Early and accurate prediction and simulation of grain crop yield can help maximize the revision and development of regional food policy, which is crucial for ensuring national food security. The development of unmanned aerial vehicle (UAV) technology is gradually gaining an advantage over satellite remote sensing at the field scale. In this study, we predicted maize yield using canopy vegetation indices (VIs) and crop phenology metrics obtained through UAV with ordinary least squares (OLS), stepwise multiple linear regression (SMLR) and gradient‐boosted regression tree (GBRT). The results reveal that the VIs extracted from UAV imagery had a high correlation with yield (R = 0.92), facilitating crop yield estimation. Additionally, coupling crop phenology significantly improved the prediction accuracy of SMLR, with the highest R² and lowest RMSE of 0.894, 1.238 × 10³ kg ha⁻¹, respectively. But, the enhancement of GBRT by this method was slender. Its simulation outperformed OLS and SMLR with dramatic R², RMSE, and MAE of 0.892, 1.189 × 10³ kg ha⁻¹, and 9.150 × 10² kg ha⁻¹, respectively. Moreover, the blister stage was deemed the optimal stage for maize yield prediction with an accuracy rate exceeding 81%. These demonstrated the feasibility of using UAV images to predict crop yields, providing an important reference at the field scale.

Grassland classification via remote sensing is essential for ecosystem monitoring and precision management, yet conventional satellite-based approaches are fundamentally constrained by coarse spatial resolution. To overcome this limitation, we harness high-resolution UAV multi-sensor data, integrating multi-scale image fusion with deep learning to achieve fine-scale grassland classification that satellites cannot provide. First, four categories of UAV data, including RGB, multispectral, thermal infrared, and LiDAR point cloud, were collected, and a fused image tensor consisting of 10 channels (NDVI, VCI, CHM, etc.) was constructed through orthorectification and resampling. For feature-level fusion, four deep fusion networks were designed. Among them, the MultiScale Pyramid Fusion Network, utilizing a pyramid pooling module, effectively integrated spectral and structural features, achieving optimal performance in all six image fusion evaluation metrics, including information entropy (6.84), spatial frequency (15.56), and mean gradient (12.54). Subsequently, training and validation datasets were constructed by integrating visual interpretation samples. Four backbone networks, including UNet++, DeepLabV3+, PSPNet, and FPN, were employed, and attention modules (SE, ECA, and CBAM) were introduced separately to form 12 model combinations. Results indicated that the UNet++ network combined with the SE attention module achieved the best segmentation performance on the validation set, with a mean Intersection over Union (mIoU) of 77.68%, overall accuracy (OA) of 86.98%, F1-score of 81.48%, and Kappa coefficient of 0.82. In the categories of Leymus chinensis and Puccinellia distans, producer’s accuracy (PA)/user’s accuracy (UA) reached 86.46%/82.30% and 82.40%/77.68%, respectively. Whole-image prediction validated the model’s coherent identification capability for patch boundaries. In conclusion, this study provides a systematic approach for integrating multi-source UAV remote sensing data and intelligent grassland interpretation, offering technical support for grassland ecological monitoring and resource assessment.

The Fifth IPCC Assessment Report indicates that climate change will affect crop growth and threaten the stability of food systems. Accumulated temperature, which is closely related to vegetation phenology and cropping systems, is an important indicator of heat in a region. Studying the history and future accumulated temperature changes can provide scientific reference for the change of crop phenology and cropping system, which is important for the improvement of grain production in China. Based on the MK trend test, MK abrupt change test and interpretable machine learning model, this study analyzes the spatial and temporal variation of accumulated temperature in China from 1979 to 2018, predicts its future variation based on CMIP6, and investigates the dominant influencing factors among different agricultural regions. The study found that (1) the accumulated temperature belt shows a northward shift and retreat trend toward higher altitudes, and the area of the high accumulated temperature belt increases year by year, leading to the narrowing of the area of the low accumulated temperature belt year by year, and the trend remains unchanged under the future scenario; meanwhile, the northward shift trend of the accumulated temperature belt is greatly mitigated and curbed under the SSP126 scenario. (2) The changes of accumulated temperature belt are mainly influenced by the increase of accumulated temperature duration days, and secondarily by the increase of temperature. The contribution brought by the first day of accumulated temperature from 1979 to 2018 is greater than that brought by the last day of accumulated temperature, while in the future scenario, on the contrary, changes in vegetation phenology delay should be given more attention.

Studying climate change’s impact on vegetation canopy growth and senescence is significant for understanding and predicting vegetation dynamics. However, there is a lack of adequate research on canopy changes across the lifecycles of different vegetation types. Using GLASS LAI (leaf area index) data (2001–2020), we investigated canopy development (April–June), maturity (July–August), and senescence (September–October) rates in Northeast China, focusing on their responses to preseason climatic factors. We identified that early stages saw canopy development acceleration, with over 71% of areas experiencing such acceleration in April and May. As the vegetation grew, the accelerating canopy development slowed down, and the canopy reached its maturation earlier. By analyzing the partial correlation between canopy growth and preseason climatic factors, it was identified that changes in canopy growth were most significantly affected by preseason air temperature. A positive correlation was observed in the early stages, which shifted to a negative correlation during canopy maturation and senescence. Notably, the transition timing varied among different vegetation types, with grasslands (June) occurring earlier than forests (July) and farmlands (August). Additionally, grassland canopy growth showed a stronger response to precipitation than forests and farmlands, with a lagged effect of 2.50 months. Our findings improve understanding of vegetation canopy growth across different stages, holding significant importance for ecological environmental monitoring, land-use planning, and sustainable development.

Exploring crop climatic yield potential under changing environments provides critical insights for enhancing land productivity and guiding agricultural adaptation. Recent studies demonstrate that unprecedented climate warming has threatened global food security, particularly in thermally privileged regions. Yet the impacts of both observed and projected climate change on crop yield potential—especially in thermally constrained mid‐ to high‐latitude zones—are still inadequately quantified. In this study, we investigated the response of maize ( Zea mays L.) yield potential to climate warming across Northeast Asia using the Python Package of Agro‐Ecological Zones model, integrating both historical observations and future climate projections. Our analysis reveals that climate warming will significantly prolong the growing season between 2020 and 2100 relative to historical baselines. Under the SSP2‐4.5 and SSP5‐8.5 scenarios, the thermal growing period is projected to extend by 2.02 and 4.15 days per decade (d·decade ⁻¹ ), respectively, while the hydrothermal growing period increased by 1.48 and 2.39 d·decade ⁻¹ . Our findings further indicate a pronounced northwestward migration of climatically viable maize cultivation zones under both scenarios, with potential areal expansions of 61.02% (5.78 × 10 ⁵ km ² ) and 76.73% (7.26 × 10 ⁵ km ² ) relative to historical baselines. As a result, the maize climatic yield potential under rainfed conditions is projected to increase at 0.19 and 0.30 t·ha ⁻¹ ·decade ⁻¹ for SSP2‐4.5 and SSP5‐8.5, respectively. Irrigation amplifies these gains, with yield rising by 0.24 and 0.36 t·ha ⁻¹ ·decade ⁻¹ under corresponding scenarios. These findings provide robust evidence for maintaining regional food security under climate change, revealing significant untapped potential. To capitalize on these warming‐induced agricultural opportunities while mitigating associated risks, we recommend implementing climate‐smart agriculture through: (i) optimized planting calendars, (ii) strategic redistribution of cultivated areas, and (iii) advanced precision irrigation systems.