A Multi-Modal Approach for Monitoring Changes in Agriculture in the Mekong River Delta

Smallholder farms in South East Asia are characterized
by small irregular field patterns, dense cloud cover and
haze which limits our ability to observe changes in
agriculture land-use. Very-high resolution (VHR, < 5
m) Earth observing (EO) satellites have grown into
constellations with global repeat coverage that can
support multiple observations within a growing season.
Here we present a multi-modal approach to map and
monitor changes in agriculture at the field scale in the
Mekong River Delta with VHR optical imagery from
Worldview-1, 2 and 3, and synthetic aperture radar
(SAR) from Sentinel-1. Our approach leverages the
benefits of SAR and VHR imagery with geographic
object-based image analysis (GEOBIA) in a high-end
computing environment to rapidly map the distribution
and size of agriculture fields that are not observable at
moderate resolution (> 30 m) in regions with dense
persistent cloud cover and haze from biomass burning.