parnian.moghadaspour

Final Reflection

This project demonstrates how space technology and ocean sensing can work together to create sustainable marine monitoring systems.

It is not just a biodiversity tool — it is a framework for responsible ocean stewardship.

Phase 5 – Outcomes:
The integrated system enables:

• Habitat mapping with multi-scale data fusion
• Predictive modeling of shark presence
• Improved marine conservation planning
• Safer fishing operations through ecological forecasting

Phase 4 – AI-Assisted Optimization:
AI tools were used for:

• Improving documentation clarity
• Refining Python syntax
• Enhancing presentation quality
  All scientific modeling and interpretation were manually designed and validated.

Phase 3 – Data Integration Pipeline:
We developed a Python-based workflow that:

• Retrieves NASA data via earthaccess
• Preprocesses and filters satellite datasets
• Matches tag sensor timestamps with satellite grids
• Generates spatial overlays and habitat prediction maps
  All datasets are real and sourced from NASA’s open repositories. No synthetic data were used.

System Architecture Design

We defined three core layers:

1-In-Situ Sensing Layer

. Motion detection

. Depth & pressure sensing

. Temperature monitoring

. Optical sensing for water color estimation

2- Satellite Data Layer (NASA datasets)

. Sea Surface Temperature (SST)

. Chlorophyll-a concentration

. Ocean circulation & eddy detection

3- Data Fusion & Modeling Layer (Python-based)

. Synchronization of temporal datasets

. Geospatial alignment

. Habitat probability mapping

. Behavioral inference modeling

Phase 1 – Concept Ideation

The project began with a core question:
How can space-based data improve real-time understanding of marine predator behavior?

We designed a hybrid framework combining:

Low-power shark tagging hardware

Environmental sensing (depth, temperature, movement, water color)

Satellite-derived oceanographic indices (SST, phytoplankton concentration, eddies)

The main goal was to bridge local biological sensing with global Earth observation data.