The timely and accurate acquisition of spatial distribution information for crops holds significant scientific significance for crop yield estimation, management, and timely adjustments to crop planting structures. This study revolves around Henan and Shaanxi provinces, employing a spatiotemporal image data fusion approach. Utilizing the characteristic representation of the Normalized difference vegetation index (NDVI) temporal data from Sentinel-2 satellite imagery, a multi-scale segmentation of patches is conducted based on spatiotemporal fusion images. Decision tree classification rules are constructed through the analysis of crop phenological differences, facilitating the extraction of the crop spatial patterns (CSPs) in the two provinces. The classification accuracy is assessed, yielding overall accuracies of 91.11% and 90.12%, with Kappa coefficients of 0.897 and 0.887 for Henan and Shaanxi provinces, respectively. The results indicate the following: (1) the proposed method enhances crop identification capabilities; (2) an accuracy evaluation against the data from the Third National Land Resource Survey and provincial statistical yearbook data for 2022 demonstrates extraction accuracy exceeding 90%; and (3) an analysis of the crop spatial patterns in 2022 reveals that wheat and corn are the predominant crops in Henan and Shaanxi provinces, covering 74.42% and 62.32% of the total crop area, respectively. The research outcomes can serve as a scientific basis for adjusting the crop planting structures in these two provinces.

Freezing–thawing cycle (FTC) event plays a significant role in the regions with relative higher altitude and latitude, which is judged based on soil temperature. It affects soil environment and ecosystem productivity by altering soil physical structure, including physicochemical properties and water phase changes. Drawing on more than a decade of continuous measurements from 24 eddy‐covariance towers, we quantified how freeze–thaw cycles affect net ecosystem exchange (NEE) and ecosystem respiration (RE) and assessed the capacity of these carbon fluxes to withstand such events. The average percentile of ecosystem NEE in the first, middle, and last three stages of freeze–thaw events is 66.57%, 61.77%, and 57.21%, respectively. Prior to the freeze–thaw event, ecosystem respiration accounted for 28.07% of the reference level; during the event, this proportion declined to 24.38%, whereas it subsequently rose to 31.75% after the freeze–thaw disturbance. Resistance denotes an ecosystem's ability to preserve its functional stability throughout a freeze–thaw cycle. It is quantified as the ratio of the change in ecosystem carbon exchange before and during the freeze–thaw event to the corresponding change in soil temperature. Mean annual temperature (MAT), duration of freeze–thaw events, and elevation emerged as the primary drivers governing the resistance of both NEE and RE. Collectively, our results underscore how freeze–thaw cycles modulate carbon dynamics and why this interaction merits heightened attention under a changing climate.

Terraces constitute a critical form of land surface modification, serving both as essential agricultural resources and effective soil and water conservation measures. However, their morphological diversity, pronounced scale variation, and ambiguous geometric boundaries pose substantial challenges for automated extraction from high-resolution remote sensing imagery. Existing CNN- and Transformer-based methods still face difficulties in simultaneously preserving fine spatial details and modeling long-range contextual information. To address these limitations, this study proposes TerraceNet, a hybrid CNN–Transformer architecture with an encoder–dual-decoder design. The framework employs a ConvNeXt encoder to extract multi-scale features, which are subsequently aggregated by a dynamic fusion feature pyramid network (DF-FPN) and fed into two parallel decoders: a boundary decoder dedicated to fine-grained edge localization and a multi-scale Transformer decoder that incorporates boundary priors for global context modeling and final segmentation. Experimental results on a 2 m resolution GF-1 satellite imagery dataset from the Wuding River Basin in the Loess Plateau demonstrate that TerraceNet an IoU of 77.61% and an F1-Score of 87.39%. These results validate the effectiveness of the proposed architecture for extracting morphologically diverse terraces in complex terrain.