Satellite and unmanned aerial system (UAS) images are effective in monitoring crop growth at various spatial, temporal, and spectral scales. The objective of the study was to estimate cotton biomass at different growth stages using vegetation indices (VIs) derived from UAS and satellite images. This research was conducted in a cotton field in Hale County, Texas, in 2021. Data collected include 54 plant samples at different locations for three dates of the growing season. Multispectral images from UAS and Sentinel-2A images and dual-polarized (VV and VH) Synthetic Aperture Radar (SAR) data from the Sentinel-1 were acquired on or near ground data collections. VIs derived from the UAS and Sentinel-2A images coupled with the dual-polarized Sentinel-1 data were used to predict plant biomass using the random forest regression algorithm. The result showed that Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI), and Soil Adjusted Vegetation Index (SAVI), VV, and VH obtained from the UAS and Sentinel data were good predictors of biomass at different growth stages. This study provides insight into the modeling of cotton biomass using remote sensing techniques.