Drop in a Tour Itinerary.
Get a Footprint in Seconds.

Humí estimates emissions from the main tour components that typically contribute most to a trip’s carbon footprint, including transportation, accommodations, meals, and planned activities identified from the itinerary details provided.

You’ll receive the total tour footprint, per-traveler emissions, and a breakdown by category and component, so you can quickly see where emissions are coming from across the itinerary.

The tool is designed to focus on the highest-impact parts of a tour, helping you measure what matters most and identify where to take action first without getting bogged down in every detail. As a result, some smaller or indirect sources are not currently included, such as products purchased for guests, optional add-ons, traveler purchases made independently, or waste generated during the tour (except for food waste, which is built into the meal calculations).

A note on carbon reporting and scopes: Humí measures the product-level footprint of a tour, meaning the emissions generated by delivering the itinerary itself. This approach is aligned with the GHG Protocol’s accounting principles. The emissions measured by Humí may ultimately fall within Scope 1, 2, or 3, depending on who owns or controls the vehicles, facilities, and services used to deliver the tour. For organizations that report emissions using the GHG Protocol, Humí’s results can be incorporated into your carbon inventory and assigned to the appropriate scope.

The tool is designed to measure a wide range of guided and packaged tours. This includes multi-day tours, day trips, self-guided tours, bespoke private journeys, student travel programs, and expedition-style travel.

It works best with itineraries that include at least a basic outline of the trip, such as destinations, route, accommodations, and planned activities. Even if some details are missing, the tool can still generate an estimate by interpreting the itinerary and filling in gaps based on the information available.

Keep in mind that emissions can vary widely depending on the type of tour. For example, a walking tour with no transportation or meals included may have a very low footprint, while a multi-day itinerary with hotels and vehicle transfers will typically have a much higher footprint.

Humí calculates tour emissions using Sustainable Travel International’s carbon methodology for travel. Emissions are calculated using a standard carbon accounting formula: activity data (such as distances traveled or nights stayed) is multiplied by the relevant emissions factor for that activity (which represents the standardized amount of carbon that a given activity produces). The resulting footprint is expressed in kilograms of CO₂e (carbon dioxide equivalent), a standard unit that quantifies the warming impact of different greenhouse gases as an equivalent amount of carbon dioxide.

Transportation

For all transportation modes, emissions account for the full lifecycle of the fuel, from its production and refining through to its use during travel. Transportation emissions factors are sourced primarily from the UK’s Department for Energy Security and Net Zero (DESNZ), unless otherwise noted.

Flights

Flight emissions are calculated based on the great circle distance between the two airports, derived from their geographic coordinates. An 8% uplift is applied to account for indirect routing, and the factors also include an allowance for the warming effect of aviation’s non-CO₂ emissions, such as contrails and NOx. Emissions scale with cabin class and number of passengers for scheduled flights.

For charter flights, emissions are calculated using aircraft fuel-burn rates from our database. Because the plane is chartered exclusively for the group, all emissions from the flight are attributed to the tour.

Ground Transport

Road transfer emissions are calculated based on distance, vehicle type, and fuel type. Distance is calculated based on the origin and destination locations stated in the itinerary. The amount of CO₂ emitted per kilometer depends on the vehicle and fuel type. When the vehicle type is not specified, the tool estimates the most appropriate vehicle type based on the context of the transfer, for example, assigning a large group a coach. For less common transport modes, the tool maps them to the closest matching vehicle type. When fuel type is not specified, the tool applies a default based on vehicle type, for example, gasoline for cars.

For public transport such as scheduled buses and trains, emissions are calculated based on the number of passengers and the distance traveled. For rail, emissions are calculated using a global emissions factor.

Boats

For cruises and liveaboards, emissions are calculated based on the number of passengers and the number of days, using data from the European Maritime Safety Agency (EMSA) and our own analysis of liveaboard operations, respectively. Wind-powered overnight sailing cruises use the same approach, but with a lower emissions factor to reflect their reduced fuel consumption.

For ferries, emissions are calculated based on the number of passengers and the distance traveled.

Other vessels, such as yachts, catamarans, speedboats, and small boats, are calculated using vessel-specific fuel-burn rates and trip duration. For private charters, the vessel’s full emissions are attributed to the group. For scheduled shared services, emissions are allocated on a per-passenger basis.

Accommodation

Hotel emissions are calculated based on the number of room nights, using data from the Cornell University Hotel Sustainability Benchmarking (CHSB) Index to determine the carbon intensity of each night based on the property’s location and star rating. The location is used to account for the local energy mix, meaning a hotel in a country with a high proportion of renewable energy will have a lower footprint than one in a country that relies more heavily on fossil fuels. When the number of rooms is not specified, the tool assumes double occupancy and derives the number of rooms from the group size. When a star rating is not specified, the tool will attempt to identify it from the property name or description. Off-grid stays, such as camping or mountain huts, are calculated per person per night using emissions factors derived from Breda University of Applied Sciences statistical research.

Meals

Meal emissions are based on the number of meals included and the diet type. Unless the itinerary specifies otherwise, meals are assumed to include meat. Our factors are derived from a peer-reviewed study on the greenhouse gas impacts of different diets and generalized to apply globally. An additional food-waste allowance developed by Sustainable Travel International accounts for waste generated throughout food service, from preparation and inventory losses to food left on the plate.

Humí is designed to provide a reliable estimate of a tour’s carbon footprint based on the information available in the itinerary.

The tool uses established carbon accounting methods and emissions factors sourced from leading environmental and scientific organizations, such as the UK’s Department for Energy Security and Net Zero and Cornell University. Emissions factors estimate the greenhouse gas impact of a given activity, for example, per kilometer traveled in a gasoline sedan or per hotel night in a three-star property. Because collecting precise fuel, energy, or consumption data for every component of a tour is rarely feasible, emissions factors are the standard approach used across carbon accounting and provide a credible way to estimate impacts.

Humí also applies tourism-specific logic to determine the most appropriate way to calculate different tour components. For example, transportation modes such as tuk tuks and snowmobiles that don’t have their own emissions factors are mapped to the closest matching emissions category.

Because the calculations rely on information from the itinerary to determine the appropriate data inputs, the more detail provided, the more accurate the results. For example, if an itinerary does not specify whether a transfer is by van or bus, or how many guests share a hotel room, the tool may need to make reasonable assumptions to fill in those gaps. Every result includes a high, medium, or low confidence score based on how much information was explicitly provided in the itinerary versus how much had to be assumed.

We know it’s nearly impossible to have every detail for every part of a tour. Information is often missing or spread across different systems, documents, and suppliers. That shouldn’t stop you from being able to measure (and thus, reduce!) your emissions.

Humí is designed to work with the itineraries you already have. It uses AI to read the provided information, extract trip details, and fill in gaps using structured logic and reasonable assumptions based on the itinerary context.

When details are missing, the tool fills gaps in one of four ways:

• Calculating from stated information: For example, calculating the distance between two locations listed in the itinerary.
• Looking up additional details: For example, identifying a hotel’s star rating based on its name.
• Making a reasonable inference from context: For example, inferring an unnamed hotel’s star rating based on how it is described in the itinerary, such as “upscale.”
• Applying a reasonable default: For example, assuming double occupancy for a hotel room or a standard meat-based meal when the meal type is not specified.

You’ll also receive a confidence score with your results, so you can see how much the calculation relies on itinerary-provided information versus assumptions. You can always add more information and rerun the analysis to improve accuracy and confidence.

The confidence score is a rating from 1–100 that indicates how much of the information used to calculate your tour footprint came directly from the itinerary versus how much Humí had to fill in using reasonable assumptions.

Each piece of information used in the calculation is assigned a level of certainty based on how it was obtained. The more Humí has to fill in missing information, the lower the confidence score. Information that can be calculated or looked up using details provided in the itinerary, such as the distance between two locations, only slightly reduces the score. Information that must be inferred from context or filled using a default assumption reduces the score more. For example, if a transfer is included but the vehicle and fuel types are not specified, Humí may assume a diesel-powered van based on the group size, and points would be deducted from the confidence score.

Confidence scores are grouped into the following ranges:

• High (75–100): Most trip details were clearly provided in the itinerary.
• Medium (40–74): A mix of itinerary details and assumptions was used.
• Low (0–39): More information was missing, so more assumptions were needed.

A confidence score is assigned to each trip component (such as a hotel stay, transfer, or meal) and to the tour overall. The overall tour score is weighted by carbon contribution, meaning high-emitting components, like flights, have more influence than smaller ones like meals.

It’s important to note that the confidence score reflects the certainty of the information used in the calculation. It does not account for trip components that were completely omitted from the itinerary and therefore could not be included in the footprint.

In general, the more detailed your itinerary, the higher your confidence score will be. But even when some details are missing, measuring your tours is still a valuable place to start. You can always refine the inputs over time.

The easiest way to improve the accuracy of your results is to provide more detail in your itinerary. The more specific the trip information, the less the tool needs to rely on assumptions, and the higher your confidence score will be.

Helpful details include things like:

• Hotel or property names, and star ratings when known
• Transportation type (for example, a van, coach, ferry, or aircraft type)
• Whether transport is privately arranged, such as a charter, or a scheduled, shared service
• Fuel or power type where notable (for example, an electric or hybrid vehicle)
• Room occupancy
• Group size
• Meal inclusions, and any specific diets (for example, vegetarian or vegan)
• Transfer departure and arrival locations, including activity locations

If you’re choosing between formats, PDFs generally produce better results than webpage links because website pages are often built in ways that can make some content harder for the tool to retrieve.

If you’ve used a general AI chatbot, you’ve seen how the answer can vary depending on the prompt, the sources it happens to pull from, or the assumptions it makes along the way. For emissions measurement, that’s a real problem. There’s an enormous amount of information online about how to calculate emissions, and not all of it is current, based on a credible methodology, or relevant to the specific experiences that make up a tour. A general chatbot may invent the emissions factor used in a calculation, producing a plausible-looking result with no credible source to support it. Calculating emissions for tour itineraries is especially challenging because the details that matter are often missing or only implied.

Rather than letting AI guess its way through an itinerary, Humí follows a structured process. It interprets what’s actually included and identifies the most likely details where information is missing. For example, if a hotel’s emissions data isn’t directly available, it can use the hotel’s name to identify the property and apply a relevant emissions profile based on its star rating and location.

It then calculates emissions using our consistent tourism-specific methodology, with formulas built for different tour components based on established industry best practices, instead of improvising a fresh approach for every prompt.

The confidence score gives you visibility into that process by showing how much came straight from the itinerary versus where assumptions were needed.

So instead of starting from a blank prompt and a generic answer, you get a tour-specific emissions estimate backed by a defined methodology, with transparency into how any missing information was handled along the way.

The tool is always free to try.

For a limited time during launch, you can use it as many times as you’d like at no cost. It’s a simple way to test the tool with your own itineraries, explore the results, and see how it fits into your workflow.

For companies looking to measure tours in bulk across their portfolio, access centralized dashboards, or receive expert review of results, paid enterprise plans are also available with pricing tailored to your portfolio size and needs. Contact us to learn more.

No. The itinerary data you submit to Humí is yours. We do not sell it, share it with partners, or use it to train AI models. It is stored securely on our servers and accessible only to you and the Sustainable Travel team members who work on your measurement. We may use aggregated, anonymized data — with nothing that could identify your company or tours — to develop industry benchmarks, but your raw data stays private.

As with any digital platform, using Humí requires energy. But the footprint of processing an itinerary is extremely small. Humí runs on a low-emissions AI framework, so a typical itinerary emits around 3 grams of CO₂e and uses about a teaspoon (7 mL) of water. That’s only about one-sixth of the emissions associated with a detailed work email. This footprint includes the AI model, cloud servers, and network traffic. Because the data centers powering the tool generally use cleaner-than-average energy, Humí’s actual footprint is likely lower than reported, since our calculations use global average grid emissions.

Humí’s footprint is also far lower than the alternative. Doing the same work by hand, including reading the itinerary, classifying each leg, looking up missing details, and entering everything into a spreadsheet, typically takes anywhere from 30 minutes to 2 hours. Humí uses roughly 4 to 16 times less energy than completing the process manually on a laptop, while completing the same work 40 to 200 times faster.

The bigger benefit is what measurement makes possible: once you know where emissions come from, you can start cutting them sooner. Across dozens or hundreds of tours, the emissions avoided far outweigh the footprint of the tool itself.