Header

VesselAI

Enabling Maritime Digitalisation by extreme-scale analytics, AI and Digital Twins

VesselAI aims at realising a holistic, beyond the state-of-the-art AI-empowered framework for decision-support models, data analytics and visualisations to build digital twins and maritime applications for a diverse set of cases with high impact, including simulating and predicting vessel behaviour and manoeuvring (including the human factor), ship energy design optimisation, autonomous shipping and fleet intelligence

Funding Call

https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/opportuni…

Business Categories

Maritime Sector

01.01.2021 - 31.12.2023

vessel-ai.eu

Shipping is the lifeblood of global economy, consequently one of the leading sources of greenhouse gases and one of the high-incident domains, due to heavy traffic especially in congested waters, therefore facing escalating pressure for safety, energy efficiency improvement and emissions reduction. Meanwhile, shipping generates extremely large amount of data in every minute, which potential, however, still remains untapped due to the involvement of enormous stakeholders and the sophistication of modern vessel design and operation. To address these challenges, VesselAI aims to develop, validate and demonstrate a unique framework to unlock the potential of extreme-scale data and advanced HPC, AI and Digital Twin technologies, and hence to promote the adoption and application of Big Datadriven innovations and solutions in maritime industry and beyond. By combining Digital Twin technologies and practices, VesselAI can efficiently fuse and assimilate huge amount of data, coming from both observations and simulations, to achieve highly accurate modelling, estimation and optimization of design and operation of ships and fleets under various dynamic conditions in near real time. Their technical enhancements and practical performance improvements are further demonstrated in 4 maritime industry pilots, tackling practical challenges for 1) global vessel traffic monitoring and management, 2) globally optimal ship energy system design, 3) short-sea autonomous shipping
and 4) global fleet intelligence. VesselAI brings in a consortium of renowned actors in maritime and ICT domains, providing a perfect mix of high-level expertise in both domains and readily accessibility to huge amount of data for industry-leading research and innovation in the project. Together, VesselAI addresses the challenges of implementing extreme-scale analytics in industries and showcase how AI, cloud computing and HPC can encourage, and enable deeper digitalization in the maritime and wider industries

Assets related to VesselAI

AI ethics AI services Automated reasoning Computer vision Constraints and satisfiability Machine learning Optimisation Planning and scheduling Agriculture Cloud, Edge and Infrastructure Energy Healthcare Manufacturing Maritime Sector Public Services Education Institution

Decision Support Systems Laboratory - National Technical University of Athens

AI services Machine learning Education Institution

University of Helsinki

ML Model

Mooring DBSCAN

An implementation of the DBSCAN algorithm,that extracts mooring places out of AIS messages. Package also includes methods to analyze extracted clusters.

Machine learning Optimisation Maritime Sector Company

NAPA Group (Napa Ltd)

AI services Automated reasoning Computer vision Connected and automated vehicles Knowledge Representation Machine learning Multi-agent systems Maritime Sector Transportation Company

MarineTraffic

ML Model

Detecting representative trajectories from global AIS datasets

Model for port to port vessel route forecasting using massive Automatic Identification System (AIS) datasets

Dataset

Open Research Maritime Vessel Tracking Dataset

Automatic Identification System (AIS) dataset from the Mediterranean Sea

Dataset

Single Ground Based AIS Receiver Vessel Tracking Dataset

AIS dataset collected within a 24h period (starting from 29/02/2020 10PM UTC) from a single receiver located near the port of Piraeus (Greece)

ML Model

Ship energy system design optimisation

Optimisation of the design and operation of ship energy systems in terms of energy efficiency and lifecycle costs

Executable

Information extraction from technical specification PDFs

Tools for extraction of numerical specifications from technical documentation in PDF format

AI services Knowledge Representation Machine learning Optimisation Education Institution

University of Piraeus Research Centre (UPRC) - Data Science Lab (DataStories)

ML Model

An Efficient LSTM Neural Network-Based Framework for Vessel Location Forecasting

An improved version of the core parts of the code that implements the Vessel Location Forecasting (VLF) and Vessel Route Forecasting (VRF) methods.

ML Model

Vessel Traffic Flow Forecasting (VTFF) using Machine Learning Methods

Descriptions of the implementation of the Vessel Traffic Flow Forecasting (VTFF) model that forecasts the vessel traffic flow within a given region.

ML Model

Vessel Collision Risk Assessment and Forecasting (VCRA/F)

Python implementation of the VCRA/F model from the paper "Collision Risk Assessment and Forecasting on Maritime Data"

ML Model

Simple NN ship performance model

NN-SPM estimates ship fuel consumption taking into consideration weather and operational conditions.

ML Model

Data driven digital twins for the maritime domain

Digital twins are computational models that replicate the structure, behaviour and overall characteristics of a physical asset in the digital world. In the maritime domain, conventional approaches have relied on mathematical modeling (e.g., linearised equ...

Machine learning Maritime Sector Research Institution

SINTEF Ocean

ML Model

Autoencoder-Based Maritime Anomaly Detection

A model capable of detecting anomalous ship behavior for a given geographical region.

Executable

AIS Pre-Processing

Pre-processing of AIS data

ML Model

Maritime Route Prediction for Remote Control Centre Decision Support

A route prediction model geared towards enhancing safety of autonomous ships by supporting remote control center situation awareness.

ML Model

Weather rerouting decision support model

A lightweight AI rerouting decision model that helps to determine whether running weather routing is beneficial. The goal of the model is to help minimize the high computational workload demanded by a commercial weather routing system that performs freque...

Dataset

The Piraeus AIS Dataset for Large-scale Maritime Data Analytics

AIS data collected by the University of Piraeus' AIS receiver

Jupyter Notebook

VesselAI Fuel Consumption Regression and Time Series Forecasting

This asset includes code forthe prediction of fuel consumption using AI regression models and time series forecasting techniques. The asset was developed in the context of H2020 VesselAI project

Jupyter Notebook

VesselAI CO2 Emissions Prediction using ML algorithms

Using a unique dataset, comprising historical maritime data for different vessel voyages, including vessel type, voyage information and environmental factors, we employ decision trees, a number of regression, and artificial neural network algorithms for p...

As a Service

Data Exploration Tool

The purpose of the Data Exploration Service is to allow the users of VesselAI to explore the available datasets, combine them and express complex queries on them. The service offers an environment through which the user can discover the available datasets...

AI services Computer vision Knowledge Representation Machine learning Multi-agent systems Optimisation Robotics and automation Agriculture Cultural Heritage Energy Healthcare Manufacturing Maritime Sector Regional Engagement - DIHs Transportation Research Institution

UNINOVA-CTS

Docker container

VesselAI Data Harmonisation Services

The VesselAI Data Harmonisation Services is a set of services provided through an User Interface for harmonising Maritime Domain-related data sources with Big Data characteristics. This harmonisation process entails the mapping of raw data schemas/formats...