Stefania Di Tommaso

TL;DR: In this article, the use of Google Earth Engine (GEE) was used to build a 10"m resolution map of cropland presence, maize presence, and maize yields for the main 2017 maize season in Kenya and Tanzania.

TL;DR: In this paper, partial least squares regression was used to select optimal spectral features in situ and with satellite reflectance data to develop predictive models of aboveground biomass for common emergent freshwater marsh species,Typhaspp andSchoenoplectus acutus, at two restored marshes in the Sacra- mento-San Joaquin River Delta, California, USA.

TL;DR: This work explores the use of crowdsourced data, Sentinel-2 and DigitalGlobe imagery, and convolutional neural networks (CNNs) for crop type mapping in India, and illustrates the potential of non-traditional, high-volume/high-noise datasets forcrop type mapping, some improvements that neural networks can achieve over random forests, and the robustness of such methods against moderate levels of training set noise.

TL;DR: This work used the now-public Landsat archive and cloud computing services to map corn and soybean at 30 m resolution across the US Midwest from 1999–2018, and validated the predictions on CDL 1999–2007 where available.

TL;DR: The regression covariates explain more than twice as much variation in calibrated satellite yields compared to self-reported or crop cut yields, suggesting that a satellite-based approach anchored in crop cuts can be used to track sorghum yields as well or perhaps better than traditional measures.