Rice Mapping in Training Sample Shortage Regions Using a Deep Semantic Segmentation Model Trained on Pseudo-Labels

A deep semantic segmentation model-based method can achieve state-of-the-art accuracy and high computational efficiency in large-scale crop mapping. However, the model cannot be widely used in actual large-scale crop mapping applications, mainly because the annotation of ground truth data for deep semantic segmentation model training is time-consuming. At the operational level, it is extremely difficult to obtain a large amount of ground reference data by photointerpretation for the model training. Consequently, in order to solve this problem, this study introduces a workflow that aims to extract rice distribution information in training sample shortage regions, using a deep semantic segmentation model (i.e., U-Net) trained on pseudo-labels. Based on the time series Sentinel-1 images, Cropland Data Layer (CDL) and U-Net model, the optimal multi-temporal datasets for rice mapping were summarized, using the global search method. Then, based on the optimal multi-temporal datasets, the proposed workflow (a combination of K-Means and random forest) was directly used to extract the rice-distribution information of Jiangsu (i.e., the K-RF pseudo-labels). For comparison, the optimal well-trained U-Net model acquired from Arkansas (i.e., the transfer model) was also transferred to Jiangsu to extract local rice-distribution information (i.e., the TF pseudo-labels). Finally, the pseudo-labels with high confidences generated from the two methods were further used to retrain the U-Net models, which were suitable for rice mapping in Jiangsu. For different rice planting pattern regions of Jiangsu, the final results showed that, compared with the U-Net model trained on the TF pseudo-labels, the rice area extraction errors of pseudo-labels could be further reduced by using the U-Net model trained on the K-RF pseudo-labels. In addition, compared with the existing rule-based rice mapping methods, he U-Net model trained on the K-RF pseudo-labels could robustly extract the spatial distribution information of rice. Generally, this study could provide new options for applying a deep semantic segmentation model to training sample shortage regions.

Automated summary

This study introduces a workflow that utilizes a deep semantic segmentation model to extract rice distribution information in regions with limited training samples. By training the model on pseudo-labels, the time-consuming annotation process for ground truth data can be reduced. Experimental results show that the proposed method outperforms existing approaches in terms of accurately extracting rice area and spatial distribution information.