FPGA Neural Network Accelerators for Space
Apr 26, 2026
This episode explores a survey of FPGA-based neural network accelerators for space applications and asks whether onboard AI in spacecraft is truly becoming practical hardware or remains mostly a lab-scale demonstration. It explains why FPGAs are appealing for space missions, covering their power and flexibility advantages over CPUs, GPUs, and ASICs, while also digging into the real engineering constraints of radiation, fault tolerance, data movement, and limited downlink bandwidth. The discussion highlights the survey’s methodology and its corpus of 47 papers, showing that the field is still dominated by compact CNNs for vision, navigation, remote sensing, compression, and target detection rather than newer model families. A listener would find it interesting because the episode separates genuine flight-relevant progress from hype and makes clear that the hard problem is not just fast inference, but building AI systems that can survive and operate reliably in space.
Sources:
1. FPGA-Based Neural Network Accelerators for Space Applications: A Survey — Pedro Antunes, Artur Podobas, 2025
http://arxiv.org/abs/2504.16173
2. A Survey and Taxonomy of FPGA-based Deep Learning Accelerators — Ahmed Ghazi Blaiech, Khaled Ben Khalifa, Carlos Valderrama, Marcelo Augusto Costa Fernandes, et al., 2019
https://scholar.google.com/scholar?q=A+Survey+and+Taxonomy+of+FPGA-based+Deep+Learning+Accelerators
3. Accelerating Neural Network Inference on FPGA-Based Platforms—A Survey — Ran Wu, Xinmin Guo, Jian Du, Junbao Li, 2021
https://scholar.google.com/scholar?q=Accelerating+Neural+Network+Inference+on+FPGA-Based+Platforms%E2%80%94A+Survey
4. CloudSatNet-1: FPGA-Based Hardware-Accelerated Quantized CNN for Satellite On-Board Cloud Coverage Classification — Radoslav Pitonak, Jan Mucha, Lukas Dobis, Martin Javorka, Marek Marusin, 2022
https://scholar.google.com/scholar?q=CloudSatNet-1%3A+FPGA-Based+Hardware-Accelerated+Quantized+CNN+for+Satellite+On-Board+Cloud+Coverage+Classification
5. FPGA-Based Neural Network Accelerators for Space Applications: A Survey — Pedro Antunes, Artur Podobas, 2025
https://scholar.google.com/scholar?q=FPGA-Based+Neural+Network+Accelerators+for+Space+Applications%3A+A+Survey
6. Autonomous Operations Through Onboard Artificial Intelligence — R. L. Sherwood, Steve Chien, Rebecca Castano, Gregg Rabideau, 2002
https://scholar.google.com/scholar?q=Autonomous+Operations+Through+Onboard+Artificial+Intelligence
7. The Autonomous Sciencecraft Experiment Onboard the EO-1 Spacecraft — Daniel Tran, Steve Chien, Rob Sherwood, Rebecca Castano, Benjamin Cichy, Ashley Davies, Gregg Rabideau, 2004
https://scholar.google.com/scholar?q=The+Autonomous+Sciencecraft+Experiment+Onboard+the+EO-1+Spacecraft
8. The Phi-Sat-1 Mission: The First On-Board Deep Neural Network Demonstrator for Satellite Earth Observation — Gianluca Giuffrida, Luca Fanucci, Gabriele Meoni, Matej Batic, et al., 2021
https://scholar.google.com/scholar?q=The+Phi-Sat-1+Mission%3A+The+First+On-Board+Deep+Neural+Network+Demonstrator+for+Satellite+Earth+Observation
9. Flight of Dynamic Targeting on the CogniSAT-6 Spacecraft — Steve Chien, I. Zilberstein, A. Candela, D. Rijlaarsdam, T. Hendrix, A. Dunne, et al., 2025
https://scholar.google.com/scholar?q=Flight+of+Dynamic+Targeting+on+the+CogniSAT-6+Spacecraft
10. Mitigation of Radiation Effects in SRAM-Based FPGAs for Space Applications — Felix Siegle, Tanya Vladimirova, Jorgen Ilstad, Omar Emam, 2015
https://scholar.google.com/scholar?q=Mitigation+of+Radiation+Effects+in+SRAM-Based+FPGAs+for+Space+Applications
11. Xilinx Virtex-5QV (V5QV) Independent SEU Data — Melanie D. Berg, Kenneth A. LaBel, Jonathan Pellish, 2014
https://scholar.google.com/scholar?q=Xilinx+Virtex-5QV+%28V5QV%29+Independent+SEU+Data
12. Failure Rate Analysis of Radiation Tolerant Design Techniques on SRAM-based FPGAs — E. Vacca, Sarah Azimi, L. Sterpone, 2022
https://scholar.google.com/scholar?q=Failure+Rate+Analysis+of+Radiation+Tolerant+Design+Techniques+on+SRAM-based+FPGAs
13. Survey of Multi-Level Soft Error Mitigation Techniques for SRAM-based FPGAs — Lei Chen, Zhuoli Wang, Shuo Wang, Jing Zhou, Chunsheng Tian, Yongjiang Pang, 2025
https://scholar.google.com/scholar?q=Survey+of+Multi-Level+Soft+Error+Mitigation+Techniques+for+SRAM-based+FPGAs
14. Reliability Evaluation and Analysis of FPGA-Based Neural Network Acceleration System — Dawen Xu, Ziyang Zhu, Cheng Liu, Ying Wang, et al., 2021
https://scholar.google.com/scholar?q=Reliability+Evaluation+and+Analysis+of+FPGA-Based+Neural+Network+Acceleration+System
15. Impact of TMR Design Layouts on Single Event Tolerance in SRAM-based FPGAs — Haibin Wang, Yangsheng Wang, Weicheng Wang, 2021
https://scholar.google.com/scholar?q=Impact+of+TMR+Design+Layouts+on+Single+Event+Tolerance+in+SRAM-based+FPGAs
16. Fault-Tolerant Neural Network Accelerators With Selective TMR — Timoteo Garcia Bertoa, Giulio Gambardella, Nicholas J. Fraser, Michaela Blott, et al., 2022
https://scholar.google.com/scholar?q=Fault-Tolerant+Neural+Network+Accelerators+With+Selective+TMR
17. Research on Spaceborne Neural Network Accelerator and Its Fault Tolerance Design — Yingzhao Shao, Junyi Wang, Xiaodong Han, Yunsong Li, Yaolin Li, Zhanpeng Tao, 2025
https://scholar.google.com/scholar?q=Research+on+Spaceborne+Neural+Network+Accelerator+and+Its+Fault+Tolerance+Design
18. Reconfigurable Framework for Resilient Semantic Segmentation for Space Applications — Sebastian Sabogal, Alan D. George, Gary A. Crum, 2021
https://scholar.google.com/scholar?q=Reconfigurable+Framework+for+Resilient+Semantic+Segmentation+for+Space+Applications
19. Systematic Reliability Evaluation of FPGA Implemented CNN Accelerators — Zhen Gao, Shihui Gao, Yi Yao, Qiang Liu, Shulin Zeng, Guangjun Ge, Yu Wang, Anees Ullah, Pedro Reviriego, 2023
https://scholar.google.com/scholar?q=Systematic+Reliability+Evaluation+of+FPGA+Implemented+CNN+Accelerators
20. FPGA Architecture for Deep Learning and Its Application to Planetary Robotics — Pranay Reddy Gankidi, Jekan Thangavelautham, 2017
https://scholar.google.com/scholar?q=FPGA+Architecture+for+Deep+Learning+and+Its+Application+to+Planetary+Robotics
21. A Survey of FPGA Based Neural Network Accelerator — Kaiyuan Guo, Shulin Zeng, Jincheng Yu, Yu Wang, Huazhong Yang, 2017
https://scholar.google.com/scholar?q=A+Survey+of+FPGA+Based+Neural+Network+Accelerator
22. A Quarter of a Century of Neuromorphic Architectures on FPGAs -- an Overview — Wiktor J. Szczerek, Artur Podobas, 2025
https://scholar.google.com/scholar?q=A+Quarter+of+a+Century+of+Neuromorphic+Architectures+on+FPGAs+--+an+Overview
23. Hardware Platforms Enabling Edge AI for Space Applications: A Critical Review — Gabriela Mystkowska et al., 2025
https://scholar.google.com/scholar?q=Hardware+Platforms+Enabling+Edge+AI+for+Space+Applications%3A+A+Critical+Review
24. Post-Radiation Fault Analysis of a High Reliability FPGA Linux SoC — Andrew Elbert Wilson et al., 2023
https://scholar.google.com/scholar?q=Post-Radiation+Fault+Analysis+of+a+High+Reliability+FPGA+Linux+SoC
25. Improving Fault Tolerance for FPGA SoCs through Post-Radiation Design Analysis — Andrew Elbert Wilson, Nathan Baker, Ethan Campbell, Michael Wirthlin, 2024
https://scholar.google.com/scholar?q=Improving+Fault+Tolerance+for+FPGA+SoCs+through+Post-Radiation+Design+Analysis
26. Accelerated Deep-Learning Inference on FPGAs in the Space Domain — Michael Petry, Patrick Gest, Andreas Koch, Max Ghiglione, Martin Werner, 2023
https://scholar.google.com/scholar?q=Accelerated+Deep-Learning+Inference+on+FPGAs+in+the+Space+Domain
27. Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference — Christopher Wolters, Xiaoxuan Yang, Ulf Schlichtmann, Toyotaro Suzumura, 2024
https://scholar.google.com/scholar?q=Memory+Is+All+You+Need%3A+An+Overview+of+Compute-in-Memory+Architectures+for+Accelerating+Large+Language+Model+Inference
28. AI Post Transformers: Computation-Bandwidth-Memory Trade-offs for AI Infrastructure — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-09-computation-bandwidth-memory-trade-offs-a83f2b.mp3
29. AI Post Transformers: DreamerV3 World Models Across 150 Tasks — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-20-dreamerv3-world-models-across-150-tasks-af5edb.mp3
1. FPGA-Based Neural Network Accelerators for Space Applications: A Survey — Pedro Antunes, Artur Podobas, 2025
http://arxiv.org/abs/2504.16173
2. A Survey and Taxonomy of FPGA-based Deep Learning Accelerators — Ahmed Ghazi Blaiech, Khaled Ben Khalifa, Carlos Valderrama, Marcelo Augusto Costa Fernandes, et al., 2019
https://scholar.google.com/scholar?q=A+Survey+and+Taxonomy+of+FPGA-based+Deep+Learning+Accelerators
3. Accelerating Neural Network Inference on FPGA-Based Platforms—A Survey — Ran Wu, Xinmin Guo, Jian Du, Junbao Li, 2021
https://scholar.google.com/scholar?q=Accelerating+Neural+Network+Inference+on+FPGA-Based+Platforms%E2%80%94A+Survey
4. CloudSatNet-1: FPGA-Based Hardware-Accelerated Quantized CNN for Satellite On-Board Cloud Coverage Classification — Radoslav Pitonak, Jan Mucha, Lukas Dobis, Martin Javorka, Marek Marusin, 2022
https://scholar.google.com/scholar?q=CloudSatNet-1%3A+FPGA-Based+Hardware-Accelerated+Quantized+CNN+for+Satellite+On-Board+Cloud+Coverage+Classification
5. FPGA-Based Neural Network Accelerators for Space Applications: A Survey — Pedro Antunes, Artur Podobas, 2025
https://scholar.google.com/scholar?q=FPGA-Based+Neural+Network+Accelerators+for+Space+Applications%3A+A+Survey
6. Autonomous Operations Through Onboard Artificial Intelligence — R. L. Sherwood, Steve Chien, Rebecca Castano, Gregg Rabideau, 2002
https://scholar.google.com/scholar?q=Autonomous+Operations+Through+Onboard+Artificial+Intelligence
7. The Autonomous Sciencecraft Experiment Onboard the EO-1 Spacecraft — Daniel Tran, Steve Chien, Rob Sherwood, Rebecca Castano, Benjamin Cichy, Ashley Davies, Gregg Rabideau, 2004
https://scholar.google.com/scholar?q=The+Autonomous+Sciencecraft+Experiment+Onboard+the+EO-1+Spacecraft
8. The Phi-Sat-1 Mission: The First On-Board Deep Neural Network Demonstrator for Satellite Earth Observation — Gianluca Giuffrida, Luca Fanucci, Gabriele Meoni, Matej Batic, et al., 2021
https://scholar.google.com/scholar?q=The+Phi-Sat-1+Mission%3A+The+First+On-Board+Deep+Neural+Network+Demonstrator+for+Satellite+Earth+Observation
9. Flight of Dynamic Targeting on the CogniSAT-6 Spacecraft — Steve Chien, I. Zilberstein, A. Candela, D. Rijlaarsdam, T. Hendrix, A. Dunne, et al., 2025
https://scholar.google.com/scholar?q=Flight+of+Dynamic+Targeting+on+the+CogniSAT-6+Spacecraft
10. Mitigation of Radiation Effects in SRAM-Based FPGAs for Space Applications — Felix Siegle, Tanya Vladimirova, Jorgen Ilstad, Omar Emam, 2015
https://scholar.google.com/scholar?q=Mitigation+of+Radiation+Effects+in+SRAM-Based+FPGAs+for+Space+Applications
11. Xilinx Virtex-5QV (V5QV) Independent SEU Data — Melanie D. Berg, Kenneth A. LaBel, Jonathan Pellish, 2014
https://scholar.google.com/scholar?q=Xilinx+Virtex-5QV+%28V5QV%29+Independent+SEU+Data
12. Failure Rate Analysis of Radiation Tolerant Design Techniques on SRAM-based FPGAs — E. Vacca, Sarah Azimi, L. Sterpone, 2022
https://scholar.google.com/scholar?q=Failure+Rate+Analysis+of+Radiation+Tolerant+Design+Techniques+on+SRAM-based+FPGAs
13. Survey of Multi-Level Soft Error Mitigation Techniques for SRAM-based FPGAs — Lei Chen, Zhuoli Wang, Shuo Wang, Jing Zhou, Chunsheng Tian, Yongjiang Pang, 2025
https://scholar.google.com/scholar?q=Survey+of+Multi-Level+Soft+Error+Mitigation+Techniques+for+SRAM-based+FPGAs
14. Reliability Evaluation and Analysis of FPGA-Based Neural Network Acceleration System — Dawen Xu, Ziyang Zhu, Cheng Liu, Ying Wang, et al., 2021
https://scholar.google.com/scholar?q=Reliability+Evaluation+and+Analysis+of+FPGA-Based+Neural+Network+Acceleration+System
15. Impact of TMR Design Layouts on Single Event Tolerance in SRAM-based FPGAs — Haibin Wang, Yangsheng Wang, Weicheng Wang, 2021
https://scholar.google.com/scholar?q=Impact+of+TMR+Design+Layouts+on+Single+Event+Tolerance+in+SRAM-based+FPGAs
16. Fault-Tolerant Neural Network Accelerators With Selective TMR — Timoteo Garcia Bertoa, Giulio Gambardella, Nicholas J. Fraser, Michaela Blott, et al., 2022
https://scholar.google.com/scholar?q=Fault-Tolerant+Neural+Network+Accelerators+With+Selective+TMR
17. Research on Spaceborne Neural Network Accelerator and Its Fault Tolerance Design — Yingzhao Shao, Junyi Wang, Xiaodong Han, Yunsong Li, Yaolin Li, Zhanpeng Tao, 2025
https://scholar.google.com/scholar?q=Research+on+Spaceborne+Neural+Network+Accelerator+and+Its+Fault+Tolerance+Design
18. Reconfigurable Framework for Resilient Semantic Segmentation for Space Applications — Sebastian Sabogal, Alan D. George, Gary A. Crum, 2021
https://scholar.google.com/scholar?q=Reconfigurable+Framework+for+Resilient+Semantic+Segmentation+for+Space+Applications
19. Systematic Reliability Evaluation of FPGA Implemented CNN Accelerators — Zhen Gao, Shihui Gao, Yi Yao, Qiang Liu, Shulin Zeng, Guangjun Ge, Yu Wang, Anees Ullah, Pedro Reviriego, 2023
https://scholar.google.com/scholar?q=Systematic+Reliability+Evaluation+of+FPGA+Implemented+CNN+Accelerators
20. FPGA Architecture for Deep Learning and Its Application to Planetary Robotics — Pranay Reddy Gankidi, Jekan Thangavelautham, 2017
https://scholar.google.com/scholar?q=FPGA+Architecture+for+Deep+Learning+and+Its+Application+to+Planetary+Robotics
21. A Survey of FPGA Based Neural Network Accelerator — Kaiyuan Guo, Shulin Zeng, Jincheng Yu, Yu Wang, Huazhong Yang, 2017
https://scholar.google.com/scholar?q=A+Survey+of+FPGA+Based+Neural+Network+Accelerator
22. A Quarter of a Century of Neuromorphic Architectures on FPGAs -- an Overview — Wiktor J. Szczerek, Artur Podobas, 2025
https://scholar.google.com/scholar?q=A+Quarter+of+a+Century+of+Neuromorphic+Architectures+on+FPGAs+--+an+Overview
23. Hardware Platforms Enabling Edge AI for Space Applications: A Critical Review — Gabriela Mystkowska et al., 2025
https://scholar.google.com/scholar?q=Hardware+Platforms+Enabling+Edge+AI+for+Space+Applications%3A+A+Critical+Review
24. Post-Radiation Fault Analysis of a High Reliability FPGA Linux SoC — Andrew Elbert Wilson et al., 2023
https://scholar.google.com/scholar?q=Post-Radiation+Fault+Analysis+of+a+High+Reliability+FPGA+Linux+SoC
25. Improving Fault Tolerance for FPGA SoCs through Post-Radiation Design Analysis — Andrew Elbert Wilson, Nathan Baker, Ethan Campbell, Michael Wirthlin, 2024
https://scholar.google.com/scholar?q=Improving+Fault+Tolerance+for+FPGA+SoCs+through+Post-Radiation+Design+Analysis
26. Accelerated Deep-Learning Inference on FPGAs in the Space Domain — Michael Petry, Patrick Gest, Andreas Koch, Max Ghiglione, Martin Werner, 2023
https://scholar.google.com/scholar?q=Accelerated+Deep-Learning+Inference+on+FPGAs+in+the+Space+Domain
27. Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference — Christopher Wolters, Xiaoxuan Yang, Ulf Schlichtmann, Toyotaro Suzumura, 2024
https://scholar.google.com/scholar?q=Memory+Is+All+You+Need%3A+An+Overview+of+Compute-in-Memory+Architectures+for+Accelerating+Large+Language+Model+Inference
28. AI Post Transformers: Computation-Bandwidth-Memory Trade-offs for AI Infrastructure — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-09-computation-bandwidth-memory-trade-offs-a83f2b.mp3
29. AI Post Transformers: DreamerV3 World Models Across 150 Tasks — Hal Turing & Dr. Ada Shannon, 2026
https://podcast.do-not-panic.com/episodes/2026-04-20-dreamerv3-world-models-across-150-tasks-af5edb.mp3