pith. sign in

arxiv: 2602.08924 · v2 · submitted 2026-02-09 · 📡 eess.SY · cs.SY

Automating the Wildfire Detection and Scheduling Pipeline with Maneuverable Earth Observation Satellites

Brycen D. Pearl , Joshua G. Warner , Hang Woon Lee This is my paper

Pith reviewed 2026-05-16 05:17 UTC · model grok-4.3

classification 📡 eess.SY cs.SY
keywords wildfire detectionsatellite schedulingconvolutional neural networksBayesian updatingEarth observationautonomous systemsmaneuverable satellitesconstellation scheduling
0
0 comments X p. Extension

The pith

A new automated pipeline uses satellite imagery, neural networks, and optimization to detect and track wildfires without manual intervention.

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

The paper develops and tests an end-to-end system that detects wildfires in Earth-observation images, updates detection probabilities with each new satellite pass, and then chooses which satellites to retask next. It combines convolutional neural networks for initial detection, Bayesian updating to refine beliefs over repeated flyovers, and a scheduling solver that assigns maneuvers to a constellation. The authors run the full pipeline on real wildfire locations and real satellite orbits inside a simulator. If the approach holds up, satellites could respond to emerging fires faster and with less ground control. The work is presented as a proof-of-concept demonstration rather than a deployed system.

Core claim

The paper claims that integrating convolutional neural network wildfire detection with sensor fusion, Bayesian statistical updating from repeated satellite passes, and reconfigurable multi-satellite scheduling produces an autonomous pipeline that improves wildfire monitoring performance in simulation.

What carries the argument

The WildFIRE-DS framework, which chains CNN-based detection, Bayesian posterior updating, and the Reconfigurable Earth Observation Satellite Scheduling Problem solver into one closed-loop algorithm.

If this is right

  • Satellite constellations can be retasked automatically after each new image rather than waiting for ground commands.
  • Repeated passes over the same fire allow the system to raise or lower detection confidence using Bayesian updating.
  • The scheduling layer chooses which satellites to maneuver next, trading off coverage of new fires against continued monitoring of existing ones.
  • The complete pipeline runs from raw image to scheduled maneuver without human review at any step.

Where Pith is reading between the lines

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

  • The same detection-plus-scheduling loop could be applied to other fast-changing phenomena such as floods or oil spills.
  • If the Bayesian update step proves robust, future satellites could carry lighter sensors and still achieve high detection rates by fusing multiple passes.
  • The approach implies that onboard compute for CNN inference plus ground-based optimization may be a practical division of labor for responsive Earth observation.

Load-bearing premise

The detection accuracy and scheduling performance measured in the simulator will remain similar when the same algorithms run on real satellite sensors, actual orbital perturbations, and live communication delays.

What would settle it

Running the detection and scheduling code on actual archived satellite imagery and orbit data for the same wildfire events and measuring whether the reported detection rates and response times match the simulated numbers.

read the original abstract

Wildfires are becoming increasingly frequent, with potentially devastating consequences, including loss of life, infrastructure destruction, and severe environmental damage. Low Earth orbit satellites equipped with onboard sensors can capture critical information relative to active wildfires and enable near real-time detection through machine learning algorithms applied to the acquired data. We propose a framework that automates the complete wildfire detection and satellite scheduling pipeline, entitled the WildFire-applicable Intelligent and Responsive Ensemble for Detection and Scheduling (WildFIRE-DS). This paper develops an algorithm to realize the vision of the WildFIRE-DS as a proof of concept, integrating three key components: wildfire detection in satellite imagery, statistical updating that incorporates data from repeated flyovers, and multi-satellite scheduling optimization. The algorithm enables wildfire detection using convolutional neural networks with sensor fusion techniques, incorporates subsequent flyover information via Bayesian statistics, and schedules a constellation of satellites using the state-of-the-art Reconfigurable Earth Observation Satellite Scheduling Problem. Simulated experiments conducted using real-world wildfire locations and the orbits of operational Earth observation satellites to demonstrate that this autonomous detection and scheduling approach effectively enhances wildfire monitoring capabilities.

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

2 major / 1 minor

Summary. The paper proposes the WildFIRE-DS framework to automate the wildfire detection and scheduling pipeline for maneuverable Earth observation satellites. It integrates three components: convolutional neural network-based detection with sensor fusion on satellite imagery, Bayesian statistical updating to incorporate information from repeated flyovers, and optimization of multi-satellite schedules via the Reconfigurable Earth Observation Satellite Scheduling Problem. The central claim is that simulated experiments using real-world wildfire locations and operational satellite orbits demonstrate that this autonomous approach effectively enhances wildfire monitoring capabilities.

Significance. If the simulation results can be shown to hold under realistic conditions, the work would provide a concrete, integrated pipeline for near-real-time autonomous wildfire monitoring that leverages existing satellite constellations more responsively. The choice to ground simulations in actual fire locations and orbits is a strength that could support practical deployment claims once validation gaps are addressed.

major comments (2)
  1. [Abstract] Abstract: The claim that the approach 'effectively enhances wildfire monitoring capabilities' is unsupported by any reported quantitative metrics (detection accuracy, false-positive rates, scheduling latency or coverage improvements, or baseline comparisons), leaving the central empirical claim without visible evidence.
  2. [Simulated Experiments] Simulated Experiments: The experiments use real locations and orbits but give no indication that realistic sensor noise models, attitude perturbations, or communication delays are injected into the imagery or state updates; performance is therefore shown only under idealized conditions, which directly undermines the operational enhancement claim.
minor comments (1)
  1. [Abstract] The acronym WildFIRE-DS is expanded only after first use; define it on first appearance for clarity.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We have revised the abstract to include quantitative metrics and added explicit discussion of simulation assumptions in the experiments section to address the concerns raised.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim that the approach 'effectively enhances wildfire monitoring capabilities' is unsupported by any reported quantitative metrics (detection accuracy, false-positive rates, scheduling latency or coverage improvements, or baseline comparisons), leaving the central empirical claim without visible evidence.

    Authors: We agree that the abstract should include specific quantitative support for the central claim. The revised manuscript updates the abstract to report key metrics from the simulated experiments, including CNN-based detection accuracy, false-positive rates, improvements in coverage percentage relative to baseline static scheduling, and reductions in average scheduling latency. These additions provide direct evidence for the enhancement in wildfire monitoring capabilities. revision: yes

  2. Referee: [Simulated Experiments] Simulated Experiments: The experiments use real locations and orbits but give no indication that realistic sensor noise models, attitude perturbations, or communication delays are injected into the imagery or state updates; performance is therefore shown only under idealized conditions, which directly undermines the operational enhancement claim.

    Authors: We acknowledge that the simulations are conducted under idealized conditions without explicit injection of sensor noise models, attitude perturbations, or communication delays. The revised manuscript adds a dedicated paragraph in the Simulated Experiments section that explicitly states these assumptions, discusses their implications for the reported results, and outlines how such factors could be incorporated in future extensions. This revision improves transparency while preserving the proof-of-concept value of the integrated pipeline under the stated conditions. revision: partial

Circularity Check

0 steps flagged

No significant circularity; pipeline uses external standard methods

full rationale

The paper's derivation chain integrates CNN detection with sensor fusion, Bayesian flyover updating, and Reconfigurable Earth Observation Satellite Scheduling optimization, all presented as standard external techniques applied to real wildfire locations and operational orbits in simulation. No equations reduce by construction to fitted inputs renamed as predictions, no self-definitional loops appear in the described components, and no load-bearing uniqueness theorems or ansatzes are imported solely via self-citation. The central claim rests on simulated performance of these independent modules rather than any self-referential reduction, rendering the pipeline self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The framework rests on standard assumptions from computer vision and optimization literature without introducing new free parameters, axioms, or invented entities in the abstract description.

pith-pipeline@v0.9.0 · 5499 in / 988 out tokens · 27846 ms · 2026-05-16T05:17:22.627371+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

77 extracted references · 77 canonical work pages

  1. [1]

    A review of machine learning applications in wildfire science and management,

    Jain, P., Coogan, S. C., Subramanian, S. G., Crowley, M., Taylor, S., and Flannigan, M. D., “A review of machine learning applications in wildfire science and management,”Environmental Reviews, Vol. 28, No. 4, 2020, pp. 478–505. https://doi.org/10.1139/er-2020-0019

    work page doi:10.1139/er-2020-0019 2020

  2. [2]

    The Economics of Wildfire in the United States,

    Bayham, J., Yoder, J. K., Champ, P. A., and Calkin, D. E., “The Economics of Wildfire in the United States,”Annual Review of Resource Economics, Vol. 14, 2022, pp. 379–401. https://doi.org/10.1146/annurev-resource-111920-014804

    work page doi:10.1146/annurev-resource-111920-014804 2022

  3. [3]

    Wildfire risk modeling,

    Oliveira, S., Rocha, J., and Sá, A., “Wildfire risk modeling,”Current Opinion in Environmental Science & Health, Vol. 23, 2021, p. 100274. https://doi.org/10.1016/j.coesh.2021.100274

    work page doi:10.1016/j.coesh.2021.100274 2021

  4. [4]

    Editorial: the 2019/20 Black Summer bushfires,

    Davey, S. M., and and, A. S., “Editorial: the 2019/20 Black Summer bushfires,”Australian Forestry, Vol. 83, No. 2, 2020, pp. 47–51. https://doi.org/10.1080/00049158.2020.1769899

    work page doi:10.1080/00049158.2020.1769899 2019

  5. [5]

    Large California wildfires: 2020 fires in historical context,

    Keeley, J., and Syphard, A., “Large California wildfires: 2020 fires in historical context,”Fire Ecology, Vol. 17, No. 22, 2021. https://doi.org/10.1186/s42408-021-00110-7

    work page doi:10.1186/s42408-021-00110-7 2020

  6. [6]

    Revisiting the 2023 wildfire season in Canada,

    Pelletier, F., Cardille, J. A., Wulder, M. A., White, J. C., and Hermosilla, T., “Revisiting the 2023 wildfire season in Canada,” Science of Remote Sensing, Vol. 10, 2024, p. 100145. https://doi.org/10.1016/j.srs.2024.100145

    work page doi:10.1016/j.srs.2024.100145 2023

  7. [7]

    Real-Time Wildfire Monitoring via Geostationary Satellite and Artificial Intelligence: Insights from the March 2025 South Korea Wildfires,

    Sung, T., Lee, G., Kim, D., Kim, W., Yang, S., and Im, J., “Real-Time Wildfire Monitoring via Geostationary Satellite and Artificial Intelligence: Insights from the March 2025 South Korea Wildfires,”Korean Journal of Remote Sensing, Vol. 41, No. 3, 2025, pp. 565–580. https://doi.org/10.7780/kjrs.2025.41.3.6

    work page doi:10.7780/kjrs.2025.41.3.6 2025

  8. [8]

    Early Wildfire Detection Technologies in Practice—A Review,

    Mohapatra, A., and Trinh, T., “Early Wildfire Detection Technologies in Practice—A Review,”Sustainability, Vol. 14, No. 19,

    work page

  9. [9]

    https://doi.org/10.3390/su141912270

    work page doi:10.3390/su141912270

  10. [10]

    ANewApproachbasedonWirelessSensorNetworkandFuzzyLogicforForestFireDetection,

    Ammar,M.B.,andSouissi,R.,“ANewApproachbasedonWirelessSensorNetworkandFuzzyLogicforForestFireDetection,” International Journal of Computer Applications, Vol. 89, No. 2, 2014, pp. 48–55. https://doi.org/10.5120/15477-4169

    work page doi:10.5120/15477-4169 2014

  11. [11]

    A smart wireless sensor network node for fire detection,

    Khalid, W., SATTAR, A., Qureshi, M., Amin, A., MALIK, M., and Memon, K., “A smart wireless sensor network node for fire detection,”TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, Vol. 27, No. 4, 2019, pp. 2541–2556. https://doi.org/10.3906/elk-1812-81

    work page doi:10.3906/elk-1812-81 2019

  12. [12]

    Forest fire detection system using wireless sensor networks and machine learning,

    Dampage, U., Bandaranayake, L., Wanasinghe, R., Kottahachchi, K., and Jayasanka, B., “Forest fire detection system using wireless sensor networks and machine learning,”Scientific Reports, Vol. 12, No. 46, 2022. https://doi.org/10.1038/s41598-021- 03882-9. 38

    work page doi:10.1038/s41598-021- 2022

  13. [13]

    Kalman Filter-Based Large-Scale Wildfire Monitoring With a System of UAVs,

    Lin, Z., Liu, H. H. T., and Wotton, M., “Kalman Filter-Based Large-Scale Wildfire Monitoring With a System of UAVs,”IEEE Transactions on Industrial Electronics, Vol. 66, No. 1, 2019, pp. 606–615. https://doi.org/10.1109/TIE.2018.2823658

    work page doi:10.1109/tie.2018.2823658 2019

  14. [14]

    Multi-Agent Reinforcement Learning-Based Fairness-Aware Scheduling for Bursty Traffic

    Lewicki, T., and Liu, K., “Multimodal Wildfire Surveillance with UAV,”2021 IEEE Global Communications Conference (GLOBECOM), 2021, pp. 1–6. https://doi.org/10.1109/GLOBECOM46510.2021.9685547

    work page doi:10.1109/globecom46510.2021.9685547 2021

  15. [15]

    The effect of natural disasters on economic activity in US counties: Acenturyofdata,

    Boustan, L. P., Kahn, M. E., Rhode, P. W., and Yanguas, M. L., “The effect of natural disasters on economic activity in US counties: Acenturyofdata,”JournalofUrbanEconomics ,Vol.118,2020,p.103257. https://doi.org/10.1016/j.jue.2020.103257

    work page doi:10.1016/j.jue.2020.103257 2020

  16. [16]

    High-resolution imaging with small satellites: what are the possibilities and limitations?

    Sandau, R., “High-resolution imaging with small satellites: what are the possibilities and limitations?”Sensors and Systems for Space Applications, Vol. 6555, edited by R. T. Howard and R. D. Richards, International Society for Optics and Photonics, SPIE, 2007, p. 65550O. https://doi.org/10.1117/12.717570

    work page doi:10.1117/12.717570 2007

  17. [17]

    Satellite Image Analysis for Disaster and Crisis-Management Support,

    Voigt, S., Kemper, T., Riedlinger, T., Kiefl, R., Scholte, K., and Mehl, H., “Satellite Image Analysis for Disaster and Crisis-Management Support,”IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, No. 6, 2007, pp. 1520–1528. https://doi.org/10.1109/TGRS.2007.895830

    work page doi:10.1109/tgrs.2007.895830 2007

  18. [18]

    Limitations and capabilities of the NOAA satellite advanced very high resolution radiometer (AVHRR) for remote sensing of the Earth’s surface,

    Huh, O. K., “Limitations and capabilities of the NOAA satellite advanced very high resolution radiometer (AVHRR) for remote sensing of the Earth’s surface,”Preventive Veterinary Medicine, Vol. 11, No. 3, 1991, pp. 167–183. https: //doi.org/10.1016/S0167-5877(05)80003-0

    work page doi:10.1016/s0167-5877(05)80003-0 1991

  19. [19]

    The Advanced Very High Resolution Radiometer: Contributing to Earth Observations for over 40 Years,

    Kalluri, S., Cao, C., Heidinger, A., Ignatov, A., Key, J., and Smith, T., “The Advanced Very High Resolution Radiometer: Contributing to Earth Observations for over 40 Years,”Bulletin of the American Meteorological Society, Vol. 102, No. 2, 2021, pp. E351–E366. https://doi.org/10.1175/BAMS-D-20-0088.1

    work page doi:10.1175/bams-d-20-0088.1 2021

  20. [20]

    The use of NOAA/AVHRR satellite data for monitoring and assessment of forest fires and floods,

    Domenikiotis, C., Loukas, A., and Dalezios, N. R., “The use of NOAA/AVHRR satellite data for monitoring and assessment of forest fires and floods,”Natural Hazards and Earth System Sciences, Vol. 3, No. 1/2, 2003, pp. 115–128. https: //doi.org/10.5194/nhess-3-115-2003

    work page doi:10.5194/nhess-3-115-2003 2003

  21. [21]

    MODIS Design,

    NASA MODIS, “MODIS Design,” https://modis.gsfc.nasa.gov/about/design.php, 2015. Last accessed January 23, 2026

    work page 2015

  22. [22]

    Mapping the daily progression of large wildland fires using Modis Active Fire Data,

    Veraverbeke, S., Sedano, F., Hook, S. J., Randerson, J. T., Jin, Y., and Rogers, B. M., “Mapping the daily progression of large wildland fires using Modis Active Fire Data,”International Journal of Wildland Fire, Vol. 23, No. 5, 2014, pp. 655–667. https://doi.org/10.1071/wf13015

    work page doi:10.1071/wf13015 2014

  23. [23]

    Long-term on-orbit performance of the VIIRS on Suomi NPP, NOAA-20, and NOAA-21 in reference to partner missions,

    Cao, C., Blonski, S., Shao, X., Wang, W., Choi, T., Zhang, F., Uprety, S., and Bai, Y., “Long-term on-orbit performance of the VIIRS on Suomi NPP, NOAA-20, and NOAA-21 in reference to partner missions,”Earth Observing Missions and Sensors: Development, Implementation, and Characterization VI, Vol. 13267, edited by X. Xiong, T. Kimura, and P.-H. Huang, Int...

    work page doi:10.1117/12.3042122 2025

  24. [24]

    Real-Time Wildfire Detection Algorithm BasedonVIIRSFireProductandHimawari-8Data,

    Zhang, D., Huang, C., Gu, J., Hou, J., Zhang, Y., Han, W., Dou, P., and Feng, Y., “Real-Time Wildfire Detection Algorithm BasedonVIIRSFireProductandHimawari-8Data,” RemoteSensing,Vol.15,No.6,2023. https://doi.org/10.3390/rs15061541. 39

    work page doi:10.3390/rs15061541 2023

  25. [25]

    LANCE Land, Atmosphere Near real-time Capability for Earth observation,

    The National Aeronautics and Space Administration, “LANCE Land, Atmosphere Near real-time Capability for Earth observation,” https://www.earthdata.nasa.gov/data/projects/lance, 2025. Last accessed January 23, 2026

    work page 2025

  26. [26]

    Fire Information for Resource Management System Version 2.11.43,

    The National Aeronautics and Space Administration, “Fire Information for Resource Management System Version 2.11.43,” https://firms.modaps.eosdis.nasa.gov/, 2025. Last accessed January 23, 2026

    work page 2025

  27. [28]

    AssessingtheShapeAccuracyofCoarseResolutionBurnedAreaIdentifications,

    Humber,M.L.,Boschetti,L.,andGiglio,L.,“AssessingtheShapeAccuracyofCoarseResolutionBurnedAreaIdentifications,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 58, No. 3, 2020, pp. 1516–1526. https://doi.org/10.1109/TGRS.2 019.2943901

    work page doi:10.1109/tgrs.2 2020

  28. [29]

    SatelliteImagesClassificationUsingCNN:ASurvey,

    Jarrallah,Z.H., andKhodher, M.A.A., “SatelliteImagesClassificationUsingCNN:ASurvey,” 2022InternationalConference on Data Science and Intelligent Computing (ICDSIC), 2022. https://doi.org/10.1109/ICDSIC56987.2022.10075828

    work page doi:10.1109/icdsic56987.2022.10075828 2022

  29. [30]

    Deep Reinforcement Learning-Based Periodic Earth Observation Scheduling for Agile Satellite Constellation,

    Wang, X., Zhao, F., Shi, Z., and Jin, Z., “Deep Reinforcement Learning-Based Periodic Earth Observation Scheduling for Agile Satellite Constellation,”Journal of Aerospace Information Systems, Vol. 20, No. 8, 2023, pp. 508–519. https: //doi.org/10.2514/1.I011209

    work page doi:10.2514/1.i011209 2023

  30. [31]

    Improving Robustness of Autonomous Earth-Observing Spacecraft Using Training Environment Enhancements,

    Mantovani, L. Q., and Schaub, H., “Improving Robustness of Autonomous Earth-Observing Spacecraft Using Training Environment Enhancements,”Journal of Aerospace Information Systems, 2026. https://doi.org/10.2514/1.I011697, (article in advance)

    work page doi:10.2514/1.i011697 2026

  31. [32]

    Enhancing Remote-Sensing Satellite Task Scheduling Using Reinforcement Learning and Multi-Objective Optimization,

    Ahmadi Khatir, P., Homayounpour, M. M., and Raissi Charmcani, K., “Enhancing Remote-Sensing Satellite Task Scheduling Using Reinforcement Learning and Multi-Objective Optimization,”Journal of Aerospace Information Systems, Vol. 22, No. 12, 2025, pp. 1066–1082. https://doi.org/10.2514/1.I011555

    work page doi:10.2514/1.i011555 2025

  32. [33]

    Optimal reconfiguration of satellite constellations with the auction algorithm,

    de Weck, O. L., Scialom, U., and Siddiqi, A., “Optimal reconfiguration of satellite constellations with the auction algorithm,” Acta Astronautica, Vol. 62, No. 2, 2008, pp. 112–130. https://doi.org/10.1016/j.actaastro.2007.02.008

    work page doi:10.1016/j.actaastro.2007.02.008 2008

  33. [34]

    RegionalConstellationReconfigurationProblem: IntegerLinearProgrammingFormulationandLagrangian Heuristic Method,

    Lee,H.,andHo,K.,“RegionalConstellationReconfigurationProblem: IntegerLinearProgrammingFormulationandLagrangian Heuristic Method,”Journal of Spacecraft and Rockets, Vol. 60, No. 6, 2023, pp. 1828–1845. https://doi.org/10.2514/1.A35685

    work page doi:10.2514/1.a35685 2023

  34. [35]

    Maximizing Observation Throughput via Multi-Stage Satellite Constellation Reconfiguration,

    Lee, H., Chen, H., and Ho, K., “Maximizing Observation Throughput via Multi-Stage Satellite Constellation Reconfiguration,” AAS/AIAA Astrodynamics Specialist Conference, 2022, pp. 1–19. AAS Paper 22-825

    work page 2022

  35. [36]

    Benchmarking Agility and Reconfigurability in Satellite Systems for Tropical Cyclone Monitoring,

    Pearl, B. D., Gold, L. P., and Lee, H., “Benchmarking Agility and Reconfigurability in Satellite Systems for Tropical Cyclone Monitoring,”Journal of Spacecraft and Rockets, Vol. 62, No. 4, 2025, pp. 1138–1151. https://doi.org/10.2514/1.A36177

    work page doi:10.2514/1.a36177 2025

  36. [37]

    Developing the Reconfigurable Earth Observation Satellite Scheduling Problem,

    Pearl, B. D., Miller, J. M., and Lee, H., “Developing the Reconfigurable Earth Observation Satellite Scheduling Problem,” AIAA SCITECH 2025 Forum, 2025, pp. 1–34. https://doi.org/10.2514/6.2025-0589. 40

    work page doi:10.2514/6.2025-0589 2025

  37. [38]

    ReconfigurableEarthObservationSatelliteSchedulingProblem,

    Pearl,B.D.,Miller,J.M.,andLee,H.,“ReconfigurableEarthObservationSatelliteSchedulingProblem,” JournalofAerospace Information Systems, 2025. https://doi.org/10.2514/1.I011659, (article in advance)

    work page doi:10.2514/1.i011659 2025

  38. [39]

    AutonomousSpace-BasedWildfireMonitoring: DynamicSchedulingofManeuverable Satellites with CNN-Based Detection,

    Pearl,B.D.,Warner,J.G.,andLee,H.,“AutonomousSpace-BasedWildfireMonitoring: DynamicSchedulingofManeuverable Satellites with CNN-Based Detection,”AAS/AIAA Astrodynamics Specialist Conference, 2025, pp. 1–20. AAS Paper 25-687

    work page 2025

  39. [40]

    Active fire detection in Landsat-8 imagery: A large-scale dataset and a deep-learning study,

    de Almeida Pereira, G. H., Fusioka, A. M., Nassu, B. T., and Minetto, R., “Active fire detection in Landsat-8 imagery: A large-scale dataset and a deep-learning study,”ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 178, 2021, pp. 171–186. https://doi.org/10.1016/j.isprsjprs.2021.06.002

    work page doi:10.1016/j.isprsjprs.2021.06.002 2021

  40. [41]

    http://www.deeplearningbook.org

    Goodfellow, I., Bengio, Y., and Courville, A.,Deep Learning, MIT Press, 2016. http://www.deeplearningbook.org

    work page 2016

  41. [42]

    BASNet: BurnedAreaSegmentationNetworkforReal-TimeDetection of Damage Maps in Remote Sensing Images,

    Bo,W.,Liu,J.,Fan,X.,Tjahjadi,T.,Ye,Q.,andFu,L.,“BASNet: BurnedAreaSegmentationNetworkforReal-TimeDetection of Damage Maps in Remote Sensing Images,”IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 2022, pp. 1–13. https://doi.org/10.1109/TGRS.2022.3197647

    work page doi:10.1109/tgrs.2022.3197647 2022

  42. [43]

    Spatial–Spectral Attention Network Guided With Change Magnitude Image for Land Cover Change Detection Using Remote Sensing Images,

    Lv, Z., Wang, F., Cui, G., Benediktsson, J. A., Lei, T., and Sun, W., “Spatial–Spectral Attention Network Guided With Change Magnitude Image for Land Cover Change Detection Using Remote Sensing Images,”IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 2022, pp. 1–12. https://doi.org/10.1109/TGRS.2022.3197901

    work page doi:10.1109/tgrs.2022.3197901 2022

  43. [44]

    Automaticdetectionoffiresmokeusingartificialneuralnetworksandthreshold approaches applied to AVHRR imagery,

    Li,Z.,Khananian,A.,Fraser,R.,andCihlar,J.,“Automaticdetectionoffiresmokeusingartificialneuralnetworksandthreshold approaches applied to AVHRR imagery,”IEEE Transactions on Geoscience and Remote Sensing, Vol. 39, No. 9, 2001, pp. 1859–1870. https://doi.org/10.1109/36.951076

    work page doi:10.1109/36.951076 2001

  44. [45]

    The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection,

    Ali, M. L., and Zhang, Z., “The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection,”Computers, Vol. 13, No. 12, 2024. https://doi.org/10.3390/computers13120336

    work page doi:10.3390/computers13120336 2024

  45. [46]

    AMFLW-YOLO: A Lightweight Network for Remote Sensing Image Detection BasedonAttentionMechanismandMultiscaleFeatureFusion,

    Peng, G., Yang, Z., Wang, S., and Zhou, Y., “AMFLW-YOLO: A Lightweight Network for Remote Sensing Image Detection BasedonAttentionMechanismandMultiscaleFeatureFusion,” IEEETransactionsonGeoscienceandRemoteSensing ,Vol.61, 2023, pp. 1–16. https://doi.org/10.1109/TGRS.2023.3327285

    work page doi:10.1109/tgrs.2023.3327285 2023

  46. [47]

    MobileOne-YOLO: An Improved Real-Time Fire Detection Algorithm for Aircraft Cargo Compartments,

    Zhang, W., Wang, K., Zhou, X., Shi, L., and Song, X., “MobileOne-YOLO: An Improved Real-Time Fire Detection Algorithm for Aircraft Cargo Compartments,”Journal of Aerospace Information Systems, Vol. 22, No. 6, 2025, pp. 447–456. https://doi.org/10.2514/1.I011514

    work page doi:10.2514/1.i011514 2025

  47. [48]

    Few-Shot Object Detection on Remote Sensing Images,

    Li, X., Deng, J., and Fang, Y., “Few-Shot Object Detection on Remote Sensing Images,”IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 2022, pp. 1–14. https://doi.org/10.1109/TGRS.2021.3051383

    work page doi:10.1109/tgrs.2021.3051383 2022

  48. [49]

    FFCA-YOLO for Small Object Detection in Remote Sensing Images,

    Zhang, Y., Ye, M., Zhu, G., Liu, Y., Guo, P., and Yan, J., “FFCA-YOLO for Small Object Detection in Remote Sensing Images,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 62, 2024, pp. 1–15. https://doi.org/10.1109/TGRS.2024.3363057

    work page doi:10.1109/tgrs.2024.3363057 2024

  49. [50]

    Airborne Optical and Thermal Remote Sensing for Wildfire Detection and Monitoring,

    Allison, R. S., Johnston, J. M., Craig, G., and Jennings, S., “Airborne Optical and Thermal Remote Sensing for Wildfire Detection and Monitoring,”Sensors, Vol. 16, No. 8, 2016. https://doi.org/10.3390/s16081310. 41

    work page doi:10.3390/s16081310 2016

  50. [51]

    Airborne Remote Sensing of Wildland Fires,

    Riggan, P. J., and Tissell, R. G., “Airborne Remote Sensing of Wildland Fires,”Wildland Fires and Air Pollution, Developments in Environmental Science, Vol. 8, edited by A. Bytnerowicz, M. J. Arbaugh, A. R. Riebau, and C. Andersen, Elsevier, 2008, pp. 139–168. https://doi.org/10.1016/S1474-8177(08)00006-5

    work page doi:10.1016/s1474-8177(08)00006-5 2008

  51. [52]

    Estimating fire properties by remote sensing,

    Riggan, P. J., Hoffman, J. W., and Brass, J. A., “Estimating fire properties by remote sensing,”IEEE Aerospace and Electronic Systems Magazine, Vol. 24, No. 2, 2009, pp. 13–19. https://doi.org/10.1109/MAES.2009.4798987

    work page doi:10.1109/maes.2009.4798987 2009

  52. [53]

    Autonomous Satellite Wildfire Detection Using Hyperspectral Imagery and Neural Networks: A Case Study on Australian Wildfire,

    Thangavel, K., Spiller, D., Sabatini, R., Amici, S., Sasidharan, S. T., Fayek, H., and Marzocca, P., “Autonomous Satellite Wildfire Detection Using Hyperspectral Imagery and Neural Networks: A Case Study on Australian Wildfire,”Remote Sensing, Vol. 15, No. 3, 2023. https://doi.org/10.3390/rs15030720

    work page doi:10.3390/rs15030720 2023

  53. [54]

    Remote sensing of forest fires in Southern Europe using IRS-WiFS and MODIS data,

    Barbosa, P. M., San-Miguel-Ayanz, J., and Schmuck, G., “Remote sensing of forest fires in Southern Europe using IRS-WiFS and MODIS data,”Remote Sensing for Environmental Monitoring, GIS Applications, and Geology, Vol. 4545, edited by M. Ehlers, International Society for Optics and Photonics, SPIE, 2002, pp. 165–173. https://doi.org/10.1117/12.453670

    work page doi:10.1117/12.453670 2002

  54. [55]

    Daytimefiredetectionusingairbornehyperspectraldata,

    Dennison,P.E.,andRoberts,D.A.,“Daytimefiredetectionusingairbornehyperspectraldata,” RemoteSensingofEnvironment , Vol. 113, No. 8, 2009, pp. 1646–1657. https://doi.org/10.1016/j.rse.2009.03.010

    work page doi:10.1016/j.rse.2009.03.010 2009

  55. [56]

    Managing the Data Flood—Analyzing Images Onboard Small Earth Observation Satellites,

    Heimbach, M. P., Kumar, P., Shrestha, S. S., Glöckner, P., Plattner, M., Fassi, C., and Schmidt, M., “Managing the Data Flood—Analyzing Images Onboard Small Earth Observation Satellites,”Deutscher Luft- und Raumfahrtkongress 2025, Deutsche Gesellschaft für Luft- und Raumfahrt - Lilienthal-Oberth e.V., 2025, pp. 1–8. https://doi.org/10.25967/650390

    work page doi:10.25967/650390 2025

  56. [57]

    AutomatedVolcanoMonitoring Using Multiple Space and Ground Sensors,

    Chien,S.A.,Davies,A.G.,Doubleday,J.,Tran,D.Q.,Mclaren,D.,Chi,W.,andMaillard,A.,“AutomatedVolcanoMonitoring Using Multiple Space and Ground Sensors,”Journal of Aerospace Information Systems, Vol. 17, No. 4, 2020, pp. 214–228. https://doi.org/10.2514/1.I010798

    work page doi:10.2514/1.i010798 2020

  57. [58]

    Chapter 11 - Leveraging Earth observation satellites for emergency response: Hotspot detection, burned area tracking, and beyond,

    Sánchez-Jiménez, D., Andrés-Anaya, P., Cifuentes, D., Charco-Toboso, J. R., Guerrero-Sevilla, D., Yali-Samaniego, R., Laguela, S., and González-Aguilera, D., “Chapter 11 - Leveraging Earth observation satellites for emergency response: Hotspot detection, burned area tracking, and beyond,”Satellite Remote Sensing for Forest and Environmental Monitoring, ed...

    work page doi:10.1016/b978-0-443-40296-8.00014-8 2026

  58. [59]

    You only look once: Unified, real-time object detection

    Redmon, J., Divvala, S., Girshick, R., and Farhadi, A., “ You Only Look Once: Unified, Real-Time Object Detection ,”2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, Los Alamitos, CA, USA, 2016, pp. 779–788. https://doi.org/10.1109/CVPR.2016.91

    work page doi:10.1109/cvpr.2016.91 2016

  59. [60]

    Research on object detection and recognition in remote sensing images based on YOLOv11,

    He, L.-h., Zhou, Y.-z., Liu, L., Cao, W., and Ma, J.-h., “Research on object detection and recognition in remote sensing images based on YOLOv11,”Scientific Reports, Vol. 15, No. 14032, 2025. https://doi.org/10.1038/s41598-025-96314-x

    work page doi:10.1038/s41598-025-96314-x 2025

  60. [61]

    Systems Tool Kit (STK),

    Ansys, “Systems Tool Kit (STK),” Software, 2025. URL https://www.agi.com/products/stk, version 12.10.0. 42

    work page 2025

  61. [62]

    Active fire detection using Landsat-8/OLI data,

    Schroeder, W., Oliva, P., Giglio, L., Quayle, B., Lorenz, E., and Morelli, F., “Active fire detection using Landsat-8/OLI data,” Remote Sensing of Environment, Vol. 185, 2016, pp. 210–220. https://doi.org/10.1016/j.rse.2015.08.032, landsat 8 Science Results

    work page doi:10.1016/j.rse.2015.08.032 2016

  62. [63]

    Detection of Small Wildfire by Thermal Infrared Camera With the Uncooled Microbolometer Array for 50-kg Class Satellite,

    Fukuhara, T., Kouyama, T., Kato, S., Nakamura, R., Takahashi, Y., and Akiyama, H., “Detection of Small Wildfire by Thermal Infrared Camera With the Uncooled Microbolometer Array for 50-kg Class Satellite,”IEEE Transactions on Geoscience and Remote Sensing, Vol. 55, No. 8, 2017, pp. 4314–4324. https://doi.org/10.1109/TGRS.2017.2690996

    work page doi:10.1109/tgrs.2017.2690996 2017

  63. [64]

    Different Image Fusion Techniques — A Critical Review,

    Sahu, D. K., and Parsai, M. P., “Different Image Fusion Techniques — A Critical Review,”International Journal of Modern Engineering Research, Vol. 2, No. 5, 2012, pp. 4298–4301

    work page 2012

  64. [65]

    Pixel-level Image Fusion using Wavelets and Principal Component Analysis,

    Naidu, V., and Raol, J. R., “Pixel-level Image Fusion using Wavelets and Principal Component Analysis,”Defence Science Journal, Vol. 58, No. 3, 2008, p. 338. https://doi.org/10.14429/dsj.58.1653

    work page doi:10.14429/dsj.58.1653 2008

  65. [66]

    Weighted boxes fusion: Ensembling boxes from different object detection models,

    Solovyev, R., Wang, W., and Gabruseva, T., “Weighted boxes fusion: Ensembling boxes from different object detection models,” Image and Vision Computing, Vol. 107, 2021, p. 104117. https://doi.org/10.1016/j.imavis.2021.104117

    work page doi:10.1016/j.imavis.2021.104117 2021

  66. [67]

    An advanced object classification strategy using YOLO through camera and LiDAR sensor fusion,

    Kim, J., Kim, J., and Cho, J., “An advanced object classification strategy using YOLO through camera and LiDAR sensor fusion,”2019 13th International Conference on Signal Processing and Communication Systems (ICSPCS), 2019, pp. 1–5. https://doi.org/10.1109/ICSPCS47537.2019.9008742

    work page doi:10.1109/icspcs47537.2019.9008742 2019

  67. [68]

    Enhancing decision-making in optimization through llm-assisted inference: A neural networks perspective

    El-Dalahmeh, A., El-Dalahmeh, M., and Li, J., “Enhanced Vehicle Detection through Multi-Sensor Fusion Utilizing YOLO-NAS and Faster R-CNN,”2024 International Joint Conference on Neural Networks (IJCNN), 2024, pp. 1–6. https://doi.org/10.1109/IJCNN60899.2024.10651024

    work page arXiv 2024

  68. [69]

    A Parallel Implementation of Computing Mean Average Precision,

    Wang, B., “A Parallel Implementation of Computing Mean Average Precision,”arXiv preprint arXiv:2206.09504, 2022. https://doi.org/10.48550/arXiv.2206.09504

    work page doi:10.48550/arxiv.2206.09504 2022

  69. [70]

    Gelman, A., Carlin, J., Stern, H., Dunson, D., Vehtari, A., and Rubin, D.,Bayesian Data Analysis, Third edition, Chapman & Hall, 2020

    work page 2020

  70. [71]

    Bayes’ theorem,

    Puga, J. L., Krzywinski, M., and Altman, N., “Bayes’ theorem,”Nature Methods, Vol. 12, No. 4, 2015, pp. 277–278. https://doi.org/10.1038/nmeth.3335

    work page doi:10.1038/nmeth.3335 2015

  71. [72]

    Deterministic Multistage Constellation Reconfiguration Using Integer Programming and Sequential Decision-Making Methods,

    Lee, H., Williams Rogers, D. O., Pearl, B. D., Chen, H., and Ho, K., “Deterministic Multistage Constellation Reconfiguration Using Integer Programming and Sequential Decision-Making Methods,”Journal of Spacecraft and Rockets, Vol. 62, No. 1, 2025, pp. 206–222. https://doi.org/10.2514/1.A35990

    work page doi:10.2514/1.a35990 2025

  72. [73]

    MATLAB, 24.2.0.2923080 (R2024b) Update 6, The MathWorks Inc., Natick, Massachusetts, 2025

    work page 2025

  73. [74]

    YALMIP : a toolbox for modeling and optimization in MATLAB,

    Löfberg, J., “YALMIP : a toolbox for modeling and optimization in MATLAB,”2004 IEEE International Conference on Robotics and Automation (IEEE Cat. No.04CH37508), Taipei, Taiwan, 2004, pp. 284–289. https://doi.org/10.1109/CACSD.20 04.1393890. 43

    work page doi:10.1109/cacsd.20 2004

  74. [75]

    URL https://www.python.org/, python version 3.9.6

    Python Core Team,Python: A dynamic, open source programming language, Python Software Foundation, 2019. URL https://www.python.org/, python version 3.9.6

    work page 2019

  75. [76]

    Space Track SATCAT Data,

    United States Space Force, “Space Track SATCAT Data,” https://www.space-track.org/#catalog (Required Login), 2025. Last accessed January 23, 2026

    work page 2025

  76. [77]

    Vallado, D.,Fundamentals of Astrodynamics and Applications, Space technology library, Microcosm Press, 2022, Chap. 6, pp. 321–428

    work page 2022

  77. [78]

    GEOSAT-1 Overview,

    European Space Agency, “GEOSAT-1 Overview,” https://earth.esa.int/eogateway/missions/geosat-1/description, 2024. Last accessed January 23, 2026. 44

    work page 2024