||Defense Meteorological Satellite Program/Operational Linescan System (DMSP/OLS) and Suomi National Polar-Orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP/VIIRS) nighttime light data are the two most commonly used indicators of gross domestic product (GDP) estimation. Few studies explore the potential of daytime satellite data for estimating GDP. This study demonstrates a linear support vector machine (Linear-SVM) model to estimate GDP over Hubei province and Guangdong province, China, in 2013 from Moderate Resolution Imaging Spectroradiometer (MODIS) data. Also, a comparison of MODIS data with DMSP/OLS and NPP/VIIRS nighttime light data was conducted. Results show that the Linear-SVM model (Hubei: R2 = 0.66, 0.71, 0.92; Guangdong: R2 = 0.37, 0.32, 0.67) has better model performance than simple linear regression (R2 = 0.54, 0.59, 0.86; R2 = 0.23, 0.23, 0.63) based on DMSP/OLS nighttime lights, DMSP/OLS corrected nighttime lights, and NPP/VIIRS nighttime lights, respectively, while MODIS data has model performance of R2 = 0.77 (Hubei) and R2 = 0.55 (Guangdong) based on the Linear-SVM model, further indicating that MODIS data improves the accuracy of GDP estimation compared to DMSP/OLS nighttime lights. In addition, MODIS data produced finer GDP estimation than DMSP/OLS nighttime lights, especially in dark and light saturated areas. Although MODIS data is not as accurate as the NPP/VIIRS nighttime lights for estimating GDP, the proposed method could be applicable to other daytime satellite data and has broad prospects for improving the spatial and temporal resolution of regional economic activity and improving estimation accuracy.