add biodiversity preprocessing

data/h3_data_importer/data_checksums/biodiversity

@@ -0,0 +1 @@
+683cfc1d67d2fbd28673965b10f5bbeb33e4a7bb7fdef3d7807967e0faaef82b  natural_crop_flii_loss_by_human_lu_50km_10km.tif

data/preprocessing/biodiversity/Makefile

@@ -0,0 +1,30 @@
+# Variables
+data_dir=data
+resampling_resolution="0.083333"
+checksums_dir=../../../h3_data_importer/data_checksums
+AWS_S3_BUCKET_URL=s3://landgriffon-raw-data
+
+# Targets
+.PHONY: all download_forest_landscape_integrity_loss resample_forest_landscape_integrity_loss upload_results write_checksum
+
+all: download_forest_landscape_integrity_loss resample_forest_landscape_integrity_loss upload_results write_checksum
+
+download_forest_landscape_integrity_loss:
+	mkdir -p $(data_dir)
+	gsutil -m cp \
+		"gs://landgriffon-gee-bucket/landscape_indicators_20230821/natural_crop_flii_loss_by_human_lu_50km_1000m.tif" \
+		$(data_dir)
+
+resample_forest_landscape_integrity_loss:
+	rio warp \
+		$(data_dir)/natural_crop_flii_loss_by_human_lu_50km_1000m.tif \
+		$(data_dir)/natural_crop_flii_loss_by_human_lu_50km_10km.tif \
+		--resampling average \
+		--res $(resampling_resolution) \
+		--overwrite
+
+upload_results:
+	aws s3 cp $(data_dir)/natural_crop_flii_loss_by_human_lu_50km_10km.tif ${AWS_S3_BUCKET_URL}/processed/biodiversity/
+
+write_checksum:
+	cd $(data_dir) && sha256sum natural_crop_flii_loss_by_human_lu_50km_10km.tif > $(checksums_dir)/biodiversity

data/preprocessing/biodiversity/README.md

@@ -0,0 +1,52 @@
+# Biodiversity Indicators
+## Forest Landscape Integrity Loss Processing
+
+This folder contains a set of Makefile targets to download, process and upload the Biodiversity - Forest Landscape Integrity Loss data. The data is downloaded from Google Cloud Storage (GCS), resampled and then uploaded to an Amazon Web Serice (AWS) S3 bucket.
+
+
+## Prerequisites
+
+Before running the pipeline, ensure you have the following prerequisites in place:
+
+1. **Google Cloud SDK (gsutil)**: You'll need gsutil to download data from Google Cloud Storage. Make sure it's installed and authenticated.
+
+2. **Rasterio (rio)**: You'll need rio (Rasterio) for resampling the raster data. Install it using pip if it's not already installed: `pip install rasterio`.
+
+3. **Amazon Web Services (AWS) CLI**: You must have the AWS CLI installed and configured with the necessary permissions to upload data to your AWS S3 bucket.
+
+## Usage
+
+### 1. Download data
+
+This target downloads the forest landscape integrity loss data from GCS and stores it in a specified data directory.
+
+```
+make download_forest_landscape_integrity_loss
+
+```
+
+### 2. Resample dorest landscape integrity loss
+
+This target resamples the downloaded data to a different resolution using Rasterio. It takes the input file from the data directory, performs resampling, and overwrites the file in the data directory with the resampled version
+
+```
+make resample_forest_landscape_integrity_loss
+```
+
+### 3. Upload results
+
+This target uploads the processed forest landscape integrity loss data to an AWS S3 bucket. Make sure to set the `AWS_S3_BUCKET_URL` environment variable to the destination S3 bucket URL.
+
+```
+make upload_results
+```
+
+### 4. Write checksums
+
+This target generates a SHA256 checksum for the processed data and writes it to a file in the specified checksums directory.
+
+```
+make write_checksum
+```
+
+`Note`: Make sure you have the necessary permissions and access to the data sources and AWS resources mentioned in this README before running the pipeline.