When MAGIC met IceCube
Gamma-Ray Astronomy with Neutrino Event Reconstruction Techniques
Jarred Green
with E. Jobst, G. Ceribella, A. Berti, D. Green
ODSL Days, 8 July 2026
Max Planck Institute for Physics
jgreen@mpp.mpg.de
Outline
- The Gamma-Ray Sky
- Current Data Reconstruction
- Graphs + Clouds
- ML Playground
- Conclusions
Jarred Green - jgreen@mpp.mpg.de
Crab Nebula
NASA (JWST)
Centaurus A
ESO
1. The Gamma-Ray Sky
Gamma-ray Energy [log]
Flux
[log]
[ number / area / time ]
a few gamma rays every second in 1 m²
a few gamma rays every year in 1 m²
MeV
GeV
TeV
HIGH ENERGY
Our galaxy (Fermi)
1. The Gamma-Ray Sky
γ ray
e+
e-
e-
γ ray
Flux
[log]
a few gamma rays every second in 1 m²
a few gamma rays every year in 1 m²
"Imaging Atmospheric Cherenkov Telescopes"
MeV
GeV
TeV
VERY HIGH ENERGY
HIGH ENERGY
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
}
Dimensionality Reduction
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
One Pixel, 30ns
Time [ns]
Counts
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
{
'size': 546.88637,
'xc': -3.78983,
'yc': 7.29427,
'length': 7.76769,
'width': 1.76480,
'delta': -0.56875,
...
}"Hillas Parameters" (1977!)
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
{
'size': 546.88637,
'xc': -3.78983,
'yc': 7.29427,
'length': 7.76769,
'width': 1.76480,
'delta': -0.56875,
...
}
Random Forests
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
0. Raw data
1. Calibration
2. Cleaning
3. Parameterization
4. ML
5. Science
- Particle Type
- Energy
- Arrival Direction
Detections
Skymaps
Spectra
Jarred Green - jgreen@mpp.mpg.de
2. Event Reconstruction
ML
{
'size': 546.88637,
'xc': -3.78983,
'yc': 7.29427,
'length': 7.76769,
'width': 1.76480,
'delta': -0.56875,
...
}- Particle Type
- Energy
- Arrival Direction
Dimensionality
reduction
tl;dr
Jarred Green - jgreen@mpp.mpg.de
3. Graphs for MAGIC?
Proton
Gamma
Muon
Jarred Green - jgreen@mpp.mpg.de
3. Graphs for MAGIC
an IceCube case study
- A GNN framework for Neutrino observatories
- Easy to adapt to other detectors
Jarred Green - jgreen@mpp.mpg.de
IceMix
Proven model:
Jarred Green - jgreen@mpp.mpg.de
3. Graphs for MAGIC
We effectively deal with:
- irregular camera geometry
- sparse data
- non gridlike pixels
- arrays with different camera types
Why Graphs?
Jarred Green - jgreen@mpp.mpg.de
Visualized as a point cloud
when we include the time axis
time
Jarred Green - jgreen@mpp.mpg.de
4. ML Playground
Jarred Green - jgreen@mpp.mpg.de
How does the model work?
Each node in our point cloud becomes a token:
[x,y,t,charge,tel_id]
Jarred Green - jgreen@mpp.mpg.de
Energy Reconstruction
Direction Reconstruction
5. Conclusions
MAGIC Raw Data
- Contains full time evolution of events
-
Saves on data processing
-
Are naturally represented as graphs
Reconstruction with GraphNET
- Apply domain knowledge from IceCube
- 'Built-in' neutrino models work on gamma-ray data
- Robust performance with minimal modifications
Further evidence for the benefits
of cross-domain collaboration
Jarred Green - jgreen@mpp.mpg.de
P.S. No hyperparameter tuning done yet!
5. Future Motivation
70+ Telescopes!!
Cherenkov Telescope Array
Jarred Green - jgreen@mpp.mpg.de
Domain adaptation
Semi-supervised learning
MC augmentation
More simulations!
Thank you!
Jarred Green - jgreen@mpp.mpg.de
Credit: G. Ceribella