AgriSense-STARS: Advancing Methods of Agricultural Monitoring for Food Security in Smallholder Regions - the Case for Tanzania

Thursday, 17 December 2015: 16:00
2006 (Moscone West)
Jan Dempewolf1, Inbal Becker-Reshef2, Catherine Lilian Nakalembe3, Siza Tumbo4, Sixbert Maurice4, Boniface Mbilinyi4, Onasimbo Ntikha5, Matthew Hansen1, Christina Jade Justice3, Bernard Adusei3 and Victor Kongo6, (1)University of Maryland, College Park, MD, United States, (2)University of Maryland College Park, Geographical Sciences, College Park, MD, United States, (3)University of Maryland College Park, College Park, MD, United States, (4)Sokoine University of Agriculture, Morogoro, Tanzania, (5)Ministry of Agriculture, Food and Cooperatives, National Food Security Division, Dar es Salaam, Tanzania, (6)4Independent Research Consultant, Dar es Salaam, Tanzania
In-season monitoring of crop conditions provides critical information for agricultural policy and decision making and most importantly for food security planning and management. Nationwide agricultural monitoring in countries dominated by smallholder farming systems, generally relies on extensive networks of field data collectors. In Tanzania, extension agents make up this network and report on conditions across the country, approaching a “near-census”. Data is collected on paper which is resource and time intensive, as well as prone to errors. Data quality is ambiguous and there is a general lack of clear and functional feedback loops between farmers, extension agents, analysts and decision makers. Moreover, the data are not spatially explicit, limiting the usefulness for analysis and quality of policy outcomes.

Despite significant advances in remote sensing and information communication technologies (ICT) for monitoring agriculture, the full potential of these new tools is yet to be realized in Tanzania. Their use is constrained by the lack of resources, skills and infrastructure to access and process these data. The use of ICT technologies for data collection, processing and analysis is equally limited.

The AgriSense-STARS project is developing and testing a system for national-scale in-season monitoring of smallholder agriculture using a combination of three main tools, 1) GLAM-East Africa, an automated MODIS satellite image processing system, 2) field data collection using GeoODK and unmanned aerial vehicles (UAVs), and 3) the Tanzania Crop Monitor, a collaborative online portal for data management and reporting. These tools are developed and applied in Tanzania through the National Food Security Division of the Ministry of Agriculture, Food Security and Cooperatives (MAFC) within a statistically representative sampling framework (area frame) that ensures data quality, representability and resource efficiency.