Abstract
Soybean cultivation in China has significantly decreased due to the rising import of genetically modified soybeans from other countries. Understanding soybean’s extent and change information is of great value for national agricultural policy implications and global food security. Some previous studies have explored the quantitative relationships between crop area and spectral variables derived from remote sensing data. However, both those linear or non-linear relationships were expressed by global regression models, which ignored the spatial non-stationarity of crop spectral signature and may limit the prediction accuracy. This study presented a geographically weighted regression model (GWR) to estimate fractional soybean at 250 m spatial resolution in Heilongjiang Province, one of the most important food production regions in China, using time-series MODIS data and high-quality calibration information derived from Landsat data. A forward stepwise optimization strategy was embedded with the GWR model to select the optimal subset of independent variables for soybeans. Normalized Difference Vegetation Index (NDVI) of Julian day 233 to 257 when soybeans are filling seed was found to be the most important temporal period for sub-pixel soybean area estimation. Our MODIS-based soybean area compared well with Landsat-based results at pixel-level. Also, there was a good agreement between the MODIS-based result and census data at county level, with the coefficient of determination (R2) of 0.80 and the root mean square error (RMSE) was 340.21 km2. Additionally, F-test results showed GWR model had better model goodness-of-fit and higher prediction accuracy than the traditional ordinary least squares (OLS) model. These promising results suggest crop spectral variations both at temporal and spatial scales should be considered when exploring its relationship with pixel-level crop acreage. The optimized GWR model by combining an automated feature selection strategy has great potential for estimating sub-pixel crop area at regional scale based on remote sensing time-series data.
Highlights
Soybean, one of the most important crop types and commodities for vegetable oil and protein in the global agricultural market, comprises 5% of global cropland and ranks 5th among major crop categories [1,2]
We presented and evaluated a method for estimating the fractional soybean cultivation at 250 m spatial resolution using the Moderate Resolution Imaging Spectroradiometer (MODIS)-Normalized Difference Vegetation Index (NDVI) time series
We developed a geographically weighted regression model calibrated using sub-250 m percentage soybean information from Landsat, focusing on Heilongjiang region of China in 2013
Summary
One of the most important crop types and commodities for vegetable oil and protein in the global agricultural market, comprises 5% of global cropland and ranks 5th among major crop categories [1,2]. Reliable and timely information on soybean planting area is essential for global food security and agricultural policy implications, and of great value in understanding global land use changes under the changing climate. The short temporal revisit cycle and rich spectral information of such data allows for the identification of the subtle differences in phenological characteristics between various crop types and improvement for their spectral separability [7,8]. Since these data are available on a global scale and with nearly twenty years of data, there is great potential for large-region crop mapping including changes to crop cultivation through time. The one substantial challenge for using MODIS time series data for these purposes is their inherently coarse spatial resolution (>230 m), which increases the occurrence of mixtures of different land cover classes within a pixel and may result in significant errors in the estimated crop areas [9,10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
