Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

On-chain Validation of Tracking Data Messages (TDM) Using Distributed Deep Learning on a Proof of Stake (PoS) Blockchain

Yasir Latif, Anirban Chowdhury, Samya Bagchi

TL;DR

This work proposes a state-of-the-art, transformer-based orbit propagator that outperforms traditional methods like SGP4, enabling cross-validation of multiple observations for a single RSO, using a trustless mechanism for TDM validation and verification using deep learning over blockchain.

Abstract

Trustless tracking of Resident Space Objects (RSOs) is crucial for Space Situational Awareness (SSA), especially during adverse situations. The importance of transparent SSA cannot be overstated, as it is vital for ensuring space safety and security. In an era where RSO location information can be easily manipulated, the risk of RSOs being used as weapons is a growing concern. The Tracking Data Message (TDM) is a standardized format for broadcasting RSO observations. However, the varying quality of observations from diverse sensors poses challenges to SSA reliability. While many countries operate space assets, relatively few have SSA capabilities, making it crucial to ensure the accuracy and reliability of the data. Current practices assume complete trust in the transmitting party, leaving SSA capabilities vulnerable to adversarial actions such as spoofing TDMs. This work introduces a trustless mechanism for TDM validation and verification using deep learning over blockchain. By leveraging the trustless nature of blockchain, our approach eliminates the need for a central authority, establishing consensus-based truth. We propose a state-of-the-art, transformer-based orbit propagator that outperforms traditional methods like SGP4, enabling cross-validation of multiple observations for a single RSO. This deep learning-based transformer model can be distributed over a blockchain, allowing interested parties to host a node that contains a part of the distributed deep learning model. Our system comprises decentralised observers and validators within a Proof of Stake (PoS) blockchain. Observers contribute TDM data along with a stake to ensure honesty, while validators run the propagation and validation algorithms. The system rewards observers for contributing verified TDMs and penalizes those submitting unverifiable data.

On-chain Validation of Tracking Data Messages (TDM) Using Distributed Deep Learning on a Proof of Stake (PoS) Blockchain

TL;DR

This work proposes a state-of-the-art, transformer-based orbit propagator that outperforms traditional methods like SGP4, enabling cross-validation of multiple observations for a single RSO, using a trustless mechanism for TDM validation and verification using deep learning over blockchain.

Abstract

Trustless tracking of Resident Space Objects (RSOs) is crucial for Space Situational Awareness (SSA), especially during adverse situations. The importance of transparent SSA cannot be overstated, as it is vital for ensuring space safety and security. In an era where RSO location information can be easily manipulated, the risk of RSOs being used as weapons is a growing concern. The Tracking Data Message (TDM) is a standardized format for broadcasting RSO observations. However, the varying quality of observations from diverse sensors poses challenges to SSA reliability. While many countries operate space assets, relatively few have SSA capabilities, making it crucial to ensure the accuracy and reliability of the data. Current practices assume complete trust in the transmitting party, leaving SSA capabilities vulnerable to adversarial actions such as spoofing TDMs. This work introduces a trustless mechanism for TDM validation and verification using deep learning over blockchain. By leveraging the trustless nature of blockchain, our approach eliminates the need for a central authority, establishing consensus-based truth. We propose a state-of-the-art, transformer-based orbit propagator that outperforms traditional methods like SGP4, enabling cross-validation of multiple observations for a single RSO. This deep learning-based transformer model can be distributed over a blockchain, allowing interested parties to host a node that contains a part of the distributed deep learning model. Our system comprises decentralised observers and validators within a Proof of Stake (PoS) blockchain. Observers contribute TDM data along with a stake to ensure honesty, while validators run the propagation and validation algorithms. The system rewards observers for contributing verified TDMs and penalizes those submitting unverifiable data.
Paper Structure (23 sections, 5 figures)

This paper contains 23 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Decentralization and its importance for space
  3. The role of blockchain in S3
  4. Blockchain to manage the satellite manufacturing supply chain
  5. Space Domain Awareness Blockchain
  6. On-orbit Collaborative Operations and Services Blockchain
  7. Resident Space Object (RSO) Tracking in Space Situational Awareness (SSA)
  8. Track Correlation and Matching
  9. Processing Uncorrelated and Ambiguous Tracks
  10. Collaborative Approach and Tracking Data Messages (TDM)
  11. Motivation for a Trustless Coordination System
  12. Blockchain-Based Solution
  13. Space Domain Awareness (SDA) chain ecosystem
  14. Task queue, prioritization, and observations
  15. Verification and Validation of TDMs
  16. ...and 8 more sections

Figures (5)

  • Figure 1: The three proposed chains for space safety, sustainability, and security.
  • Figure 2: An overview of the SDA chain ecosystem consisting of a ledger (storage), decentralized sensing and compute nodes. See Sec. \ref{['sec:bdb-ecosystem']} for details about each component.
  • Figure 3: Operation of the SDA chain: Sensor tasking, data collection, decision making and recording the data onto the SDA chain. (See Sec. \ref{['sec:bdb-ecosystem']} for details.)
  • Figure 4: A schema of how the global propagation model is maintained and updated within the SDA chain ecosystem: compute nodes fetch data and current model from the network, and use the new data to refine the model parameters. These parameters are broadcast to other compute nodes, who can verify the capabilities of the new model since the have access to the corresponding training data in the network. Once the update has been verified by a set of participanting nodes, the global model is updated by merging the new weights.
  • Figure 5: Caption