Technology Targeting with Remote Sensing.

Remote sensing data are nowadays being acquired within short intervals for the entire globe and the American and European space agencies provide most of their satellite data for free. This opens up opportunities for new remote sensing applications, such as characterizing entire regions to identify most promising areas for technology targeting. Increasing population growth and changing dietary habits in South Asia call for increased cereal production to achieve future food security. In the Delta area of Bangladesh, surface water is considered to be available in quantities large enough to support intensification by adding an irrigated dry season (‘Rabi’) crop. Fuel-efficient low lift axial flow pumps have shown to be suitable to carry water to fields that are within a buffer of four hundred meters of the rivers. However, information on how and where to target surface water irrigation efforts, while making the best use of available freshwater resources without exhausting supply, is currently lacking. Fallow and extensively cropped land that is adjacent to rivers and canals was deemed to be most suitable. Maximum tolerable salinity thresholds for surface water and soils were assumed to be 4 dS/m. Based on Landsat images, we first delineated rivers and cropland using a multi-resolution segmentation approach, followed by supervised classification with the random forest algorithm. The presence of water in the rivers in late March was then tested with the modified normalized difference water index (MNDWI) based on the green and middle infrared bands. Within the cropland layer, we then identified the following three land classes: fallow, low intensity and high intensity. This information, in conjunction with measured soil and water salinity data, allowed us to delineate regions which are most suitable for technology targeting. There are at least 100’000 ha of land that could be utilized to intensify food production.