pith. sign in

arxiv: 2604.05937 · v1 · submitted 2026-04-07 · 💻 cs.NI

Edge Intelligence for Satellite-based Earth Observation: Scheduling Image Acquisition and Processing

Beatriz Soret , Antonio M. Mercado-Mart\'inez , Antonio Jurado-Navas , Nicolai D. Lyholm , Marco Moretti , Petar Popovski , Israel Leyva-Mayorga This is my paper

Pith reviewed 2026-05-10 18:53 UTC · model grok-4.3

classification 💻 cs.NI
keywords edge computingsatellite constellationearth observationobservation schedulingturbulence modelingsemantic processingpower optimizationLEO satellites
0
0 comments X

The pith

Task- and turbulence-aware scheduling lets LEO satellite constellations capture more high-quality images while cooperative edge processing cuts power use compared to full downlink.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper develops an energy-aware framework for LEO satellite constellations that have heterogeneous onboard computing to perform real-time semantic processing of Earth observation imagery. It formulates two coupled optimization problems: observation scheduling that selects acquisition opportunities while factoring in turbulence-induced image degradation and energy limits, and processing scheduling that distributes semantic workloads across onboard and ground processors. The work evaluates the approach for vessel detection and localization using YOLOv8, with experimental characterization of turbulence effects and execution times on different platforms. If the claims hold, future EO missions could manage massive data volumes more autonomously without overwhelming downlink and ground-processing capacities. A sympathetic reader cares because time-critical applications need responsive insights from imagery that current architectures struggle to deliver promptly.

Core claim

The authors introduce an energy-aware framework that optimizes resource use under data acquisition, computing, and communication constraints for LEO satellite constellations. They formulate two coupled problems: observation scheduling that accounts for turbulence-induced degradation and energy budgets when selecting image opportunities, and processing scheduling that allocates semantic workloads across onboard heterogeneous edge processors and ground stations. For vessel detection, results show that task- and turbulence-aware scheduling improves both the quality and quantity of observed targets, while cooperative edge processing within the constellation reduces power consumption relative to

What carries the argument

An energy-aware framework built from two coupled optimization problems: turbulence-aware observation scheduling that selects acquisition opportunities based on predicted image degradation and energy budget, together with processing scheduling that allocates semantic workloads across onboard and ground heterogeneous platforms.

If this is right

  • Task- and turbulence-aware observation scheduling preserves image quality and increases the number of usable targets observed.
  • Cooperative edge processing across the constellation reduces overall power consumption compared with downlink-centric designs.
  • The framework supports real-time semantic inference for time-critical Earth observation applications.
  • The formulation applies beyond maritime surveillance to a broad class of semantic and goal-oriented inference tasks.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Satellites could use short-term turbulence forecasts to dynamically reprioritize acquisitions and stretch limited energy budgets further.
  • Adding inter-satellite data sharing to the processing scheduler might allow even larger constellations to balance workloads without increasing ground traffic.
  • The same structure could be tested on other sensors where atmospheric or orbital factors degrade raw data quality.

Load-bearing premise

That turbulence-induced image degradation can be predicted accurately enough to guide acquisition choices, and that measured execution-time distributions of models like YOLOv8 on different platforms are representative for optimization.

What would settle it

A side-by-side comparison, either in simulation or on-orbit, of turbulence-aware schedules versus standard schedules that shows no measurable gain in image quality metrics or power savings for the same set of targets.

Figures

Figures reproduced from arXiv: 2604.05937 by Antonio Jurado-Navas, Antonio M. Mercado-Mart\'inez, Beatriz Soret, Israel Leyva-Mayorga, Marco Moretti, Nicolai D. Lyholm, Petar Popovski.

Figure 1
Figure 1. Figure 1: Scenario overview: EO satellites capture images of a set of tracked objects (vessels), with image [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Impact of the atmospheric turbulence in ship detection and localization using YOLOv8. The [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: CDF for C 2 n (0) based on experimental ground-level measurements. Measures taken from [36]. and localization algorithm, YOLOv8, applied to a pre-trained EO database of images collected from a 500 m eye altitude level [35]. As the turbulence becomes more severe, parameterized in larger refractive index fluctuations and structure parameter C 2 n [34], the algorithm struggles to detect vessels. However, this… view at source ↗
Figure 4
Figure 4. Figure 4: E2E procedure of the proposed framework: (1) Upon receiving a task, the ground station [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Performance results for the turbulence-free scenario. (a) Observation profit (left) and number [PITH_FULL_IMAGE:figures/full_fig_p017_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Impact of atmospheric turbulence (C 2 n,max(0) = 2 × 10−14 , m−2/3 ) on the actual collected observation profit (left) and average schedule precision defined as the ratio of observations meeting quality requirements (right). acquisitions with lower GSD, i.e., better image spatial resolution. In turn, improved spatial resolution enhances the accuracy of the semantic extraction algorithm, YOLOv8 in this stud… view at source ↗
Figure 7
Figure 7. Figure 7: Estimated mean execution time of YOLOv8 on individual images with the considered com [PITH_FULL_IMAGE:figures/full_fig_p019_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Probability density of YOLOv8 execution time on the NVIDIA Jetson Orin (a) Nano Super and [PITH_FULL_IMAGE:figures/full_fig_p019_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: (a) Empirical and fitted Gamma distribution parameters [PITH_FULL_IMAGE:figures/full_fig_p019_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Power consumption for the three considered computing architectures at the satellites for 60 [PITH_FULL_IMAGE:figures/full_fig_p021_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Mean, 5th, and 95th quantiles for the optimal energy consumption of semantic extraction [PITH_FULL_IMAGE:figures/full_fig_p021_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Optimal average power consumption for EO with the three considered satellite edge computing [PITH_FULL_IMAGE:figures/full_fig_p021_12.png] view at source ↗
read the original abstract

Modern Earth Observation (EO) missions generate massive volumes of imagery that challenge existing downlink and ground-processing capabilities, particularly for time-critical applications. This work investigates how a low Earth orbit (LEO) satellite constellation equipped with heterogeneous edge computing resources can enable real-time semantic processing of data acquired by EO satellites. We introduce an energy-aware framework that optimizes the use of resources accounting for data acquisition, computing, and communication constraints. Although we focus on maritime surveillance, the formulation is task-agnostic and accommodates a broad class of semantic and goal-oriented inference problems. Specifically, we formulate two coupled optimization problems: (i) observation scheduling, which selects image acquisition opportunities while accounting for turbulence-induced image degradation and energy budget, and (ii) processing scheduling, which allocates semantic workloads across onboard and ground processors. We evaluate these mechanisms for the task of detection and localization of vessels, for which we quantify the benefits of turbulence-aware observation scheduling for preserving image quality and experimentally characterize the execution-time distribution of YOLOv8 on different computing platforms. Results demonstrate that task- and turbulence-aware observation scheduling can significantly improve the quality and quantity of observed targets. Furthermore, cooperative edge processing within the constellation substantially reduces power consumption compared to traditional downlink-centric architectures. These findings highlight the potential of distributed edge intelligence to enhance the responsiveness and autonomy of future satellite-based EO systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 1 minor

Summary. The paper proposes an energy-aware framework for a LEO satellite constellation with heterogeneous edge computing resources to enable real-time semantic processing of Earth observation imagery. Focusing on maritime surveillance and vessel detection with YOLOv8, it formulates two coupled optimization problems: (i) observation scheduling that selects acquisition opportunities while accounting for turbulence-induced image degradation and energy budgets, and (ii) processing scheduling that allocates semantic workloads across onboard and ground processors. The evaluation claims that task- and turbulence-aware scheduling improves the quality and quantity of observed targets, while cooperative edge processing substantially reduces power consumption relative to traditional downlink-centric architectures.

Significance. If the results hold under realistic conditions, the work would highlight the value of distributed edge intelligence for enhancing responsiveness and autonomy in future satellite-based EO systems, particularly by reducing downlink volumes and enabling onboard inference for time-critical tasks such as maritime surveillance.

major comments (3)
  1. Abstract: The abstract states the problems and qualitative benefits but supplies no equations, algorithm details, quantitative metrics, or validation setup; central claims cannot be verified from available text.
  2. Evaluation section: The experimental characterization is limited to execution-time distributions of YOLOv8 on heterogeneous platforms; no independent validation is provided that the turbulence-induced image degradation model matches actual LEO imagery statistics for the relevant orbital geometries and weather regimes. This assumption is load-bearing for the claimed scheduling gains in target quality and quantity.
  3. Problem formulation (optimization problems): Without the explicit mathematical statements of the two coupled optimization problems (objective functions, decision variables, and constraints on acquisition, computing, and communication), it is not possible to assess whether the framework correctly balances the stated physical and hardware constraints.
minor comments (1)
  1. Abstract: The phrasing 'significantly improve' and 'substantially reduces' would be more informative if accompanied by the specific quantitative deltas reported in the results.

Simulated Author's Rebuttal

3 responses · 1 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. We address each major comment below and indicate the planned revisions. We believe these changes will improve the clarity and rigor of the work.

read point-by-point responses

  1. Referee: Abstract: The abstract states the problems and qualitative benefits but supplies no equations, algorithm details, quantitative metrics, or validation setup; central claims cannot be verified from available text.

    Authors: We agree that the abstract is primarily qualitative. In the revised version, we will incorporate specific quantitative results (e.g., improvements in observed target quality and power consumption reductions) and a concise description of the coupled optimization approach. Full equations and algorithmic details will remain in the main body due to abstract length constraints, but the abstract will better highlight the key contributions and evaluation setup. revision: yes

  2. Referee: Evaluation section: The experimental characterization is limited to execution-time distributions of YOLOv8 on heterogeneous platforms; no independent validation is provided that the turbulence-induced image degradation model matches actual LEO imagery statistics for the relevant orbital geometries and weather regimes. This assumption is load-bearing for the claimed scheduling gains in target quality and quantity.

    Authors: The turbulence model parameters are drawn from established literature on LEO atmospheric effects. We did not conduct new empirical validation against real LEO imagery datasets, as this would require substantial additional data collection and analysis beyond the paper's scope. In the revision, we will expand the evaluation section with a dedicated discussion of model assumptions, sensitivity analysis, cited supporting references, and explicit limitations. This will clarify the basis for the scheduling gains without new experiments. revision: partial

  3. Referee: Problem formulation (optimization problems): Without the explicit mathematical statements of the two coupled optimization problems (objective functions, decision variables, and constraints on acquisition, computing, and communication), it is not possible to assess whether the framework correctly balances the stated physical and hardware constraints.

    Authors: The manuscript presents the mathematical formulations of the two coupled optimization problems in Sections III and IV. To improve accessibility, we will revise these sections to state the objective functions, decision variables, and all constraints more explicitly, and we will add a summary table of notation and constraints. A brief overview will also be included earlier in the paper for better flow. revision: yes

standing simulated objections not resolved
  • Independent empirical validation of the turbulence-induced image degradation model against actual LEO imagery statistics for the relevant conditions cannot be provided without new data collection and analysis outside the current work's scope.

Circularity Check

0 steps flagged

No circularity; optimization and evaluation rest on independent models and experiments

full rationale

The paper formulates observation and processing scheduling as coupled optimization problems that take turbulence-induced degradation, energy budgets, and task requirements as explicit inputs, then quantifies benefits via experimental runtime distributions of YOLOv8 on heterogeneous platforms. No derivation step reduces by construction to a fitted parameter renamed as prediction, a self-definitional loop, or a load-bearing self-citation chain; the reported improvements in target quality and power consumption are direct outputs of the stated models and measurements rather than tautological restatements of the inputs. The framework is therefore self-contained against external hardware benchmarks and physical constraints.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No explicit free parameters, axioms, or invented entities are identifiable from the abstract; the work relies on standard optimization assumptions and hardware constraints typical of the domain.

pith-pipeline@v0.9.0 · 5567 in / 1044 out tokens · 32365 ms · 2026-05-10T18:53:10.237700+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

56 extracted references · 56 canonical work pages

  1. [1]

    H. Chen, S. Peng, C. Du, and J. Li,Earth Observation Satellites - Task Planning and Scheduling. Springer Singapore, 2023

    work page 2023

  2. [2]

    Earth observation satellites set to triple over the next decade,

    Novaspace, “Earth observation satellites set to triple over the next decade,” Press release, 2024, accessed: 2026-02-20. [Online]. Available: https://nova.space/press-release/earth-observation- satellites-set-to-triple-over-the-next-decade/

    work page 2024

  3. [3]

    The role of satellite remote sensing in climate change studies,

    J. Yang, P. Gong, R. Fu, M. Zhang, J. Chen, S. Liang, B. Xu, J. Shi, and R. Dickison, “The role of satellite remote sensing in climate change studies,”Nature Climate Change, vol. 3, no. 10, pp. 875–883, 2013

    work page 2013

  4. [4]

    Deep learning and earth observation to support the sustainable development goals: Current approaches, open challenges, and future opportunities,

    C. Persello, J. D. Wegner, R. H¨ ansch, D. Tuia, P. Ghamisi, M. Koeva, and G. Camps-Valls, “Deep learning and earth observation to support the sustainable development goals: Current approaches, open challenges, and future opportunities,”IEEE Geoscience and Remote Sensing Magazine, vol. 10, no. 2, pp. 172–200, 2022

    work page 2022

  5. [5]

    Space-based global maritime surveillance. part i: Satellite technologies,

    G. Soldi, D. Gaglione, N. Forti, A. D. Simone, F. C. Daffin` a, G. Bottini, D. Quattrociocchi, L. M. Millefiori, P. Braca, S. Carniel, P. Willett, A. Iodice, D. Riccio, and A. Farina, “Space-based global maritime surveillance. part i: Satellite technologies,”IEEE Aerospace and Electronic Systems Mag- azine, vol. 36, no. 9, pp. 8–28, 2021

    work page 2021

  6. [6]

    The value of near real-time earth observations for improved flood disaster response,

    P. Oddo and J. D. Bolton, “The value of near real-time earth observations for improved flood disaster response,”Frontiers in Environmental Science, vol. 7, no. 2, pp. 2–3, 2019

    work page 2019

  7. [7]

    Satellite edge computing for real-time and very-high resolution Earth observation,

    I. Leyva-Mayorga, M. Gost, M. Moretti, A. P´ erez-Neira, M. V´ azquez, P. Popovski, and B. Soret, “Satellite edge computing for real-time and very-high resolution Earth observation,”IEEE Trans- actions on Communications, vol. 71, no. 10, pp. 6180–6194, 2023

    work page 2023

  8. [8]

    Semantic communications: Overview, open issues, and future research directions,

    X. Luo, H.-H. Chen, and Q. Guo, “Semantic communications: Overview, open issues, and future research directions,”IEEE Wireless Communications, vol. 29, no. 1, pp. 210–219, 2022

    work page 2022

  9. [9]

    Semantic enabled 6G LEO satellite communication for Earth observation: A resource-constrained network optimization,

    S. S. Hassan, L. X. Nguyen, Y. K. Tun, Z. Han, and C. S. Hong, “Semantic enabled 6G LEO satellite communication for Earth observation: A resource-constrained network optimization,” in Proc. IEEE Global Communications Conference (GLOBECOM), 2024, pp. 4472–4478

    work page 2024

  10. [10]

    Beyond transmitting bits: Context, semantics, and task-oriented communications,

    D. G¨ und¨ uz, Z. Qin, I. E. Aguerri, H. S. Dhillon, Z. Yang, A. Yener, K. K. Wong, and C.-B. Chae, “Beyond transmitting bits: Context, semantics, and task-oriented communications,”IEEE Journal on Selected Areas in Communications, vol. 41, no. 1, pp. 5–41, 2023. 22 Draft

    work page 2023

  11. [11]

    Edge ai for earth observation,

    N. Ruan, K. Li, Q. Zhang, L. Lov´ en, P. K. Donta, Y. Jia, and S. Dustdar, “Edge ai for earth observation,”IEEE Internet Computing, vol. 29, no. 3, pp. 31–40, 2025

    work page 2025

  12. [12]

    Orbital edge computing: Machine inference in space,

    B. Denby and B. Lucia, “Orbital edge computing: Machine inference in space,”IEEE Computer Architecture Letters, vol. 18, no. 1, pp. 59–62, 2019

    work page 2019

  13. [13]

    Scheduling agile earth observation satellites with onboard processing and real-time monitoring,

    A. M. Mercado-Mart´ ınez, B. Soret, and A. Jurado-Navas, “Scheduling agile earth observation satellites with onboard processing and real-time monitoring,” 2025. [Online]. Available: https://arxiv.org/abs/2506.11556

    work page arXiv 2025

  14. [14]

    A compre- hensive survey of orbital edge computing: Systems, applications, and algorithms,

    Z. Yin, C. Wu, C. Guo, Y. Li, M. Xu, W. Gao, and C. Chi, “A compre- hensive survey of orbital edge computing: Systems, applications, and algorithms,” Chinese Journal of Aeronautics, vol. 38, no. 7, p. 103316, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1000936124004709

    work page 2025

  15. [15]

    Satellite-terrestrial integrated edge computing networks: Architecture, challenges, and open issues,

    R. Xie, Q. Tang, Q. Wang, X. Liu, F. R. Yu, and T. Huang, “Satellite-terrestrial integrated edge computing networks: Architecture, challenges, and open issues,”IEEE Network, vol. 34, no. 3, pp. 224–231, 2020

    work page 2020

  16. [16]

    Federated learning in satellite constellations,

    B. Matthiesen, N. Razmi, I. Leyva-Mayorga, A. Dekorsy, and P. Popovski, “Federated learning in satellite constellations,”IEEE Network, vol. 38, no. 2, pp. 232–239, 2024

    work page 2024

  17. [17]

    Kodan: Addressing the computational bottleneck in space,

    B. Denby, K. Chintalapudi, R. Chandra, B. Lucia, and S. Noghabi, “Kodan: Addressing the computational bottleneck in space,” inProceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3, ser. ASPLOS

    work page

  18. [18]

    New York, NY, USA: Association for Computing Machinery, 2023, p. 392–403. [Online]. Available: https://doi.org/10.1145/3582016.3582043

    work page doi:10.1145/3582016.3582043 2023

  19. [19]

    Joint observation, transmission, and computation scheduling for earth observation tasks,

    T. Xiong, Y. Li, L. Chen, and J. Dai, “Joint observation, transmission, and computation scheduling for earth observation tasks,” in2025 IEEE/CIC International Conference on Communications in China (ICCC), 2025, pp. 1–6

    work page 2025

  20. [20]

    Scheduling algorithms for rapid imaging using agile cubesat constellations,

    S. Nag, A. S. Li, and J. H. Merrick, “Scheduling algorithms for rapid imaging using agile cubesat constellations,”Advances in Space Research, vol. 61, no. 3, pp. 891–913, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0273117717308050

    work page 2018

  21. [21]

    Agile earth observation satellite scheduling over 20 years: Formulations, methods, and future directions,

    X. Wang, G. Wu, L. Xing, and W. Pedrycz, “Agile earth observation satellite scheduling over 20 years: Formulations, methods, and future directions,”IEEE Systems Journal, vol. 15, no. 3, p. 3881–3892, Sep. 2021

    work page 2021

  22. [22]

    H. Chen, S. Peng, C. Du, and J. Li,Earth observation satellites : task planning and scheduling, 1st ed. Singapore: Springer Nature Singapore, 2023

    work page 2023

  23. [23]

    Agile Earth obser- vation satellite scheduling: An orienteering problem with time-dependent profits and travel times,

    G. Peng, R. Dewil, C. Verbeeck, A. Gunawan, L. Xing, and P. Vansteenwegen, “Agile Earth obser- vation satellite scheduling: An orienteering problem with time-dependent profits and travel times,” Computers & Operations Research, vol. 111, pp. 84–98, 2019

    work page 2019

  24. [24]

    Reinforcement learning for the agile earth-observing satellite schedul- ing problem,

    A. Herrmann and H. Schaub, “Reinforcement learning for the agile earth-observing satellite schedul- ing problem,”IEEE Transactions on Aerospace and Electronic Systems, vol. 59, no. 5, pp. 5235–5247, 2023

    work page 2023

  25. [25]

    Mission Re-planning For Multiple Agile Earth Observation Satellites based on Cloud Coverage Forecasting,

    G. Yi, C. Han, Y. Chen, and W. Xing, “Mission Re-planning For Multiple Agile Earth Observation Satellites based on Cloud Coverage Forecasting,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. PP, pp. 1–1, 12 2021

    work page 2021

  26. [26]

    Selecting and scheduling observations of agile satellites,

    M. Lemaˆ ıtre, G. Verfaillie, F. Jouhaud, J.-M. Lachiver, and N. Bataille, “Selecting and scheduling observations of agile satellites,”Aerospace Science and Technology, vol. 6, no. 5, pp. 367–381, 2002

    work page 2002

  27. [27]

    A reinforcement learning-enhanced dung beetle optimization approach for agile earth observation satellite scheduling,

    W. Huang, H. Wang, J. Wu, H. Hou, J. Li, Z. Li, and Y. Song, “A reinforcement learning-enhanced dung beetle optimization approach for agile earth observation satellite scheduling,”IEEE Geoscience and Remote Sensing Letters, vol. 22, pp. 1–5, 2025. 23 Draft

    work page 2025

  28. [28]

    Joint observation and transmission scheduling of multiple agile satellites with energy constraint using improved aco algorithm,

    M. Shang, R. Yuan, B. Song, X. Huang, B. Yang, and S. Li, “Joint observation and transmission scheduling of multiple agile satellites with energy constraint using improved aco algorithm,”Acta Astronautica, vol. 230, pp. 92–103, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0094576525000797

    work page 2025

  29. [29]

    The integrated agile earth observation satellite scheduling problem,

    Y. Rocha, G. O. Chagas, L. C. Coelho, and A. Subramanian, “The integrated agile earth observation satellite scheduling problem,”Computers & Operations Research, vol. 184, p. 107212,

    work page

  30. [30]

    Available: https://www.sciencedirect.com/science/article/pii/S0305054825002400

    [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0305054825002400

    work page

  31. [31]

    Planetscope,

    ESA, “Planetscope,” accessed: 2026-02-20. [Online]. Available: https://earth.esa.int/eogateway/missions/planetscope

    work page 2026

  32. [32]

    WorldView-1, WorldView-2, WordView-3 datasheet,

    DigitalGlove, “WorldView-1, WorldView-2, WordView-3 datasheet,” accessed: 2026-02-20. [Online]. Available: https://earth.esa.int/eogateway/missions/worldview

    work page 2026

  33. [33]

    Ultralytics YOLOv8,

    G. Jocher, A. Chaurasia, and J. Qiu, “Ultralytics YOLOv8,” 2023, accessed: 2026-02-20. [Online]. Available: https://github.com/ultralytics/ultralytics

    work page 2023

  34. [34]

    Learning to track at 100 fps with deep regression networks,

    D. Held, S. Thrun, and S. Savarese, “Learning to track at 100 fps with deep regression networks,” inProceedings of (ECCV) European Conference on Computer Vision. Springer, October 2017, pp. 749 – 765

    work page 2017

  35. [35]

    Deep encoder–decoder networks for classification of hyperspectral and lidar data,

    D. Hong, L. Gao, R. Hang, B. Zhang, and J. Chanussot, “Deep encoder–decoder networks for classification of hyperspectral and lidar data,”IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022

    work page 2022

  36. [36]

    Laser beam propagation through random media,

    L. C. Andrews and R. L. Phillips, “Laser beam propagation through random media,”Laser Beam Propagation Through Random Media: Second Edition, 2005

    work page 2005

  37. [37]

    Ships-google-earth dataset,

    K. Stavrakakis, “Ships-google-earth dataset,” https://universe.roboflow.com/k–stavrakakis/ships- google-earth, May 2022, accessed: 2026-02-20

    work page 2022

  38. [38]

    Impact of pointing errors on the performance of generalized atmospheric optical channels,

    A. Jurado-Navas, J. M. Garrido-Balsells, J. F. Paris, M. Castillo-V´ azquez, and A. Puerta- Notario, “Impact of pointing errors on the performance of generalized atmospheric optical channels,”Opt. Express, vol. 20, no. 11, pp. 12 550–12 562, May 2012. [Online]. Available: https://opg.optica.org/oe/abstract.cfm?URI=oe-20-11-12550

    work page 2012

  39. [39]

    Speckle cn2 profiler: Improving satellite communications with machine learning,

    S. Ciarella, L. Orozco, V. Azizi, M. Arvis, and R. Saathof, “Speckle cn2 profiler: Improving satellite communications with machine learning,”Journal of Open Source Software, vol. 10, no. 114, p. 9127, 2025. [Online]. Available: https://doi.org/10.21105/joss.09127

    work page doi:10.21105/joss.09127 2025

  40. [40]

    Turbulence strengthc 2 n estimation from video using physics-based deep learning,

    R. K. Saha, E. Salcin, J. Kim, J. Smith, and S. Jayasuriya, “Turbulence strengthc 2 n estimation from video using physics-based deep learning,”Opt. Express, vol. 30, no. 22, pp. 40 854–40 870, Oct

    work page

  41. [41]

    Available: https://opg.optica.org/oe/abstract.cfm?URI=oe-30-22-40854

    [Online]. Available: https://opg.optica.org/oe/abstract.cfm?URI=oe-30-22-40854

    work page

  42. [42]

    Estimation of turbulence from time-lapse imagery,

    J. E. McCrae, S. R. Bose-Pillai, and S. T. Fiorino, “Estimation of turbulence from time-lapse imagery,”Optical Engineering, vol. 56, no. 7, p. 071504, 2017. [Online]. Available: https://doi.org/10.1117/1.OE.56.7.071504

    work page doi:10.1117/1.oe.56.7.071504 2017

  43. [43]

    Correlated satellite-derived turbulence, clouds & aerosol data,

    D. C. Meier and S. T. Fiorino, “Correlated satellite-derived turbulence, clouds & aerosol data,” in Imaging and Applied Optics 2014. Optica Publishing Group, 2014, p. PM1E.4. [Online]. Available: https://opg.optica.org/abstract.cfm?URI=pcDVT-2014-PM1E.4

    work page 2014

  44. [44]

    Satellite and radar measurement of ct2, cn2, and cv2,

    S. T. Fiorino, “Satellite and radar measurement of ct2, cn2, and cv2,” inImaging and Applied Optics 2014. Optica Publishing Group, 2014, p. PM1E.1. [Online]. Available: https://opg.optica.org/abstract.cfm?URI=pcDVT-2014-PM1E.1

    work page 2014

  45. [45]

    Comparison of index of refraction structure function ( c n 2) profiles derived from polar-orbiting satellite data and numerical weather prediction models,

    D. C. Meier and S. T. Fiorino, “Comparison of index of refraction structure function ( c n 2) profiles derived from polar-orbiting satellite data and numerical weather prediction models,” inImaging and Applied Optics 2015. Optica Publishing Group, 2015

    work page 2015

  46. [46]

    Computing refractive index structure parameter cn2 in a numerical weather prediction model,

    S. Wang, Q. Wang, B. J. Wauer, and Q. Jiang, “Computing refractive index structure parameter cn2 in a numerical weather prediction model,”Geophysical Research Letters, vol. 47, no. 17, 2020. [Online]. Available: https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2020GL089168 24 Draft

    work page doi:10.1029/2020gl089168 2020

  47. [47]

    Estimates of Cn2 from numerical weather prediction model output [presentation],

    R. Frehlich, R. D. Sharman, F. Vandenberghe, W. Yu, Y. Liu, J. C. Knievel, and G. Jumper, “Estimates of Cn2 from numerical weather prediction model output [presentation],” 14th Conference on Aviation, Range, and Aerospace Meteorology, Atlanta, US. NCAR Report, 2010, Jan. 2010

    work page 2010

  48. [48]

    Founda- tion models for remote sensing and earth observation: A survey, 2025, 2410.16602

    A. Xiao, W. Zuan, J. Wang, J. Huang, D. Tao, S. Lu, and N. Yokoya, “Foundation models for remote sensing and earth observation: A survey,” 2025. [Online]. Available: https://arxiv.org/abs/2410.16602

    work page arXiv 2025

  49. [49]

    Ksat global ground station network,

    Kongsberg Satellite Services (KSAT), “Ksat global ground station network,” accessed: 2026-02-20. [Online]. Available: https://www.ksat.no/ground-network-services/the-ksat-global-ground-station- network/

    work page 2026

  50. [50]

    An adaptive large neighborhood search metaheuristic for agile satellite scheduling with time-dependent transition time,

    X. Liu, G. Laporte, Y. Chen, and R. He, “An adaptive large neighborhood search metaheuristic for agile satellite scheduling with time-dependent transition time,”Computers & Operations Research, vol. 86, pp. 41–53, 2017

    work page 2017

  51. [51]

    A simple BSP-based model to predict execution time in GPU applications,

    M. Amaris, D. Cordeiro, A. Goldman, and R. Y. De Camargo, “A simple BSP-based model to predict execution time in GPU applications,” inProc. IEEE International Conference on High Performance Computing (HiPC), 2015, pp. 285–294

    work page 2015

  52. [52]

    “Digital Video Broadcasting (DVB); Second generation framing structure, channel coding and mod- ulation systems for broadcasting, interactive services, news gathering and other broadband satellite applications (DVB-S2),” ETSI, France, Standard, October 2014

    work page 2014

  53. [53]

    Stellato, G

    T. Achterberg, “Scip: solving constraint integer programs,”Mathematical Programming Computation, vol. 1, no. 1, pp. 1–41, Jul 2009. [Online]. Available: https://doi.org/10.1007/s12532- 008-0001-1

    work page doi:10.1007/s12532- 2009

  54. [54]

    Constraint integer programming: A new approach to integrate cp and mip,

    T. Achterberg, T. Berthold, T. Koch, and K. Wolter, “Constraint integer programming: A new approach to integrate cp and mip,” inIntegration of AI and OR Techniques in Constraint Pro- gramming for Combinatorial Optimization Problems, L. Perron and M. A. Trick, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2008, pp. 6–20

    work page 2008

  55. [55]

    pymoo: Multi-objective optimization in python,

    J. Blank and K. Deb, “pymoo: Multi-objective optimization in python,”IEEE Access, vol. 8, pp. 89 497–89 509, 2020

    work page 2020

  56. [56]

    VHRShips: an extensive benchmark dataset for scalable deep learning-based ship detection applications,

    S. Kızılkayaet al., “VHRShips: an extensive benchmark dataset for scalable deep learning-based ship detection applications,”ISPRS International Journal of Geo-Information, vol. 11, no. 8, 2022. 25

    work page 2022