Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep Learning
The establishment of maritime safety and security is an important concern. Ship position prediction for maritime situational awareness (MSA), as a critical aspect of maritime safety and security, requires a longer time interval than collision avoidance and maritime traffic monitoring. However, previ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/21/7169 |
| _version_ | 1797511773920690176 |
|---|---|
| author | Ibadurrahman Kunihiro Hamada Yujiro Wada Jota Nanao Daisuke Watanabe Takahiro Majima |
| author_facet | Ibadurrahman Kunihiro Hamada Yujiro Wada Jota Nanao Daisuke Watanabe Takahiro Majima |
| author_sort | Ibadurrahman |
| collection | DOAJ |
| description | The establishment of maritime safety and security is an important concern. Ship position prediction for maritime situational awareness (MSA), as a critical aspect of maritime safety and security, requires a longer time interval than collision avoidance and maritime traffic monitoring. However, previous studies focused mainly on shorter time-interval predictions ranging from 30 min to 10 h. A longer time-interval ship position prediction is required not only for MSA, but also for efficient allocation of ships by shipping companies in accordance with global freight demand. This study used an end-to-end tracking method that inputs the previous position of a vessel to a trained deep learning model to predict its next position with an average 24-h interval. An AIS dataset with a long-time-interval distribution in a nine-year timespan for capesize bulk carriers worldwide was used. In the first experiment, a deep learning model of the Indian Ocean was examined. Subsequently, the model performance was compared for six different oceans and six primary maritime chokepoints to investigate the influence of each area. In the third experiment, a sample location within the Malacca Strait area was selected, and the number of ships was counted daily. The results indicate that the ship position can be predicted accurately with an average time interval of 24 h using deep learning systems with AIS data. |
| first_indexed | 2024-03-10T05:52:50Z |
| format | Article |
| id | doaj.art-54f5d7f58dfe4b48aab2182c213efd32 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:52:50Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-54f5d7f58dfe4b48aab2182c213efd322023-11-22T21:37:36ZengMDPI AGSensors1424-82202021-10-012121716910.3390/s21217169Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep LearningIbadurrahman0Kunihiro Hamada1Yujiro Wada2Jota Nanao3Daisuke Watanabe4Takahiro Majima5Graduate School of Engineering, Hiroshima University, Hiroshima 739-8527, JapanGraduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima 739-8527, JapanGraduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima 739-8527, JapanKawasaki Kisen Kaisha, Ltd., Tokyo 100-8540, JapanMarubeni Corporation, Tokyo 100-8088, JapanKnowledge and Data System Department, National Maritime Research Institute, Tokyo 181-0004, JapanThe establishment of maritime safety and security is an important concern. Ship position prediction for maritime situational awareness (MSA), as a critical aspect of maritime safety and security, requires a longer time interval than collision avoidance and maritime traffic monitoring. However, previous studies focused mainly on shorter time-interval predictions ranging from 30 min to 10 h. A longer time-interval ship position prediction is required not only for MSA, but also for efficient allocation of ships by shipping companies in accordance with global freight demand. This study used an end-to-end tracking method that inputs the previous position of a vessel to a trained deep learning model to predict its next position with an average 24-h interval. An AIS dataset with a long-time-interval distribution in a nine-year timespan for capesize bulk carriers worldwide was used. In the first experiment, a deep learning model of the Indian Ocean was examined. Subsequently, the model performance was compared for six different oceans and six primary maritime chokepoints to investigate the influence of each area. In the third experiment, a sample location within the Malacca Strait area was selected, and the number of ships was counted daily. The results indicate that the ship position can be predicted accurately with an average time interval of 24 h using deep learning systems with AIS data.https://www.mdpi.com/1424-8220/21/21/7169deep learningAISship position predictionlong-termend-to-end |
| spellingShingle | Ibadurrahman Kunihiro Hamada Yujiro Wada Jota Nanao Daisuke Watanabe Takahiro Majima Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep Learning Sensors deep learning AIS ship position prediction long-term end-to-end |
| title | Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep Learning |
| title_full | Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep Learning |
| title_fullStr | Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep Learning |
| title_full_unstemmed | Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep Learning |
| title_short | Long-Term Ship Position Prediction Using Automatic Identification System (AIS) Data and End-to-End Deep Learning |
| title_sort | long term ship position prediction using automatic identification system ais data and end to end deep learning |
| topic | deep learning AIS ship position prediction long-term end-to-end |
| url | https://www.mdpi.com/1424-8220/21/21/7169 |
| work_keys_str_mv | AT ibadurrahman longtermshippositionpredictionusingautomaticidentificationsystemaisdataandendtoenddeeplearning AT kunihirohamada longtermshippositionpredictionusingautomaticidentificationsystemaisdataandendtoenddeeplearning AT yujirowada longtermshippositionpredictionusingautomaticidentificationsystemaisdataandendtoenddeeplearning AT jotananao longtermshippositionpredictionusingautomaticidentificationsystemaisdataandendtoenddeeplearning AT daisukewatanabe longtermshippositionpredictionusingautomaticidentificationsystemaisdataandendtoenddeeplearning AT takahiromajima longtermshippositionpredictionusingautomaticidentificationsystemaisdataandendtoenddeeplearning |