• Analysis shows the total emissions of the 100 largest disclosing and non-disclosing companies is equivalent to over 11 billion tonnes of CO₂ annually.
• ESG Book’s data reveals the climate impact alone of the 100 largest companies that do not report their emissions is more than 2.1 billion tonnes of CO₂e, just behind the annual carbon output of India.
• New data coincides with the launch of ESG Book’s Emissions Estimation Model, which estimates the greenhouse gas emissions of over 37,000 companies worldwide.
• Less than 4,000 of leading companies publicly disclose emissions, impairing financial market ability to accurately assess climate risks and opportunities.
• Based on machine learning, ESG Book’s new Emissions Estimation Model provides Scope 1, Scope 2 and Scope 3 emissions for 37,000 listed corporates, covering 99% of top global indices.
• With 30,000 Scope 3 estimations, the Emissions Estimation Model is the largest dataset in the market, helping investors close the data gap in understanding companies’ climate impact.

If the world’s leading companies were a country, it would be the globe’s largest emitter of greenhouse gas emissions, according to new ESG Book analysis. Its research shows the total emissions of both the 100 largest disclosing and non-disclosing companies is equivalent to over 11 billion tonnes of CO₂ annually, or more than double the annual emissions output of the United States.

ESG Book’s data reveals the climate impact alone of the 100 largest companies that do not report their emissions is more than 2.1 billion tonnes of CO₂e, just behind the annual carbon output of India.

The analysis coincides with the launch today of ESG Book’s Emissions Estimation Model, which estimates the GHG emissions of over 37,000 companies worldwide.

Less than 4,000 of leading companies publicly disclose their emissions, resulting in a data gap that impairs financial market ability to accurately assess climate risks and opportunities. Using a best-in-class machine learning approach, ESG Book has developed the Emissions Estimation Model in response to provide clients with greater transparency around the emissions of tens of thousands of companies, enhancing decision-making capabilities around climate risks and opportunities.

The model is the latest addition to ESG Book’s comprehensive climate data suite, which includes reported emissions data for over 3,000 companies globally across three emissions scopes, together with temperature scores and emissions intensity ratios for more than 36,000 funds.

Covering 99% of top global indices, the Emissions Estimation Model estimates Scope 1, Scope 2 and Scope 3 emissions for each company using independent, industry-leading models which incorporate the latest research on emissions estimation. With 30,000 Scope 3 total estimations, the Emissions Estimation Model is the largest dataset of its kind in the market.

See related article: ESG Book Closes $35 million Series B to Build the World’s Leading ESG Data Platform

Dr Daniel Klier, CEO of ESG Book, said: “Emissions data is essential for investors to understand portfolio alignment to various climate pathways, climate scenario stress-testing to identify transition risks and opportunities, and for engaging with and holding companies accountable on meeting net- zero targets. However, the availability of publicly reported corporate emissions data is woefully insufficient, and our analysis only highlights the vast climate data gap that currently exists in global markets.”

“Our response is the Emissions Estimation Model, a powerful new tool that enables investors, financial institutions and other stakeholders to more accurately assess the climate impact of companies worldwide. Part of ESG Book’s comprehensive climate data suite, the Emissions Estimation Model will equip our clients with a next generation solution to improve their understanding of financed emissions.”

Comprised of over 800 sub-models, each developing relationships between available company level data and emissions for a given industry, geography and emissions scope, ESG Book’s model uses 15 of the most relevant and commonly-disclosed predictors of emissions to better constrain the accuracy of the estimations. The Emissions Estimation Model’s inputs are carefully selected and processed to ensure that the model learns using accurate input data, while a nine-level regression optimisation process for each company selects the best emission estimate for each scope of emissions.

Additionally, five levels of confidence ratings provide an overview of how accurate an estimation is based on the amount of data available and used in the estimation process. The model’s approach has been trialled against conventional multivariable regression and other machine learning models, and has been found to predict emissions more accurately across sectors and geographies.

Source: ESG Book