Page 379 - Special Topic Session (STS) - Volume 4
P. 379
STS2319 Lakshman N. R. et al.
selection of Landsat–MODIS pair images. To address this issue, we used a gap-
filling algorithm called Geostatistical Neighborhood Similar Pixel Interpolator
(GNSPI) (Zhu, Liu, and Chen 2012). Second, the ratio of valid pixels of MODIS
images from both Terra and Aqua were also limited due to clouds. Thus, we
use a pair of MODIS and Landsat images to train the STARFM algorithm and
apply it to the rest of the MODIS images when MODIS surface reflectance data
is available.
C. Paddy Rice Mapping and Land-Cover Classification
To identify paddy rice area from satellite images, we classify the land cover
of Thai Binh into six categories, namely croplands, barren, built-ups, water,
wetlands, and other vegetation. These were based on the International
Geosphere-Biosphere Programme (IGBP) classification scheme used by
MODIS global land cover product (Friedl et al. 2002). The six classes were
selected based on our visual interpretation of high-resolution images on
Google Earth and the knowledge from local field crew. Since paddy rice is the
predominant crop grown in Thai Binh during the rainy season, the category
“Croplands” refers to paddy rice in our study.
Our land cover classification uses a random forest classifier (RFC)
algorithm (Breiman 2001), which has been widely tested and proved robust
and efficient in the classification of remote sensing images (Hansen et al. 2000;
Pal 2005; Zhu et al. 2016). The training pixels were selected as evenly as
possible across the spatial extent of the images and excluded from pixel
sampling during the assessment of classification accuracy. For the
classification accuracy assessment, we follow the protocol set up by Olofsson
et al. (2014). We obtain the conjectured overall accuracy and user’s accuracy
from the cross validation of RFC and prescribe the expected standard errors
of user’s accuracy for the six classes as 0.01 for croplands, 0.05 for barren, 0.05
for built-ups, 0.02 for water, 0.05 for wetlands, and 0.10 for other vegetation.
D. Crop Yield Estimation
A three-stage stratified sampling methodology was employed for the
crop cutting survey, using an area frame that was constructed based on the
expected likelihood of finding paddy rice area. Training of field staff on crop-
cutting activities was conducted in September 2015 with significant attention
paid to the creation of the survey instruments and methodology for crop
cutting (Durante et. al 2018). The actual fieldwork took place between late
September 2015 and early November 2015, covering the period associated
with rice harvesting in Thai Binh. Crop cutting was implemented in random
2.5m x 2.5m square sub-plots in selected rice plots.
Usually, two variables are needed to predict yield – Aboveground Biomass
(AGB), and Harvest Index. AGB usually can be approximated by the peak
vegetation index, which can be derived from the Landsat–MODIS fusion data
368 | I S I W S C 2 0 1 9