Modeling Global Urban Air Temperature Trends Using Machine Learning on Satellite Land Surface Data

Accurately forecasting air temperature is vital for gaining insights into atmospheric phenomena. However, the limited availability of air temperature data presents significant challenges for conducting comprehensive analyses and predictions. While land surface temperature (LST) and air temperature are often shown to be correlated, data for the latter is not as readily accessible as LST data, making integrated analysis and forecasting difficult. NASA’s Moderate Resolution Imaging Spectroradiometer (MODIS) satellite provides continuous global coverage of LST data. However, Automated Surface Observing Systems (ASOS) weather stations that capture air temperature data are only available at specific points, creating a lack of data between ASOS stations where only MODIS data is available, especially in urban areas. A supervised machine learning model was developed using the K-Nearest-Neighbors (KNN) regression algorithm to model air temperature trends and predict air temperature values when given land surface data from the MODIS satellite. 227 weather stations spanning multiple cities across 125 countries around the world were randomly selected. LST data was obtained from MODIS observations at 1 km resolution at the weather station locations. The model effectively utilizes LST data from both Terra and Aqua MODIS satellites, considering both day and night observations, in conjunction with Normalized Difference Vegetation Index (NDVI) data from Terra and Aqua to produce air temperature value predictions. It performs with an average accuracy of 85%, RMSE of 4.27 °C, and a median absolute error of 3.11 °C. Notably, this model excels in accurately predicting and modeling air temperature data not only for the United States but also for other nations. It even has the capability to predict air temperature in regions lacking ASOS air temperature data, thereby bridging data gaps. This unique capability opens up new avenues for generating comprehensive air temperature forecasts for urban regions with heterogeneous land cover types. The model has the potential to continue predicting future air temperature trends and values across the world, fill in gaps in data, and provide spatial heat maps of air temperature estimates to create a more comprehensive understanding of air temperature in urban settings.