Feature: Support machine-learning based kinetic energy density functional for OFDFT #5777

sunliang98 · 2024-12-27T06:42:20Z

Reminder

Have you linked an issue with this pull request?
Have you added adequate unit tests and/or case tests for your pull request?
Have you noticed possible changes of behavior below or in the linked issue?
Have you explained the changes of codes in core modules of ESolver, HSolver, ElecState, Hamilt, Operator or Psi? (ignore if not applicable)

Linked Issue

Fix #...

Unit Tests and/or Case Tests for my changes

A unit test is added for each new feature or bug fix.

What's changed?

Support machine-learning based kinetic energy density functional for OFDFT, under source/module_hamilt_pw/hamilt_ofdft.
Provide the training manuscript of ML-based KEDF, under source/module_hamilt_pw/hamilt_ofdft/ml_tools.
Add a compile option ENABLE_MLKEDF for CMake and Makefile to turn on the ML-based KEDF.
Add two integrate tests: 902_OF_KE_MPN and 902_OF_KE_CPN5.
Update the document of input parameters.

This Pr is not complete yet.

Update compile and usage documents.
Provide default parameters for MPN and CPN5 KEDFs.
(Optional) Romove useless input parameters of ML-based KEDF.

Any changes of core modules? (ignore if not applicable)

Example: I have added a new virtual function in the esolver base class in order to ...

…ut variable 'pseudo_type'. Now the type of pseudopotential is assigned in STRU, not INPUT, and different type of pseudopotentials can be assigned for different elements in one calculation. Following are the supported format of STRU: Al 26.98 Al_ONCV_PBE-1.2.upf Al 26.98 Al_ONCV_PBE-1.2.upf auto Al 26.98 Al_ONCV_PBE-1.2.upf upf201 Al 26.98 Al_ONCV_PBE-1.2.upf upf201 # annotations... If no pseudo_type is assigned in STRU, the default value is 'auto', and ABACUS will recongnize the pp by itself.

into develop

… them into STRU. Add two integrate tests, `101_PW_upf201_blps_pseudopots` and `101_PW_upf201_upf100_pseudopots`, which contain two elements (Mg3Al), and different types of pseudopotentials are specified for different elements.

into develop

…into ML_KEDF_merge

…develop into ML_KEDF_merge

…into ML_KEDF_merge

source/module_hamilt_pw/hamilt_ofdft/ml_tools/potential.h

tests/PP_ORB/si.gga.psp

tests/integrate/902_OF_KE_CPN5/net.pt

…auliPotential). 2. Replace si.gga.psp used by 902_OF_KE_CPN5 with si.lda.lps.

…into ML_KEDF_merge-develop

source/module_hamilt_pw/hamilt_ofdft/ml_tools/pauli_potential.h

source/module_hamilt_pw/hamilt_ofdft/ml_tools/train.h

…into ML_KEDF_merge-develop

source/module_esolver/esolver_ks.cpp

…nergy contributed by local pseudopotential.

…s not considered. Delet the output of Ekinetic, since it only works for local pp.

…into ML_KEDF_merge-develop

source/module_esolver/esolver_ks.cpp

source/module_hamilt_pw/hamilt_ofdft/ml_tools/data.cpp

…into ML_KEDF_merge-develop

…/abacus-develop into ML_KEDF_merge-develop

…onal for OFDFT (deepmodeling#5777) * refactor: Remove the global variable 'global_pseudo_type' and the input variable 'pseudo_type'. Now the type of pseudopotential is assigned in STRU, not INPUT, and different type of pseudopotentials can be assigned for different elements in one calculation. Following are the supported format of STRU: Al 26.98 Al_ONCV_PBE-1.2.upf Al 26.98 Al_ONCV_PBE-1.2.upf auto Al 26.98 Al_ONCV_PBE-1.2.upf upf201 Al 26.98 Al_ONCV_PBE-1.2.upf upf201 # annotations... If no pseudo_type is assigned in STRU, the default value is 'auto', and ABACUS will recongnize the pp by itself. * test: Remove `pseudo_type` from INPUT of all integrate tests, and add them into STRU. Add two integrate tests, `101_PW_upf201_blps_pseudopots` and `101_PW_upf201_upf100_pseudopots`, which contain two elements (Mg3Al), and different types of pseudopotentials are specified for different elements. * <Feature> Add input parameters about ML_KE * <Feature> Add files about ML_KE into module_hamilt_pw/hamilt_ofdft * <Feature> Link MPN KEDF to ABACUS * <Test> Add a unittest of MPN KEDF: 902_OF_KE_MPN * <Feature> Output more detailed information of Energy in KSDFT * <Test> Update the integrate test 902_OF_KE_MPN * <Feature> In order to check the validity of MPN KEDF, calculate and output TF KEDF when running MPN KEDF. * Check the input rho in the localTest of MPN KEDF * <Feature> Add a new descriptor: r_min = min|r-R| / r0, r0 = (Omega / natom) ** (1/3). * <Fix> Fix the scaling formula of kernel. * Correct the defination of img. * Update parameters * Feature: Add a compile option ENABLE_MLKEDF to control the ML KEDF module. * Feature: Simplify the code. * Support Makefile * Refactor: Remove GlobalC::ucell. Optimize the format of input parameters of ML KEDF. * Refactor: 1. Update annotation. 2. Remove useless parameters and codes. * Doc: Update documents. * Test: Add two integrate tests: 902_OF_KE_MPN and 902_OF_KE_CPN5 * Doc: Update annotations. * Refactor: Update the CMakeLists.txt of nnof * Test: Configure compilation test. * [pre-commit.ci lite] apply automatic fixes * Replace pow with std::pow * 1. Rename potential.h (class Potential) as pauli_potential.h (class PauliPotential). 2. Replace si.gga.psp used by 902_OF_KE_CPN5 with si.lda.lps. * Feature: Provide default parameters for MPN and CPN5 KEDF. * Doc: Update the document of `of_kinetic`. * Update the file names of nnof * Make: Update Makefile, and compile documents. * Remove useless input parameters: `of_ml_nnode` and `of_ml_nlayer` * Update the integrate tests of MPN and CPN5 KEDFs * Add function `get_local_pp_energy` into ElecState to calculatet the energy contributed by local pseudopotential. * Correct the name of eion_elec to elocal_pp, since the nonlocal part is not considered. Delet the output of Ekinetic, since it only works for local pp. * Test: Fix module_elecstate/test/elecstate_energy_test.cpp * [pre-commit.ci lite] apply automatic fixes * Remove useless head file parallel_reduce.h from esolver_ks.cpp * Format ml_tools/data.cpp and ml_tools/grid.cpp * [pre-commit.ci lite] apply automatic fixes --------- Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>

sunliang98 and others added 30 commits September 15, 2022 17:30

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

bddc45b

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

8c827a1

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

e19d414

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

861ea9f

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

fcd542e

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

fc9bd11

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

3ed4231

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

e4b6222

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

27dac25

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

9459daa

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

c74fa52

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

1737eec

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

bb133e7

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

604bff5

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

135c504

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

2616267

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

cc3fc0b

into develop

Merge branch 'develop' of https://github.com/deepmodeling/abacus-develop

491270d

into develop

<Feature> Add input parameters about ML_KE

235055a

<Feature> Add files about ML_KE into module_hamilt_pw/hamilt_ofdft

aaaf87b

<Feature> Link MPN KEDF to ABACUS

f8b4975

<Test> Add a unittest of MPN KEDF: 902_OF_KE_MPN

4d7ad73

Merge branch 'develop' of https://github.com/sunliang98/abacus-develop …

4d97f05

…into ML_KEDF_merge

Merge branch 'deepmodeling:develop' into ML_KEDF_merge

0e6921c

<Feature> Output more detailed information of Energy in KSDFT

f5df6ad

Merge branch 'ML_KEDF_merge' of https://github.com/sunliang98/abacus-…

a3833d1

…develop into ML_KEDF_merge

<Test> Update the integrate test 902_OF_KE_MPN

ffa2dcf

Merge branch 'master' of https://github.com/sunliang98/abacus-develop …

dc28b4a

…into ML_KEDF_merge

mohanchen reviewed Dec 28, 2024

View reviewed changes

source/module_hamilt_pw/hamilt_ofdft/ml_tools/potential.h Outdated Show resolved Hide resolved

tests/PP_ORB/si.gga.psp Outdated Show resolved Hide resolved

tests/integrate/902_OF_KE_CPN5/net.pt Show resolved Hide resolved

mohanchen added Features Needed The features are indeed needed, and developers should have sophisticated knowledge Compile & CICD & Docs & Dependencies Issues related to compiling ABACUS labels Dec 28, 2024

sunliang98 added 5 commits December 30, 2024 15:01

1. Rename potential.h (class Potential) as pauli_potential.h (class P…

3b9876d

…auliPotential). 2. Replace si.gga.psp used by 902_OF_KE_CPN5 with si.lda.lps.

Merge branch 'develop' of https://github.com/sunliang98/abacus-develop …

48bf3f2

…into ML_KEDF_merge-develop

Feature: Provide default parameters for MPN and CPN5 KEDF.

fa46030

Doc: Update the document of of_kinetic.

679e66f

Merge branch 'develop' of https://github.com/sunliang98/abacus-develop …

54e1d8f

…into ML_KEDF_merge-develop

mohanchen reviewed Jan 2, 2025

View reviewed changes

source/module_hamilt_pw/hamilt_ofdft/ml_tools/pauli_potential.h Outdated Show resolved Hide resolved

source/module_hamilt_pw/hamilt_ofdft/ml_tools/train.h Outdated Show resolved Hide resolved

sunliang98 added 6 commits January 2, 2025 21:08

Update the file names of nnof

6190d29

Merge branch 'develop' of https://github.com/sunliang98/abacus-develop …

39f07bb

…into ML_KEDF_merge-develop

Make: Update Makefile, and compile documents.

6d97982

Merge branch 'develop' of https://github.com/sunliang98/abacus-develop …

a79c595

…into ML_KEDF_merge-develop

Remove useless input parameters: of_ml_nnode and of_ml_nlayer

6c98b37

Update the integrate tests of MPN and CPN5 KEDFs

c749f72

YuLiu98 reviewed Jan 5, 2025

View reviewed changes

source/module_esolver/esolver_ks.cpp Outdated Show resolved Hide resolved

sunliang98 and others added 5 commits January 5, 2025 22:03

Add function get_local_pp_energy into ElecState to calculatet the e…

6213fdf

…nergy contributed by local pseudopotential.

Correct the name of eion_elec to elocal_pp, since the nonlocal part i…

168e9b9

…s not considered. Delet the output of Ekinetic, since it only works for local pp.

Merge branch 'develop' of https://github.com/sunliang98/abacus-develop …

97c92ad

…into ML_KEDF_merge-develop

Test: Fix module_elecstate/test/elecstate_energy_test.cpp

99eae78

[pre-commit.ci lite] apply automatic fixes

09547e3

mohanchen reviewed Jan 6, 2025

View reviewed changes

source/module_esolver/esolver_ks.cpp Outdated Show resolved Hide resolved

source/module_hamilt_pw/hamilt_ofdft/ml_tools/data.cpp Show resolved Hide resolved

sunliang98 and others added 5 commits January 6, 2025 15:54

Remove useless head file parallel_reduce.h from esolver_ks.cpp

62e17e1

Merge branch 'develop' of https://github.com/sunliang98/abacus-develop …

01dc920

…into ML_KEDF_merge-develop

Merge branch 'ML_KEDF_merge-develop' of https://github.com/sunliang98…

3e25aaa

…/abacus-develop into ML_KEDF_merge-develop

Format ml_tools/data.cpp and ml_tools/grid.cpp

fbd9a6e

[pre-commit.ci lite] apply automatic fixes

c15aed2

mohanchen approved these changes Jan 6, 2025

View reviewed changes

mohanchen merged commit 4009f6a into deepmodeling:develop Jan 6, 2025
14 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Feature: Support machine-learning based kinetic energy density functional for OFDFT #5777

Feature: Support machine-learning based kinetic energy density functional for OFDFT #5777

Uh oh!

sunliang98 commented Dec 27, 2024 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Feature: Support machine-learning based kinetic energy density functional for OFDFT #5777

Feature: Support machine-learning based kinetic energy density functional for OFDFT #5777

Uh oh!

Conversation

sunliang98 commented Dec 27, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Reminder

Linked Issue

Unit Tests and/or Case Tests for my changes

What's changed?

Any changes of core modules? (ignore if not applicable)

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

sunliang98 commented Dec 27, 2024 •

edited

Loading