Supply chain optimization and decarbonisation efforts can not rely on erroneous or outdated data. When it comes to maritime emissions calculations, most methodologies available today rely on either aggregate historical data or assumptions about vessel and voyage characteristics.
However, VesselBot’s digital twin technology, which tracks data in real-time and provides clarity on the actual execution of each voyage, is a powerful tool for any shipper that aims to optimize his supply chain.
To validate the accuracy of our dynamic digital twin modeled calculations, we compare our findings about containership emissions (calculations performed in 2024) with data about the actual emissions in the same period, published recently. The data in question were sourced from the Maersk McKinney Møller Center for Zero Carbon Shipping, derived from fuel-consumption disclosures submitted to the International Maritime Organization. This dataset provides a credible reference point based on real vessel activity, while the comparison results validate the accuracy of VesselBot’s methodology.
VesselBot’s execution-based emissions modeling remained within 4% of independently reported IMO DCS fuel-consumption data. At fleet scale, such a narrow variance constitutes robust validation of the methodology.
|
TtW CO2e Emissions |
|
|
VesselBot |
200,901,708 |
|
Maersk Mc-Kinney Moller Center |
209,345,450 |
|
Difference |
-4% |
The comparison leads to two important conclusions that materially change how maritime emissions data can be used. First, dynamic digital twin fuel-consumption modeling can replicate real reported emissions at fleet scale with a high degree of accuracy. Second, and more importantly for shippers, this level of accuracy does not need to arrive months after operations are completed. It can be available in real time, enabling operational decisions before and during shipment execution rather than after the fact.
To validate execution-level emissions accuracy against regulated reporting, VesselBot benchmarked its dynamic digital twin model against this independently published dataset.
Proof of Accuracy: VesselBot vs an IMO DCS Based Benchmark
Let’s look at how that 4% variance, observed between VesselBot and Maersk Mc Kinney Møller Center for Zero Carbon Shipping, is translated on a single vessel basis:
- Maersk Mc Kinney Møller Center - 38,349 tons per vessel
- VesselBot (TtW, similar coverage) - 36,802 tons per vessel
A 4% variance across more than 5,000 vessels is strong quantitative evidence that VesselBot’s approach is robust at fleet scale, especially given that even minor differences in coverage and operational boundaries can introduce meaningful deltas.
The comparison methodology is analyzed below to verify dataset alignment.
Comparison Steps
Step 1: Convert Well-to-Wake Emissions to Tank-to-Wake Emissions
To be able to compare VesselBot’s execution-grade voyage data with the figures published by the Mærsk Mc-Kinney Møller Center for Zero Carbon Shipping, we convert Well-to-Wake (WTW) Emissions to Tank-to-Wake (TtW) Emissions, a standard requirement when working with IMO DCS benchmark data.
Well-to-Wake Emissions is the sum of Well-to-Tank Emissions and Tank-to-Wake Emissions. To convert Well-to-Wake CO2e to Tank-to-Wake CO2e, we need the following calculation:
Therefore, our 188,600,402 tons of WTW CO2e emissions are 174,220,312.24 tons of TTW CO2e emissions.
Step 2: Calculate the figures based on the same number of vessels
In 2024, VesselBot tracked the movement of 4,734 vessels. Our capabilities have been steadily evolving in 2025, and today we are tracking more than 6,000 container-carrying vessels.
Assuming a coverage of 5,459 vessels (same as the Mærsk Mc-Kinney Møller Center for Zero Carbon Shipping did in 2024), the respective Tank-to-Wake CO2e emissions would be 200,901,707.75 tons.
Step 3: Difference calculation
With both datasets converted to Tank-to-Wake and normalized to the same vessel count, we compare like-for-like. The Maersk McKinney Møller Center's Tank-to-Wake total is 209,345,450 tons. VesselBot's equivalent Tank-to-Wake total is 200,901,708 tons. This represents a 4% deviation across more than 5,000 vessels, demonstrating near-parity between VesselBot’s execution-level digital twin emissions calculations and regulated fuel-consumption reporting.
The table below summarizes the comparison for the same period (2024) and segment as the benchmark dataset from Maersk McKinney Møller Center for Zero Carbon Shipping.
|
|
Maersk Mc-Kinney Moller Center (TtW) |
VesselBot (WtW) |
VesselBot (TtW) |
VesselBot (Ttw & Similar Voyage Coverage) |
Difference |
|
Vessels |
5,459 |
4,734 |
4,734 |
5,459 |
- |
|
Emissions (tons) |
209,345,450 |
188,600,402 |
174,220,312.24 |
200,901,707.75 |
-4.0334% |
What Is Being Validated Here, and Why It Is Credible
This comparison tests VesselBot against a reference grounded in IMO DCS regulated reporting rather than against another estimation framework. The benchmark dataset is derived from fuel-consumption disclosures submitted to the International Maritime Organization and consolidated by the Maersk McKinney Møller Center for Zero Carbon Shipping, making it a credible representation of real vessel activity for 2024.
VesselBot’s emissions calculations are generated using AIS-based vessel movement data, a digital twin of vessel fuel-consumption, and vessel-specific operational parameters. This approach simulates actual voyage execution rather than relying on aggregated fleet averages.
The close alignment between modeled execution-level emissions and reported emissions confirms that execution-based methodology can replicate real-world emissions outcomes at fleet scale. This establishes the reliability of the methodology for operational use.
With accuracy validated, the differentiator shifts from whether the methodology performs to when its outputs reach decision-makers.
Why Maritime Emissions Accuracy Matters: Real-Time Insight Enables Real-World Action
Maritime emissions data only creates value when it is available at the moment decisions are made. Validation against regulated reporting demonstrates that execution-based modeling is trustworthy. The advantage comes from delivering that same level of precision in real time.
As VesselBot CEO Constantine Komodromos puts it: "If you measure emissions quarterly but operations change daily, you are managing the past. Sustainability has to become an operational KPI, evaluated at the moment of planning and execution, alongside reliability and cost."
Operational impact requires both accuracy and timeliness. VesselBot delivers real-time emissions visibility at the shipment, voyage, and vessel levels, enabling teams to act immediately, not retroactively.
What Real Time, Shipment Granular Data Enables
- Selecting lower-emission services before booking
Instead of relying on generalized emission factors or backward-looking averages, shippers can compare vessel-specific and service-specific outputs per trade lane and select the best available option at the point of decision. - Monitoring voyage performance as it unfolds
When execution changes, such as speed adjustments, weather deviation, congestion, or rerouting, the emissions footprint changes too. Real-time execution-level emissions allow shippers to forecast the impact early and respond with operational decisions. - Evaluating carrier performance based on execution, not assumptions
With consistent Tank to Wake and Well to Wake outputs and vessel-level transparency, shippers can benchmark carriers on what actually happened operationally, not on opaque methodologies or aggregated reporting that is difficult to compare across providers. - Converting visibility into measurable reductions
When emissions data is both accurate and real-time, optimization decisions translate into verified decarbonization outcomes, not historical insights.
Turning Verified Accuracy Into Operational Decisions
The benchmark dataset reflects 2024 reported emissions, data that becomes available months after voyages are completed. Its purpose is validation. And it succeeds. It proves that execution-based modeling can replicate regulated fuel-consumption reporting at fleet scale with a high degree of precision.
But validation is not the real story. Validation is the prerequisite. The operational advantage lies in timing. Companies using VesselBot’s Supply Chain Sustainability platform do not need to wait for annual disclosures or delayed reporting cycles to reach this level of accuracy. The same execution-based modeling is available in real time at shipment, voyage, and vessel level.
That difference fundamentally changes how emissions data is used. Instead of reporting historical performance, teams can model scenarios, compare carrier and routing options, and take operational decisions while shipments are still moving.
Accuracy validates the methodology. Real-time visibility turns emissions into an operational control variable.
Supply chains are dynamic systems. Vessels are swapped, routes shift, blank sailings occur, and congestion reshapes itineraries in real time. Each of these events alter a shipment’s emissions footprint. And each represents a decision point: whether to reroute cargo, reselect a carrier or service, adjust procurement strategy, or even renegotiate future contracts based on demonstrated execution performance. Those decisions are only defensible when the data behind them reflects actual execution conditions, not assumptions based on voyages completed months earlier under different conditions.
When emissions data is months behind the voyages it is supposed to describe, logistics decisions, carrier selections, and decarbonization commitments are built on a baseline that no longer reflects reality. That is not a reporting inconvenience. It is a resilience risk that compounds quietly until it emerges as a compliance exposure, a missed target, or an avoidable cost.
Validated, real-time emissions intelligence gives supply chain and logistics teams the same live visibility into carbon performance that they already expect for cost and service reliability. When conditions change, and they always do, decisions can change with them. That is what turns emissions from a reporting obligation into an operational capability.