Accurate thermospheric density modeling is critical for predicting atmospheric drag and satellite orbit evolution. Empirical models often show biases under different solar and geomagnetic conditions. In this study, we developed TT-NRL, a hybrid temporal convolu tional network(TCN)-Transformer framework designed to calibrate the NRLMSISE-00 using satellite orbit data. The model is trained on CHAMP accelerometer-derived densities combined with space weather and positional parameters, using the density ratio between observations and model outputs as the target. Evaluations across annual, monthly, and daily scales demonstrate consistent error reduc-tions compared with NRLMSISE-00 during both quiet and storm-time conditions. TT-NRL provides balanced improvements in both short and long-term scenarios, establishing it as a reliable framework for enhancing empirical thermospheric density models. 2025 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining. Al training, and similar technologies.

With the rapid increase in low Earth orbit space objects, accurate orbit prediction (OP) is becoming critical for satellite safety and space environment management. Traditional physics-based OP methods, especially those relying on publicly available two-line element (TLE) data, often struggle with accuracy due to complex orbital perturbations. However, the availability of long-term, large-scale TLE datasets enables the analysis of underlying orbital error patterns. This study proposes a high-precision OP error compensation method solely based on TLE data. A bidirectional long short-term memory (BiLSTM) neural network is used to model time-varying orbital error trends and correct TLE/simplified general perturbation model 4-based predictions. Experiments on 340 low Earth orbit objects show that the BiLSTM framework effectively captures temporal error patterns, achieving an average accuracy improvement of 82% and a compensation effectiveness exceeding 94% across all targets. To assess the model’s robustness, the impact of training sample size and sampling intervals is examined, revealing that proper data configurations markedly influence compensation performance. Comparative analysis with other deep learning models (recurrent neural network, gated recurrent unit, long short-term memory, and convolutional neural network) further confirms the superior fitting and correction ability of BiLSTM. This study highlights the potential of BiLSTM networks to enhance the accuracy and reliability of TLE-based OP, providing a valuable approach for improving space situational awareness.

With the increasing number of satellites being launched and the accumulation of space debris, the atmospheric density in low Earth orbit is becoming increasingly important for precise orbit determination. This study aims to optimize the accuracy of atmospheric density prediction in low Earth orbit using support vector regression (SVR). The SVR-based model uses high-resolution geomagnetic data and CHAMP satellite observation data to optimize the density of JB2008. Tests were conducted under various solar activity conditions and different periods. The results show that SVR improves the RMSE of the original model, the improvement rate of RMSE is between 10 % and 40 % and directly reduce MAPE to 2 % similar to 25 %. (c) 2024 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

This study aims to enhance Low Earth Orbit (LEO) satellite orbit prediction accuracy. We propose the Precise Orbit Determination with Optimized Perturbations (PODOP) method, considering Earth’s non-spherical gravity, atmospheric drag, etc., and a Long Short-Term Memory (LSTM)-based approach for orbital element time series. Validation shows that PODOP’s 10-day median error is 8.1 km (19% larger than Simplified General Perturbations (SGP4)’s 10.1 km) and LSTM’s 10-day median error is 5.3 km, outperforming SGP4 (48.5 km) and PODOP and improving constellation management and collision prevention.

Functional fatigue in the superelastic NiTi shape memory alloys occurs due to the accumulation of dislocations and retention of martensite with the cyclic loading. These mechanisms reduce the amount of the material available for the stress-induced transformation and, thus, lower the elastocaloric effect that originates from the stress-induced latent heat variations. In this study, the individual contributions of the micromechanisms responsible for the functional fatigue in superelastic NiTi at different maximum tensile stress (σmax) are critically examined. Results show that the elastocaloric effect degrades significantly with cycling, and the saturated degraded value increases with σmax; the steady-state adiabatic temperature change is unexpectedly non-proportional to σmax. An overheating treatment (‘healing’) after mechanical fatigue reverts the retained martensite into austenite, making it available for subsequent transformation and restoring the elastocaloric effect significantly. Such a restoration increases exponentially with σmax. Consequently, the steady-state elastocaloric effect of the healed NiTi is proportional to σmax and can reach more than twice that of NiTi without healing. The work sheds light on the physical origins of elastocaloric degradation of superelastic NiTi and also provides a feasible method for ameliorating functional fatigue.

The coexistence of cloud and snow is very common in remote sensing images. It presents persistent challenges for automated interpretation systems, primarily due to their highly similar visible light spectral characteristic in optical remote sensing images. This intrinsic spectral ambiguity significantly impedes accurate cloud and snow segmentation tasks, particularly in delineating fine boundary features between cloud and snow regions. Much research on cloud and snow segmentation based on deep learning models has been conducted, but there are still deficiencies in the extraction of fine boundaries between cloud and snow regions. In addition, existing segmentation models often misjudge the body of clouds and snow with similar features. This work proposes a Multi-scale Feature Mixed Attention Network (MFMANet). The framework integrates three key components: (1) a Multi-scale Pooling Feature Perception Module to capture multi-level structural features, (2) a Bilateral Feature Mixed Attention Module that enhances boundary detection through spatial-channel attention, and (3) a Multi-scale Feature Convolution Fusion Module to reduce edge blurring. We opted to test the model using a high-resolution cloud and snow dataset based on WorldView2 (CSWV). This dataset contains high-resolution images of cloud and snow, which can meet the training and testing requirements of cloud and snow segmentation tasks. Based on this dataset, we compare MFMANet with other classical deep learning segmentation algorithms. The experimental results show that the MFMANet network has better segmentation accuracy and robustness. Specifically, the average MIoU of the MFMANet network is 89.17%, and the accuracy is about 0.9% higher than CSDNet and about 0.7% higher than UNet. Further verification on the HRC_WHU dataset shows that the MIoU of the proposed model can reach 91.03%, and the performance is also superior to other compared segmentation methods.

The space environment is becoming increasingly crowded, raising the likelihood of collisions between satellites. Accurate prediction of satellite orbits is crucial for space transportation and communications. This article proposes an orbit prediction method based on the long short-term memory (LSTM) neural network algorithm and two-line elements (TLEs). The effectiveness of the proposed method was validated and evaluated by selecting space objects from different orbits [low Earth orbit (LEO), medium Earth orbit, and geostationary Earth orbit]. Six months of TLE data for these space objects were collected. The predicted orbits for LEO using the LSTM and Simplified General Perturbation Version 4 methods were compared with reference orbits derived from precision orbits released by the International Laser Ranging Service. Calculations were performed every two days for six months of data, and the results indicate that LSTM can improve the orbit prediction accuracy of these satellites by at least 20% over half a month.

Partial phase transformation in NiTi-based refrigerants usually enables efficient and durable elastocaloric cooling, but its thermomechanical behavior with varying temperatures remains unclear. Keeping this in view, the elastocaloric effect of NiTi under incomplete transformation across 15-100 degrees C is investigated and a superelastic deformation window between 25 and 85 degrees C is identified. Synchronous infrared thermography and digital image correlation, and an innovative macro-micro phase-field model are employed to examine martensitic transformation and elastocaloric properties of NiTi within the superelastic window. Experimental and simulated results consistently reveal that the spatiotemporal thermal profiles correlate with L & uuml;ders strain band evolution. As superelastic deformation temperature increases, strain localization intensifies, with L & uuml;ders bands favoring an inward strain growth over an outward expansion, resulting in a smaller yet more deformed martensitic transformation zone. The aggravated strain inhomogeneity makes the local endothermic undercooling tested at 85 degrees C up to about twice (-30.05 degrees C) that at 25 degrees C (-15.32 degrees C), boosting the global cooling capacity by 65 %, despite constant strain. The seeming contradiction between the larger elastocaloric effect and the narrower apparent martensitic transformation zone is elucidated by recourse to the simulations. It is found that the martensitic transformation within the L & uuml;ders bands is incomplete, proceeding in a macroscopically uniform but microscopically heterogeneous manner. Elevated temperatures within the superelastic window increase the transformed volume fraction and enhance martensitic transformation, thereby strengthening the global caloric effect. The work sheds light on the interplay between partial martensitic transformation and thermal behavior in NiTi under varying superelastic deformation temperatures, providing insights for advanced elastocaloric cooling applications. (c) 2025 Published by Elsevier Ltd on behalf of The editorial office of Journal of Materials Science & Technology.

To ensure real-time positioning services, the Low Earth Orbit Enhanced Global Navigation Satellite System relies on navigation signals similar to GNSS to enhance satellite orbit and clock information. Due to limited signal bandwidth and computational delays, the system requires orbit prediction to deliver accurate real-time positioning services. This paper proposes a method for compensating propagation orbit errors of Starlink satellites based on a Bidirectional Long Short-Term Memory (BiLSTM) network, aiming to improve the accuracy of satellite orbit propagation. The method utilizes data from two consecutive ephemeris files to first calculate the orbit propagation errors and classify them. Subsequently, these classified errors are trained using a BiLSTM network to obtain a model capable of predicting orbit propagation errors at future time. Finally, the orbit propagation is compensated based on the errors predicted by this model. The experiment used data from over 3600 Starlink satellites, and the results demonstrated that after compensation by the BiLSTM model, the median and average errors of the orbit components are smaller than those of the original propagation orbits and the CNN and RNN models, with the accuracy improvement accounting for 66

The Starlink program has accelerated the problem of space congestion, thereby increasing the probability of collisions with space objtcts. Accurate prediction of Starlink orbits is essential for ensuring the sustainability of space missions and reducing the risk of space debris generation. This study introduces a novel orbit prediction method based on a bidirectional Long Short-Term Memory (BiLSTM) neural network algorithm using ephemeris data. The effectiveness of the proposed method is validated and evaluated by selecting three Starlink satellites using data collected over one month. The results demonstrate that the proposed method improves the accuracy and precision of satellite orbit prediction. In comparison to the original ephemeris errors, the position errors have been reduced by approximately 21%. The X-axis component has been reduced by 27%, the Y-axis component by 21%, and the Z-axis component by 25%. The proposed BiLSTM orbit prediction model can effectively predict Starlink satellite orbits and has excellent potential for application in spacecraft collision prevention and space debris reduction.

Abstract The Hunga Tonga‐Hunga Ha'apai volcanic eruption on 15 January 2022 had a significant impact on the ionosphere‐thermosphere system, resulting in large‐scale ionospheric irregularities with longitudinal and latitudinal asymmetries. Multiple instruments recorded these irregularities, indicating the propagation of a westward wave at an average velocity of 354 ± 8 m/s, which led to plasma irregularities of 0.2 TECu/min. Conversely, an eastward‐propagating wave was detected on the Pacific's east coast, traveling at a speed of 348 ± 6 m/s, with a corresponding decrease in plasma fluctuations to 0.1 TECu/min. In Asia, noticeable plasma irregularities appeared within a few hours after the eruption, and the maximum speed exceeded 1,100 m/s, which cannot be explained by the acoustic wave model. There was also a significant latitudinal asymmetry of ionospheric disturbances in the Asian‐Oceania sector, with the plasma density around Oceania depleted by 2–3 orders of magnitude within the altitudes of ∼150–575 km, while the ion density over Asia was enhanced by 1–2 orders of magnitude, and was uplifted ∼50 km. The plasma temperature was proportional to ion density, indicating the ion temperature reduced ∼500 K and increased 100–200 K around Oceania and Asia, respectively. The equatorial electric field, vertical E × B drifts and thermospheric O/N2 density ratio also fluctuated significantly following the eruption, indicating the redistribution of charged particles due to the magnetic field mapping effect, which was the main contributor to the asymmetries observed.

Acquiring accurate space object orbits is crucial for many applications such as satellite tracking, space debris detection, and collision avoidance. The widely used two-line element (TLE) method estimates the position and velocity of objects in space, but its accuracy can be limited by various factors. A combination of multiple TLEs and advanced modeling techniques such as batch least squares differential correction and high-precision numerical propagators can significantly improve TLE accuracy and reliability, ensuring better space object surveillance. Previous studies analyzed additional factors that may influence TLE accuracy and evaluated the accuracy of Starlink TLE using precise ephemeris data from SpaceX. The results indicate that utilizing multiple TLEs for precise orbit determination can significantly enhance the performance of orbit prediction methods, particularly when compared to SGP4. By leveraging 10-day Starlink TLEs, the accuracy of 5-day predictions can be improved by approximately twofold. Additionally, producing two pseudo-observations within an orbital period near the TLE epoch yields the greatest effect on prediction accuracy, with this distribution of pseudo-observations increasing accuracy by approximately 10% compared to a uniform distribution. Further research can explore more data fusion and machine learning approaches to optimize operations in space.

Accurately modeling the density of atmospheric mass is critical for orbit determination and prediction of space objects. Existing atmospheric mass density models (ADMs) have an accuracy of about 15%. Developing high-precision ADMs is a long-term goal that requires a better understanding of atmospheric density characteristics, more accurate modeling methods, and improved spatiotemporal data. This study proposes a method for calibrating ADMs using sparse angular data of space objects in low-Earth orbit over a certain period of time. Applying the corrected ADM not only improves the accuracy of orbit determination, but also enhances the accuracy of orbit prediction beyond the correction period. The study compares the impact of two calibration methods: atmospheric mass density model coefficient (ADMC) calibration and high precision satellite drag model (HASDM) calibration on the accuracy of orbit prediction of space objects. One month of ground-based telescope array angular data is used to validate the results. Space objects are classified as calibration objects, participating in ADM calibration, and verification objects, inside and outside the calibration orbit region, respectively. The results show that applying the calibrated ADM can significantly increase the accuracy of orbit prediction. For objects within the calibration orbit region, the calibration object’s orbit prediction error was reduced by about 55%, while that of verification objects was reduced by about 45%. The reduction in orbit prediction error outside this region was about 30%. This proposed method contributes significantly to the development of more reliable ADMs for orbit prediction of space objects with sparse angular data and can provide significant academic value in the field of space situational awareness.

Grain-size (GS) effects on the temperature-dependent elastocaloric cooling performance of NiTi with the average GS of 11, 22, 30, 45 and 70 nm are investigated over a temperature range from-50 degrees C to 80 degrees C. It is found that GS refinement is conducive to improving the thermal stability of superelasticity and the asso-ciated elastocaloric effect, while the trade-off between cooling temperature drop AT and effective working temperature span Tspan, more or less, is inevitable regardless of GS. The large AT of the 70 nm-GS specimen, which is characterized by sharp first-order martensitic transformation and strong temperature dependence of the transformation stress d sigma tr/dT (= 5.7 MPa/degrees C), is restricted to a narrow Tspan (= 19 degrees C). Tspan can be widened by five times via reducing GS to 11 nm but at the expense of a significant sacrifice in AT, as the combined result of high strength and small d sigma tr/dT (= 0.9 MPa/degrees C). Among the five microstructures, the 30 nm-GS one achieves a favorable compromise between AT and Tspan owing to the mild transformation nature together with robust mechanical properties. Consequently, its AT can reach 50% & ndash; 440% of that of the 70 nm-GS counterpart and the resultant cooling efficiency can be enhanced by a factor of half to six. The work demonstrates that GS engineering is a feasible approach for reconciling various elastocaloric cooling metrics of the NiTi refrigerant. (c) 2022 Elsevier B.V. All rights reserved. Superscript/Subscript Available

Tailoring properties of engineering materials to meet various application requirements is a long-standing challenge in materials science. Here, we demonstrate an unprecedented strategy to achieve highly tunable mechanical behavior and significantly enhanced elastocaloric effect in superelastic NiTi via gradient structure fabricated by laser surface annealing on a severely deformed matrix. The gradient-structured (GS) NiTi sheet is characterized by a nanocrystalline core sandwiched between two coarse-grained layers with grain-size gradients enabled by progressive annealing within the thickness due to the natural degradation of heat penetration. Tailorable martensitic transformation characteristics, which gradually change from a uniform mode with quasi-linear stress-strain response to a nucleation and growth mode with plateau-type superelasticity, are readily realized through tuning the grain-size gradient. Furthermore, the GS NiTi exhibits more than 50% and 130% improvement in elastocaloric cooling capacity and efficiency compared to traditional nanocrystalline and coarse-grained NiTi with homogeneous microstructures, respectively. Such significant performance breakthroughs are attributed to the strong synergetic strengthening between fine and coarse grains in the GS NiTi, which cannot be offered by the freestanding components. The unique strengthening mechanism is activated, even in the absence of plastic deformation, by the high mechanical incompatibility among heterogeneous domains and the resultant pronounced strain gradient accommodated by martensite variants. The work opens a novel avenue for fabricating bulk GS materials with desired mechanical properties and inspires the microstructure optimization in a wide range of ferroelastic materials for giant caloric effects.

目前,主要用经验模型进行热层大气密度建模和预测,但存在较大误差,因此提出一种基于长短期记忆神经网络的热层大气密度模型校正方法,以减少经验模型计算的密度误差.该方法将NRLMSISE-00模型计算的密度、太阳和地磁活动指数作为基础输入,以CHAMP卫星的加速度计密度数据为目标值,获得NRLMSISE-00的模型误差.结果表明,校正后模型的精度显著优于原始模型的精度.

目前应用于空间碎片仅角度观测值的甚短弧初轨确定问题的Gauss方法、Gooding方法等解析方法并不能得到很高的精度.依据神经网络算法的"万能近似性质",将其应用于甚短弧初轨确定问题中,并利用Python的Scikit-Learn库中的主成分分析函数和Keras库中的前馈神经网络函数处理了 一批仿真数据,这些数据观测弧长仅为21s.结果表明,该算法能够提升传统的初轨确定解算精度.

关于生态环境损害赔偿磋商协议的法律性质,现有民事协议说存在磋商性质无法契合纠纷解决"程序"的问题,故难以在 《民事诉讼法》和环境法典(尚需编纂出台)中找到合理定位.现有学说观点需要进一步补强与丰富:一方面,民事协议说既契合了生态环境损害赔偿磋商政策的目的,亦可实现 《生态环境损害赔偿制度改革方案》与 《民事诉讼法》所规定的救济程序的衔接,从而凸显民事实体法与程序法衔接后司法救济的积极效果;另一方面,需要在环境保护基本法律(如环境法典)中明确生态环境损害赔偿磋商协议的民事协议性质,以弥补生态环境损害赔偿磋商在法律中的性质缺位.基于此,才能正确认识生态环境损害赔偿磋商协议的实体性质和拘束力司法程序救济的效果.