On the heels of the major AI-based update to NOAA sea surface temperature data, another one of NOAA’s most widely-used datasets has gotten an AIupgrade. This ensures NOAA’s premier global land and ocean surface temperature dataset is more complete and accurate than ever before.

NOAAGlobalTemp is a dataset that combines long-term sea surface temperature (SST) and land surface temperature datasets. It creates a complete, accurate depiction of global temperature trends and identifies temperature anomalies (different-from-average temperatures). With the release of the January 2026 Global Temperature and Precipitation Analysis, NOAA transitioned to this new version 6.1.0 of the NOAAGlobalTemp dataset, a fully artificial intelligence-based global temperature dataset.

About NOAAGlobalTemp

NOAAGlobalTemp consists of land surface air temperature records from the Global Historical Climatology Network monthly (GHCNm), and sea surface temperatures (SST) from the Extended Reconstructed SST (ERSST). It has data from 1850–present and is presented on a 5×5 grid. NOAAGlobalTemp is a key component of the global temperature and precipitation analysis which is updated monthly.

Diagram illustrating how land surface air temperature and water surface temperature are combined for a globally-complete surface temperature in NOAA’s Global Surface Temperature dataset. Courtesy of NOAA NCEI

NOAAGlobalTemp is a reconstructed dataset, meaning that the entire period of record is recalculated each month with the newest and most accurate data. Based on those new calculations, the historical data can bring about updates to previously reported values. These factors, together, mean that the most recent data may take the place of past calculations and can affect the numbers reported in the monthly climate reports. The most current reconstruction analysis is always considered the most precise, and it is publicly available through Climate at a Glance.

NOAAGlobalTemp has been used by multiple science organizations such as the World Meteorological Organization and in assessments and the Bulletin of the American Meteorological Society (BAMS) State of the Climate reports. Private sector interests use the data for global climate monitoring and assessment, environmental research, and informational products and services for various industries and economic sectors, such as agriculture.

Power of Artificial Intelligence

In 2024, NCEI scientists began using artificial intelligence to improve land surface air temperature calculations. They created an artificial neural network (ANN), a method in artificial intelligence that teaches computers to learn complex patterns so they can produce insights and predictions. This ANN method replaced the traditional empirical orthogonal teleconnection (EOT) approach for the land surface air temperatures over land and the Arctic Ocean in NOAAGlobalTemp version 6.0.0. The ANN improved the accuracy of land surface air temperature reconstruction. 

With NOAAGlobalTemp version 6.1.0, the NOAAGlobalTemp goes further into AI, by extending ANN into sea surface temperatures. Version 6.1.0 uses the most recent release of the ERSST version 6, which uses ANN to fill in missing data points, creating a complete picture of global SSTs. Thanks to the use of these ANNs, the output of the NOAAGlobalTemp 6.1.0 is a fully AI-based global temperature dataset, providing more accurate data.