Leaf area index (LAI) is often used to quantify plant production and evapotranspiration with terrestrial ecosystem models (TEMs). This study evaluated theLAIsimulation in North America using a data assimilation technique and a process‐based TEM as well as in situ and satellite data. We first optimized the parameters related toLAIin theTEMusing a Markov Chain Monte Carlo method, and AmeriFlux site‐level and regionalLAIdata from advanced very high‐resolution radiometer. The parameterized model was then verified with the observed monthlyLAIof major ecosystem types at site level. SimulatedLAIwas compared well with the observed data at sites of Harvard Forest (R² = 0.96), University of Michigan Biological Station (R² = 0.87), Howland Forest (R² = 0.96), Morgan Monroe State Forest (R² = 0.85), Shidler Tallgrass Prairie (R² = 0.82), and Donaldson (R² = 0.75). The root‐mean‐square error (RMSE) between modeled and satellite‐based monthlyLAIin North America is 1.4 m²/m²for the period of 1985–2010. The simulated average monthlyLAIin recent three decades increased by (3 ± 0.5)% in the region, with 1.24, 1.46, and 2.21 m²/m²on average, in Alaska, Canada, and the conterminous United States, respectively, which is consistent with satellite data. The model performed well for wet tundra, boreal forest, temperate coniferous forests, temperate deciduous forests, grasslands, and xeric shrublands (RMSE < 1.5 m²/m²), but not for alpine tundra and xeric woodlands (RMSE > 1.5 m²/m²). Both the spring and fallLAIin the 2000s are higher than that in the 1980s in the region, suggesting that the leaf phenology has an earlier onset and later senescence in the 2000s. The averageLAIincreased in April and September by 0.03 and 0.24 m²/m², respectively. This study provides a way to quantifyLAIwith ecosystem models, which will improve future carbon and water cycling studies.

To better understand the role of terrestrial ecosystems in the global carbon cycle and their feedbacks to the global climate system, process-based biogeochemistry models need to be improved with respect to model parameterization and model structure. To achieve these improvements, the spin-up time for those differential equation-based models needs to be shortened. Here, an algorithm for a fast spin-up was developed by finding the exact solution of a linearized system representing the cyclo-stationary state of a model and implemented in a biogeochemistry model, the Terrestrial Ecosystem Model (TEM). With the new spin-up algorithm, we showed that the model reached a steady state in less than 10 years of computing time, while the original method requires more than 200 years on average of model run. For the test sites with five different plant functional types, the new method saves over 90 % of the original spin-up time in site-level simulations. In North American simulations, average spin-up time savings for all grid cells is 85 % for either the daily or monthly version of TEM. The developed spin-up method shall be used for future quantification of carbon dynamics at fine spatial and temporal scales.

The weakly supervised aircraft fine-grained detection task remains challenging due to the lack of fine-grained category labels. In addition, the high inter-class similarity among aircraft categories and complex background interference further hinders discriminative feature learning. To address these challenges, we propose a weakly supervised fine-grained aircraft detection framework based on prior-knowledge prototype learning. Specifically, a Prior-knowledge-based Soft-label Generator (PSG) is designed to exploit geometric and semantic priors, enabling the propagation of fine-grained category annotations from a few annotated samples to large-scale unlabeled data through reliable soft-label generation. To alleviate category ambiguity caused by highly similar aircraft categories, a Text Prototype Alignment (TPA) strategy is introduced to align vision-language semantic knowledge with the remote sensing domain and construct discriminative semantic prototypes. Furthermore, a Feature Purification Module (FPM) is developed to suppress background noise through morphology-guided feature purification and enhance aircraft-specific representations. Experiments on the FAIR1M-Aircraft dataset demonstrate that the proposed method achieves 30.5% mAP with only 50 fine-grained annotated images, outperforming the baseline by 10.1 mAP points.

The rapid proliferation of high-resolution remote sensing video (RSV) has made object segmentation an increasingly critical yet challenging task. Existing methods face two fundamental limitations in this domain: (1) the intrinsic complexity of RSVs arising from diminutive object sizes, dense distributions, and drastic scale variations; (2) prohibitive computational overhead and latency caused by the massive spatial resolution of remote sensing imagery. To address these challenges, we propose Trajectory-SAM, a novel object trajectory-guided segmentation framework tailored for rapid and accurate object segmentation in RSVs. Specifically, we first employ a Graph Neural Network to extract representative keyframes, improving data utilization efficiency while suppressing attention drift and interpretation bias induced by redundant frames. We then introduce Temporal-LoRA, a parameter-efficient fine-tuning strategy for the Segment Anything Model (SAM), substantially enhancing its spatiotemporal contextual understanding in remote sensing domains. Finally, we devise a sample-augmentation-based knowledge distillation strategy to accelerate inference without sacrificing segmentation quality. Extensive experiments on the SAT-MTB, iSAID, and VHR-10 datasets demonstrate that our proposed Trajectory-SAM achieves superior performance, establishing a compelling trade-off between accuracy and speed.

To better understand the role of terrestrial ecosystems in the global carbon cycle and their feedbacks to the global climate system, process-based biogeochemistry models need to be improved with respect to model parameterization and model structure. To achieve these improvements, the spin-up time for those differential equation-based models needs to be shortened. Here, an algorithm for a fast spin-up was developed and implemented in a biogeochemistry model, the Terrestrial Ecosystem Model (TEM). With the new spin-up algorithm, we showed that the model reached a steady state in less than 10 years of computing time, while the original method requires more than 200 years on average of model run. For the test sites with five different plant function types, the new method saves over 90 % of the original spin-up time in site-level simulations. In North America simulations, average spin-up time saving for all grid cells is 85 % for either daily or monthly version of TEM. The developed spin-up method shall greatly facilitate our future quantification of carbon dynamics at fine spatial and temporal scales.