Accurate mapping of winter wheat over a large area is of great significance for guiding policy formulation related to food security, farmland management, and the international food trade. Due to the complex phenological features of winter wheat, the cloud contamination in time-series imagery, and the influence of the soil/snow background on vegetation indices, there remains no effective method for mapping winter wheat at a medium spatial resolution (10–30 m). In this study, we proposed a novel method called phenology-time weighted dynamic time warping (PT-DTW) for identifying winter wheat based on Sentinel 2A/B time-series data. The main advantages of PT-DTW include (1) the use of phenological features in two periods, i.e., the greenness increase before winter and greenness decrease after heading, which are common to all winter wheat and are distinct from the features of other land cover types, and (2) the use of the normalized differential phenology index (NDPI) instead of traditional vegetation indices to provide more robust vegetation information and to suppress the adverse impacts of soil and snow cover, especially during the before-winter growth period. The proposed PT-DTW method was employed for winter wheat mapping based on Sentinel 2A/B data on the Huang-Huai Plain, China. Validation with visually interpreted samples showed that the produced winter wheat map achieved an overall classification accuracy of 89.98% and a kappa coefficient of 0.7978, outperforming previous winter wheat classification methods. Moreover, the planting area derived from PT-DTW agreed well with census data at the municipal level, with a coefficient of determination of 0.8638, indicating that the winter wheat map produced at 20 m resolution was reliable overall. Therefore, the PT-DTW method is recommended for winter wheat mapping over large areas.

Phenology provides important information for wheat growth management and the estimation of wheat yield and quality. The relative threshold method has been widely used to retrieve phenological metrics from remotely sensed data owing to its simplicity. However, the thresholds vary substantially among phenological metrics and locations, hampering us from effectively detecting spatial and temporal variations in winter wheat phenology. In this study, we developed a calibrated relative threshold method based on ground phenological observations. Compared with the traditional relative threshold method, our method can minimize the bias and uncertainty caused by unreasonable thresholds in determining phenological dates. On this basis, seven key phenological dates and three growth periods of winter wheat were estimated from long-term series (1981–2016) of the remotely sensed Normalized Difference Vegetation Index for North China (106°18′–122°41′E, 28°59′–39°57′N). Results show that the pre-wintering phenological dates of winter wheat (i.e., emergence and tillering) occurred in December in the south and in mid- to late- October in the north, while the post-wintering phenological dates (i.e., green-up onset, jointing, heading, milky stage, and maturity) exhibited the opposite pattern, that is, January to May in the south and February to June in the north. Consequently, the vegetative growth period increased from 49 days in the south to 77 in the north, and the reproductive growth period decreased from 51 days to 29 days. At the regional scale, all winter wheat phenological dates predominantly advanced, with the most pronounced advancement being for green-up onset (–0.10 days/year, p > 0.1), emergence (–0.09 days/year, p > 0.1), and jointing (–0.08 days/year, p > 0.1). The vegetative growth period and reproductive growth period at the regional scale predominantly extended by 0.03 (p > 0.1) and 0.09 (p < 0.001) days/year, respectively. In general, the later phenological events (i.e., heading, milky stage, and maturity) tended to advance with higher temperature, while the earlier phenological events (i.e., emergence, tillering, green-up onset, and jointing) showed a weak correlation with temperature, suggesting that the earlier events might be mainly affected by management while later ones were more responsive to warming. These findings provide a critical reference for improving winter wheat management under the ongoing climate warming.

Machine learning (ML) models trained with remote sensing data have the potential to improve cereal yield estimation across various geographic scales. However, the complexity and heterogeneity of agricultural landscapes present significant challenges to the robustness of ML-based field-level yield estimation over large areas. In our study, we propose decomposing the landscape complexity into homogeneous zones using existing landform, agroecological, and climate classification datasets, and subsequently applying stratum-based ML to estimate cereal yield. This approach was tested in a heterogeneous region in northern Morocco, where wheat is the dominant crop. We compared the results of the stratum-based ML with those applied to the entire study area. Sentinel-1 and Sentinel-2 satellite imagery were used as input variables to train three ML models: Random Forest, Extreme Gradient Boosting (XGBoost), and Multiple Linear Regression. The results showed that the XGBoost model outperformed the other assessed models. Furthermore, the stratum-based ML approach significantly improved the yield estimation accuracy, particularly when using landform classifications as homogeneous strata. For example, the accuracy of XGBoost model improved from R² = 0.58 and RMSE = 840 kg ha⁻¹ when the ML models were trained on data from the entire study area to R² = 0.72 and RMSE = 809 kg ha⁻¹ when trained in the plain area. These findings highlight that developing stratum-based ML models using landform classification as strata leads to more accurate predictions by allowing the models to better capture local environmental conditions and agricultural practices that affect crop growth.