Precise distance-based two-dimensional automated mesh generation toolbox intended for coastal ocean/shallow water flow models
Note
This is the default and recommended PROJECTION
branch. Please use it unless you otherwise require legacy (MASTER
branch) or the absolute newest features (DEV
branch).
Warning
The boundary of the meshing domain must be a polygon (first point equals the last and non-self intersecting) but it does not need to be simplified. Read the user guide for more information about the inputs.
OceanMesh2D is a set of user-friendly MATLAB functions to generate two-dimensional (2D) unstructured meshes for coastal ocean circulation problems. These meshes are based on a variety of feature driven geometric and bathymetric mesh size functions, which are generated according to user-defined parameters. Mesh generation is achieved through a force-balance algorithm combined with a number of topological improvement strategies aimed at improving the worst case triangle quality. The software embeds the mesh generation process into an object-orientated framework that contains pre- and post-processing workflows, which makes mesh generation flexible, reproducible, and script-able.
Tip
PLEASE READ THE USER GUIDE! A recent pdf of the user guide is located in this branch. For a continually updated version click here (wait for compilation and then click download PDF)
Besides posting issues with the code on Github, you can also ask questions via our Slack channel here.
Note: If the slack link invite isn't working, please send either one of us and an email and we'll fix it. By default, the invite link expires every 30 days.
Otherwise please reach out to either Dr. William Pringle (wpringle@anl.gov) or Dr. Keith Roberts (keithrbt0@gmail.com) with questions or concerns or feel free to start an Issue in the issues tab above.
All contributions are welcome!
To contribute to the software:
- Fork the repository.
- Clone the forked repository, add your contributions and push the changes to your fork.
- Create a Pull request
Before creating the pull request, make sure that the examples pass...
Some things that will increase the chance that your pull request is accepted:
- Write minimal working examples that demonstrate the functionality.
- Write good commit and pull request messages.
OceanMesh2D
consists of four standalone classes that are called in sequence. It requires no paid toolboxes to build meshes and has been tested to work with a trial version of MATLAB.
OceanMesh2D::
├── geodata -- process geospatial data.
├── edgefx -- build mesh size functions.
├── meshgen -- generate mesh based on mesh size functions and boundaries.
└── msh -- store, write, read, inspect, and visualize meshes and their
axuillary components for numerical simulation.
-
Clone or download and unzip the current repository.
-
Run the
setup.sh
bash script orsetup.bat
batch script to download the requiredm_map
package and the base datasets:- GSHHG global shoreline
- SRTM15_PLUS global topobathy DEM
-
Create or modify
startup.m
file located under your home folder by executing command in MATLAB:edit(fullfile(userpath,'startup.m'))
And add the line:
run(<PATH_TO_OCEANMESH2D>/setup_oceanmesh2d.m)
Replace
<PATH_TO_OCEANMESH2D>
with the folder name where you cloned/unzipped the repository. -
Restart MATLAB to get paths added.
Additional data required for some of the following examples must be downloaded manually from here. Specifically, Examples 2, 3, 4, 5 and 5b require additional datasets from the google drive folder while base datasets are sufficient for the other examples.
Featured in ┌── Examples/Example_1_NZ.m -- A simple mesh around South Island
| New Zealand that uses GSHHS shoreline.
user guide ├── Examples/Example_2_NY.m -- A high-resolution mesh around
| the New York/Manhattan area that uses a DEM
| created from LiDAR data.
└── Examples/Example_3_ECGC.m -- Builds a mesh for the western North Atlantic
with a local high-resolution nest around New York
Featured in ┌── Examples/Example_4_PRVI.m -- Builds a mesh for the western North Atlantic
| with three high-resolution nests around
Geoscientific Model | Puerto Rico and US Virgin Islands
├── Examples/Example_5_JBAY.m -- An extremely high-fidelity (15-m) mesh from
Development paper[1]| LiDAR data around Jamaica Bay with CFL-limiting.
└── Examples/Example_6_GBAY.m -- An example of the polyline/thalweg mesh size
function along the Houston Ship Channel.
See Testing to test OceanMesh2D on your system.
To ensure the software is fully functional on your system before building some crazy meshes it is strongly recommended to run the tests (RunTests.m
) in the Tests/ directory.
We test all pull requests using this test suite on a local host before accepting. For substantial pull requests we will also test the Examples from the Examples/ directory.
If you make use of OceanMesh2D
please include a reference to [1], and to any of [2]-[5] if pertinent (latex .bib file). We would also appreciate using our logo in a presentation featuring OceanMesh2D
.
[1] - Roberts, K. J., Pringle, W. J., and Westerink, J. J., 2019.
OceanMesh2D 1.0: MATLAB-based software for two-dimensional unstructured mesh generation in coastal ocean modeling,
Geosci. Model Dev. (GMD), https://doi.org/10.5194/gmd-12-1847-2019.
[2] - Roberts, K. J., Pringle, W. J, 2018.
OceanMesh2D: User guide - Precise distance-based two-dimensional automated mesh generation toolbox intended for coastal
ocean/shallow water. https://doi.org/10.13140/RG.2.2.21840.61446/2.
[3] - Roberts, Keith J. Unstructured Mesh Generation and Dynamic Load Balancing for Coastal Ocean Hydrodynamic Simulation, 2019.
PhD Thesis, University of Notre Dame. https://curate.nd.edu/show/4q77fr0022c.
[4] - Roberts, Keith J., Pringle W.J., Westerink J. J. Contreras, M.T., Wirasaet, D., 2019.
On the automatic and a priori design of unstructured mesh resolution for coastal ocean circulation models,
Ocean Modelling, 144, 101509. https://doi.org/10.1016/j.ocemod.2019.101509.
[5] - Pringle, W. J., Wirasaet, D., Roberts, K. J., and Westerink, J. J., 2021.
Global Storm Tide Modeling with ADCIRC v55: Unstructured Mesh Design and Performance,
Geoscientific Model Development, 14(2), 1125-1145. https://doi.org/10.5194/gmd-14-1125-2021.
In addition, best practice when using software in a scientific publication is to cite the permanent doi corresponding to the version used (e.g., for reproducibility). All our releases are archived at the following Zenodo
repository doi link.
Authors (202X). CHLNDDEV/OceanMesh2D: OceanMesh2D VX.X. Zenodo. https://doi.org/10.5281/zenodo.1341384
Please fill in the version (VX.X), author list and year corresponding to the version used.
We would also like to acknowledge various scripts and algorithms from mesh2d
included in OceanMesh2D that have been developed by @dengwirda. Please also see JIGSAW-GEO
:
[i] - Engwirda, D., 2017.
JIGSAW-GEO (1.0): Locally orthogonal staggered unstructured grid generation for general circulation modelling on the sphere.
Geoscientific Model Development, 10(6), 2117–2140. https://doi.org/10.5194/gmd-10-2117-2017.
- These images can be made by running the examples
                       Â
- The following images are provided from happy users. Please send us your meshes.
Jiangchao Qiu from his publication.
The format is based on Keep a Changelog
- User inputted edge constraints are now saved when no weirs are being constrained during mesh generation.
- Added a check in
Read_shapefile.m
to handle, warn, and correct cases where there are empty objects in a shapefile. #315
- Added ability to generate constrainsts for shorelines automatically using the new high-fidelity method. #264
- auxiliary file reader function that can be used standalone e.g., m = m.read({'fort.13','fort.15'})), as well as called from within msh() function. #287
- swanoutput namelist for SWAN model outputs. #287
- Added new function in
msh
calledremesh_patch
to remesh within specified polygonal domains and insert back into parent mesh. #301 - Read and write to 2dm format. #300
namelist
andRSTIMNC
input arguments forMake_f15.m
fort.15 generator. updated the help message for all input argumebts toMake_f15
. #283- New stability namelist options to
Make_f15.m
fort.15 generator. #283 - Optionality for mesh2dgen to choose the method of mesh generation
kind
, and the maximum iteration countiter
. #272 - Option
improve_with_reduced_quality
tomeshgen
for allowing for mesh improvements even when quality is decreasing or large number of nodes eliminated, which sometimes is necessary to force the advancement in mesh quality. - Option
delaunay_elim_on_exit
tomeshgen
to skip the last call todelaunay_elim
to potentially avoid deleting boundary elements. - Geoid offset nodal attribute in
Calc_f13
subroutine. #251 - Support for writing Self Attraction and Loading (SAL) files in NetCDF for the ADCIRC model. #231
- Added 'high-fidelity' option for automatically forming and constraining edges into the mesh. #264
- treating logicals in namelists as a logicals type within MATLAB but ouput as a string. #287
Calc_Sponge.m
to allow for sponge in polygon region and coefficents based on spatially varying depth. #287- removed namelists from default setup in
Make_f15.m
fort.15 generator to be invoked by user as an input argument instead. #283 - Use implicit smoother (
ds=1
) inmsh.clean
when fix points are present. #283 - Default filename for the dynamicWaterLevelCorrection is now
null
so that it is not evoked by default. #272 - Default mesh improvement strategy is
ds
2. - Retrieve boundary indices in
msh.get_boundary_of_mesh
method. #259 msh.offset63
struct and associated write/make routines for dynamicwaterlevel offset functionality. #259- dynamicWaterLevelCorrection to fort.15 namelist, and PRBCKGRND option to met fort.15 namelist. #261
- Improved code readability by auto-indenting core functions and reworking 'setup' and 'Examples' functions, including adding necessary files for separation from core functions. #308
- Renamed functions for clarity and fixed multiple small bugs; changes are compatible with OpenEarthTools but distinct. #308
- catch for offset_nodes of int type in writeoffset63.m. #287
- writing out the wave coupling timestep
RSTIMNC
on theWTIMNC
line of fort.15 whenNWS > 300
. #283 make_bc
call with empty varargin, e.g., when calling inner. #283Make_offset63
call with constant offset (length 1time_vector
). #283ourKNNsearch
call innanfill
option ofGriddata
(msh.interp
). #283m_map
link insetup.sh
Issue #277. #283- Updated
Calc_f13.m
to avoid an "Unrecognized variable" error by ensuring "broken" is always defined. #282 - Fixed test for likely geographic coordinates in
Make_f15.m
. #282 - updated
Gridded_to_Mesh_SeaBed_DepthAveraged.m
to fix the infinite loop in usingCal_IT_Fric.m
by filling in the NaNs at greater depths with values from above. #280 - Recursive cleaning issues: infinite loop and preservation of fixed points.
msh.interp
method forK
argument of length 1, and for the test to determine whether the bathymetry grid is irregular. #259- Printing of namelist character strings or numbers. #261
Make_offset63.m
time interval computation. #261 and #272- Removed dependency on statistics toolbox when using the 'nanfill' option in
msh.interp
. #269 - Missing routines for reading in elvstaname and velstaname in readfort15.m by adding readlinevecname() method. #281
- Incorrect reference to
ibtype
was changed toibtypee
inmap_mesh_properties
function. #298
meshgen.build()
now will rewind the iteration set in the case mesh improvement cannot improve the qualities. #234msh.plot()
now has acmap
in which the user can specify their anycmocean
colormapradius_separated_points
function that trims the points in the mesh to have a specified resolution that can be used beforem_quiver
so that vectors are evenly plotted. #225- Deleting boundary conditions by specifyng their indices in
msh.object.bd
field. See #205 - Ability for user to set their own axis limits when plotting with
msh.plot()
. #224
- Minor fix to
msh.make_bc
using theauto
method. #237 - correction in setting stereographic projection bounds in
setProj
to make sure points are not pushed outside and become NaNs (was limited to radius of 178 deg but made sure can go up to full 180 deg). #225 - Correctly deleting weirs from boundary object through
make_bc
delete method. See #205 - Array format fix for reading in ibtype and nvell from fort.14 file and when executing carry_over_weirs. See #206
- Fix for irregular grid spacings in DEMs. See #204
- tidal constituents for
Make_f15
can now contain "major8" in addition to other constituents in the string/cell array #221 - Correctly collect NDBC and NOS stations in mesh when creating
fort15
file usingMake_f15
for meteorological, velocity and elevation records #242
msh.plot()
using typebd
option now creates a legend for the different boundary condition types. #247- forcing facecolor to white in
m_trimesh
so that it does not intefere with background color option. #245 - made topographic elevation bound option for max_ele, wl, slp, and g
edgefx
kwargs consistent and added explanation of this option is included inedgefx
help. #230 m_plot()
function callsm_grid()
with background color input kwarg (ifbackcolor
option used) instead of manual application. #225tidal_data_to_ob
function called fromMake_f15
populates boundary condition tidal constituents that do not exist in the tidal database with zero values so that user can add user-defined values later (previously did not populate). #225- Improved
cmocean
for pivot handling with discrete colormap. #225 - Renamed
Calc_NLCD_Mannings
toCalc_Mannings_Landcover
and making option for 'ccap' landcover type in addition to 'nlcd' (default) and added the ability to using user specified inteprolation (e.g., nearest, linear, cell-averaging, etc.) of the landcover data to the mesh vertices. #221
mesh2d
interface improvements to filter small polygons.- Support for creation of
fort.20
files for forcing rivers by @Jiangchao3 - Mesh "cleaning" modes moderate and aggressive transfer nodal attributes via improvements to
msh.map_mesh_properties
msh.remove_attribute()
method to remove f13 attribute(s)- new
msh.interp()
slope_calc
kwarg option to set the method of computing the topographic gradients (slopes), eitherrms
[default] orabs
- new
extract_subdomain()
keep_numbering
kwarg option to keep the full mesh triangulation numbering on the subdomain [off by default].
msh.plot()
overhaul. All options specified via kwarg.msh.plot()
optionsubset
option is now calledsubdomain
msh.plot()
arbitary f13 option now utilizescolormap
kwargutilities/extract_subdomain
now is called with kwargs.- Cleaning up
msh.bound_courant_number()
to usemsh.get_boundary_of_mesh()
for Delaunay-triangulation and allowingmsh.clean()
to do the transfer of attributes automatically. msh.plus(obj1,obj2)
can now carry over obj2 f13 attributes if also exist in obj1msh()
more efficient storing of boundary conditions read in from fort.xx files, andmsh.write()
can write out arbitrary vertex indices (instead of just 1 to NP).
- Boundary labeling fix
- Prompt when labeling bcs using
outer
kwarg inmake_bc
- fix for boundary condition mapping in
msh.map_mesh_properties()
especially for weirs/barriers - fix for barrier mapping in
msh.plus()
routine - fix for
msh.make_bc(m,auto,gdat)
where gdat is empty. In this case it uses the depths on the mesh to determine the open boundaries. - check for
poly2ccw
mapping toolbox function inkml2struct
- fix for
msh.plot()
on log colormap when plotting f13 attributes
- Deprecating
msh.CheckTimestep()
formsh.bound_courant_number
. Added error message and instruction in the CheckTimestep help
- Users without mapping toolbox could not read in shapefiles because of a bug that made them required to have a 3d shapefiles.
- plotting
gdat
with no shoreline. - plotting a mesh's bathymetry with a non-zero datum using cmocean.
- cell-averaging interpolation method in msh.interp fixed for unequal lon-lat DEM grid spacings
- Mesh patch smoother
- Ability to remesh abritary patches of elements within the domain while respecting user-defined mesh sizes and the patches boundaries.
- Ability to use the TPXO9 Atlas for the tidal bcs and sponge (inside tidal_data_to_ob.m and Calc_Sponge.m) by using '**' wildcards in place of the constituent name within the tidal atlas filename (the atlas has an individual file for each constituent).
- Introducing 'auto_outer' option for the make_bc msh method which populates the bc for the outermost mesh boundary polygon (ignores islands)
- Changelog to README
- "mapMeshProperties" msh method ports over mesh properties for a mesh subset
- 'invert' option in the msh.interp method to turn off the DEM value inversion typically performed
- for the make_bc msh method 'auto'/'auto_outer' options, allowing for the 'depth' method of classification to use the interpolated depths on the mesh if gdat is empty.
- improving help for make_bc msh method, Make_f15.m and Calc_Sponge.m
- renamed "ExtractSubDomain.m" to "extract_subdomain.m"
- improving "extract_subdomain.m" help and facilitating NaN-delimited polygons
- ability to return boundary as a cell in "get_boundary_of_mesh" msh method
- "Example_1_NZ.m" includes example of plotting bcs of a msh subset
- using "mapMeshproperties" method in "fixmeshandcarry"
- using "fixmeshandcarry" in the "cat" msh method
- improving warning and error messages for the "interp" msh method
- adding geofactor into "writefort15" for the GAHM vortex model