Background réaliste CsI(Tl) + hybridation mesuré/synthétique + dashboard continuum
- Remplace le continuum exponentiel par un modèle réaliste CsI(Tl) dans l'entraînement (bosse asymétrique ~110 keV + queue Compton) - Ajoute l'injection de background mesuré (70% mesuré / 30% synthétique) via --measured_background et MEASURED_BACKGROUND_PATH - Ajoute l'endpoint /api/background/continuum et le toggle "Continuum CsI" sur le dashboard background - Exclut le canal 1023 (overflow bin) de l'affichage web (NUM_CHANNELS=1023) - Corrige le lissage Gaussien du background (normalisation locale aux bords) - Met à jour README.md, CLAUDE.md, TUTORIEL.md, TOTO.md, vega_ml/README.md Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Jacquin Antoine
@ -8,22 +8,25 @@ A machine learning system for identifying radioactive isotopes from gamma-ray sp
|
||||
✅ **Completed:** Vega ML model architecture (CNN-FCNN hybrid)
|
||||
✅ **Completed:** Training pipeline with GPU support
|
||||
✅ **Completed:** Inference engine
|
||||
🔲 **Next:** Generate large training dataset (10,000-100,000 samples)
|
||||
🔲 **Future:** Real-time inference on Radiacode devices
|
||||
✅ **Completed:** Realistic CsI(Tl) background model
|
||||
✅ **Completed:** Hybrid training (measured + synthetic background)
|
||||
✅ **Completed:** Web dashboard (FastAPI + Chart.js)
|
||||
🔲 **Next:** Retrain model with realistic background
|
||||
🔲 **Future:** Real-time inference on Radiacode devices
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
This project aims to build a neural network that can identify radioactive isotopes from gamma spectra. Since collecting real gamma spectra requires radioactive sources and is expensive/regulated, we generate **synthetic training data** based on realistic physics models.
|
||||
This project builds a neural network that identifies radioactive isotopes from gamma spectra. Since collecting real spectra requires radioactive sources and is expensive/regulated, we generate **synthetic training data** based on realistic physics models.
|
||||
|
||||
### Target Hardware
|
||||
- **Training:** NVIDIA RTX 5090 GPU (requires PyTorch nightly with CUDA 12.8)
|
||||
- **Training:** NVIDIA RTX 5060 Ti GPU (Blackwell, requires PyTorch 2.7+ with CUDA 12.8)
|
||||
- **Inference:** Radiacode 101, 102, 103, 103G, 110 scintillation detectors
|
||||
|
||||
### Data Format
|
||||
- **Input:** 2D spectrograms (time intervals × 1023 energy channels)
|
||||
- **Output:** Multi-label isotope classification with activity estimation
|
||||
- **Input:** 1D spectrum (1023 energy channels, 20-3000 keV, normalized to max)
|
||||
- **Output:** Multi-label isotope classification (82 isotopes) with activity estimation (Bq)
|
||||
|
||||
---
|
||||
|
||||
@ -34,8 +37,7 @@ This project aims to build a neural network that can identify radioactive isotop
|
||||
```bash
|
||||
# Create virtual environment
|
||||
python -m venv .venv
|
||||
.venv\Scripts\activate # Windows
|
||||
# or: source .venv/bin/activate # Linux/Mac
|
||||
source .venv/bin/activate # Linux/Mac
|
||||
|
||||
# Install dependencies
|
||||
pip install numpy scipy pillow
|
||||
@ -47,25 +49,34 @@ pip install --pre torch torchvision --index-url https://download.pytorch.org/whl
|
||||
### Generate Synthetic Data
|
||||
|
||||
```bash
|
||||
# Generate 10 test samples
|
||||
python -m synthetic_spectra.generate_spectra
|
||||
# Generate 10 test samples (default)
|
||||
python -m vega_ml.synthetic_spectra.generate_spectra --num_samples 10 --output_dir data/synthetic
|
||||
|
||||
# With measured background for hybrid training (recommended)
|
||||
python -m vega_ml.synthetic_spectra.generate_spectra \
|
||||
--num_samples 50000 \
|
||||
--output_dir data/synthetic \
|
||||
--measured_background /path/to/background_24h.npy
|
||||
```
|
||||
|
||||
### Train the Model
|
||||
|
||||
```bash
|
||||
# Quick test run (5 epochs, small dataset)
|
||||
python training/vega/run_training.py --test
|
||||
python -m vega_ml.training.vega.run_training --test
|
||||
|
||||
# Full training
|
||||
python training/vega/run_training.py --epochs 100 --batch-size 32
|
||||
python -m vega_ml.training.vega.run_training \
|
||||
--data-dir data/synthetic \
|
||||
--model-dir models \
|
||||
--epochs 100 --batch-size 64
|
||||
```
|
||||
|
||||
### Run Inference
|
||||
|
||||
```bash
|
||||
# Run inference on synthetic data
|
||||
python inference/run_inference.py --model models/vega_best.pt --data data/synthetic
|
||||
python -m vega_ml.inference.run_inference --model models/vega_best.pt --data data/synthetic
|
||||
```
|
||||
|
||||
---
|
||||
@ -95,56 +106,74 @@ python inference/run_inference.py --model models/vega_best.pt --data data/synthe
|
||||
|
||||
## Synthetic Spectra Generation
|
||||
|
||||
### Realistic Background Model
|
||||
|
||||
The background continuum uses a realistic CsI(Tl) shape calibrated against real Radiacode 103 measurements, not a simple exponential:
|
||||
|
||||
- **Asymmetric hump** at ~110 keV (sigma_left=55 keV, sigma_right=50 keV) — the dominant low-energy scatter peak characteristic of CsI(Tl) detectors
|
||||
- **Compton tail**: 0.45*exp(-E/240) + 0.04*exp(-E/700) — realistic high-energy falloff
|
||||
- **Noise floor** at 0.8% of peak — prevents zero-count channels
|
||||
|
||||
This replaces the previous simple exponential `A*exp(-0.002*E)` which failed to reproduce the characteristic CsI(Tl) response.
|
||||
|
||||
### Hybrid Training with Measured Background
|
||||
|
||||
When a measured background file (`background_24h.npy`) is available, the generator blends it with the synthetic model:
|
||||
- **70% measured** background shape (scaled to target CPS)
|
||||
- **30% synthetic** continuum (for robustness against measurement artifacts)
|
||||
- Stochastic isotope peaks (K-40, radon, thorium) are still added on top with random activity levels
|
||||
|
||||
This is controlled by the `--measured_background` CLI argument or the `MEASURED_BACKGROUND_PATH` environment variable.
|
||||
|
||||
### Features
|
||||
- **82 isotopes** with accurate gamma emission lines
|
||||
- **Realistic physics:** Gaussian peaks, Poisson noise, Compton continuum, environmental background
|
||||
- **Realistic physics:** Gaussian peaks, Poisson noise, Compton continuum, CsI(Tl) background shape
|
||||
- **Multiple detector models:** Radiacode 101, 102, 103, 103G, 110 with correct FWHM and energy ranges
|
||||
- **Configurable variation:** Activity levels, measurement durations, isotope combinations
|
||||
- **Decay chains:** Uranium-238, Thorium-232 chains with secular equilibrium
|
||||
|
||||
### Sample Distribution
|
||||
### Sample Distribution (v3)
|
||||
| Type | Proportion | Description |
|
||||
|------|------------|-------------|
|
||||
| Single isotope | 40% | One source + background |
|
||||
| Dual isotope | 30% | Two sources blended |
|
||||
| Multi isotope | 20% | 3-5 sources combined |
|
||||
| Background only | 10% | Environmental only |
|
||||
|
||||
### Scaling Up
|
||||
Edit `synthetic_spectra/generate_spectra.py` to generate larger datasets:
|
||||
```python
|
||||
generate_training_batch(
|
||||
n_samples=100000, # Generate 100k samples
|
||||
output_dir=Path("data/synthetic/spectra"),
|
||||
detector_type="radiacode_103"
|
||||
)
|
||||
```
|
||||
| Background only | 15% | Environmental background only |
|
||||
| Single calibration | 20% | One check source + background |
|
||||
| Single medical | 8% | Medical isotope + background |
|
||||
| Single industrial | 5% | Industrial source + background |
|
||||
| Uranium chain | 10% | U-238 + daughters in equilibrium |
|
||||
| Thorium chain | 10% | Th-232 + daughters in equilibrium |
|
||||
| NORM | 7% | Naturally occurring radioactive material |
|
||||
| Fallout | 5% | Cs-137 + Cs-134 signature |
|
||||
| Mixed | 10% | Random 2-3 isotope mixes |
|
||||
| Complex mix | 5% | 4-6 isotopes from various categories |
|
||||
| Weak source | 5% | Near-detection-limit sources |
|
||||
|
||||
---
|
||||
|
||||
## Project Structure
|
||||
|
||||
```
|
||||
ml-for-isotope-identification/
|
||||
train/vega_ml/
|
||||
├── README.md # This file
|
||||
├── agents.md # AI agent context documentation
|
||||
├── .gitignore # Git ignore rules
|
||||
│
|
||||
├── synthetic_spectra/ # Spectrum generation package
|
||||
│ ├── __init__.py
|
||||
│ ├── config.py # Detector configurations
|
||||
│ ├── generator.py # Main generation logic
|
||||
│ ├── generate_spectra.py # CLI batch generation
|
||||
│ ├── config.py # Detector configurations (Radiacode 101-110)
|
||||
│ ├── generator.py # Main generation logic (SpectrumConfig)
|
||||
│ ├── generate_spectra.py # CLI batch generation (v1)
|
||||
│ ├── generate_spectra_v3.py # CLI batch generation (v3, parallel)
|
||||
│ ├── ground_truth/
|
||||
│ │ ├── isotope_data.py # 82 isotopes database
|
||||
│ │ └── decay_chains.py # Decay chain definitions
|
||||
│ └── physics/
|
||||
│ └── spectrum_physics.py # Physics calculations
|
||||
│ └── spectrum_physics.py # Physics calculations + realistic CsI(Tl) background
|
||||
│
|
||||
├── training/ # Training infrastructure
|
||||
│ └── vega/ # Vega model package
|
||||
│ ├── __init__.py
|
||||
│ ├── isotope_index.py # Isotope ↔ index mapping
|
||||
│ ├── model.py # VegaModel architecture
|
||||
│ ├── model.py # VegaModel architecture + VegaLoss
|
||||
│ ├── dataset.py # PyTorch Dataset/DataLoader
|
||||
│ ├── train.py # Training loop & utilities
|
||||
│ └── run_training.py # CLI training script
|
||||
@ -176,11 +205,14 @@ ml-for-isotope-identification/
|
||||
| Radiacode 103G | GAGG(Ce) | 7.4% | 20-3000 keV | 1024 |
|
||||
| Radiacode 110 | CsI(Tl) | 8.4% | 20-3000 keV | 1024 |
|
||||
|
||||
Note: Only the first 1023 channels are used (channel 1023 is an overflow bin).
|
||||
|
||||
### Physics Model
|
||||
- **Peak shape:** Gaussian with FWHM scaling as √(E/662)
|
||||
- **Expected counts:** λ = A × t × I × ε × T
|
||||
- **Peak shape:** Gaussian with FWHM scaling as sqrt(E/662) for scintillators
|
||||
- **Expected counts:** lambda = A * t * I * epsilon * T
|
||||
- **Noise:** Poisson counting statistics
|
||||
- **Background:** Exponential continuum + environmental isotopes (K-40, Pb-214, Bi-214, etc.)
|
||||
- **Background:** Realistic CsI(Tl) continuum (asymmetric hump + Compton tail) + environmental isotope peaks (K-40, radon daughters, thorium daughters)
|
||||
- **Hybrid mode:** Measured background can be blended with synthetic (70/30 ratio) for maximum realism
|
||||
|
||||
### Isotope Categories
|
||||
- Natural background (K-40, Ra-226, Rn-222)
|
||||
@ -199,21 +231,18 @@ ml-for-isotope-identification/
|
||||
numpy>=1.24.0
|
||||
scipy>=1.10.0
|
||||
pillow>=9.0.0
|
||||
torch>=2.11.0 (nightly with CUDA 12.8 for RTX 5090)
|
||||
scikit-learn>=1.3.0
|
||||
torch>=2.0.0
|
||||
```
|
||||
|
||||
### GPU Support
|
||||
The RTX 5090 (Blackwell architecture, sm_120) requires PyTorch nightly builds with CUDA 12.8:
|
||||
For Blackwell GPUs (RTX 50-series, sm_120), use PyTorch 2.7+ with CUDA 12.8:
|
||||
```bash
|
||||
pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu128
|
||||
```
|
||||
|
||||
### For AI Agents
|
||||
See [agents.md](agents.md) for comprehensive documentation on:
|
||||
- System architecture and design decisions
|
||||
- Physics model implementation details
|
||||
- Vega model architecture and training
|
||||
- Configuration options and variation strategies
|
||||
See [agents.md](agents.md) for comprehensive documentation on system architecture, physics model details, and configuration options.
|
||||
|
||||
---
|
||||
|
||||
@ -224,12 +253,11 @@ See [agents.md](agents.md) for comprehensive documentation on:
|
||||
- [x] ~~Implement CNN-FCNN model architecture (Vega)~~
|
||||
- [x] ~~Create training script with logging~~
|
||||
- [x] ~~Implement inference module~~
|
||||
- [ ] Generate large training dataset (100k samples)
|
||||
- [ ] Train model to convergence
|
||||
- [ ] Add data augmentation pipeline
|
||||
- [x] ~~Realistic CsI(Tl) background model~~
|
||||
- [x] ~~Hybrid training with measured background~~
|
||||
- [ ] Retrain model with realistic background
|
||||
- [ ] Add model evaluation metrics & confusion matrix
|
||||
- [ ] Implement real-time inference module
|
||||
- [ ] Create Radiacode device integration
|
||||
- [ ] Implement real-time inference on Radiacode devices
|
||||
|
||||
---
|
||||
|
||||
|
||||
@ -136,6 +136,7 @@ def generate_training_batch(
|
||||
background_only_fraction: float = 0.1,
|
||||
save_png: bool = False,
|
||||
random_seed: int = None,
|
||||
measured_background_path: str = None,
|
||||
) -> list:
|
||||
"""
|
||||
Generate a batch of training samples with various configurations.
|
||||
@ -210,6 +211,7 @@ def generate_training_batch(
|
||||
duration,
|
||||
detector_name=detector_name,
|
||||
include_background=True,
|
||||
measured_background_path=measured_background_path,
|
||||
)
|
||||
|
||||
# Save spectrum (don't accumulate in memory)
|
||||
@ -240,6 +242,7 @@ def generate_training_batch(
|
||||
duration,
|
||||
detector_name=detector_name,
|
||||
include_background=True,
|
||||
measured_background_path=measured_background_path,
|
||||
)
|
||||
|
||||
save_spectrum(
|
||||
@ -270,6 +273,7 @@ def generate_training_batch(
|
||||
duration,
|
||||
detector_name=detector_name,
|
||||
include_background=True,
|
||||
measured_background_path=measured_background_path,
|
||||
)
|
||||
|
||||
save_spectrum(
|
||||
@ -295,6 +299,7 @@ def generate_training_batch(
|
||||
sources=[], # No additional sources
|
||||
include_background=True,
|
||||
detector_name=detector_name,
|
||||
measured_background_path=measured_background_path,
|
||||
)
|
||||
|
||||
spectrum = generator.generate_spectrum(config)
|
||||
@ -367,6 +372,13 @@ def main():
|
||||
default=100.0,
|
||||
help="Maximum source activity in Bq (default: 100.0)"
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--measured_background",
|
||||
type=str,
|
||||
default=None,
|
||||
help="Path to measured background .npy file for hybrid training"
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--save_png",
|
||||
@ -402,6 +414,7 @@ def main():
|
||||
activity_range=(args.min_activity, args.max_activity),
|
||||
save_png=args.save_png,
|
||||
random_seed=args.seed,
|
||||
measured_background_path=args.measured_background,
|
||||
)
|
||||
|
||||
print("\n" + "=" * 60)
|
||||
|
||||
@ -405,6 +405,7 @@ def generate_single_sample(args: Tuple[int, dict]) -> Optional[str]:
|
||||
include_radon=bg_params['include_radon'],
|
||||
include_thorium=bg_params['include_thorium'],
|
||||
detector_name=config['detector_name'],
|
||||
measured_background_path=config.get('measured_background_path'),
|
||||
)
|
||||
|
||||
# Generate spectrum
|
||||
@ -437,6 +438,7 @@ def generate_training_data_v3(
|
||||
scenarios: Optional[List[SampleScenario]] = None,
|
||||
num_workers: int = None,
|
||||
random_seed: int = None,
|
||||
measured_background_path: Optional[str] = None,
|
||||
) -> int:
|
||||
"""
|
||||
Generate training samples in parallel.
|
||||
@ -498,6 +500,7 @@ def generate_training_data_v3(
|
||||
'bg_intensity_max': bg_intensity_range[1],
|
||||
'base_seed': random_seed,
|
||||
'scenarios': scenarios,
|
||||
'measured_background_path': measured_background_path,
|
||||
}
|
||||
|
||||
# Create work items
|
||||
@ -560,9 +563,11 @@ def main():
|
||||
help='Minimum activity in Bq')
|
||||
parser.add_argument('--activity_max', type=float, default=100.0,
|
||||
help='Maximum activity in Bq')
|
||||
|
||||
parser.add_argument('--measured_background', type=str, default=None,
|
||||
help='Path to measured background .npy file for hybrid training')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
|
||||
generate_training_data_v3(
|
||||
num_samples=args.num_samples,
|
||||
output_dir=Path(args.output_dir),
|
||||
@ -570,6 +575,7 @@ def main():
|
||||
activity_range=(args.activity_min, args.activity_max),
|
||||
num_workers=args.workers,
|
||||
random_seed=args.seed,
|
||||
measured_background_path=args.measured_background,
|
||||
)
|
||||
|
||||
|
||||
|
||||
@ -63,6 +63,7 @@ class SpectrumConfig:
|
||||
include_k40: bool = True
|
||||
include_radon: bool = True
|
||||
include_thorium: bool = True
|
||||
measured_background_path: Optional[str] = None
|
||||
|
||||
# Detector configuration
|
||||
detector_name: str = "radiacode_103"
|
||||
@ -166,7 +167,8 @@ class SpectrumGenerator:
|
||||
include_k40=background_config.get('include_k40', True),
|
||||
include_radon=background_config.get('include_radon', True),
|
||||
include_thorium=background_config.get('include_thorium', True),
|
||||
detector_config=self.detector_config
|
||||
detector_config=self.detector_config,
|
||||
measured_background_path=background_config.get('measured_background_path')
|
||||
)
|
||||
spectrum += bg_spectrum
|
||||
background_isotopes = bg_isotopes
|
||||
@ -264,6 +266,7 @@ class SpectrumGenerator:
|
||||
'include_k40': config.include_k40,
|
||||
'include_radon': config.include_radon,
|
||||
'include_thorium': config.include_thorium,
|
||||
'measured_background_path': config.measured_background_path,
|
||||
}
|
||||
)
|
||||
all_source_isotopes.extend(src_iso)
|
||||
|
||||
@ -9,6 +9,7 @@ Implements the physics of gamma spectrum generation including:
|
||||
"""
|
||||
|
||||
import numpy as np
|
||||
from pathlib import Path
|
||||
from scipy import special
|
||||
from typing import Optional, Tuple, List
|
||||
from dataclasses import dataclass
|
||||
@ -274,14 +275,14 @@ def generate_exponential_background(
|
||||
) -> np.ndarray:
|
||||
"""
|
||||
Generate exponential background continuum.
|
||||
|
||||
|
||||
B(E) = A * exp(-b * E)
|
||||
|
||||
|
||||
Args:
|
||||
energy_bins: Array of energy bin centers (keV)
|
||||
amplitude: Background amplitude at E=0
|
||||
decay_constant: Exponential decay constant (1/keV)
|
||||
|
||||
|
||||
Returns:
|
||||
Array of background counts
|
||||
"""
|
||||
@ -294,26 +295,123 @@ def generate_polynomial_background(
|
||||
) -> np.ndarray:
|
||||
"""
|
||||
Generate polynomial background.
|
||||
|
||||
|
||||
B(E) = Σ c_m * E^m
|
||||
|
||||
|
||||
Args:
|
||||
energy_bins: Array of energy bin centers (keV)
|
||||
coefficients: Polynomial coefficients [c0, c1, c2, ...]
|
||||
|
||||
|
||||
Returns:
|
||||
Array of background counts
|
||||
"""
|
||||
if coefficients is None:
|
||||
coefficients = [10.0, -0.005, 1e-6] # Default quadratic
|
||||
|
||||
|
||||
background = np.zeros_like(energy_bins)
|
||||
for m, c in enumerate(coefficients):
|
||||
background += c * (energy_bins ** m)
|
||||
|
||||
|
||||
return np.maximum(0, background)
|
||||
|
||||
|
||||
def generate_realistic_continuum(
|
||||
energy_bins: np.ndarray,
|
||||
total_counts: float,
|
||||
detector_config: Optional[DetectorConfig] = None
|
||||
) -> np.ndarray:
|
||||
"""
|
||||
Generate realistic CsI(Tl) background continuum shape.
|
||||
|
||||
Calibrated against real Radiacode 103 background measurements.
|
||||
Produces the characteristic asymmetric hump at ~110 keV and
|
||||
Compton-like tail that simple exponentials miss.
|
||||
|
||||
Shape components:
|
||||
- Asymmetric hump centered at ~110 keV (sigma_left=55, sigma_right=50 keV)
|
||||
- Compton continuum: 0.45*exp(-E/240) + 0.04*exp(-E/700)
|
||||
- Noise floor at 0.8% of peak
|
||||
|
||||
Args:
|
||||
energy_bins: Array of energy bin centers (keV)
|
||||
total_counts: Target total counts in the continuum
|
||||
detector_config: Detector configuration (unused, kept for API consistency)
|
||||
|
||||
Returns:
|
||||
Array of background counts matching real CsI(Tl) continuum shape
|
||||
"""
|
||||
E = energy_bins
|
||||
|
||||
# Asymmetric hump at ~110 keV (low-energy scatter peak in CsI(Tl))
|
||||
hump_center = 110.0
|
||||
sigma_left = 55.0 # Broader on the low-energy side
|
||||
sigma_right = 50.0 # Narrower on the high-energy side
|
||||
hump = np.where(
|
||||
E <= hump_center,
|
||||
np.exp(-0.5 * ((E - hump_center) / sigma_left) ** 2),
|
||||
np.exp(-0.5 * ((E - hump_center) / sigma_right) ** 2),
|
||||
)
|
||||
|
||||
# Compton continuum tail
|
||||
tail = 0.45 * np.exp(-E / 240.0) + 0.04 * np.exp(-E / 700.0)
|
||||
|
||||
# Noise floor (low-level baseline)
|
||||
noise_floor = 0.008
|
||||
|
||||
# Combine shape components
|
||||
continuum = hump + tail + noise_floor
|
||||
|
||||
# Normalize to target total counts
|
||||
if continuum.sum() > 0 and total_counts > 0:
|
||||
continuum *= total_counts / continuum.sum()
|
||||
|
||||
return continuum
|
||||
|
||||
|
||||
def load_measured_background(
|
||||
path: str,
|
||||
energy_bins: np.ndarray,
|
||||
duration_seconds: float
|
||||
) -> Optional[np.ndarray]:
|
||||
"""
|
||||
Load a measured background spectrum from a .npy file and rescale it
|
||||
to match the target duration.
|
||||
|
||||
The .npy file should contain a dict with keys 'counts' and 'duration'.
|
||||
|
||||
Args:
|
||||
path: Path to the .npy background file
|
||||
energy_bins: Array of energy bin centers (keV) for alignment
|
||||
duration_seconds: Target duration to scale the spectrum to
|
||||
|
||||
Returns:
|
||||
Background spectrum scaled to target duration, or None if file not found
|
||||
"""
|
||||
bg_path = Path(path)
|
||||
if not bg_path.exists():
|
||||
return None
|
||||
|
||||
try:
|
||||
bg_data = np.load(str(bg_path), allow_pickle=True).item()
|
||||
bg_counts = bg_data["counts"].astype(np.float64)
|
||||
bg_duration = float(bg_data["duration"])
|
||||
|
||||
# Truncate or pad to match energy_bins length
|
||||
num_channels = len(energy_bins)
|
||||
if len(bg_counts) > num_channels:
|
||||
bg_counts = bg_counts[:num_channels]
|
||||
elif len(bg_counts) < num_channels:
|
||||
bg_counts = np.pad(bg_counts, (0, num_channels - len(bg_counts)))
|
||||
|
||||
# Scale to target duration (cps * target_duration)
|
||||
if bg_duration > 0:
|
||||
scale = duration_seconds / bg_duration
|
||||
return bg_counts * scale
|
||||
return None
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def generate_environmental_background(
|
||||
energy_bins: np.ndarray,
|
||||
duration_seconds: float,
|
||||
@ -321,17 +419,19 @@ def generate_environmental_background(
|
||||
include_k40: bool = True,
|
||||
include_radon: bool = True,
|
||||
include_thorium: bool = True,
|
||||
detector_config: Optional[DetectorConfig] = None
|
||||
detector_config: Optional[DetectorConfig] = None,
|
||||
measured_background_path: Optional[str] = None
|
||||
) -> Tuple[np.ndarray, List[str]]:
|
||||
"""
|
||||
Generate realistic environmental background spectrum.
|
||||
|
||||
|
||||
Includes:
|
||||
- Exponential continuum (cosmic rays, scattered gammas)
|
||||
- Realistic CsI(Tl) continuum shape (asymmetric hump + Compton tail)
|
||||
- Or measured background if path provided and file exists
|
||||
- K-40 peak (1460 keV) - ubiquitous in environment
|
||||
- Radon daughters (Pb-214, Bi-214) - indoor air
|
||||
- Thorium daughters (Pb-212, Tl-208) - building materials
|
||||
|
||||
|
||||
Args:
|
||||
energy_bins: Array of energy bin centers (keV)
|
||||
duration_seconds: Acquisition time
|
||||
@ -340,27 +440,47 @@ def generate_environmental_background(
|
||||
include_radon: Include radon daughter peaks
|
||||
include_thorium: Include thorium daughter peaks
|
||||
detector_config: Detector configuration
|
||||
|
||||
measured_background_path: Path to .npy file with measured background.
|
||||
If provided and file exists, used as the continuum base instead
|
||||
of the synthetic continuum. Isotope peaks are still added on top
|
||||
with stochastic variation for training diversity.
|
||||
|
||||
Returns:
|
||||
Tuple of (background_spectrum, list_of_background_isotopes)
|
||||
"""
|
||||
if detector_config is None:
|
||||
detector_config = get_default_config()
|
||||
|
||||
|
||||
background_isotopes = []
|
||||
|
||||
# Start with exponential continuum
|
||||
|
||||
# Use measured background if available, otherwise synthetic continuum
|
||||
total_continuum_counts = background_cps * duration_seconds * 0.7
|
||||
background = generate_exponential_background(
|
||||
energy_bins,
|
||||
amplitude=total_continuum_counts / 500,
|
||||
decay_constant=0.002
|
||||
)
|
||||
|
||||
# Normalize continuum to target count rate
|
||||
if background.sum() > 0:
|
||||
background *= (total_continuum_counts / background.sum())
|
||||
|
||||
|
||||
measured = None
|
||||
if measured_background_path:
|
||||
measured = load_measured_background(
|
||||
measured_background_path, energy_bins, duration_seconds
|
||||
)
|
||||
|
||||
if measured is not None:
|
||||
# Scale measured background to match target CPS
|
||||
measured_total = measured.sum()
|
||||
if measured_total > 0 and total_continuum_counts > 0:
|
||||
# Blend: 70% measured shape, 30% synthetic for robustness
|
||||
synthetic = generate_realistic_continuum(
|
||||
energy_bins, total_counts=total_continuum_counts * 0.3,
|
||||
detector_config=detector_config
|
||||
)
|
||||
measured_scaled = measured * (total_continuum_counts * 0.7 / measured_total)
|
||||
background = measured_scaled + synthetic
|
||||
else:
|
||||
background = measured
|
||||
else:
|
||||
background = generate_realistic_continuum(
|
||||
energy_bins, total_counts=total_continuum_counts,
|
||||
detector_config=detector_config
|
||||
)
|
||||
|
||||
# Add K-40 peak (very common)
|
||||
if include_k40:
|
||||
k40_activity = np.random.uniform(0.5, 5.0) # Bq
|
||||
@ -376,11 +496,11 @@ def generate_environmental_background(
|
||||
)
|
||||
background += peak
|
||||
background_isotopes.append("K-40")
|
||||
|
||||
|
||||
# Add radon daughters
|
||||
if include_radon:
|
||||
radon_activity = np.random.uniform(0.1, 2.0) # Bq
|
||||
|
||||
|
||||
# Pb-214 lines
|
||||
for energy, intensity in [(295.22, 0.1842), (351.93, 0.356)]:
|
||||
peak = generate_peak_spectrum(
|
||||
@ -394,7 +514,7 @@ def generate_environmental_background(
|
||||
detector_config
|
||||
)
|
||||
background += peak
|
||||
|
||||
|
||||
# Bi-214 lines
|
||||
for energy, intensity in [(609.31, 0.4549), (1120.29, 0.1492), (1764.49, 0.1531)]:
|
||||
peak = generate_peak_spectrum(
|
||||
@ -408,13 +528,13 @@ def generate_environmental_background(
|
||||
detector_config
|
||||
)
|
||||
background += peak
|
||||
|
||||
|
||||
background_isotopes.extend(["Pb-214", "Bi-214"])
|
||||
|
||||
|
||||
# Add thorium daughters
|
||||
if include_thorium:
|
||||
thorium_activity = np.random.uniform(0.05, 1.0) # Bq
|
||||
|
||||
|
||||
# Ac-228 line
|
||||
peak = generate_peak_spectrum(
|
||||
energy_bins,
|
||||
@ -427,7 +547,7 @@ def generate_environmental_background(
|
||||
detector_config
|
||||
)
|
||||
background += peak
|
||||
|
||||
|
||||
# Pb-212 line
|
||||
peak = generate_peak_spectrum(
|
||||
energy_bins,
|
||||
@ -440,7 +560,7 @@ def generate_environmental_background(
|
||||
detector_config
|
||||
)
|
||||
background += peak
|
||||
|
||||
|
||||
# Tl-208 lines
|
||||
for energy, intensity in [(583.19, 0.845 * 0.36), (2614.51, 0.998 * 0.36)]:
|
||||
# Branching ratio of 36% for Tl-208 path
|
||||
@ -455,9 +575,9 @@ def generate_environmental_background(
|
||||
detector_config
|
||||
)
|
||||
background += peak
|
||||
|
||||
|
||||
background_isotopes.extend(["Ac-228", "Pb-212", "Tl-208"])
|
||||
|
||||
|
||||
return background, background_isotopes
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user