Satellite-based monitoring of irrigated cropland dynamics in data-sparse environments

Water scarcity is a major constraint to agricultural productivity, food security, and economic development, in particular in low- and middle-income countries in regions such as Sub-Saharan Africa (SSA). However, our ability to effectively design, target, and implement interventions to reduce agricultural water insecurity is limited by a lack of data on the locations, dynamics, and outcomes of irrigated croplands in these regions. In this talk, we demonstrate how satellite remote sensing can be combined with machine learning methods to develop continuous fine-resolution maps of irrigated cropland areas in data-sparse environments distributed across SSA. Our results demonstrate that past large-scale irrigation projects initiated by governments and donors in SSA have failed to deliver on promises of agricultural expansion and intensification. In contrast, our mapping shows a more rapid recent growth in small-scale informal irrigation in SSA, typically initiated by farmers themselves and outside of official irrigation infrastructure and monitoring systems. We contextualise the economic, political, and social drivers of these historic irrigated cropland dynamics in SSA, while also discussing some of the opportunities and challenges that exist for mainstreaming use of satellite-based monitoring in future water management and policy in SSA.