2D Multi-Modal Data Fusion for Electron Microscopy
Fused multi-modal electron microscopy, a combines elastic scattering (HAADF) and inelastic spectroscopic signals (EELS/EDX) to recover high signal-to-noise ratio chemical maps at nano- and atomic-resolution.
By linking simultaneously acquired modalities through regularized optimization, the method can reduce dose requirements by over one order of magnitude while substantially improving SNR for chemical maps.
Installation
The package is available on PyPI:
pip install multimodal-fusion
For local development, clone the repository and install in editable mode:
git clone https://github.com/jtschwar/Multi-Modal-2D-Data-Fusion.git --recursive
cd Multi-Modal-2D-Data-Fusion
pip install -e .
Quick Start
from multimodal_fusion import DataFusion
# Initialize fusion with list of elements
elements = ['Co', 'S', 'O']
fusion = DataFusion(elements)
# Load your chemical maps
# Provide as a dictionary where keys match your element list
# This helper function loads starter data from github
cobalt_map, sulfur_map, oxygen_map, haadf_im = fusion.load_edx_example()
chemical_maps = {
'Co': cobalt_map, # 2D numpy arrays
'S': sulfur_map,
'O': oxygen_map
}
fusion.load_chemical_maps(chemical_maps)
# Load the simultaneously acquired HAADF image
fusion.load_haadf(haadf_im) # 2D numpy array
# Run the fusion algorithm
# We can adjust with regularization parameters
fusion.run(
nIter=50,
lambdaEDS = 0.005, lambdaTV=0.1,
plot_images=True, plot_convergence=True)
# Get results in dictionary format
results = fusion.get_results()
fused_cobalt = results['Co']
fused_sulfur = results['S']
Documentation
A comprehensive tutorial for learning how to adjust the hyperparameters is available: J. Manassa, M. Shah, et. al. "Fused Multi-Modal Electron Microscopy - A Beginner's Guide, Elemental Microscopy (2024).
Citation
If you use any of the data and source codes in your publications and/or presentations, we request that you cite our papers:
A tutorial for learning how to adjust the hyper-parameters is also available here: J. Manassa, M. Shah, et. al. "Fused Multi-Modal Electron Microscopy - A Beginner's Guide, Elemental Microscopy (2024).
1 maintainer
Metadata
1 maintainer
Release files for multimodal-fusion 0.6.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| multimodal_fusion-0.6.0.tar.gz | 1.6 MB | Details |
Built distributions (wheels)
Total release size: 3.3 MB
Release files / multimodal_fusion-0.6.0.tar.gz
| Download URL | multimodal_fusion-0.6.0.tar.gz |
|---|---|
| Size | 1.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
75ab6bf170bc89cc805a5794343d13f206af0d7285fe9aa5c0a8a236055798f7
|
|
BLAKE2b-256 checksum How to use checksums |
72c07ff28f3260b78ab38874c84420dbc0eefc89f93d682cae93ab176e59066e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp312-cp312-win_amd64.whl
| Download URL | multimodal_fusion-0.6.0-cp312-cp312-win_amd64.whl |
|---|---|
| Size | 92.5 kB |
| Tags | CPython 3.12 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
054baca0687c6fc86484d6053f9264ec199925f7e8021fd0c91716ed5dd21134
|
|
BLAKE2b-256 checksum How to use checksums |
e76f3c16ee2d8e8f07f153194f3fcc6e3cf2e789312bfacc98bff6d9e7495b88
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | multimodal_fusion-0.6.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 147.5 kB |
| Tags | CPython 3.12 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
61ff1d8b06c455f7f23c3005f22724c0386c8d23c87eb3a66f136266c4f7ebfd
|
|
BLAKE2b-256 checksum How to use checksums |
fffa13396b10fc0fa6b0af170decf0d1e5f3012da44be05b94a6ad7e43435b60
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp312-cp312-macosx_11_0_arm64.whl
| Download URL | multimodal_fusion-0.6.0-cp312-cp312-macosx_11_0_arm64.whl |
|---|---|
| Size | 100.5 kB |
| Tags | CPython 3.12 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
d7294658ce6e034aff4b38ef10ef69ead0700a6b61a6385d593a1b2d1293ee6a
|
|
BLAKE2b-256 checksum How to use checksums |
100639dc8aba97f8446f6e97a283d51417423b41a729d4398fc573c2096c661e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp311-cp311-win_amd64.whl
| Download URL | multimodal_fusion-0.6.0-cp311-cp311-win_amd64.whl |
|---|---|
| Size | 91.2 kB |
| Tags | CPython 3.11 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
2f14e4eb109709c1d44bd0ebcaccc53b71d43a230004b11ac955b754b20b7c6a
|
|
BLAKE2b-256 checksum How to use checksums |
3f1cc168a74eda5289a177461da9a8702e83b6f72f69dd99446bfe07a5a9a1ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | multimodal_fusion-0.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 146.5 kB |
| Tags | CPython 3.11 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
995216588685c5acdf41c7846a49ba2a9eb80db222ab15b1cf84e01b604ed326
|
|
BLAKE2b-256 checksum How to use checksums |
b9233353f2d2eaa3476f3944125adec09979c1503de067057e6c2436f1526826
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp311-cp311-macosx_11_0_arm64.whl
| Download URL | multimodal_fusion-0.6.0-cp311-cp311-macosx_11_0_arm64.whl |
|---|---|
| Size | 99.6 kB |
| Tags | CPython 3.11 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
88b2aa4e00ae7acbd4ecab6d4ea76177abd2a0c178dd105be19febcb2fdbc452
|
|
BLAKE2b-256 checksum How to use checksums |
986b280a57f3b3f4a612bf079075810eea6e870a68b929205537338bfcbc8ba4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp310-cp310-win_amd64.whl
| Download URL | multimodal_fusion-0.6.0-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 90.6 kB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
bea82aaffe0719b6aec6c3e504d1689ff92545e480c7d0e278f233bf8abd4bc3
|
|
BLAKE2b-256 checksum How to use checksums |
b4a784632c90fd60ca88886e3730632b1325f3f45707c7ac9f8f3169fe67e647
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | multimodal_fusion-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 145.3 kB |
| Tags | CPython 3.10 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
f6af4f2d89c125516e7c99cf272e07d3ad56d12e8fc45fda2cd8a41db249e3e3
|
|
BLAKE2b-256 checksum How to use checksums |
fdfc5ae78a1d813f6db454b98cba32728010fb517f1d3d465e90f6b04684bd3e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp310-cp310-macosx_11_0_arm64.whl
| Download URL | multimodal_fusion-0.6.0-cp310-cp310-macosx_11_0_arm64.whl |
|---|---|
| Size | 97.9 kB |
| Tags | CPython 3.10 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
4a288bbaba6ea8d1de6fa7467210603a72222593e6e23a6391fcf6cdea915703
|
|
BLAKE2b-256 checksum How to use checksums |
7d70ba2c289b99f29fcfd0ddb35b7bf02169cac6b2f6f4964d156b9e234ab7f0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp39-cp39-win_amd64.whl
| Download URL | multimodal_fusion-0.6.0-cp39-cp39-win_amd64.whl |
|---|---|
| Size | 91.5 kB |
| Tags | CPython 3.9 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
432a96d74f862b08ee318dcbb885f3ef6ee8d621cb9628a8704bf9cc3bb23799
|
|
BLAKE2b-256 checksum How to use checksums |
9becfeb9165d4472a26572addb010fc7710dbcae9eac0de93a7ea04981862435
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | multimodal_fusion-0.6.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 145.7 kB |
| Tags | CPython 3.9 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
46e1b49314506ec3652361891d7d0ffa4923bdf503e44e5602e93874db6abf3d
|
|
BLAKE2b-256 checksum How to use checksums |
00663c71fa562fdc1674781ef426485f84a441f6c3e56f143d46ef7d64c28a02
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp39-cp39-macosx_11_0_arm64.whl
| Download URL | multimodal_fusion-0.6.0-cp39-cp39-macosx_11_0_arm64.whl |
|---|---|
| Size | 98.0 kB |
| Tags | CPython 3.9 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
c56fef7cda26bd5d559050707e471819c4b6f2d41373ac3ba61309e9ad182cd1
|
|
BLAKE2b-256 checksum How to use checksums |
983e99eaacc68c5681b5b5b6e35855089b7ca13d3a35f038c3e8539584b51fdd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp38-cp38-win_amd64.whl
| Download URL | multimodal_fusion-0.6.0-cp38-cp38-win_amd64.whl |
|---|---|
| Size | 90.2 kB |
| Tags | CPython 3.8 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
0d1f220a0f72a261e16fceca06eb899bf6f1f58001c5a462779be59e2451b908
|
|
BLAKE2b-256 checksum How to use checksums |
387ebf8248b7d7b8065df990ac5364b5df70ee69197111e80f48fd5768c43455
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | multimodal_fusion-0.6.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 144.9 kB |
| Tags | CPython 3.8 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
4fd271078c36d38bde48dfd6ffe3d1fe5376177f24beb8d9b5226291e6af899f
|
|
BLAKE2b-256 checksum How to use checksums |
aee8b2911e4bc577cc866bfb10301cf7455bc95677886f6104cb759e358d787c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency logRelease files / multimodal_fusion-0.6.0-cp38-cp38-macosx_11_0_arm64.whl
| Download URL | multimodal_fusion-0.6.0-cp38-cp38-macosx_11_0_arm64.whl |
|---|---|
| Size | 97.7 kB |
| Tags | CPython 3.8 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
2f6f7f24a1a483e193e2f28180155a06953714aeac947f0d29b501df00a01006
|
|
BLAKE2b-256 checksum How to use checksums |
5abd79912682ad918a6ef2d82fa8b62e44a1cf18efa77edc47c80f7d35971032
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 26, 2025.
Transparency log
