Maritime AI in the
Maritime Industry: an Overview
The maritime Artificial Intelligence market is expanding rapidly. Valued at £4.13 billion in 2024, it is projected to grow at a 23% Compound Annual Growth Rate (CAGR) over the next five years, according to a recent report from Lloyd’s Register. In the last 12 months alone, 420 organisations have adopted AI technologies in maritime, a significant rise from 276 in 2023. Start-ups and SMEs are leading the charge, making up 63% of the AI tech suppliers in the sector. A prime example is Orca AI, a (as they call it themselves) ‘fully automated lookout on the bridge’. Orca AI secured £23 million in May 2024 to enhance its platform, improving voyage safety and reducing CO2 emissions by 170,000 tonnes annually. This growth shows just how quickly Artificial Intelligence is becoming integrated into the maritime sector. But how exactly is it transforming the industry?
Unlike traditional methods, AI systems continuously learn and adapt. How? The answer is machine learning. Imagine a machine that doesn't just follow instructions but learns from experience becoming smarter over time. That's the magic of machine learning, a branch of Artificial Intelligence that's revolutionising industries and everyday life. Think of it as teaching a computer to recognise patterns, make predictions, or even develop solutions based on past experiences. Unlike traditional software, which operates based on explicitly programmed instructions, machine learning algorithms get smarter the more data they process, gradually improving their accuracy, efficiency and self- programming. In simple terms, machine learning algorithms are sets of instructions that help computers learn from past data. The more training data the system receives, the better it can predict future outcomes. This "learning" ability (the quotes are not to be ignored, as what we call ‘learning’ is mostly statistical induction) is what enables Artificial Intelligence to handle complex tasks — from diagnosing diseases to predicting the stock market.
The maritime sector is experiencing a transformative shift as Artificial Intelligence redefines how ships are operated, maintained, and navigated. Maritime is embracing AI with open arms, driven by the need for increased efficiency, safety, and sustainability. AI’s ability to process vast amounts of data and make real-time decisions is helping optimise voyages, reduce fuel consumption, improve navigational safety, and ensure better reliability across the board. Let’s take a closer look.
AI By Aliceluna Parenti AI
One of the most impactful uses of AI in the maritime industry is weather forecasting. AI-driven models analyse vast datasets from historical weather patterns, satellite imagery, ocean currents, and more, enabling more accurate predictions and longer lead times. This is crucial, as it helps shipping companies work out the best course time and money-wise.
IBM, in collaboration with NASA, has released a new open-source AI foundation model called Prithvi WxC, designed for weather and climate-related applications, where ‘open-source’ simply means the software is freely available to everyone, unlike proprietary software that requires a license. A ‘foundation model' refers to an Artificial intelligence system that’s initially trained on a broad task, and can then be fine-tuned or customised to perform a variety of specific tasks — think of it as a 'base' model that learns general patterns, and then can be 'adapted' to handle more specialised tasks, much like how a general knowledge meteorologist might be trained to focus on a specific field like marine weather. Trained on 40 years of historical weather data from NASA's MERRA-2 dataset, the model is built on advanced AI architectures, including a masked autoencoder, a type of AI model designed to learn from incomplete data. A masked autoencoder works by 'masking' or hiding part of the information and then learning how to predict or fill in the missing pieces — think of it as a puzzle-solving Artificial Intelligence that uses the pieces it has to guess what’s missing. These sophisticated techniques allow it to handle complex spatial-temporal data, making it one of the most advanced tools in maritime forecasting. It also has a unique training process that teaches it to predict missing weather data, mimicking the forecasting process. Nonetheless, it is also designed to run efficiently on desktop computers, offering accessibility even without massive supercomputing resources.
THE REPORT | MAR 2025 | ISSUE 111 | 135
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132 |
Page 133 |
Page 134 |
Page 135 |
Page 136 |
Page 137 |
Page 138 |
Page 139 |
Page 140 |
Page 141 |
Page 142 |
Page 143 |
Page 144 |
Page 145 |
Page 146 |
Page 147 |
Page 148
