Large-Scale Rice Mapping Using Multi-Task Spatiotemporal Deep Learning and Sentinel-1 SAR Time Series

Abstract

Timely and accurate cropland information at large spatial scales can improve crop management and support the government in decision making. Mapping the spatial extent and distribution of crops on a large spatial scale is challenging work due to the spatial variability. A multi-task spatiotemporal deep learning model, named LSTM-MTL, was developed in this study for large-scale rice mapping by utilizing time-series Sentinel-1 SAR data. The model showed a reasonable rice classification accuracy in the major rice production areas of the U.S. (OA = 98.3%, F1 score = 0.804), even when it only utilized SAR data. The model learned region-specific and common features simultaneously, and yielded a significant improved performance compared with RF and AtBiLSTM in both global and local training scenarios. We found that the LSTM-MTL model achieved a regional F1 score up to 10% higher than both global and local baseline models. The results demonstrated that the consideration of spatial variability via LSTM-MTL approach yielded an improved crop classification performance at a large spatial scale. We analyzed the input-output relationship through gradient backpropagation and found that low VH value in the early period and high VH value in the latter period were critical for rice classification. The results of in-season analysis showed that the model was able to yield a high accuracy (F1 score = 0.746) two months before rice maturity. The integration between multi-task learning and multi-temporal deep learning approach provides a promising approach for crop mapping at large spatial scales.

Improved LSTM Model for Boreal Forest Height Mapping Using Sentinel-1 Time Series

“…LSTMs were previously demonstrated in several remote sensing applications, particularly land cover mapping and crop monitoring [26][27][28][29][30][31][32][33][34]. However, to date, the use of LSTMs in forest attribute prediction utilising Earth Observation (EO) data was limited if at all reported with SAR image time series.…”

Crop mapping based on time-series synthetic aperture radar images using deep semantic segmentation model

“…With its temporal convolutional feature (TCF) and cascaded feature fusion (CFF) modules, our TSFUNet model sets itself apart from the competition by offering an advanced way of feature extraction and fusion that represents a significant improvement over current techniques. Moreover, Yang et al 27 and Lin et al 28 explored the role of temporal features in deep learning models for crop mapping. While their work highlights the significance of learning and combining these temporal components, our TSFUNet's integrated method differs from their divided learning sequences and designs in that it harmonizes both spatial and temporal data.…”

“…Moreover, Yang et al 27 . and Lin et al 28 . explored the role of temporal features in deep learning models for crop mapping.…”

Enhancing Crop Mapping Precision through Multi-Temporal Sentinel-2 Image and Spatial-Temporal Neural Networks in Northern Slopes of Tianshan Mountain

“…Multi-temporal crop classification methods (MTCCN) leveraging RNNs adeptly preserve temporal crop information during their growth phase for classification, making them a preferred approach in the domain. For instance, Lin et al [34] employed a multi-task learning LSTM framework, achieving an impressive 98.3% accuracy in classifying major rice-producing regions in the U.S. using Sentinel-1 SAR images. Similarly, Khan et al [35] utilized LSTM and Sentinel-2 imagery to classify wheat, rice, and sugarcane, obtaining up to 93.77% accuracy.…”