Long history paddy rice mapping across Northeast China with deep learning and annualresult enhancement method

Abstract

Northeast China, a significant production base for paddy rice, has received lots of attention in crop mapping. However, understanding the spatiotemporal dynamics of paddy rice expansion in this region remains limited, making it difficult to track the changes in paddy rice planting over time. For the first time, this study utilized multi-sensor Landsat data and a deep learning model, the full resolution network (FR-Net), to explore the annual mapping of paddy rice for Northeast China from 1985 to 2023 (available at 10.6084/m9.figshare.27604839.v1, Zhang et al., 2024). First, a cross-sensor paddy training dataset comprising 155 Landsat images was created to map the paddy rice. Then, we developed the annual result enhancement (ARE) method, which considers the differences in category probability of FR-Net at different stages to diminish the impact of the limited training sample in large-scale and across-sensor paddy rice mapping. ARE integrates differences in category probability and confidence levels of the FR-Net across phenological stages, effectively reducing classification uncertainty. This approach could mitigate the impact of limited training sample on large-scale and across-sensor paddy rice mapping. The accuracy of the paddy rice dataset was evaluated using 107 954 ground truth samples. In comparison to traditional rice mapping methods, the results obtained using the ARE method showed a 5 % increase in the F1 score. The overall mapping result obtained from the FR-Net model and ARE methods achieved high average values of user accuracy (UA) of paddy, producer accuracy (PA) of paddy, overall accuracy (OA), F1 score, and Matthews correlation coefficient (MCC) of 0.93, 0.91, 0.91, 0.92, and 0.82, respectively. The study revealed that the area used for paddy rice cultivation in Northeast China increased from 1.11 × 104 to 6.45 × 104 km2 between 1985 to 2023. Between 1985 and 2023, there was an overall expansion of 5.34 × 104 km2 in the paddy rice cultivation area, with the highest growth (4.33 × 104 km2) occurring in Heilongjiang province. This study shows that long-history crop mapping could be achieved with deep learning, and the result of paddy rice will be beneficial for making timely adjustments to cultivation patterns and ensuring food security.