Smallholder maize area and yield mapping at national scales with Google Earth Engine

Use of Google Earth Engine to build “wall-to-wall” 10 m resolution maps of cropland and maize presence and maize yields in Kenya and Tanzania

From:
Department for International Development
Published
12 April 2019
Country:
Kenya, Tanzania
Document Type:
Journal Article
Theme:
Agriculture
Authors:
Jin, Z., Azzari, G, You, C, Di Tommaso, S, Aston, S., Burke, M., Lobell, D.B

Abstract

Highlights

  • National maps of crop and maize areas are generated at 10 m resolution in Africa.

  • Maize yields are mapped accurately without any ground calibration.

  • Independent soil data can explain over 70% of variability in yield estimates.

  • Soil nitrogen and organic carbon exhibit the strongest association with yields.

  • Google Earth Engine and Sentinel data offer new opportunities for mapping agriculture.

This work is part of a Stanford University project funded in part by Global Innovation Fund.

Citation

Jin, Z., Azzari, G., You, C., Di Tommaso, S., Aston, S., Burke, M. and Lobell, D.B., 2019. Smallholder maize area and yield mapping at national scales with Google Earth Engine. Remote sensing of environment, 228, pp.115-128.

Smallholder maize area and yield mapping at national scales with Google Earth Engine

Published 12 April 2019
Contents