Ammonia electrosynthesis via nitrate reduction offers a sustainable alternative to Haber–Bosch process, and this reaction involves an initial deoxygenation step from NO 3− to *NO 2 , followed by successive hydrogenation steps to NH 3 . Previous studies have mainly focused on the hydrogenation steps due to the competitive hydrogen evolution reaction, and overlooked that early‐stage adsorption and activation govern the overall reaction rate. Here we show that modulating the spin state of octahedral Co in Ni‐doped cobalt spinel markedly accelerates nitrate adsorption and activation. The high‐spin HS‐(Co 0.75 Ni 0.25 )Co 2 O x delivers a current density of 1.1 A cm −2 and achieves an ammonia yield rate of 83.64 mg·h −1 ·cm −2 with a Faradaic efficiency of 97.8% at −0.32 V versus RHE, substantially outperforming its low‐spin counterpart (52.53 mg·h −1 ·cm −2 , 94.8%). Operando characterizations combined with theoretical calculations reveal that high‐spin octahedral Co sites optimize orbital hybridization with nitrate and facilitate subsequent reduction steps. This electronic modulation lowers the Gibbs free energy change of the NO 3− to *NO 2 step by 1.55 eV, substantially reducing the energetic penalty for the initial nitrate activation. This work elucidates a spin‐state‐dependent mechanism for accelerated nitrate deoxygenation kinetics and establishes spin engineering as an effective strategy to promote rate‐limiting steps in tandem electrocatalysis, enabling industrially relevant ammonia electrosynthesis.
Comprehensive soil surveys necessitate the integration of multidimensional pedological information, ranging from the morphological delineation of horizons and the taxonomic identification of soil groups to the quantitative assessment of soil organic matter (SOM). These attributes collectively constitute the basis for interpreting pedogenesis and guiding sustainable soil management. However, conventional methods are limited by the subjectivity of expert judgment for horizon and soil group identification, and the time-consuming nature of laboratory analyses for SOM quantification. We developed a novel multimodal deep learning framework based on an improved Mask R-CNN architecture that integrates soil profile images with auxiliary soil property data to concurrently delineate soil horizons, classify soil groups, and quantify SOM. The model was trained on high-resolution soil profile images from 451 soil survey sampling sites spanning ten soil groups across Anhui Province, China. Data augmentation and transfer learning with pre-training on large general image datasets were employed to address the dataset size limitations and improve model generalization. In addition to accurately delineating master horizons, we evaluated three schemes for classifying transitional horizons, which are often ambiguously determined by expert assessments: (i) assigning the transitional horizon to one adjacent master horizon; (ii) assigning it to both neighboring master horizons as an overlapping section; and (iii) treating the transitional horizon as an independent layer. Scheme (iii) achieved the best overall performance, e.g., horizon delineation with accuracy = 0.925, recall = 0.933, F1-score = 0.929, and segmentation mean average precision (seg-mAP) = 0.918, soil group classification accuracy = 0.717 and prediction of SOM with R2 = 0.565. These results demonstrate that treating transitional horizons as independent layers yields superior segmentation. Consequently, this integrated framework provides a robust, automated solution for high-throughput soil resource assessment.