The STARFM algorithm uses comparisons of one or more pairs of observed Landsat/MODIS maps, collected on the same day, to predict maps at Landsat-scale on other MODIS observation dates. STARFM was initially developed at the NASA Goddard Space Flight Center by Dr. Feng Gao. This version (v1.2) has been greatly improved in computing efficiency (e.g. one run for multiple dates and parallel computing) for large-area processing (Gao et al., 2015). Additional improvements (e.g. Landsat and MODIS images co-registration, daily MODIS nadir BRDF-adjusted reflectance) in the operational data fusion system (Wang et al., 2014) are beyond the STARFM program and are not included in this package. Improvement and continuous maintenance are being undertaken in the USDA-ARS Hydrology and Remote Sensing Laboratory (HRSL), Beltsville, MD by Dr. Feng Gao.

The Ogallala Agro-Climate Tool is a Visual Basic application that estimates irrigation demand and crop water use over the Ogallala Aquifer region.

An interactive computer program was developed to simulate the interactions among the above factors. It shows how changing one factor impacts the outcome of the other factors for a single growing season. The user selects a climate, a crop, and soil characteristics from menu lists, and then sets the water table depth and quality, irrigation (river or well) water quality and then develops an irrigation schedule. On execution, the relative yield reductions due to over irrigation, under irrigation, and salinity, water table rise or fall and surface runoff are shown numerically for the growing season. Soil water content, soil salinity, water table depth changes and rain and irrigation events during the season are also shown graphically.

With the goal of automating bloom intensity estimation, a method a novel method for apple flower detection is presented in which a pre-trained convolutional neural network (CNN) is fine-tuned to become specially sensitive to flowers.