A Novel Two-Step Framework for Mapping Fraction of Mulched Film Based on Very-High-Resolution Satellite Observation and Deep Learning

The fraction of mulched film is of great significance for evaluating the agricultural water-saving effect and controlling environmental plastic pollution. Unfortunately, there is no work that has been done to obtain this parameter due to the mixed pixel issue of satellite imagery with medium and low resolutions, until now. In this study, we proposed a novel two-step framework for mapping fraction of mulched film based on very-high-resolution satellite observation and deep learning. The first step is extracting the extent of the mulched film based on a new few-shot learning model named parameter transition convolutional neural network (PT-CNN), which aims to increase the extraction accuracy and overcome the lack of labeled training data. The second step is retrieving the fraction of the mulched film at pixel scale based on a spectrum analysis method. The result shows that the proposed PT-CNN outperforms several state-of-the-art methods in mulched film extracting, with
$F1$
-scores of 97.09% and 98.65% for white and black mulched film, respectively. Meanwhile, the retrieved pixel scale fraction of mulched film shows high consistency to in situ measurement, with mean absolute error (MAE) of 0.0321. The proposed method can be useful in agricultural water resource management and environmental governance.