BRAILS++: Building Regional Asset Inventories for Large Scale Simulation
What is it?
BRAILS++ is an object-oriented framework for building applications that focus on generating asset inventories for large geographic regions.
BRAILS++ provides modular workflows for generating inventories by integrating diverse data sources, including public datasets, features extracted from imagery, and ruleset-based inference models.
In BRAILS++, an asset inventory consists of geographically referenced points, line-strings, or polygons, each annotated with key attributes. To build these inventories, the data scrapers in BRAILS++ interact with web servers to create an inventory blueprint suitable as a starting point for regional-scale analysis. Example datasets accessed through BRAILS++ include FEMA’s USA Structures (FEMA, 2022), Microsoft Footprints (Microsoft, 2022), Overture Maps (Overture Maps Foundation, 2023), OpenStreetMap (OpenStreetMap contributors, 2017), the U.S. Army Corps of Engineer’s NSI, TIGER/Line roadway data (U.S. Census Bureau, 2024), FHWA’s National Bridge and Tunnel Inventories (FHWA, 2023; FHWA, 2024), ASCE REST services for design loads (ASCE, 2025), and HIFLD infrastructure data (U.S. Department of Homeland Security, 2024).
Despite their value, these datasets often contain incomplete or inconsistent information, requiring further enhancement to address the corresponding uncertainties. BRAILS++ incorporates methods for handling missing data and enhancing the available datasets through modules that enable: 1) feature extraction from publicly available images, e.g. Google Street View; 2) inventory merging to integrate metadata from various sources and resolve inconsisties, such as differening metadata values or spatial issues e.g. misaligned footprints ; 3) statistical imputation to generate pluasable inventories with all features defined for all assets given some assets will have missing features and finally 4) data inference to add asset attributes for which no information exists in the inventory, e.g. building codes applicable at the time of construction can be used to infer typical connection details (Kijewski-Correa et al., 2022) such as roof-to-wall connections for wind vulnerability assessments.
How is the repo laid out?
brails: A directory containing the classesbrails/types: directory containing useful datatypes, e.g.,ImageSetandAssetInventorybrails/processors: directory containing classes that doimage_processingto make predictions, e.g. RoofShapebrails/scrapers: directory containing classes that do internet downloads, e.g., footprint and image scrapers.brails/filters: directory containing image filters, e.g., classes that take images and revise or filter out unnecessary portions of images.brails/aggregators: directory containing classes for doing merge, join and allocation operations, e.g., combining data from different datasets (inventories or other) to create a single inventory.brails/imputers: directory containing classes that fill in missingAssetInventorydatasets, i.e., filling in features that are missing in certain Assets of the AssetInventory.brails/inferers: directory containing classes that infer new asset features based on existing features in the Assets ofAssetInventory.brails/utils: directory containing misc classes that do useful things, e.g. geometric conversions
examples: A directory containing example scripts and Jupyter notebookstests: A directory containing unit tests. The directory structure follows that ofbrails
Quick Links
Installation
pip install brails
Note
To install the package from GitHub, run:pip install git+https://github.com/NHERI-SimCenter/BrailsPlusPlusIf it's already installed and you want to update:
pip install --upgrade git+https://github.com/NHERI-SimCenter/BrailsPlusPlus
Acknowledgments
This work is based on material supported by the National Science Foundation under grants CMMI 1612843 and CMMI 2131111.
Contributors
Want to see who made this possible? Check out the full list of contributors here.
Contact
NHERI-SimCenter nheri-simcenter@berkeley.edu
4 maintainers
Metadata
4 maintainers
Release files for brails 4.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| brails-4.3.1.tar.gz | 2.1 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| brails-4.3.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 4.5 MB
Release files / brails-4.3.1.tar.gz
| Download URL | brails-4.3.1.tar.gz |
|---|---|
| Size | 2.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5eddf3ca0dc03b2e0b2e5aef7fbe961e837987824dbbdb79ecaafc5f2b02013c
|
|
BLAKE2b-256 checksum How to use checksums |
cc9fa930f2adf2521744f8a75e87713577cd23cdab532a3a181ce6326fea1e91
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.7
|
Release files / brails-4.3.1-py3-none-any.whl
| Download URL | brails-4.3.1-py3-none-any.whl |
|---|---|
| Size | 2.4 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
061ba318ac9db506d9e2b77b712dc3f5c8f78cd95cda4e9a8f87d1e62d92cb20
|
|
BLAKE2b-256 checksum How to use checksums |
b576b774675aec3c869b6e745277ed7426fb8d4d10146e69d002d18a7f97d18e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.7
|
