Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI techniques for near real-time monitoring of contaminants in coastal waters on board future Phisat-2 mission

Francesca Razzano, Pietro Di Stasio, Francesco Mauro, Gabriele Meoni, Marco Esposito, Gilda Schirinzi, Silvia L. Ullo

TL;DR

This work addresses the need for near real-time coastal water contaminant monitoring by fusing satellite remote sensing with onboard AI processing on the Φsats-2 mission. It introduces AI4EDoET, a two-stage onboard framework that combines a Fully Connected Neural Network and a CNN-based regressor to estimate turbidity and pH from 8-band VIS/NIR data, processed entirely on the Myriad 2 VPU. A Liguria ARPA in situ dataset is aligned with Φsats-2 L1C simulations to build 256×256 patches (1805 samples) for training, validation, and testing. CPU-based results show competitive RMSE/MAE, and onboard deployment via Rupia achieves 24 FPS with 40.5 ms per inference, confirming practical feasibility for real-time alerts and reduced ground transmission. The study sets the stage for expanding to additional water-quality parameters and advancing autonomous, spaceborne environmental monitoring.

Abstract

Differently from conventional procedures, the proposed solution advocates for a groundbreaking paradigm in water quality monitoring through the integration of satellite Remote Sensing (RS) data, Artificial Intelligence (AI) techniques, and onboard processing. The objective is to offer nearly real-time detection of contaminants in coastal waters addressing a significant gap in the existing literature. Moreover, the expected outcomes include substantial advancements in environmental monitoring, public health protection, and resource conservation. The specific focus of our study is on the estimation of Turbidity and pH parameters, for their implications on human and aquatic health. Nevertheless, the designed framework can be extended to include other parameters of interest in the water environment and beyond. Originating from our participation in the European Space Agency (ESA) OrbitalAI Challenge, this article describes the distinctive opportunities and issues for the contaminants monitoring on the Phisat-2 mission. The specific characteristics of this mission, with the tools made available, will be presented, with the methodology proposed by the authors for the onboard monitoring of water contaminants in near real-time. Preliminary promising results are discussed and in progress and future work introduced.

AI techniques for near real-time monitoring of contaminants in coastal waters on board future Phisat-2 mission

TL;DR

This work addresses the need for near real-time coastal water contaminant monitoring by fusing satellite remote sensing with onboard AI processing on the Φsats-2 mission. It introduces AI4EDoET, a two-stage onboard framework that combines a Fully Connected Neural Network and a CNN-based regressor to estimate turbidity and pH from 8-band VIS/NIR data, processed entirely on the Myriad 2 VPU. A Liguria ARPA in situ dataset is aligned with Φsats-2 L1C simulations to build 256×256 patches (1805 samples) for training, validation, and testing. CPU-based results show competitive RMSE/MAE, and onboard deployment via Rupia achieves 24 FPS with 40.5 ms per inference, confirming practical feasibility for real-time alerts and reduced ground transmission. The study sets the stage for expanding to additional water-quality parameters and advancing autonomous, spaceborne environmental monitoring.

Abstract

Differently from conventional procedures, the proposed solution advocates for a groundbreaking paradigm in water quality monitoring through the integration of satellite Remote Sensing (RS) data, Artificial Intelligence (AI) techniques, and onboard processing. The objective is to offer nearly real-time detection of contaminants in coastal waters addressing a significant gap in the existing literature. Moreover, the expected outcomes include substantial advancements in environmental monitoring, public health protection, and resource conservation. The specific focus of our study is on the estimation of Turbidity and pH parameters, for their implications on human and aquatic health. Nevertheless, the designed framework can be extended to include other parameters of interest in the water environment and beyond. Originating from our participation in the European Space Agency (ESA) OrbitalAI Challenge, this article describes the distinctive opportunities and issues for the contaminants monitoring on the Phisat-2 mission. The specific characteristics of this mission, with the tools made available, will be presented, with the methodology proposed by the authors for the onboard monitoring of water contaminants in near real-time. Preliminary promising results are discussed and in progress and future work introduced.
Paper Structure (14 sections, 1 equation, 9 figures, 8 tables)

This paper contains 14 sections, 1 equation, 9 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Water contaminants parameters
  4. $\Phi$sat-2 Mission
  5. $\Phi$sat-2 Simulator
  6. Myriad 2 device
  7. Dataset creation
  8. Method proposed
  9. Fully Connected Neural Network Regression model
  10. AI4EDoET
  11. Results
  12. Results with CPU
  13. Results with Myriad 2
  14. Discussions and Conclusion

Figures (9)

  • Figure 1: Workflow for anomalies' extraction
  • Figure 2: Configuration of $\Phi$sat-2 in the Deployed State
  • Figure 3: Ground Projection of the $\Phi$sat-2 Imager
  • Figure 4: Distribution of monitoring station in Liguria region
  • Figure 5: AI4EDoET – The proposed Neural Network
  • ...and 4 more figures