demand anticipation, or being able to accurately predict spatiotemporal demand of e-scooter usage, is one supply–demand balancing strategy. In this paper, we present a dockless e-scooter demand prediction model based on a fully convolutional network (FCN) coupled with a masking process and a weighted loss function, namely, masked FCN (or MFCN). The MFCN model handles the sparse e-scooter usage data with its masking process and weighted loss function. The model is trained with highly correlated features through our feature selection process. Next-hour and next 24-h prediction schemes have been tested for both pick-up and drop-off demands. Overall, the proposed MFCN outperforms other baseline models including a naïve forecasting, linear regression, and convolutional long short-term memory networks with mean absolute errors of 0.0434 and 0.0464 for the next-hour pick-up and drop-off demand prediction, respectively, and the errors of 0.0491 and 0.0501 for the next 24-h pick-up and drop-off demand prediction, respectively. The developed MFCN expands the collection of deep learning techniques that can be applied in the transportation domain, especially spatiotemporal demand prediction.Santi PhithakkitnukooonKarn PatanukhomMerkebe Getachew DemissieMDPI AGarticlee-scootermicromobilityfree-floating systemsurban mobilitymobility-as-a-servicespatiotemporal demandGeography (General)G1-922ENISPRS International Journal of Geo-Information, Vol 10, Iss 773, p 773 (2021)
institution DOAJ
collection DOAJ
language EN
topic e-scooter
micromobility
free-floating systems
urban mobility
mobility-as-a-service
spatiotemporal demand
Geography (General)
G1-922
spellingShingle e-scooter
micromobility
free-floating systems
urban mobility
mobility-as-a-service
spatiotemporal demand
Geography (General)
G1-922
Santi Phithakkitnukooon
Karn Patanukhom
Merkebe Getachew Demissie
Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network
description Dockless electric scooters (e-scooter) have emerged as a green alternative to automobiles and a solution to the first- and last-mile problems. Demand anticipation, or being able to accurately predict spatiotemporal demand of e-scooter usage, is one supply–demand balancing strategy. In this paper, we present a dockless e-scooter demand prediction model based on a fully convolutional network (FCN) coupled with a masking process and a weighted loss function, namely, masked FCN (or MFCN). The MFCN model handles the sparse e-scooter usage data with its masking process and weighted loss function. The model is trained with highly correlated features through our feature selection process. Next-hour and next 24-h prediction schemes have been tested for both pick-up and drop-off demands. Overall, the proposed MFCN outperforms other baseline models including a naïve forecasting, linear regression, and convolutional long short-term memory networks with mean absolute errors of 0.0434 and 0.0464 for the next-hour pick-up and drop-off demand prediction, respectively, and the errors of 0.0491 and 0.0501 for the next 24-h pick-up and drop-off demand prediction, respectively. The developed MFCN expands the collection of deep learning techniques that can be applied in the transportation domain, especially spatiotemporal demand prediction.
format article
author Santi Phithakkitnukooon
Karn Patanukhom
Merkebe Getachew Demissie
author_facet Santi Phithakkitnukooon
Karn Patanukhom
Merkebe Getachew Demissie
author_sort Santi Phithakkitnukooon
title Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network
title_short Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network
title_full Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network
title_fullStr Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network
title_full_unstemmed Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network
title_sort predicting spatiotemporal demand of dockless e-scooter sharing services with a masked fully convolutional network
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/25383b616feb4c89bd22128ffb8532f0
work_keys_str_mv AT santiphithakkitnukooon predictingspatiotemporaldemandofdocklessescootersharingserviceswithamaskedfullyconvolutionalnetwork
AT karnpatanukhom predictingspatiotemporaldemandofdocklessescootersharingserviceswithamaskedfullyconvolutionalnetwork
AT merkebegetachewdemissie predictingspatiotemporaldemandofdocklessescootersharingserviceswithamaskedfullyconvolutionalnetwork
_version_ 1718411852102238208