Understanding transitions in rice paddy extent and management in the Vietnamese Mekong River Delta using Landsat data

Abstract:

Rice is a staple food crop for the majority of the world’s population, yet paddy fields are threatened by urban expansion, climate change, and degraded agricultural land. For example, Vietnam, the second largest exporter of rice globally, grows most of its rice in the Mekong River Delta at the country’s southern tip, yet this low-lying and heavily populated area is proving susceptible to land cover changes in the area. To properly monitor and manage the rice crops in this region, remote sensing of satellite imagery has been particularly useful; however, most efforts to map regional paddy area utilize coarse resolution MODIS or AVHRR data since the high temporal resolution of these datasets can overcome missing data issues due to clouds. Here, we aim to map the landscape using finer-scale Landsat data by generating dense time stacks over multiple growing seasons. First, we exploit dense stacks of data for circa 2000 and circa 2010 to classify rice using vegetation trajectories (EVI and NDWI). Next, these pixel-based rice maps are combined with image-based segments (generated using the open-source Mean-shift region-growing segmentation algorithm, which has been proven to optimally identify clusters within an image) to generate a polygon-based rice map using the majority rule. Results show that this method can map rice paddy agriculture with over 90% accuracy at a much finer spatial resolution than has ever been produced. Finally, this work also aims to differentiate between double- and triple-cropped rice paddies in the region, again by exploiting EVI trajectories, in an effort to determine how management practices have changed over the decade-long study period. Increasing the number of annual cropping cycles over the area can lead to soil degradation and lower yields per harvest, albeit larger total annual yields, so monitoring these practices is vital to understanding the sustainability of these agricultural systems.