Four ways Google Research scientists are using empirical research support

Climate and sustainability: using weather satellites to monitor CO₂

Regular observation of carbon dioxide (CO)₂) started in Hawaii Mauna Loa Observatory In the late 1950s, the iconic produce keeling curve It documents rising global CO₂ Concentration in the Earth’s atmosphere. Mapping human greenhouse gas emissions and understanding how plants, trees, soils and oceans absorb those emissions requires us to track how CO₂ Varies across regions and over time. Current space-based CO₂ NASA like sensors Orbiting Carbon Observatory-2 (OCO-2) were designed to make high-precision observations, but they map only a small portion of the Earth’s surface and return to each location only once every 16 days. Geostationary satellites, such as goes east The satellite, designed to support weather forecasting, orbits the Earth at very high altitude and can scan an entire hemisphere every 10 minutes. However, none of the existing geostationary satellites were designed to map CO₂.

Google researchers use ERA to develop single-pixel, physics-guided neural networks to distill column-average CO₂ Signal from previous GOES observations. To do this, the model combines the data 16 wavelength bands Lower-troposphere meteorology, from GOES-East with solar angle and day of year. After training on sparse observations from OCO-2 and OCO-3The model was then able to obtain an estimate of column-averaged CO₂ Everywhere and every 10 minutes.

Research shared on International Workshop on Greenhouse Gas Measurements from Space demonstrates that the AI-developed model is able to take advantage of the high spatial and temporal density of GOES East observations to track column-averaged CO.₂ With unprecedented spatial and temporal resolution. Comparison of additional years of OCO-2 observations and independent ground-based data. Total Column Carbon Observation NetworkConfirm the model’s ability to capture actual CO₂ Variability.

These results show how AI algorithms can extract additional value from existing observational instruments, especially for resource-intensive satellite research missions. The project is one of many questions related to climate and greenhouse gases that Google researchers are exploring using ERA.