The-Data-for-Children-Collaborative/scipe

Code for Sustainable Census Independent Population Estimation (SCIPE) in Mozambique. # SCIPE Research code for _Sustainable Census Independent Population Estimation (SCIPE)_ - a pipeline for predicting population maps using microcensus data and satellite imagery. SCIPE is introduced in the paper ['Census-Independent Population Estimation using Representation Learning' [Scientific Reports (2022)]](nature.com). ## Scripts There are several scripts included with the project. They are intended to be run in the following order: 1. `/scripts/rasterize_survey.py` ` ` - rasterize survey data to geoTiff. This script is dependent on survey format, and is designed for SpaceSUR population survey from Mozambique. 2. `/scripts/estimate_footprints.py` ` ` - estimate probability maps using building footprint models defined in the config file. 3. `/scripts/run_pipeline.py` ` ` - run preprocessing, build dataset, predict population, and output results of experiments according to the config file. 4. `/scripts/split_imagery.py` ` ` ` ` ` ` - split large raster files contained within ` ` into grid defined by geoTiff at ` ` ## Config Each script takes a separate YAML config file as input, examples of each can be found in `/scripts/config/`. ## Models Pretrained population models are available from the authors upon request. ## Documentation Documentation is available at `/docs/_build/html/index.html` ## Examples Executing `run_pipeline.py` yields the following results for the example `pipeline.yaml` with outliers removed: