arminmehrabian/nasa-eosdis-heterogeneous-gnn

EOSDIS Graph Neural Network Model Card

Model Overview

Model Name: EOSDIS-GNN Version: 1.0.0 Type: Heterogeneous Graph Neural Network Framework: PyTorch + PyTorch Geometric License: MIT Base Language Model: nasa-impact/nasa-smd-ibm-st-v2

Model Architecture

Architecture Diagram

Core Components

• Base Text Encoder: NASA-SMD-IBM Language Model (768-dimensional embeddings)
• Graph Neural Network: Heterogeneous GNN with multiple layers
• Node Types: Dataset, Publication, Instrument, Platform, ScienceKeyword
• Edge Types: Multiple relationship types between nodes

Technical Specifications

• Input Dimensions: 768 (NASA-SMD-IBM embeddings)
• Hidden Dimensions: Configurable (default: 256)
• Output Dimensions: 768 (aligned with NASA-SMD-IBM space)
• Number of Layers: Configurable (default: 3)
• Activation Function: ReLU
• Dropout: Applied between layers

Training Details

Training Data

• Source: NASA EOSDIS Knowledge Graph
• Node Types and Counts:
  • Datasets: Earth science datasets from NASA DAACs
  • Publications: Publications citing NASA EOSDIS datsets and publications citing those publications
  • Instruments: Earth observation instruments
  • Platforms: Satellite and other observation platforms
  • Science Keywords: NASA GCMD Science Keywords

Training Process

• Optimization: Adam optimizer
• Loss Function: Contrastive loss for semantic alignment
• Training Strategy:
  • Initial node embedding generation
  • Message passing through graph structure
  • Contrastive learning with NASA-SMD-IBM embeddings

Performance and Limitations

Strengths

1. Semantic Understanding:

   • Strong performance in finding semantically related content
   • Effective cross-modal relationships between text and graph structure

2. Domain Specificity:

   • Specialized for Earth science terminology
   • Understands relationships between instruments, platforms, and datasets

3. Multi-modal Integration:

   • Combines text-based and graph-based features
   • Preserves domain-specific relationships

Limitations

1. Data Coverage:

   • Performance depends on training data coverage
   • May have gaps in newer or less documented areas

2. Computational Requirements:

   • Requires significant memory for full graph processing
   • Graph operations can be computationally intensive

3. Domain Constraints:

   • Optimized for Earth science domain
   • May not generalize well to other domains

Usage Guide

Installation Requirements

pip install torch torch-geometric transformers huggingface-hub

Basic Usage

from transformers import AutoTokenizer, AutoModel
import torch
from gnn_model import EOSDIS_GNN

# Load models
tokenizer = AutoTokenizer.from_pretrained("nasa-impact/nasa-smd-ibm-st-v2")
text_model = AutoModel.from_pretrained("nasa-impact/nasa-smd-ibm-st-v2")
gnn_model = EOSDIS_GNN.from_pretrained("arminmehrabian/nasa-eosdis-heterogeneous-gnn")

# Process query
def get_embedding(text):
    inputs = tokenizer(text, return_tensors="pt", max_length=512, 
                      truncation=True, padding=True)
    with torch.no_grad():
        outputs = text_model(**inputs)
        return outputs.last_hidden_state[:, 0, :]

Semantic Search Example

from semantic_search import SemanticSearch

# Initialize searcher
searcher = SemanticSearch()

# Perform search
results = searcher.search(
    query="atmospheric carbon dioxide measurements",
    top_k=5,
    node_type="Dataset"  # Optional: filter by node type
)

Evaluation Metrics

Semantic Search Performance

• Top-5 Accuracy: [Add metric]
• Mean Reciprocal Rank: [Add metric]
• Node Type Classification: [Add metric]

Relationship Prediction

• Link Prediction Accuracy: [Add metric]
• Triple Classification: [Add metric]

Ethical Considerations

1. Data Bias:

   • Model may reflect biases in scientific documentation
   • Some regions or topics may be underrepresented

2. Environmental Impact:

   • Consider computational resources for inference
   • Batch processing recommended for efficiency

3. Usage Guidelines:

   • Intended for research and data discovery
   • Not designed for critical decision-making systems

Maintenance and Support

Version Control

• Model versions tracked on Hugging Face Hub
• Regular updates for improved performance

Issue Reporting

• GitHub Issues: [Add repository link]
• Bug reports and feature requests welcome

Citation

@misc{eosdis-gnn-2025,
  title={EOSDIS Graph Neural Network Model},
  author={Armin Mehrabian},
  year={2025},
  publisher={Hugging Face},
  howpublished={\url{https://huggingface.co/arminmehrabian/nasa-eosdis-heterogeneous-gnn}}
}

Contact Information

• Maintainer: [Armin Mehrabian]
• Email: [armin@gwu.edu]