Classification Of Winter Land Cover In New Zealand Hill Country For Risky Practice Identification

IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM(2020)

Cited 0|Views8
No score
Abstract
Research in New Zealand indicates that winter forage grazing on steep land creates a high risk of sediment loss. This loss can have a significant impact on sediment and associated nutrient content of waterways. A national-scale map of winter forage cropping on land with slope of greater than 7 degrees was created using spectral and temporal analysis of Sentinel-2 imagery. Images between March and September 2018 were masked for cloud, cloud shadow, and snow using a time-series-controlled layer. Land cover classification using maximum likelihood estimation was applied. Field boundaries were generated using the temporal image stack so that field-level homogeneity could be exploited. The mode classification per-polygon and bare ground observation dates allowed polygons totaling 0.69% of New Zealand's agricultural hill country to be stratified into three certainty levels of risky agricultural practice. For the first time, extent and spatial distribution of these practices have been estimated for policy development.
More
Translated text
Key words
Land cover classification, Sentinel-2, winter forage, image segmentation, cloud masking
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined