Information about the distribution and condition of the maize crop in East Africa is central for making food security assessments. Collecting this information on the ground is necessary but expensive, labor-intensive and data delivery often leads to significant delays. In this project we aim to complement the existing system with remote sensing information from time series of satellite imagery at coarse (MODIS), medium (Landsat) and high resolution (RapidEye/BlackBridge, Worldview-2) and from unmanned aerial vehicle (UAV) imagery.
The multi-agency project funded by USDA, "Agricultural Information System - Building Provincial Capacity in Pakistan for Crop Estimation, Forecasting, and Reporting based on the integral use of Remotely Sensed Data; GCP/PAK/125/USA" focuses on enhancing and improving current systems for the integral use of remotely sensed data into existing data collection, analysis,This project is part of a group of projects under the Spurring a Transformation for Agriculture through Remote Sensing (STARS) program at the University of Twente, Netherlands (Faculty of Geo-Information Science and Earth Observation, ITC), funded by the Bill and Melinda Gates Foundation (BMGF). Partner projects are implemented in Asia (Bangladesh), West Africa (Nigeria and Mali) and East Africa (Tanzania and Uganda). The University of Maryland (UMD) is leading activities for the East Africa project; main local partners are the Ministry of Agriculture Food Security and Cooperatives (MAFC), Tanzania; Sokoine University of Agriculture (SUA); Environmental Surveys, Information, Planning & Policy Systems (ESIPPS) Uganda Ltd.; International Institute for Applied Systems Analysis (IIASA); MANOBI; and Agricultural Assessments International Corporation (AAIC).
The main project activities are to enhance and adapt the MODIS-based Global Agricultural Monitoring System (GLAM) to local conditions for monitoring crop condition; develop an up-to-date national-scale data layer of agricultural areas including subsistence agriculture; research and test methods for identifying maize cropping systems from high resolution satellite and UAV imagery time series; and explore public and private sector applications of the resulting information.