With the enormous scale of remote sensing imagery generation, on-orbit computing has become a crucial paradigm to enable near-real-time processing. Due to the limited onboard resources and on-orbit power supply, satellite edge computing (SEC) is developed for satellite-ground collaboration, aiding on-orbit computation. However, the intermittent satellite-to-ground transmission link poses an efficiency challenge when collaborating SEC resources. Therefore, this article proposes a satellite edge computing resource scheduling technique for on-orbit remote sensing imagery processing ($\textsf {SECORS}$). First, we design a remote sensing mission-specific SEC architecture, which involves an offline-online satellite working mode. Subsequently, a computational resource scheduling model ($\textsf {SEC}$-$\textsf {RSM}$) is established, including the directed acyclic graph (DAG) model and mathematical problem formulation. Next, to obtain effective scheduling solutions, we develop an end-to-end algorithm leveraging the multiagent proximal policy optimization and heuristic rule of the earliest finish time ($\textsf {SEC}$-$\textsf {MPH}$). Finally, we build a simulation SEC platform to carry out experiments and implement several methods as the comparison including multiobjective evolutionary algorithms, deep reinforcement learning approaches, and the scheme without optimization (baseline). Simulation results show that$\textsf {SECORS}$achieves 68.87% and 66.60% reductions in time and energy for on-orbit computation. Moreover, our method improves the energy efficiency ratio (EER) by three times and achieves high processing capacity with 548 pixels per unit of power (W) and time (ms).

Satellite on-orbit remote sensing image intelligent interpretation relies on on-orbit devices with extremely limited computational resources, utilizing advanced neural networks designed through lightweight methodologies to achieve fast and accurate interpretation of on-orbit remote sensing images. Nevertheless, the current design of lightweight neural networks exhibits three salient issues: firstly, the prevailing “one-size-fits-all" network lightweight design pattern is notably inefficient; secondly, there is a deficiency in analysing the impact of lightweight operations on network performance; thirdly, the mutual influence among various lightweight operations is overlooked. To address these issues, firstly, we propose a neural network lightweightability measurement model and its computational method by investigating the effects of various lightweight operations; secondly, we propose a neural network general lightweight design framework (GLD) tailored for satellite on-orbit remote sensing images intelligent interpretation. Specifically, GLD, based on a meta-leaning approach, integrates knowledge distillation (KD), pruning and quantization, three general lightweight technologies, into a framework. It dynamically assesses the distillability, prunability and quantifiability of neural networks, and uses this assessment and uses this as supervision to dynamically jointly optimizes KD, pruning and quantization, making it applicable to various mainstream neural networks; furthermore, we explore the mutual influence among lightweight operations based on GLD; finally, through ablation experiments and comparative experiments, we further verify the effectiveness and superiority of GLD.

Low Earth orbit satellite constellations with seamless network coverage and onboard computers enable autonomous on-orbit anomaly identification of remote wind turbines. However, they face several challenges. First, limited visible periods caused by orbital characteristics mandate that one satellite holds anomalies and the other collects surveillance data. Second, passively injected satellites could intercept and grasp onboard message flows. Third, a restricted onboard energy supply budget restrains intersatellite communications and onboard computations. With the above challenges, we propose a secure on-orbit anomaly identification (SOAI) scheme between a pair of satellites through an$\text{XOR}$filter, which further exploits laconic private set intersection to eliminate false positives. The secure on-orbit anomaly querying scheme achieves the verifiable querying of anomalies derived from$\text{SOAI}$. Comprehensive security analysis shows that the$\text{SOAI}$scheme achieves confidentiality under a simulation-based real/ideal world model. Moreover, we compare the$\text{SOAI}$scheme with two baseline schemes in terms of communication overheads and computational costs, and evaluation results show that our scheme outperforms the compared schemes, and our scheme is feasible in the OneWeb constellation near the polar regions.

The low-Earth orbit (LEO) satellite constellation holds immense potential for offshore wind farm surveillance since it can provide all-day and all-weather monitoring capabilities facilitated by satellite collaboration. However, it faces significant challenges. First, limited downlink transmission bandwidth constrained by ground stations and constraint on-orbit resources necessitate selective data downloads, focusing only on differences between consecutive data sets. Second, a passively injected satellite in open space poses a risk of unauthorized data extraction from neighboring satellites. Third, onboard energy constraints limit the feasibility of computationally intensive cryptographic operations. To tackle these challenges for the first time, we propose a novel secure and efficient on-orbit comparison (SEOC) scheme. Our solution begins with introducing a lightweight matrix encryption-based secure inner product (MSIP) technique tailored for secure on-orbit comparison. We further enhance communication efficiency by integrating a Cuckoo filter to reduce costs, complementing a novel difference comparison tree (DCTree) structure to manage false positives. Through comprehensive security analysis, the$\textsf {MSIP}$technique achieves selective security, and the$\textsf {SEOC}$scheme is secure under the universally composable (UC) framework. At last, performance evaluations demonstrate the high efficiency of our approach in terms of computational costs and communication overheads, which adapts to the limited on-orbit resources.

The role of on-orbit computing for satellites is transitioning from being a backup measure to becoming a primary key function. However, the limited computing resources available on satellites make it difficult to deploy advanced models with large parameters. Additionally, satellite on-orbit computing requires high speed and accuracy, posing significant challenges for developing suitable models. To overcome these challenges, we propose an efficient vision transformer, RepSViT, for satellite on-orbit computing. The RepSViT introduces Spiking neural networks (SNNs) with high biological plausibility, event-driven property and low power consumption into the field of remote sensing image processing and satellite on-orbit computing for the first time and incorporates structural reparameterization. Specifically, we design a dynamic dilated spiking convolution (D2SC) based on SNNs to improve the feature extraction capability and efficiency of RepSViT. We also develop a spiking guided attention module (SGAM) to make RepSViT pay more attention to object-related features with lower computational costs. Furthermore, we design an efficient coupled fine–coarse-grained block (ECFC) to enhance the model’s capability in extracting coarse and fine-grained features. To ensure effective feature extraction, inference speed and reduced computational costs, we design a reparameterized feed-forward network (RepFFN). RepSViT achieves an inference latency of 8.33 ms and a recognition accuracy of 95% on an embedded GPU, utilizing 3.77 million parameters and consuming 0.6 GFLOPs computational costs.

Extremely constrained storage and computational resources are one of the difficulties of satellite-on-orbit computing, which leads to over-parametric high-performance models not performing properly on-orbit. Knowledge distillation (KD) is an effective method for model compression; yet, there is a gap in the study of the limits and laws of KD-based model compression. To bridge this gap, we propose a novel KD framework, pyramid KD (PKD) and define a knowledge explosion and knowledge offset. Specifically, the pyramid distillation framework is built by stacking multiple sets of deep mutual learning (DML) models, with the smaller models on the top of the larger ones, and the overall structure is like a pyramid; hence, it is called PKD. To avoid knowledge explosion, we design a hybrid online–offline smooth distillation (HOSD) strategy by combining online distillation and offline distillation and reducing the difference between models. To avoid knowledge offset, we design an adaptive multiteacher distillation method to obtain multiteacher weighted knowledge by adaptively learning the weight of each teacher’s knowledge. We introduce an evolutionary algorithm to automatically find the optimal PKD configuration. We conduct ablation experiments and compare PKD with state-of-the-art distillation methods using ResNet series networks and VGG series networks as base models on Aircraft and FGSC-23 datasets, respectively. The experimental results show the effectiveness and advancement of PKD and reveal the law that the object recognition accuracy varies with the model compression rate.

The low Earth orbit (LEO) satellite edge computing paradigm provides remote sites with flexible, reliable, and scalable edge computing capabilities. Characterized by the orbital motion patterns and harsh space environments, the LEO satellite edge computing faces unique security challenges in terms of the secure collaboration of multiple satellites and the intellectual property protection of models. Under the unique space environment and security demands, we propose a secure satellite edge computing framework in this paper. By taking a remote electricity line outage identification use case as an example, our framework first achieves the secure delegation of the line outage identification task among multiple satellites, which is realized through a secure query$(\mathsf {SQuery})$scheme to check the availability of the target time slot. Meanwhile, we also design a SHE-enabled secure inner-product encryption ($\mathsf {SSIPE}$) protocol, to achieve the secure multinomial logistic regression (MLR) based line outage identification on-orbit. To reduce the complexity brought by the computationally intensive homomorphic multiplication between two ciphertexts, we further grasp the idea and design a “divide-and-conquer” based secure query ($\mathsf {DSQuery}$) scheme, which converts this homomorphic multiplication operation between ciphertexts into the homomorphic addition operation. As far as we know, this is the first scheme investigating the secure task delegation among different satellites on-orbit. Besides, detailed security analyses are performed to demonstrate the security properties of confidentiality and authentication. In performance evaluations, we test and compare the computational and communication overhead of our scheme and other straightforward schemes. Simulation results show that the$\mathsf {DSQuery}$scheme greatly reduces the computational cost, which saves the stringent on-orbit computation resources of LEO satellites.

Geographic information system (GIS) enables operations for capturing, manipulating, analyzing, and displaying the spatial characteristics of objects on Earth's surface. As the objects in GISs are mostly location-dependent, various location privacy-preserving schemes are proposed to support the secure spatial query and analysis. However, existing location privacy-preserving mechanisms mainly focus on the$k$-nearest neighbor ($k$NN) queries and range queries and fail to consider the practical geographic implementation with quad-trees. We propose an efficient and privacy-preserving point-of-interest (POI) query scheme along the movement trajectory under the quad-tree setup in a two-server mode. Specifically, we first convert the secure identification of the target lowest-level tile into a series of private information retrieval (PIR) processes and securely derive the target POIs along the movement trajectory within the identified tile by constructing a linear polynomial passing through the origin and destination for secure distance comparison. Our scheme also supports the efficient loading of POIs contained in the adjacent tiles with privacy preservation. Security analysis demonstrates that ours can achieve the security goals of privacy preservation and confidentiality. We execute performance evaluations to show and validate the system efficiency, i.e., computational costs and communication overheads.

Nowadays, the proliferation of small satellites brings the skyrocketing rise in space data, especially the shift to on-orbit computing needs. On one hand, with the increasing volume of data generation, like high-resolution remote sensing images, on-orbit computing produces near real-time onboard solutions and quick responses. However, constrained by the limited size and energy supply of satellites, achieving energy-efficient on-orbit computing remains a crucial challenge. In this article, an on-orbit remote sensing image processing complex task scheduling model facing heterogeneous multiprocessor system (HMPS) is proposed. First, aiming at accelerating image processing, we establish a novel parallel task execution model using directed acyclic graph (DAG) to universally describe typical missions, i.e., cloud detection, geometric correction, and image classification. Subsequently, a mathematical task scheduling formulation is defined to calculate the makespan, and total energy consumption (TEC) required when executing DAG on HMPS. Second, a new Pareto-based iterated greedy optimizer (PIGO) is devised to complete the energy- and time-efficient task execution and resource allocation on HMPS through confined inserting mutation, destruction-reconstruction, and local search. Finally, we build an emulated on-orbit HMPS to conduct experiments. The results show that, in comparison with the scheme without model scheduling, the most savings of around 51% and 54% in makespan and TEC, respectively, are achieved by the proposed model. Moreover, the HMPS configured with our methodology can obtain 2.2× improvement in energy efficiency and process up to 2.56×105pixels per unit of power (W) and time (s).

In recent years, the performance of the deep learning based object detection models for remote sensing images improves with the increase of the hyperparameter scale. However, the state of the art of detection models are generally too cumbersome to adapt to the resource-constrained satellite platforms, and even general lightweight detection models cannot satisfy performance requirements. To solve those problems, a lightweight and accurate oriented object detection network for satellite on-orbit computing (SOCDet) is proposed from three levels. At the computing unit level, we propose an efficient computing unit Single-kernel Omni-dimensional Dynamic Convolution to make SOCDet feature extraction more efficient. At the network module level, we design a structural reparameterization block based on composite structure reparameterization to improve inference accuracy. A guided attention module for guiding SOCDet is designed to extract object features. We design a lightweight and concise one-stage detection architecture at the network architecture level to accommodate satellite platforms with extremely constrained computing and storage resources. We conduct ablation experiments on the ground server and compare experiments with the state-of-the-art methods on embedded GPU, using DOTA, HRSC2016 and FAIR1M. The experiment results show that SOCDet can achieve 2.36 times faster than the baseline in inference speed with 10.78 more mAP, 72.6% fewer Params and 92.56% fewer floating point operations. Compared with state-of-the-art methods, SOCDet improves the inference speed and derives competitive mAP results with affordable computing capability.

High-quality remote sensing images not only provide opportunities for deep learning-based image interpretation, but also challenge satellite edge devices for storage, processing and downlinking to the ground server. Satellite on-orbit object recognition is an effective measure to solve this challenge. However, there is an insurmountable gap between the extremely limited computing and storage resources of satellites and the demand for those of deep learning. To solve this problem, a fast and lightweight intelligent satellite-on-orbit computing network (SOCNet) is proposed. First, the overall network architecture based on the idea of flat multi-branch feature extraction is proposed to accelerate model inference and reduce the network depth. Second, we propose the idea of exchanging a larger receptive field for network depth and combine the idea of depthwise separable convolution to further reduce the amount of parameters. We design a feature extraction method of coupled fine-coarse-grained for efficient feature extraction. Finally, global average pooling is used for feature fusion to further reduce network parameters amount and computational complexity. We have performed multiple sets of ablation experiments and some state-of-the-art comparison experiments on the server and carried out experimental verification on the NVIDIA Jetson TX2 mobile device to mimic the resource-constrained environment on the satellite. SOCNet with parameters of 0.21 MB, model size of 1.22 MB and computation cost of 50.81 MB floating point operations has achieved 99% comprehensive accuracy, 2.45 ms latency and 408 images per second throughput on 30 types of aircraft datasets with the 224 × 224 remote sensing images.

Nighttime light (NTL) remote sensing offers an efficient method to estimate electric power consumption (EPC). However, few research applied the estimation model of a certain year to other years' data for validation, and its transferability across years has not been investigated. Taking mainland China as an example, this paper aims to develop an EPC estimation model which is transferable across years. Partial least square regression (PLSR) was used to build the estimation model for EPC with entire DN series of NTL. Then, the model of each single year 2004-2013 was applied to the other years to validate its transferability across years. Results revealed that PLSR performed well both in model calibration (mean R2c=0.89) and model transfer (mean R2p=0.87). We concluded that PLSR models could effectively excavated reliable quantitative relationship between NTL and EPC, and held good transferability across years.