A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns
Abstract Urban mobility prediction is crucial for optimizing resource allocation, managing transportation systems, and planning urban development. We propose a novel framework, GeoTemporal LSTM (GT-LSTM), designed to address the intricate spatiotemporal dynamics of urban environments. GT-LSTM integr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-74237-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559418944094208 |
|---|---|
| author | Sangeetha S.K.B Sandeep Kumar Mathivanan Hariharan Rajadurai Jaehyuk Cho Sathishkumar Veerappampalayam Easwaramoorthy |
| author_facet | Sangeetha S.K.B Sandeep Kumar Mathivanan Hariharan Rajadurai Jaehyuk Cho Sathishkumar Veerappampalayam Easwaramoorthy |
| author_sort | Sangeetha S.K.B |
| collection | DOAJ |
| description | Abstract Urban mobility prediction is crucial for optimizing resource allocation, managing transportation systems, and planning urban development. We propose a novel framework, GeoTemporal LSTM (GT-LSTM), designed to address the intricate spatiotemporal dynamics of urban environments. GT-LSTM integrates temporal dependencies with geographic information through a multi-modal approach that combines attention mechanisms and Recurrent Neural Networks (RNNs). This method allows the model to focus on relevant spatial features while capturing sequential relationships in time-series data. The approach uses attention mechanisms to dynamically weight geographic features and LSTM layers to model temporal patterns, resulting in enhanced predictive accuracy. Evaluations using a real-world multi-modal urban transportation dataset demonstrate the performance of GT-LSTM, with significant reductions of 15% in Mean Absolute Percentage Error (MAPE) and 20% in Root Mean Square Error (RMSE) compared to traditional methods. The model also shows substantial improvements over traditional techniques, including Convolutional LSTM and Graph Convolutional Networks. The effectiveness of GT-LSTM in capturing both spatial and temporal dynamics highlights its potential for real-time urban mobility prediction and provides valuable insights for urban planners, policymakers, and transportation authorities to improve decision-making and system efficiency. |
| format | Article |
| id | doaj-art-2e5c7f64c9e54b6e99518ff0dc9e9879 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2e5c7f64c9e54b6e99518ff0dc9e98792025-01-05T12:29:34ZengNature PortfolioScientific Reports2045-23222024-12-0114111910.1038/s41598-024-74237-3A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patternsSangeetha S.K.B0Sandeep Kumar Mathivanan1Hariharan Rajadurai2Jaehyuk Cho3Sathishkumar Veerappampalayam Easwaramoorthy4Department of Computer Science and Engineering, SRM Institute of Science and TechnologySchool of Computer Science and Engineering, Galgotias UniversitySchool of Computing Science and Engineering, VIT Bhopal UniversityDepartment of Software Engineering & Division of Electronics and Information Engineering, Jeonbuk National UniversityDepartment of Computing and Information Systems, Sunway UniversityAbstract Urban mobility prediction is crucial for optimizing resource allocation, managing transportation systems, and planning urban development. We propose a novel framework, GeoTemporal LSTM (GT-LSTM), designed to address the intricate spatiotemporal dynamics of urban environments. GT-LSTM integrates temporal dependencies with geographic information through a multi-modal approach that combines attention mechanisms and Recurrent Neural Networks (RNNs). This method allows the model to focus on relevant spatial features while capturing sequential relationships in time-series data. The approach uses attention mechanisms to dynamically weight geographic features and LSTM layers to model temporal patterns, resulting in enhanced predictive accuracy. Evaluations using a real-world multi-modal urban transportation dataset demonstrate the performance of GT-LSTM, with significant reductions of 15% in Mean Absolute Percentage Error (MAPE) and 20% in Root Mean Square Error (RMSE) compared to traditional methods. The model also shows substantial improvements over traditional techniques, including Convolutional LSTM and Graph Convolutional Networks. The effectiveness of GT-LSTM in capturing both spatial and temporal dynamics highlights its potential for real-time urban mobility prediction and provides valuable insights for urban planners, policymakers, and transportation authorities to improve decision-making and system efficiency.https://doi.org/10.1038/s41598-024-74237-3Geospatial–temporalMulti-modalMobility predictionTransporationUrban Transportation |
| spellingShingle | Sangeetha S.K.B Sandeep Kumar Mathivanan Hariharan Rajadurai Jaehyuk Cho Sathishkumar Veerappampalayam Easwaramoorthy A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns Scientific Reports Geospatial–temporal Multi-modal Mobility prediction Transporation Urban Transportation |
| title | A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns |
| title_full | A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns |
| title_fullStr | A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns |
| title_full_unstemmed | A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns |
| title_short | A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns |
| title_sort | multi modal geospatial temporal lstm based deep learning framework for predictive modeling of urban mobility patterns |
| topic | Geospatial–temporal Multi-modal Mobility prediction Transporation Urban Transportation |
| url | https://doi.org/10.1038/s41598-024-74237-3 |
| work_keys_str_mv | AT sangeethaskb amultimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT sandeepkumarmathivanan amultimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT hariharanrajadurai amultimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT jaehyukcho amultimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT sathishkumarveerappampalayameaswaramoorthy amultimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT sangeethaskb multimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT sandeepkumarmathivanan multimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT hariharanrajadurai multimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT jaehyukcho multimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns AT sathishkumarveerappampalayameaswaramoorthy multimodalgeospatialtemporallstmbaseddeeplearningframeworkforpredictivemodelingofurbanmobilitypatterns |