 This article describes the development and evaluation of a neural network algorithm to generate 30-year-long global vegetation data sets of leaf area index, LAI, and fraction of photosynthetically active radiation absorbed by vegetation, FPAR. The algorithm was trained using new improved third-generation global inventory modeling and mapping studies, GIMMS Normalized Difference Vegetation Index, NDVI 3G, and Best Quality Terra Moderate Resolution Imaging Spectroradiometer, MODIS, LAI and FPAR products. The resulting data sets have attributes of 15-day temporal frequency, one 12th degree spatial resolution, and a temporal span of July 1981 to December 2011. These data sets were assessed for their suitability for scientific research in other disciplines through comparisons with field measurements, existing alternate satellite database products, plant growth limiting climatic variables, and correlations with large-scale circulation anomalies. The results showed that the LAI 3G and FPAR 3G data sets are suitable for research use in other disciplines, as they consistently overestimated satellite-based estimates of leaf area and simulated delayed peak seasonal values in the northern latitudes. These data sets can be obtained freely from the NASA Earth Exchange NEX website. This article was authored by Ranga Bminini, Shirlong Pyao, Ramakrishna Arnamani and others. We are article.tv, links in the description below.