Satellite monitoring uncovers progress but large disparities in doubling crop yields

TL;DR

Across 15,000 villages in Rwanda, high-resolution satellite-based crop yield mapping is used to design spatially explicit productivity targets that, if met, would simultaneously ensure national goals without leaving anyone behind.

Abstract

High-resolution satellite-based crop yield mapping offers enormous promise for monitoring progress towards the SDGs. Across 15,000 villages in Rwanda we uncover areas that are on and off track to double productivity by 2030. This machine learning enabled analysis is used to design spatially explicit productivity targets that, if met, would simultaneously ensure national goals without leaving anyone behind.

Figures (13)

• Figure 1: Rwanda's national progress towards SDG 2.3 shown through maize yields. The green line demonstrates the linear growth rate required to meet SDG 2.3, the blue line represents national averages published by FAO from 2015-2022 fao_crops_2022, and the orange line is the average yield observed from our high-resolution dataset from 2019-2024 fankhauser_high_2024.
• Figure 2: Rwandan villages on and off track to meet SDG 2.3. A ratio of 2.0 or higher indicates that maize productivity is projected to double by 2030 based on current growth rates. See Supplementary Figs. \ref{['fig:map:lpi']} and \ref{['fig:map:upi']} for conservative and optimistic estimates, respectively.
• Figure 3: Sub-national inequality in maize yields. Average maize yields among villages in each yield decile from 2019 to 2024 (preliminary) and the inequality ratio between the highest and lowest yielding producing villages.
• Figure 4: Projected yields over the SDG period for each development scenario with requisite growth rates and 2030 yields. See Supplementary Figs. \ref{['fig:scenarios:lpi']} and \ref{['fig:scenarios:upi']} for conservative and optimistic estimates, respectively.
• Figure 5: Lower prediction interval of Fig. \ref{['fig:map']}