Author: admin

Recognition from the Greek Prime Minister

Posted on by admin

Greek Prime Minister meets with CEO of automation giant Nabtesco following Groundbreaking Investment in Greek AI company DeepSea Technologies

ATHENS, GREECE – September 5, 2023 – A delegation from the Nabtesco corporation, one of the world’s leading robotics and motion control companies, met with Greek Prime Minister Mitsotakis and other senior officials on the 5th September 2023, following the company’s acquisition of Greek AI specialist DeepSea Technologies in July this year. The acquisition is the first step in Nabtesco’s ambitious plan to turn its new Greek partner into a global centre of excellence for developing green autonomous vessels, maritime AI, and AI automation of industrial machinery and renewable energy. It is also the first Japanese investment in Greece since the Prime Minister’s visit to Japan in January and represents a major vote of confidence in Greece’s burgeoning technology sector.

Nabtesco Corporation’s CEO, Kazumasa Kimura, was joined by its CTO, Tomohiro Kirayama, the Managing Partner of its technology investment arm, Hiroshi Nerima, and the co-founders of DeepSea, CEO Konstantinos Kyriakopoulos and President Roberto Koustas. Dr. Kyriakopoulos will continue to lead the company’s activities from Athens as it enters its new phase of growth. The delegation met with the Prime Minister as well as with Finance Minister Hatzidakis, Mr. Fragkogiannis, the Deputy Minister of Foreign Affairs, Mr. Tzortzakis, the Vice Chairman of the Hellenic Development Bank, and other key officials. The Ambassador of Japan to Greece, Mr. Nakayama also attended the meetings, representing the Japanese government.

The acquisition of DeepSea Technologies was recognised for its pivotal role in positioning the Greek startup environment on the global stage. This is a central part of Greece’s growth strategy, with several new policies having been introduced in recent years to help support this sector. DeepSea will continue to develop its range of well-known optimisation tools for the shipping industry, whilst also becoming a centre of excellence in AI research for the Nabtesco Corporation.

Konstantinos Kyriakopoulos, DeepSea’s co-founder and CEO, said “We are very grateful for the time and engagement shown by the Prime Minister and other top officials regarding our technology and our plans, together with Nabtesco, to lead the AI transformation of shipping – and other industrial machinery sectors – from here in Greece. The string of investments in the Greek technological ecosystem by major international companies, of which we are the latest example, demonstrates the enormous potential our country has to play a leading role in the coming AI technological revolution. We can leverage our phenomenal pool of talent and our leading position in industries like shipping to help forge the future.”

Nabtesco Corporation is a Japanese multinational which is committed to supporting the UN’s Sustainable Development Goals and setting the pathway towards net-zero. This commitment includes activities including investments in – and collaborative business ventures with – deep-tech start-ups specialising in motion control and related technologies.

“Voyages in HD” – download the white paper

Posted on by admin

Ask yourself one question: do you understand your vessels’ performance accurately enough to really optimise anything?

Shipping is still a world of ‘low definition’. According to our survey:

  • Most shipping companies understand their vessels’ behaviour only “quite well”
  • Most shipping companies have only “somewhat accurate” fuel consumption predictions
  • Most shipping companies do not/cannot reassess voyage plans regularly, despite the constantly changing reality

There is still a level of systematic, accepted, inaccuracy at the heart of voyage planning- based on a low definition understanding of vessels. This is a purely technical challenge.

We need a high-definition revolution. The direct result will be thousands of tonnes of fuel saved by each company.

The HD revolution is an incredible opportunity

We need a high-definition revolution. The direct result will be thousands of tonnes of fuel saved by each company.

Take the first step: read our white paper on “Voyages in HD” below

IBM Research Dublin, winner of the Shifts Challenge 2023: Interview

Posted on by admin

As the shipping industry grapples with the challenges of rapid digitalisation, it’s more important than ever that we strive for ever greater accuracy, robustness and transparency when it comes to new technology.

This year it was an expert team from IBM Research in Dublin that won the Shifts Challenge 2023, presenting a strong approach to modelling vessel behaviour using AI.

In this interview with Shivani Tomar, Pre-Doc AI Researcher at IBM Research, we delve into the team’s journey, from initial formation to finding inspiration in the wind turbine sector – and how this sort of research is vital to making the shipping industry more efficient. Join us as we discuss the facts behind their winning solution, and explore the real-world implications of their work.

Q: Tell us a bit about your team and how you came together to tackle the problem of distributional shift in the shipping industry as part of the Shifts Challenge 2023.

At IBM Research Dublin, we have a team of leading industry experts continuously working across a number of different research areas such as time series forecasting, incremental machine learning and privacy enhancing technologies. Essential to the ongoing success of the team is our culture of collaboration and continuous sharing of latest insights and information. It was this team approach that proved critical to developing a winning solution.

Q: Your novel approach applied learnings from another sector unrelated to shipping. Can you explain how the wind turbine sector’s learnings were applied to enhance vessel power estimation?

There was a stark similarity in the data relating to the wind turbine sector. We observed similar trends in the wind features as the wind-based components in the power estimation data shared by the challenge organisers. Since the distributional shift was introduced by partitioning the data across wind components, it led to the obvious choice of training specialised ensembles catering to each wind partition. The wind models that we developed were partially funded by the EU Horizon 2020 program through the MORE (Management of Realtime Energy data) project.

Q: Assessing the quality of an AI model is a major problem and critical to getting people to trust AI. DeepSea deployed a novel evaluation benchmark to help solve this challenge as part of the Shifts Challenge. What did you think about DeepSea’s methodology and approach?

The evaluation benchmark provided was quite useful, however, it only considered the extreme data distributions for evaluation purposes. We believe multiple scenarios and splits would probably be more useful to test rather than one scenario of unseen evaluation data.

Q: The reference model provided for the challenge set a benchmark. Your team achieved a 13% improvement on vessel power against the reference model provided. What were the key findings and performance improvements that you observed?

A part of the improvement came from the obvious starting points when trying to improve an existing benchmark like hyper-parameter optimisation. However, a major improvement in the results can be attributed to the cross-application of the partition-based approach from the wind turbine sector.

Q: Beyond the quantitative improvements, what are some potential real-world implications of your work? How can your approach contribute to the shipping industry’s efficiency, sustainability, or cost-effectiveness?

Our results are a step closer towards the integration of AI solutions to real world applications i.e., the shipping industry in this case. Based on the improvements achieved with our approach, we can, through collaboration, bring down the costs associated with inaccurate power prediction like errors in fuel planning and route optimisation.

Shivani is a PhD Student working in collaboration with IBM Research and Trinity College Dublin. Her research area includes incremental machine learning mainly focussing on time series data. Shivani’s current interests involve explainability in time series regression problems using prototypes in streaming context.

Steering the future of shipping with Nabtesco and DeepSea

Posted on by admin

NABTESCO BECOMES THE PRIMARY SHAREHOLDER IN DEEPSEA TECHNOLOGIES, MARKING FURTHER PROGRESS TOWARDS AUTONOMOUS VESSEL DEVELOPMENT

Press release 18/07/23; 0700 UTC

Japan-based automation multinational Nabtesco has made a major investment in the future of AI for shipping, becoming the primary shareholder in Greece-headquartered AI optimisation company DeepSea Technologies. DeepSea will continue its growth within the maritime industry while becoming a centre of excellence for AI research and product development. This decision will support Nabtesco’s move towards the development of autonomous vessels and other AI applications in its business sectors.

Nabtesco has been an investor and shareholder in DeepSea since 2021. DeepSea will join Nabtesco Marine Control Systems Company in developing the platforms and tools required to achieve its goal of scalable semi-autonomous shipping. It will also pursue AI-focused research and development covering the entire scope of Nabtesco’s activity, which extends beyond maritime, including wind turbines, rail and aviation automation and industrial robotics. 

DeepSea will continue to focus on the development of its established software platforms, Cassandra & Pythia, which enable shipping companies to decrease fuel consumption and emissions by optimising vessels and voyages respectively.

“DeepSea’s expertise and team of AI specialists are now well-known in the shipping industry, and are driving a radical improvement to vessel efficiency for their customers. We have been very impressed with their commercial traction and calibre of research since we first invested in the company. Joining forces will enable us to progress even faster towards an exciting future of automation, both within maritime and beyond. We’re excited to announce this news and look forward to driving even greater value for our clients, within each of our market areas, through enhanced innovation and R&D.”

Mr. Yukihiro Mizutani, President, Marine Control Systems Company, Executive Officer of Nabtesco

DeepSea has over 70 specialised engineers, mainly in the fields of Artificial Intelligence and software development. It will continue to operate as an autonomous company and will continue to be managed by the two original founders, with Dr. Konstantinos Kyriakopoulos as CEO and Mr. Roberto Coustas as President and head of market development. DeepSea will retain its team, premises and independent brand identity, and will continue to be an autonomous research centre for the development of applications and products based on Artificial Intelligence.

“The deepening of our existing partnership with Nabtesco unlocks even greater potential for our technology and approach, and will be key to unlocking the next wave of innovation for our customers. It’s truly the best of both worlds: DeepSea will maintain its startup culture and focus on disruptive technology, whilst harnessing all the expertise and support of a global powerhouse.”

Dr. Konstantinos Kyriakopoulos

“This is a natural next step for DeepSea as we continue to grow, focusing our industry-leading team of AI specialists on solving some of the biggest challenges in shipping. Nabtesco and DeepSea want to remain one step ahead as the sector evolves – and this decision to move forwards together will allow our combined product offering to be unmatched.”

Roberto Coustas

DeepSea provides a free entry-point for shipping companies to start exploring AI benchmarking tools as it unveils the results of the 2022-23 Shifts Challenge

Posted on by admin

DeepSea Technologies, the award-winning Al-led maritime technology company and energy efficiency experts, has announced that it is making a full vessel data set and DeepSea’s automatic model evaluation tool available for free to the shipping industry for the next 12 months. This is the first time that such tools have ever been made available to the public – and allows innovation, research and technical departments with strong data science capabilities to start exploring AI.

The announcement follows the publication of the winners of the Shifts Challenge 2023. The competition is an international collaboration of academic and industrial researchers, including Cambridge University, and is helping to make shipping a first-class citizen in AI research.

Overall, the Shifts Challenge received 175 submissions from institutional and academic research teams and individuals. The two areas of focus were ship power prediction and white matter multiple sclerosis lesion segmentation. The winning submission in the shipping track was made by a team from IBM Dublin, which proposed a novel approach harnessing learnings from the wind turbine sector in order to gain new insights from the data provided. Their solution could predict vessel power under a broad set of conditions, recording a 13% performance improvement against the reference model DeepSea provided as a baseline.

The full vessel data set from the challenge will now be provided for use to researchers and technical specialists in the maritime industry, and can be accessed via Zenodo (an open-source research database operated by CERN). DeepSea intends for it to help support the development of robust vessel models across the industry – something essential in enabling the sector to cut costs and cope with environmental regulations.

Commenting on the Shifts Challenge, Dr Nikitakis, DeepSea’s AI Director, said: “We were delighted to see the diverse set of solutions that the competitors provided. We’re also pleased to be opening this AI environment up to the whole of the shipping industry. We are always trying to “fight the hype” around AI, and there is no better way than giving the public the tools to explore – and evaluate – their own AI solutions. Perhaps later down the line we will put on a similar challenge for all AI providers in the industry – we hope they’ll take us on!”

Commenting on their winning submission, Seshu Tirupathi from the IBM Dublin team, said: “Challenges in making inferences on data with distribution shifts can be expected to gain increased importance with the exponential growth of data and real-time monitoring applications. This sort of research is extremely important, as it avoids unreliable predictions that may lead to life-threatening situations. Avenues like Shifts Challenge provide ground truth from real-world data that is essential to develop and validate robust algorithms in the space of distribution shifts and concept drifts.”

Dr. Konstantinos Kyriakopoulos, CEO and co-founder of DeepSea, said: “Though AI is still a relative newcomer to the shipping sector, it has already proven itself as an exceptional tool for those looking to optimise fuel consumption, emissions, and industry ratings. Like any other cutting-edge research area, this technology can only develop as part of an ecosystem, and the Shifts Project is (amongst other things) designed to help catalyse and support this movement.  Industrial AI is a field where bullshit is rife, and it’s these sort of initiatives that help the industry to know who to trust.”

The full vessel data set from the challenge will now be provided for use to researchers and technical specialists in the maritime industry to help support the development of robust vessel models across the industry.

Background to The Shifts Project

The Shifts Project is an international effort involving multiple institutions alongside DeepSea, including the universities of Cambridge, Basel, Lausanne, and HES-SO Valais. The initiative, which aims to build a cross-disciplinary international community, brings together core machine learning (ML) researchers studying distributional shift with applied ML researchers, who work on tasks affected by distributional shift in the real world.

Handling distributional shift is one of the greatest obstacles to the widespread adoption – and impact – of AI across all industries.  This is especially the case in shipping, and the world’s top experts are now collaborating to explore solutions. Maritime was one of two focuses in the competition – the other being distributional shift in relation to the treatment of the chronic condition, Multiple Sclerosis.

A great example of distributional shift is found in maritime – where the entire ship data set moves over time – as a result of hull fouling. Marine fouling occurs when organisms attach themselves to underwater objects, most notably the hull. This can lead to various operational inefficiencies and have a dramatic impact on vessel fuel consumption, emissions and CII – so understanding how to predict its effect using vessel data is a vital tool for the industry. Understanding how the entire ship data shifts over time is crucial to accurately modelling vessels, which is the key to unlocking shipping’s huge decarbonisation potential and minimising fuel waste.

About the IBM Dublin team

IBM Research Dublin includes data scientists and AI researchers working on different areas including time series forecasting, incremental machine learning, and security and privacy enhancing technologies like Federated Learning and differential privacy. This team came together to solve this challenge of distributional shift, robustness and uncertainty estimation in critical real-world applications.

AI in Shipping: Challenges and Opportunities

Posted on by admin

A Q&A with DeepSea’s Director of AI Research, Antonis Nikitakis

Q: What is your most exciting piece of AI research at the moment ?

Explainability is critical for building trust in AI systems. Therefore, our most exciting AI research currently involves researching methods that improve models’ explainability – to enable ever-greater trust to be built amongst stakeholders. AI can be seen as a “black box” whose input and operations may not be transparent and understandable to outsiders, particularly when they are based on complex algorithms or deep learning models. AI can be vulnerable to bias or discrimination, especially if it is trained on biased datasets or if it is designed without sufficient consideration of ethical concerns. This can lead to concerns about the accuracy or reliability of the system, which can compromise trust and confidence in its use. 

One of the most promising ways to enable trust is to promote models and methods that allow humans to understand the logic behind the system’s decisions. At DeepSea, we conduct research on models that integrate concepts and principles from Physics and Naval Engineering. This enables us to explain how the models operate and that physical principles are always respected. Additionally, we enhance explainability by introducing new methods and metrics for evaluating the performance of AI models in extrapolation regimes (i.e., outside the given datasets). Having a reliable approach to evaluating performance regardless of the available data quantity and quality is a significant step forward in promoting explainability.

Q: How is AI changing the competitive landscape of the shipping industry? What advantages can AI offer to early adopters?

AI is transforming the shipping industry in various ways, from optimising operations and increasing efficiency to improving decision-making capabilities with vessel-specific weather routing. The advantages that AI offers to early adopters are significant. We are already seeing the major impact that AI can have in our work with Wallenius Wilhelmsen. Utilising DeepSea’s Performance Routing technology, the vehicle carrier operator became the first global shipping company to adopt a fully AI-based approach to voyage optimisation. As an early adopter, Wallenius has already started to reap the quantifiable benefits of fuel savings and a reduced environmental impact.

AI can also provide early adopters with better decision-making capabilities reducing the risk of costly mistakes and improving their maintenance and operational efficiency. For example, with DeepSea’s Cassandra today we can very precisely estimate the fouling state of a vessel and its trend to help the operations team to optimally schedule a cleaning.

Q: What types of data are being collected and analysed by AI in the shipping industry?

Today there is a very large volume of data that is being collected. We have various sensor data from onboard sensors that is being collected regarding all key machinery and subsystems of the vessel such as hull, main engine, electronic chart display and information system (ECDIS), and generator engines, among others. This information is important for optimising vessel routes, predicting maintenance needs, and ensuring that each vessel is operating at maximum efficiency. Then, there is weather data, which is critical for ensuring the safety of vessels and crew members. There is live weather data from sensors, and forecast weather and historical data collected from third-party providers. Furthermore, there is manually-reported operational data (e.g. noon reports) and also live and historical data from the automatic identification system (AIS) which is responsible for transmitting a ship’s position so that other ships are aware of its position. By analysing all these types of data and turning them into practical insights, we can help shipping organisations to optimise their fleet performance, improve their operational efficiency, save on fuel costs, and decrease their carbon footprint.

Q: What are some of the challenges associated with implementing AI?

Most of the challenges in implementing AI today involve data-related challenges, challenges related to the model evaluation and its robustness, and stakeholder trust which I mentioned earlier. One major challenge is that of distributional shift. Put simply, distributional shift has to do with the mismatch that could exist in an AI model between the training environment and the actual deployment. This “shifted” data can be challenging for machine learning models. In shipping, for example, we have a prominent ‘latent phenomenon’ which is hull fouling. The fouling state of a vessel is a dynamic phenomenon that prevents a generic model from fitting the data. Data drift due to sensor miscalibration can also lead to a distributional shift. Special considerations and methods should be taken into account to ensure a consistent fit across the dataset of a vessel. DeepSea has developed sophisticated data-driven methods for unsupervised anomaly detection which can detect when such issues may appear.

Q: Are there any ethical considerations or potential risks associated with using AI in the shipping industry?  How can they be addressed?

For every decision support system based on AI there is always concern whether the recommended actions are biased due to the underlying models. In the era of deep learning, the biases can be driven directly from the data without it being obvious which parts of the data led to such biases – or how to correct them. At DeepSea, we try to alleviate such issues using a multi-faceted approach to improve a model’s interpretability, and to measure and guarantee models unbiasedness across the board. To learn how we boost model robustness, have a look at our paper on ‘How to judge the real-world effectiveness of AI in shipping’.