diff --git a/.gitignore b/.gitignore
index 484f99f..29de853 100644
--- a/.gitignore
+++ b/.gitignore
@@ -10,6 +10,9 @@ logs/
 ## slurm ----
 **/slurm*
 
+## data files ----
+data/
+
 ## Python ----
 
 # Byte-compiled / optimized / DLL files
diff --git a/Dockerfile b/Dockerfile
index c871f80..d69b3fd 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -13,8 +13,8 @@ RUN mamba env update -n base -f requirements.yaml
 #&& mamba clean -a
 
 # Create paths to data placeholders
-RUN python utils/create_dir_paths.py datapaths.input.satellite_pm25.annual=null datapaths.input.satellite_pm25.monthly=null
+RUN python utils/create_dir_paths.py datapaths.input.satellite_pm25.yearly=null datapaths.input.satellite_pm25.monthly=null
 
-# snakemake --configfile conf/config.yaml --cores 4 -C temporal_freq=annual
+# snakemake --configfile conf/config.yaml --cores 4 -C temporal_freq=yearly
 ENTRYPOINT ["snakemake", "--configfile", "conf/config.yaml"]
-CMD ["--cores", "4", "-C", "polygon_name=county", "temporal_freq=annual"]
+CMD ["--cores", "4", "-C", "polygon_name=county", "temporal_freq=yearly"]
diff --git a/README.md b/README.md
index cb3a85f..27a05aa 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-# pm25_washu_raster2polygon
+# pm25_randall_raster2polygon
 
 Code to produce spatial aggregations of pm25 estimates as generated by the [Atmospheric Composition Analysis Group](https://sites.wustl.edu/acag/datasets/surface-pm2-5/). The spatial aggregation are performed for satellite pm25 from grid/raster (NetCDF) to polygons (shp).
 
@@ -10,7 +10,7 @@ The [Atmospheric Composition Analysis Group](https://sites.wustl.edu/acag/datase
 
 The version [V5.GL.04](https://sites.wustl.edu/acag/datasets/surface-pm2-5/#V5.GL.04) consists of mean PM2.5 (ug/m3) available at:
 
-*  Temporal frequency: Annual and monthly  
+*  Temporal frequency: yearly and monthly  
 *  Grid resolutions: (0.1° × 0.1°) and (0.01° × 0.01°)  
 *  Geographic regions: North America, Europe, Asia, and Global
 
@@ -29,26 +29,89 @@ Aaron van Donkelaar, Melanie S. Hammer, Liam Bindle, Michael Brauer, Jeffery R.
 
 # Codebook
 
-## Dataset Columns:
+## Dataset Output Structure
 
-* county aggregations:
+The pipeline produces parquet files with PM2.5 aggregations at the polygon level.
 
-* zcta aggregations:
+### Yearly aggregations (`temporal_freq=yearly`):
+
+Output path: `data/V5GL/output/{polygon_name}_yearly/pm25__randall__{polygon_name}_yearly__{year}.parquet`
+
+Columns:
+* `{polygon_id}` (index): County FIPS code, ZCTA code, or Census Tract GEOID depending on polygon type
+* `pm25` (float64): Mean PM2.5 concentration (µg/m³) for the year
+* `year` (int64): Year of observation
+
+### Monthly aggregations (`temporal_freq=monthly`):
+
+Output path: `data/V5GL/output/{polygon_name}_monthly/pm25__randall__{polygon_name}_monthly__{year}.parquet`
+
+Columns:
+* `{polygon_id}` (index): County FIPS code, ZCTA code, or Census Tract GEOID depending on polygon type
+* `pm25` (float64): Mean PM2.5 concentration (µg/m³) for the month
+* `year` (int64): Year of observation
+* `month` (object/int): Month of observation
+
+### Polygon ID Variables
+
+The index column name varies by polygon type and is defined in `conf/shapefiles/shapefiles.yaml`:
+* **County**: `county` (5-digit FIPS code, e.g., "01001" for Autauga County, Alabama)
+* **ZCTA**: `zcta` (5-digit ZIP Code Tabulation Area, e.g., "00601")
+* **Census Tract**: `GEOID` (11-digit census tract identifier)
+
+### Intermediate Files (Monthly only)
+
+During monthly processing, intermediate files are created:
+* Path: `data/V5GL/intermediate/{polygon_name}_monthly/pm25__randall__{polygon_name}_monthly__{year}_{month}.parquet`
+* These are concatenated into yearly files in the output directory
 
 ---
 
 # Configuration files
 
-The configuration structure withing the `/conf` folder allow you to modify the input parameters for the following steps:
+The configuration structure within the `/conf` folder allows you to modify the input parameters for the following steps:
 
-* create directory paths: `utils/create_dir_paths.py`
+* create directory paths: `src/create_datapaths.py`
 * download pm25: `src/download_pm25.py`
 * download shapefiles: `src/download_shapefile.py`
 * aggregate pm25: `src/aggregate_pm25.py`
+* concatenate monthly files: `src/concat_monthly.py`
 
 The key parameters are:
-* `temporal_freq` which determines whether the original annual or monthly pm25 files will be aggregated. The options are: `annual` and `monthly`.
-* `polygon_name` which determines into which polygons the pm25 grid will the aggregated. The options are: `zcta` and `county`.
+* `temporal_freq` which determines whether the original yearly or monthly pm25 files will be aggregated. The options are: `yearly` and `monthly`.
+* `polygon_name` which determines into which polygons the pm25 grid will be aggregated. The options are: `zcta`, `county`, and `census_tract`.
+
+## Configuration Structure
+
+The configuration system uses Hydra with the following structure:
+
+* `/conf/config.yaml` - Main configuration file with default settings
+* `/conf/datapaths/` - Data path configurations for different environments:
+  * `cannon_v5gl.yaml` - Paths for V5GL data on Cannon cluster
+  * `cannon_v6gl.yaml` - Paths for V6GL data on Cannon cluster
+  * `datapaths.yaml` - Template configuration
+* `/conf/shapefiles/shapefiles.yaml` - Shapefile metadata including:
+  * Available years for each polygon type
+  * ID column names (`idvar`)
+  * File naming prefixes
+  * Download URLs (optional, via `url_map`)
+* `/conf/satellite_pm25/` - PM2.5 dataset configurations for different versions
+* `/conf/snakemake.yaml` - Default parameters for Snakemake workflow
+
+## Shapefile Configuration
+
+Shapefiles can be obtained in two ways:
+
+1. **Symlinks to existing Lab shapefiles** (recommended for Cannon cluster):
+   ```bash
+   python src/create_datapaths.py
+   ```
+   This creates symbolic links from the project's `data/` directory to the Lab's existing shapefile repository at `/n/dominici_lab/lab/lego/geoboundaries/`.
+
+2. **Direct download** from Census Bureau (optional):
+   Shapefiles can be downloaded automatically if URLs are configured in `conf/shapefiles/shapefiles.yaml`. The download script will use the `url_map` for the specified year.
+
+The pipeline uses backward compatibility for shapefiles - if PM2.5 data is from a year without an exact shapefile match, it automatically selects the most recent prior shapefile year available.
 
 ---
 
@@ -75,17 +138,37 @@ mamba activate <env_name>
 
 ## Input and output paths
 
-Run
+The pipeline requires setting up directory paths and symbolic links to data sources. Run:
+
+```bash
+python src/create_datapaths.py
+```
+
+This script:
+* Creates the base directory structure under `data/V5GL/` (or `data/V6GL/` depending on configuration)
+* Creates symbolic links to:
+  * PM2.5 raw data at `/n/dominici_lab/lab/lego/environmental/pm25__randall/`
+  * Shapefiles at `/n/dominici_lab/lab/lego/geoboundaries/us_geoboundaries__census/us_shapefile__census/`
+  * Output directories for aggregated results
+
+To use a different configuration, specify the datapaths config file:
 
 ```bash
-python utils/create_dir_paths.py 
+python src/create_datapaths.py datapaths=cannon_v6gl
 ```
 
 ## Pipeline
 
-You can run the pipeline steps manually or run the snakemake pipeline described in the Snakefile.
+The pipeline consists of four main steps:
+
+1. **Download/link shapefiles**: Obtain or link to US Census shapefiles (counties, ZCTAs, or census tracts)
+2. **Download PM2.5 data**: Download satellite PM2.5 NetCDF files from Washington University
+3. **Aggregate PM2.5**: Perform spatial aggregation from raster grid to polygons
+4. **Concatenate monthly files** (monthly frequency only): Combine monthly parquet files into yearly files
+
+You can run the pipeline steps manually or use the Snakemake workflow.
 
-**run pipeline steps manually**
+### Run pipeline steps manually
 
 ```bash
 python src/download_shapefile.py
@@ -98,7 +181,7 @@ python src/aggregate_pm25.py
 or run the pipeline:
 
 ```bash
-snakemake --cores 4 -C polygon_name=county temporal_freq=annual 
+snakemake --cores 4 -C polygon_name=county temporal_freq=yearly 
 ```
 
 Modify `cores`, `polygon_name` and `temporal_freq` as you find convenient.
@@ -115,7 +198,7 @@ mkdir <path>/satellite_pm25_raster2polygon
 
 ```bash
 docker pull nsaph/satellite_pm25_raster2polygon
-docker run -v <path>:/app/data/input/satellite_pm25/annual <path>/satellite_pm25_raster2polygon/:/app/data/output/satellite_pm25_raster2polygon nsaph/satellite_pm25_raster2polygon
+docker run -v <path>:/app/data/input/satellite_pm25/yearly <path>/satellite_pm25_raster2polygon/:/app/data/output/satellite_pm25_raster2polygon nsaph/satellite_pm25_raster2polygon
 ```  
 
 If you are interested in storing the input raw and intermediate data run
diff --git a/Snakefile b/Snakefile
index df4aa44..f5ac6d6 100644
--- a/Snakefile
+++ b/Snakefile
@@ -17,37 +17,32 @@ temporal_freq = config['temporal_freq']
 polygon_name = config['polygon_name']
 
 with initialize(version_base=None, config_path="conf"):
-    hydra_cfg = compose(config_name="config", overrides=[f"temporal_freq={temporal_freq}", f"polygon_name={polygon_name}"])
+    cfg = compose(config_name="config", overrides=[f"temporal_freq={temporal_freq}", f"polygon_name={polygon_name}"])
 
-satellite_pm25_cfg = hydra_cfg.satellite_pm25
-shapefiles_cfg = hydra_cfg.shapefiles
+satellite_pm25_cfg = cfg.satellite_pm25
+shapefiles_cfg = cfg.shapefiles
 
-shapefile_years_list = list(shapefiles_cfg[polygon_name].keys())
+shapefile_years_list = shapefiles_cfg[polygon_name].years
 
 months_list = "01" if temporal_freq == 'yearly' else [str(i).zfill(2) for i in range(1, 12 + 1)]
-years_list = list(range(1998, 2022 + 1))
+years_list = list(range(1998, 2023 + 1))
 
 # == Define rules ==
 rule all:
     input:
         expand(
-            f"data/output/pm25__washu/{polygon_name}_{temporal_freq}/pm25__washu__{polygon_name}_{temporal_freq}__" +  
-                ("{year}.parquet" if temporal_freq == 'yearly' else "{year}_{month}.parquet"), 
-            year=years_list,
-            month=months_list
+            f"{cfg.datapaths.base_path}/output/{polygon_name}_{temporal_freq}/pm25__randall__{polygon_name}_{temporal_freq}__" +  
+                "{year}.parquet", 
+            year=years_list
+        ) if temporal_freq == 'yearly' else expand(
+            f"{cfg.datapaths.base_path}/output/{polygon_name}_monthly/pm25__randall__{polygon_name}_monthly__" + "{year}.parquet",
+            year=years_list
         )
 
-# remove and use symlink to the us census geoboundaries 
-rule download_shapefiles:
-    output:
-        f"data/input/shapefiles/shapefile_{polygon_name}_" + "{shapefile_year}/shapefile.shp" 
-    shell:
-        f"python src/download_shapefile.py polygon_name={polygon_name} " + "shapefile_year={wildcards.shapefile_year}"
-
 rule download_satellite_pm25:
     output:
         expand(
-            f"data/input/pm25__washu__raw/{temporal_freq}/{satellite_pm25_cfg[temporal_freq]['file_prefix']}." + 
+            f"{cfg.datapaths.base_path}/input/raw/{temporal_freq}/{satellite_pm25_cfg[temporal_freq]['file_prefix']}." + 
             ("{year}01-{year}12.nc" if temporal_freq == 'yearly' else "{year}{month}-{year}{month}.nc"), 
             year=years_list,
             month=months_list)
@@ -58,23 +53,24 @@ rule download_satellite_pm25:
 
 def get_shapefile_input(wildcards):
     shapefile_year = available_shapefile_year(int(wildcards.year), shapefile_years_list)
-    return f"data/input/shapefiles/shapefile_{polygon_name}_{shapefile_year}/shapefile.shp"
+    shapefile_prefix = shapefiles_cfg[polygon_name].prefix
+    shapefile_name = f"{shapefile_prefix}{shapefile_year}"
+    return f"{cfg.datapaths.base_path}/input/shapefiles/{polygon_name}_yearly/{shapefile_name}/{shapefile_name}.shp"
 
 rule aggregate_pm25:
     input:
         get_shapefile_input,
         expand(
-            f"data/input/pm25__washu__raw/{temporal_freq}/{satellite_pm25_cfg[temporal_freq]['file_prefix']}." + 
+            f"{cfg.datapaths.base_path}/input/raw/{temporal_freq}/{satellite_pm25_cfg[temporal_freq]['file_prefix']}." + 
             ("{{year}}01-{{year}}12.nc" if temporal_freq == 'yearly' else "{{year}}{month}-{{year}}{month}.nc"), 
             month=months_list
         )
 
     output:
-        expand(
-            f"data/output/pm25__washu/{polygon_name}_{temporal_freq}/pm25__washu__{polygon_name}_{temporal_freq}__" + 
-            ("{{year}}.parquet" if temporal_freq == 'yearly' else "{{year}}_{month}.parquet"), 
-            month=months_list  # we only want to expand months_list and keep year as wildcard
-        )
+        [f"{cfg.datapaths.base_path}/output/{polygon_name}_{temporal_freq}/pm25__randall__{polygon_name}_{temporal_freq}__{{year}}.parquet"] if temporal_freq == 'yearly' else [
+            f"{cfg.datapaths.base_path}/intermediate/{polygon_name}_{temporal_freq}/pm25__randall__{polygon_name}_{temporal_freq}__{{year}}_{month}.parquet"
+            for month in months_list
+        ]
     log:
         f"logs/satellite_pm25_{polygon_name}_{{year}}.log"
     shell:
@@ -83,3 +79,22 @@ rule aggregate_pm25:
             ("year={wildcards.year}" if temporal_freq == 'yearly' else "year={wildcards.year}") +
             " &> {log}"
         )
+
+rule concat_monthly:
+    # This rule is only needed when temporal_freq is 'monthly' to create yearly files
+    # Combines monthly parquet files from intermediate directory into a single yearly parquet file
+    input:
+        lambda wildcards: expand(
+            f"{cfg.datapaths.base_path}/intermediate/{polygon_name}_monthly/pm25__randall__{polygon_name}_monthly__" + wildcards.year + "_{month}.parquet",
+            month=[str(i).zfill(2) for i in range(1, 12 + 1)]
+        )
+    output:
+        yearly_file=f"{cfg.datapaths.base_path}/output/{polygon_name}_monthly/pm25__randall__{polygon_name}_monthly__" + "{year}.parquet"
+    log:
+        f"logs/concat_monthly_{polygon_name}_" + "{year}.log"
+    shell:
+        f"PYTHONPATH=. python src/concat_monthly.py polygon_name={polygon_name} " + "year={wildcards.year} &> {log}"
+
+
+
+
diff --git a/conf/config.yaml b/conf/config.yaml
index c3c4483..3c502cd 100644
--- a/conf/config.yaml
+++ b/conf/config.yaml
@@ -1,15 +1,15 @@
 defaults:
   - _self_
-  - datapaths: cannon_datapaths
+  - datapaths: cannon_v5gl
   - shapefiles: shapefiles
-  - satellite_pm25: us_pm25
+  - satellite_pm25: V5GL0502.HybridPM25c_0p05.NorthAmerica
 
 # == aggregation args
 temporal_freq: yearly # yearly, monthly to be matched with cfg.satellite_pm25
 year: 2020
 
 # == shapefile download args
-polygon_name: zcta # zcta, county to be matched with cfg.shapefiles
+polygon_name: county # zcta, county to be matched with cfg.shapefiles
 shapefile_year: 2020 #to be matched with cfg.shapefiles
 
 show_progress: false
diff --git a/conf/datapaths/cannon_datapaths.yaml b/conf/datapaths/cannon_datapaths.yaml
deleted file mode 100644
index c41a3fe..0000000
--- a/conf/datapaths/cannon_datapaths.yaml
+++ /dev/null
@@ -1,13 +0,0 @@
-# if files are stored within the local copy of the repository, then use null:
-input:
-  pm25__washu__raw: 
-    yearly: /n/netscratch/dominici_lab/Lab/pm25__washu__raw/yearly/ #/n/dominici_lab/lab/lego/environmnetal/pm25__washu/raw/annual
-    monthly: /n/netscratch/dominici_lab/Lab/pm25__washu__raw/monthly/ #/n/dominici_lab/lab/lego/environmnetal/pm25__washu/raw/monthly
-  shapefiles: null
-
-output:
-  pm25__washu: 
-    zcta_yearly: /n/dominici_lab/lab/lego/environmental/pm25__washu/zcta_yearly
-    zcta_monthly: /n/dominici_lab/lab/lego/environmental/pm25__washu/zcta_monthly
-    county_yearly: /n/dominici_lab/lab/lego/environmental/pm25__washu/county_yearly
-    county_monthly: /n/dominici_lab/lab/lego/environmental/pm25__washu/county_monthly
diff --git a/conf/datapaths/cannon_v5gl.yaml b/conf/datapaths/cannon_v5gl.yaml
new file mode 100644
index 0000000..3df4114
--- /dev/null
+++ b/conf/datapaths/cannon_v5gl.yaml
@@ -0,0 +1,20 @@
+base_path: data/V5GL
+
+dirs:
+  input:
+    raw: 
+      yearly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/raw/yearly #/n/netscratch/dominici_lab/Lab/pm25__randall__raw/yearly 
+      monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/raw/monthly #/n/netscratch/dominici_lab/Lab/pm25__randall__raw/monthly
+    shapefiles: 
+      county_yearly: /n/dominici_lab/lab/lego/geoboundaries/us_geoboundaries__census/us_shapefile__census/county_yearly
+      zcta_yearly: /n/dominici_lab/lab/lego/geoboundaries/us_geoboundaries__census/us_shapefile__census/zcta_yearly
+    
+  intermediate:
+    zcta_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/intermediate/zcta_monthly
+    county_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/intermediate/county_monthly
+
+  output:
+    zcta_yearly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/zcta_yearly
+    zcta_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/zcta_monthly
+    county_yearly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/county_yearly
+    county_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V5GL/county_monthly
diff --git a/conf/datapaths/cannon_v6gl.yaml b/conf/datapaths/cannon_v6gl.yaml
new file mode 100644
index 0000000..313913c
--- /dev/null
+++ b/conf/datapaths/cannon_v6gl.yaml
@@ -0,0 +1,18 @@
+base_path: data/V6GL
+
+dirs:
+  input:
+    raw: 
+      yearly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/raw/yearly #/n/netscratch/dominici_lab/Lab/pm25__randall__raw/yearly 
+      monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/raw/monthly #/n/netscratch/dominici_lab/Lab/pm25__randall__raw/monthly
+    shapefiles: 
+      county_yearly: /n/dominici_lab/lab/lego/geoboundaries/us_geoboundaries__census/us_shapefile__census/county_yearly
+      zcta_yearly: /n/dominici_lab/lab/lego/geoboundaries/us_geoboundaries__census/us_shapefile__census/zcta_yearly
+  intermediate:
+    zcta_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/intermediate/zcta_monthly
+    county_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/intermediate/county_monthly
+  output:
+    zcta_yearly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/zcta_yearly
+    zcta_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/zcta_monthly
+    county_yearly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/county_yearly
+    county_monthly: /n/dominici_lab/lab/lego/environmental/pm25__randall/V6GL/county_monthly
\ No newline at end of file
diff --git a/conf/datapaths/datapaths.yaml b/conf/datapaths/datapaths.yaml
index e9d1be7..b732073 100644
--- a/conf/datapaths/datapaths.yaml
+++ b/conf/datapaths/datapaths.yaml
@@ -1,12 +1,16 @@
-# if files are stored within the local copy of the repository, then use null:
-input:
-  pm25__washu__raw: 
-    yearly: null
-    monthly: null
-  shapefiles: null
+base_path: data/V6GL
 
-output:
-  pm25__washu: 
+dirs:
+  input:
+    raw: 
+      yearly: null
+      monthly: null
+    shapefiles: null
+
+  intermediate:
+    zcta_monthly: null
+    county_monthly: null
+  output:
     zcta_yearly: null
     zcta_monthly: null
     county_yearly: null
diff --git a/conf/satellite_pm25/us_pm25.yaml b/conf/satellite_pm25/V5GL04.HybridPM25c_0p10.NorthAmerica.yaml
similarity index 100%
rename from conf/satellite_pm25/us_pm25.yaml
rename to conf/satellite_pm25/V5GL04.HybridPM25c_0p10.NorthAmerica.yaml
diff --git a/conf/satellite_pm25/V5GL0502.HybridPM25c_0p05.NorthAmerica.yaml b/conf/satellite_pm25/V5GL0502.HybridPM25c_0p05.NorthAmerica.yaml
new file mode 100644
index 0000000..94ab872
--- /dev/null
+++ b/conf/satellite_pm25/V5GL0502.HybridPM25c_0p05.NorthAmerica.yaml
@@ -0,0 +1,19 @@
+yearly:
+  url: https://wustl.app.box.com/v/ACAG-V5GL0502-GWRPM25c0p05/folder/293383209520
+
+  zipname: Annual
+
+  file_prefix: "V5GL0502.HybridPM25c_0p05.NorthAmerica"
+  #file name convention is V5GL0502.HybridPM25c_0p05.NorthAmerica.yyyymm-yyyymm.nc
+
+monthly:
+  url: https://wustl.app.box.com/v/ACAG-V5GL0502-GWRPM25c0p05/folder/293385030318
+
+  zipname: Monthly
+
+  file_prefix: "V5GL0502.HybridPM25c_0p05.NorthAmerica"
+  #file name convention is V5GL0502.HybridPM25c_0p05.NorthAmerica.yyyymm-yyyymm.nc
+
+layer: "GWRPM25" #geographic weighted regression PM2.5
+latitude_layer: "lat"
+longitude_layer: "lon"
diff --git a/conf/satellite_pm25/V6GL02.04.CNNPM25.0p10.NA.yaml b/conf/satellite_pm25/V6GL02.04.CNNPM25.0p10.NA.yaml
new file mode 100644
index 0000000..926f845
--- /dev/null
+++ b/conf/satellite_pm25/V6GL02.04.CNNPM25.0p10.NA.yaml
@@ -0,0 +1,18 @@
+yearly:
+  url: https://wustl.app.box.com/s/s7eiaxytjr9w1z7glat45cesitcemprv/folder/327763225614
+
+  zipname: Annual
+
+  file_prefix: "V6GL02.04.CNNPM25.0p10.NA"
+  #file name convention is V6GL02.04.CNNPM25.0p10.NA.yyyymm-yyyymm.nc
+
+monthly: 
+  url: https://wustl.app.box.com/s/s7eiaxytjr9w1z7glat45cesitcemprv/folder/327764742544
+  zipname: Monthly
+
+  file_prefix: "V6GL02.04.CNNPM25.0p10.NA"
+  #file name convention is V6GL02.04.CNNPM25.0p10.NA.yyyymm-yyyymm.nc
+
+layer: "PM25" #CNN PM2.5
+latitude_layer: "lat"
+longitude_layer: "lon"
diff --git a/conf/satellite_pm25/global_pm25.yaml b/conf/satellite_pm25/global_pm25.yaml
deleted file mode 100644
index 617e89a..0000000
--- a/conf/satellite_pm25/global_pm25.yaml
+++ /dev/null
@@ -1,14 +0,0 @@
-yearly: #ACAG-V5GL04-GWRPM25 has lower resolution, ACAG-V5GL04-GWRPM25c0p10 has higher resolution
-  url: https://wustl.app.box.com/v/ACAG-V5GL04-GWRPM25c0p10/folder/237172480358  
-
-  zipname: Annual
-
-  file_prefix: "V5GL04.HybridPM25c_0p10.Global"
-  #file name convention is V5GL04.HybridPM25.NorthAmerica.yyyymm-yyyymm.nc
-  # e.g. V5GL04.HybridPM25.NorthAmerica.201801-201812.nc is the file for 2018 and NorthAmerica
-  # "V5GL04.HybridPM25.NorthAmerica" #lower resolution
-  # "V5GL04.HybridPM25c_0p10.NorthAmerica" #higher resolution
-
-layer: "GWRPM25" #geographic weighted regression PM2.5
-latitude_layer: "lat"
-longitude_layer: "lon"
\ No newline at end of file
diff --git a/conf/shapefiles/shapefiles.yaml b/conf/shapefiles/shapefiles.yaml
index 420e8b4..42bcf4f 100644
--- a/conf/shapefiles/shapefiles.yaml
+++ b/conf/shapefiles/shapefiles.yaml
@@ -1,66 +1,38 @@
-# cfg.shapefile_year and cfg.polygon_name are used to match the shapefile to dowload
+# Shapefile metadata configuration
+# Each polygon type contains:
+#   - years: list of available shapefile years
+#   - idvar: ID column name in the shapefile
+#   - prefix: shapefile directory/file naming prefix
 
 census_tract:
-  2020:
-    url: https://www2.census.gov/geo/tiger/GENZ2020/shp/cb_2020_us_tract_500k.zip
-    idvar: GEOID
-  2021:
-    url: https://www2.census.gov/geo/tiger/GENZ2021/shp/cb_2021_us_tract_500k.zip
-    idvar: GEOID
-  2022:
-    url: https://www2.census.gov/geo/tiger/GENZ2022/shp/cb_2022_us_tract_500k.zip
-    idvar: GEOID
-
+  years:
+    - 2020
+    - 2021
+    - 2022
+  idvar: "GEOID"
+  prefix: "cb_us_tract_"
+ 
 county: # County shapefiles (cartographic boundaries) https://www.census.gov/programs-surveys/geography/guidance/tiger-data-products-guide.html
-  2013:
-    url: https://www2.census.gov/geo/tiger/GENZ2013/cb_2013_us_county_500k.zip # readme https://www2.census.gov/geo/tiger/GENZ2013/2013_file_name_def.pdf
-    idvar: GEOID
-  2014:
-    url: https://www2.census.gov/geo/tiger/GENZ2014/shp/cb_2014_us_county_500k.zip
-    idvar: GEOID
-  2015:
-    url: https://www2.census.gov/geo/tiger/GENZ2015/shp/cb_2015_us_county_500k.zip
-    idvar: GEOID
-  2016:
-    url: https://www2.census.gov/geo/tiger/GENZ2016/shp/cb_2016_us_county_500k.zip
-    idvar: GEOID
-  2017:
-    url: https://www2.census.gov/geo/tiger/GENZ2017/shp/cb_2017_us_county_500k.zip
-    idvar: GEOID
-  2018:
-    url: https://www2.census.gov/geo/tiger/GENZ2018/shp/cb_2018_us_county_500k.zip
-    idvar: GEOID
-  2019:
-    url: https://www2.census.gov/geo/tiger/GENZ2019/shp/cb_2019_us_county_500k.zip
-    idvar: GEOID
-  2020:
-    url: https://www2.census.gov/geo/tiger/GENZ2020/shp/cb_2020_us_county_500k.zip
-    idvar: GEOID
-  2021:
-    url: https://www2.census.gov/geo/tiger/GENZ2021/shp/cb_2021_us_county_500k.zip
-    idvar: GEOID
-  2022:
-    url: https://www2.census.gov/geo/tiger/GENZ2022/shp/cb_2022_us_county_500k.zip
-    idvar: GEOID
-
-zcta: # ZCTA shapefiles (cartographic boudaries) https://www.census.gov/programs-surveys/geography/guidance/tiger-data-products-guide.html
-  2000:
-    url: https://www2.census.gov/geo/tiger/GENZ2010/gz_2010_us_860_00_500k.zip # readme https://www2.census.gov/geo/tiger/GENZ2010/ReadMe.pdf
-    idvar: ZCTA5
-  2010:
-    url: https://www2.census.gov/geo/tiger/GENZ2019/shp/cb_2019_us_zcta510_500k.zip # latest ZCTA5CE10 available
-    idvar: ZCTA5CE10
-  2020:
-    url: https://www2.census.gov/geo/tiger/GENZ2020/shp/cb_2020_us_zcta520_500k.zip # latest ZCTA5CE20 available (to date)
-    idvar: ZCTA5CE20
-
-# zcta: # ZCTA shapefiles (tiger line) https://www.census.gov/programs-surveys/geography/guidance/tiger-data-products-guide.html
-# 2000:
-#   url: https://www2.census.gov/geo/tiger/TIGER2010/ZCTA5/2000/tl_2010_us_zcta500.zip # latest ZCTA5CE00 available
-#   idvar: ZCTA5CE00
-# 2010:
-#   url: https://www2.census.gov/geo/tiger/TIGER2020/ZCTA5/tl_2020_us_zcta510.zip # latest ZCTA5CE10 available
-#   idvar: ZCTA5CE10
-# 2020: 
-#   url: https://www2.census.gov/geo/tiger/TIGER2022/ZCTA520/tl_2022_us_zcta520.zip # latest ZCTA5CE20 available (to date)
-#   idvar: ZCTA5CE20
+  years:
+    - 2013
+    - 2014
+    - 2015
+    - 2016
+    - 2017
+    - 2018
+    - 2019
+    - 2020
+    - 2021
+    - 2022
+    - 2023
+  idvar: "county"
+  prefix: "us_shapefile__census__county_yearly__"
+  
+zcta: # ZCTA shapefiles (cartographic boundaries) https://www.census.gov/programs-surveys/geography/guidance/tiger-data-products-guide.html
+  years:
+    - 2000
+    - 2010
+    - 2020
+  idvar: "zcta"
+  prefix: "us_shapefile__census__zcta_yearly__"
+ 
\ No newline at end of file
diff --git a/requirements.yaml b/environment.yaml
similarity index 78%
rename from requirements.yaml
rename to environment.yaml
index 6f0ee4d..596e80a 100644
--- a/requirements.yaml
+++ b/environment.yaml
@@ -1,4 +1,4 @@
-name: satellite_pm25_raster2polygon
+name: pm25_randall
 channels:
   - conda-forge
   - defaults
@@ -19,6 +19,3 @@ dependencies:
     - selenium==4.29.0
     - chromedriver-binary==135.0.7030.0.0
     - tqdm==4.67.1
-    - torch==2.6.0
-    - torchaudio==2.6.0
-    - torchvision==0.21.0
diff --git a/fasrc_jobs/county_monthly.sbatch b/fasrc_jobs/county_monthly.sbatch
deleted file mode 100644
index 2f47486..0000000
--- a/fasrc_jobs/county_monthly.sbatch
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/bash
-#
-#SBATCH -p serial_requeue # partition (queue)
-#SBATCH -c 16 # number of cores 
-#SBATCH --mem 96GB # memory 
-#SBATCH -t 0-02:00 # time (D-HH:MM)
-
-singularity exec $HOME/singularity_images/satellite_pm25_raster2polygon_latest.sif snakemake --cores 16 -C polygon_name=county temporal_freq=monthly
diff --git a/fasrc_jobs/zcta_monthly.sbatch b/fasrc_jobs/zcta_monthly.sbatch
deleted file mode 100644
index 38c04a4..0000000
--- a/fasrc_jobs/zcta_monthly.sbatch
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/bash
-#
-#SBATCH -p shared # partition (queue)
-#SBATCH -c 32 # number of cores 
-#SBATCH --mem 96GB # memory 
-#SBATCH -t 0-01:00 # time (D-HH:MM)
-
-singularity exec $HOME/singularity_images/satellite_pm25_raster2polygon_latest.sif snakemake --cores 16 -C polygon_name=zcta temporal_freq=monthly
diff --git a/fasrc_jobs/README.md b/jobs/README.md
similarity index 100%
rename from fasrc_jobs/README.md
rename to jobs/README.md
diff --git a/jobs/county_monthly.sbatch b/jobs/county_monthly.sbatch
new file mode 100644
index 0000000..4e28318
--- /dev/null
+++ b/jobs/county_monthly.sbatch
@@ -0,0 +1,10 @@
+#!/bin/bash
+#
+#SBATCH -p serial_requeue # partition (queue)
+#SBATCH -c 16 # number of cores 
+#SBATCH --mem 96GB # memory 
+#SBATCH -t 0-02:00 # time (D-HH:MM)
+
+#singularity exec $HOME/singularity_images/satellite_pm25_raster2polygon_latest.sif snakemake --cores 16 -C polygon_name=county temporal_freq=monthly
+
+snakemake --cores 16 -C polygon_name=county temporal_freq=monthly
diff --git a/jobs/v5gl.sbatch b/jobs/v5gl.sbatch
new file mode 100644
index 0000000..8bb89cc
--- /dev/null
+++ b/jobs/v5gl.sbatch
@@ -0,0 +1,13 @@
+#!/bin/bash
+#
+#SBATCH -p serial_requeue # partition (queue)
+#SBATCH -c 48 # number of cores 
+#SBATCH --mem 184GB # memory 
+#SBATCH -t 0-12:00 # time (D-HH:MM)
+
+#singularity exec $HOME/singularity_images/satellite_pm25_raster2polygon_latest.sif snakemake --cores 16 -C polygon_name=county temporal_freq=monthly
+
+snakemake --cores 24 -C polygon_name=county temporal_freq=yearly
+snakemake --cores 24 -C polygon_name=county temporal_freq=monthly
+snakemake --cores 24 -C polygon_name=zcta temporal_freq=yearly
+snakemake --cores 24 -C polygon_name=zcta temporal_freq=monthly
diff --git a/jobs/zcta_monthly.sbatch b/jobs/zcta_monthly.sbatch
new file mode 100644
index 0000000..2f1d953
--- /dev/null
+++ b/jobs/zcta_monthly.sbatch
@@ -0,0 +1,11 @@
+#!/bin/bash
+#
+#SBATCH -p shared # partition (queue)
+#SBATCH -c 32 # number of cores 
+#SBATCH --mem 96GB # memory 
+#SBATCH -t 0-01:00 # time (D-HH:MM)
+
+#singularity exec $HOME/singularity_images/satellite_pm25_raster2polygon_latest.sif snakemake --cores 16 -C polygon_name=zcta temporal_freq=monthly
+
+snakemake --cores 32 -C polygon_name=zcta temporal_freq=yearly
+
diff --git a/jobs/zcta_yearly.sbatch b/jobs/zcta_yearly.sbatch
new file mode 100644
index 0000000..9d94155
--- /dev/null
+++ b/jobs/zcta_yearly.sbatch
@@ -0,0 +1,10 @@
+#!/bin/bash
+#
+#SBATCH -p shared # partition (queue)
+#SBATCH -c 32 # number of cores 
+#SBATCH --mem 96GB # memory 
+#SBATCH -t 0-01:00 # time (D-HH:MM)
+
+#singularity exec $HOME/singularity_images/satellite_pm25_raster2polygon_latest.sif snakemake --cores 16 -C polygon_name=zcta temporal_freq=monthly
+
+snakemake --cores 32 -C polygon_name=zcta temporal_freq=yearly
diff --git a/notes/eda_input.ipynb b/notes/eda_input.ipynb
index 9bb877c..55a1ae2 100644
--- a/notes/eda_input.ipynb
+++ b/notes/eda_input.ipynb
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -38,7 +38,7 @@
    ],
    "source": [
     "# Open the netCDF file\n",
-    "file_path = \"../data/input/satellite_pm25/annual/V5GL04.HybridPM25c_0p10.NorthAmerica.202201-202212.nc\"\n",
+    "file_path = f\"../{cfg.datapaths.base_path}/input/satellite_pm25/yearly/V5GL04.HybridPM25c_0p10.NorthAmerica.202201-202212.nc\"\n",
     "dataset = netCDF4.Dataset(file_path)\n",
     "\n",
     "# Print the global attributes\n",
@@ -183,7 +183,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -210,7 +210,7 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "# Open the netCDF file\n",
-    "file_path = \"data/V5GL04.HybridPM25.NorthAmerica.202201-202212.nc\"\n",
+    "file_path = f\"{cfg.datapaths.base_path}/V5GL04.HybridPM25.NorthAmerica.202201-202212.nc\"\n",
     "dataset = netCDF4.Dataset(file_path)\n",
     "\n",
     "# Get the latitude and longitude variables\n",
@@ -260,7 +260,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -280,12 +280,12 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "# Read the CSV file\n",
-    "pm25_data = pd.read_csv('data/county_pm25.csv')\n",
+    "pm25_data = pd.read_csv(f'{cfg.datapaths.base_path}/county_pm25.csv')\n",
     "# Convert GEOID to string using trailing zeros\n",
     "pm25_data['GEOID'] = pm25_data['GEOID'].astype(str).str.zfill(5)\n",
     "\n",
     "# Read the shapefile\n",
-    "shapefile = gpd.read_file('data/shapefile_cb_county_2015/shapefile.shp')\n",
+    "shapefile = gpd.read_file(f\"{cfg.datapaths.base_path}/shapefile_cb_county_2015/shapefile.shp\")\n",
     "\n",
     "# Merge the data\n",
     "merged_data = shapefile.merge(pm25_data, on='GEOID', how='left')\n",
diff --git a/notes/eda_output.ipynb b/notes/eda_output.ipynb
index 9ab63ca..dcc5f7e 100644
--- a/notes/eda_output.ipynb
+++ b/notes/eda_output.ipynb
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -47,7 +47,7 @@
    ],
    "source": [
     "# Open the netCDF file\n",
-    "file_path = \"data/V5GL04.HybridPM25.NorthAmerica.202201-202212.nc\"\n",
+    "file_path = f\"{cfg.datapaths.base_path}/input/satellite_pm25/yearly/V5GL04.HybridPM25c_0p10.NorthAmerica.202201-202212.nc\"\n",
     "dataset = netCDF4.Dataset(file_path)\n",
     "\n",
     "# Print the global attributes\n",
@@ -192,7 +192,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -219,7 +219,7 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "# Open the netCDF file\n",
-    "file_path = \"data/V5GL04.HybridPM25.NorthAmerica.202201-202212.nc\"\n",
+    "file_path = f\"{cfg.datapaths.base_path}/input/satellite_pm25/yearly/V5GL04.HybridPM25c_0p10.NorthAmerica.202201-202212.nc\"\n",
     "dataset = netCDF4.Dataset(file_path)\n",
     "\n",
     "# Get the latitude and longitude variables\n",
@@ -269,7 +269,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -279,7 +279,7 @@
     "import pyarrow.parquet as pq\n",
     "\n",
     "# Read parquet file with pm25 at county level for 2015\n",
-    "pm25_data = pq.read_table(\"data/output/satellite_pm25_raster2polygon/monthly/satellite_pm25_zcta_2015_01.parquet\").to_pandas()"
+    "pm25_data = pq.read_table(f\"{cfg.datapaths.base_path}/datapaths.base_path}/datapaths.base_path}/datapaths.base_path}/output/satellite_pm25_raster2polygon/monthly/satellite_pm25_zcta_2015_01.parquet\").to_pandas()"
    ]
   },
   {
@@ -368,7 +368,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -388,12 +388,12 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "# Read the CSV file\n",
-    "pm25_data = pd.read_csv('data/county_pm25.csv')\n",
+    "pm25_data = pd.read_csv(f'{cfg.datapaths.base_path}/county_pm25.csv')\n",
     "# Convert GEOID to string using trailing zeros\n",
     "pm25_data['GEOID'] = pm25_data['GEOID'].astype(str).str.zfill(5)\n",
     "\n",
     "# Read the shapefile\n",
-    "shapefile = gpd.read_file('data/shapefile_cb_county_2015/shapefile.shp')\n",
+    "shapefile = gpd.read_file('{cfg.datapaths.base_path}/datapaths.base_path}/datapaths.base_path}/shapefile_cb_county_2015/shapefile.shp')\n",
     "\n",
     "# Merge the data\n",
     "merged_data = shapefile.merge(pm25_data, on='GEOID', how='left')\n",
diff --git a/src/aggregate_pm25.py b/src/aggregate_pm25.py
index 21a7dd1..0d722af 100644
--- a/src/aggregate_pm25.py
+++ b/src/aggregate_pm25.py
@@ -35,13 +35,16 @@ def main(cfg):
 
     # == load shapefile
     LOGGER.info("Loading shapefile.")
-    shapefile_years_list = list(cfg.shapefiles[cfg.polygon_name].keys())
+    shapefile_years_list = cfg.shapefiles[cfg.polygon_name].years
     #use previously available shapefile
     shapefile_year = available_shapefile_year(cfg.year, shapefile_years_list)
+    shapefile_prefix = cfg.shapefiles[cfg.polygon_name].prefix
+    shapefile_name = f"{shapefile_prefix}{shapefile_year}"
 
-    shape_path = f'data/input/shapefiles/shapefile_{cfg.polygon_name}_{shapefile_year}/shapefile.shp'
+    shape_path = f'{cfg.datapaths.base_path}/input/shapefiles/{cfg.polygon_name}_yearly/{shapefile_name}/{shapefile_name}.shp'
+    LOGGER.info(f"Loading shapefile from: {shape_path}")
     polygon = gpd.read_file(shape_path)
-    polygon_ids = polygon[cfg.shapefiles[cfg.polygon_name][shapefile_year].idvar].values
+    polygon_ids = polygon[cfg.shapefiles[cfg.polygon_name].idvar].values
 
     # == filenames to be aggregated
     if cfg.temporal_freq == "yearly":
@@ -62,7 +65,7 @@ def main(cfg):
     # load the first file to obtain the affine transform/boundaries
     LOGGER.info("Mapping polygons to raster cells.")
 
-    ds = xarray.open_dataset(f"data/input/pm25__washu__raw/{cfg.temporal_freq}/{filenames[0]}")
+    ds = xarray.open_dataset(f"{cfg.datapaths.base_path}/input/raw/{cfg.temporal_freq}/{filenames[0]}")
     layer = getattr(ds, cfg.satellite_pm25.layer)
 
     # obtain affine transform/boundaries
@@ -90,7 +93,7 @@ def main(cfg):
 
         if i > 0:
             # reload the file only if it is different from the first one
-            ds = xarray.open_dataset(f"data/input/pm25__washu__raw/{cfg.temporal_freq}/{filename}")
+            ds = xarray.open_dataset(f"{cfg.datapaths.base_path}/input/raw/{cfg.temporal_freq}/{filename}")
             layer = getattr(ds, cfg.satellite_pm25.layer)
 
         # === obtain stats quickly using precomputed mapping
@@ -111,15 +114,17 @@ def main(cfg):
         # == save output file
         if cfg.temporal_freq == "yearly":
             # ignore month since len(filenames) == 1
-            output_filename = f"pm25__washu__{cfg.polygon_name}_{cfg.temporal_freq}__{cfg.year}.parquet"
+            output_filename = f"pm25__randall__{cfg.polygon_name}_{cfg.temporal_freq}__{cfg.year}.parquet"
+            output_path = f"{cfg.datapaths.base_path}/output/{cfg.polygon_name}_{cfg.temporal_freq}/{output_filename}"
 
         elif cfg.temporal_freq == "monthly":
             # use month in filename since len(filenames) = 12
             month = f"{i + 1:02d}"
             df["month"] = month
-            output_filename = f"pm25__washu__{cfg.polygon_name}_{cfg.temporal_freq}__{cfg.year}_{month}.parquet"
+            output_filename = f"pm25__randall__{cfg.polygon_name}_{cfg.temporal_freq}__{cfg.year}_{month}.parquet"
+            # Save monthly outputs to intermediate folder
+            output_path = f"{cfg.datapaths.base_path}/intermediate/{cfg.polygon_name}_{cfg.temporal_freq}/{output_filename}"
 
-        output_path = f"data/output/pm25__washu/{cfg.polygon_name}_{cfg.temporal_freq}/{output_filename}"
         df.to_parquet(output_path)
 
         # plot aggregation map using geopandas
diff --git a/src/concat_monthly.py b/src/concat_monthly.py
new file mode 100644
index 0000000..873b7cd
--- /dev/null
+++ b/src/concat_monthly.py
@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+"""
+Consolidate monthly PM2.5 aggregation files into yearly files.
+
+This script takes the monthly parquet files from the intermediate directory
+and combines all 12 months for each year into a single yearly file in the output directory.
+
+Usage:
+    python src/concat_monthly.py year=2020
+    
+    # With overrides:
+    python src/concat_monthly.py polygon_name=zcta year=2020
+"""
+
+import pandas as pd
+import os
+import hydra
+import logging
+from pathlib import Path
+
+logging.basicConfig(level=logging.INFO, format='[%(asctime)s][%(levelname)s] - %(message)s')
+LOGGER = logging.getLogger(__name__)
+
+
+def consolidate_year(intermediate_dir, output_dir, year, polygon_name, input_freq="monthly"):
+    """
+    Consolidate all monthly files for a given year into a single yearly file.
+    Reads from intermediate directory, outputs to main output directory.
+    
+    Args:
+        intermediate_dir: Directory containing monthly parquet files
+        output_dir: Directory to save yearly parquet file
+        year: Year to consolidate
+        polygon_name: Name of polygon type (county, zcta, etc.)
+        input_freq: Frequency of input files (monthly)
+    
+    Returns:
+        List of monthly files that were consolidated
+    """
+    monthly_files = []
+    
+    # Pattern: pm25__randall__county_monthly__2020_01.parquet
+    # Collect all monthly files for this year from intermediate directory
+    for month in range(1, 13):
+        month_str = str(month).zfill(2)
+        filename = f"pm25__randall__{polygon_name}_{input_freq}__{year}_{month_str}.parquet"
+        filepath = os.path.join(intermediate_dir, filename)
+        
+        if os.path.exists(filepath):
+            monthly_files.append(filepath)
+        else:
+            LOGGER.warning(f"Missing file: {filepath}")
+    
+    if not monthly_files:
+        LOGGER.error(f"No monthly files found for year {year} in {intermediate_dir}")
+        raise FileNotFoundError(f"No monthly files found for year {year}")
+    
+    if len(monthly_files) != 12:
+        LOGGER.warning(f"Only found {len(monthly_files)}/12 months for year {year}")
+    
+    # Read and concatenate all monthly files
+    LOGGER.info(f"Reading {len(monthly_files)} monthly files for year {year}")
+    dfs = [pd.read_parquet(f) for f in monthly_files]
+    yearly_df = pd.concat(dfs, ignore_index=False)
+    
+    # Sort by polygon ID and month for consistent ordering
+    if 'month' in yearly_df.columns:
+        yearly_df = yearly_df.sort_values(['month'])
+    
+    # Save yearly file to output directory
+    # Pattern: pm25__randall__county_monthly__2020.parquet
+    output_file = os.path.join(output_dir, f"pm25__randall__{polygon_name}_monthly__{year}.parquet")
+    LOGGER.info(f"Saving consolidated file: {output_file} ({len(yearly_df)} rows)")
+    yearly_df.to_parquet(output_file)
+    
+    return monthly_files
+
+
+
+
+@hydra.main(config_path="../conf", config_name="config", version_base=None)
+def main(cfg):
+    """
+    Consolidate monthly PM2.5 files for a specific year into a yearly file using Hydra configuration.
+    Reads from intermediate directory, outputs to main output directory.
+    """
+    
+    polygon_name = cfg.polygon_name
+    year = cfg.year
+    
+    # Build paths using datapaths configuration
+    monthly_dir = f"{cfg.datapaths.base_path}/output/{polygon_name}_monthly"
+    intermediate_dir = f"{cfg.datapaths.base_path}/intermediate/{polygon_name}_monthly"
+    
+    LOGGER.info(f"Polygon name: {polygon_name}")
+    LOGGER.info(f"Year: {year}")
+    LOGGER.info(f"Input directory (intermediate): {intermediate_dir}")
+    LOGGER.info(f"Output directory: {monthly_dir}")
+    
+    # Process the specified year
+    try:
+        monthly_files = consolidate_year(intermediate_dir, monthly_dir, year, polygon_name)
+        LOGGER.info(f"Successfully consolidated {len(monthly_files)} monthly files for year {year}")
+        
+    except Exception as e:
+        LOGGER.error(f"Error processing year {year}: {e}")
+        raise
+
+
+if __name__ == "__main__":
+    main()
diff --git a/utils/create_dir_paths.py b/src/create_datapaths.py
similarity index 77%
rename from utils/create_dir_paths.py
rename to src/create_datapaths.py
index 696390d..a3d0d13 100644
--- a/utils/create_dir_paths.py
+++ b/src/create_datapaths.py
@@ -5,14 +5,31 @@
 
 LOGGER = logging.getLogger(__name__)
 
+def init_folder(folder_cfg=None):
+    folder_dict = folder_cfg.dirs
+    
+    # defines a base path for the data
+    datapath = folder_cfg.base_path
+    if datapath is None:
+        datapath = "data"
+    # check if datapath exists, if not create it 
+    if os.path.exists(datapath):
+        LOGGER.info(f"Base path {datapath} already exists")
+    else:
+        LOGGER.info(f"Creating base path {datapath}")
+        os.makedirs(datapath, exist_ok=True)
+
+    # create subfolders and symbolic links
+    create_subfolders_and_links(datapath=datapath, folder_dict=folder_dict)
 
 def create_subfolders_and_links(datapath="data", folder_dict=None):
     """
     Recursively create subfolders and symbolic links.
     """
     if not os.path.exists(datapath):
-        LOGGER.info(f"Error: {datapath} does not exists.")
+        LOGGER.info(f"Error: {datapath} does not exist.")
         return
+
     if isinstance(folder_dict, DictConfig):
         for path, subfolder_dict in folder_dict.items():
             sub_datapath = os.path.join(datapath, path)
@@ -50,7 +67,7 @@ def create_subfolders_and_links(datapath="data", folder_dict=None):
 @hydra.main(config_path="../conf", config_name="config", version_base=None)
 def main(cfg):
     """Create data subfolders and symbolic links as indicated in config file."""
-    create_subfolders_and_links(folder_dict=cfg.datapaths)
+    init_folder(folder_cfg=cfg.datapaths)
 
 if __name__ == "__main__":
-    main()
+    main()
\ No newline at end of file
diff --git a/src/download_pm25.py b/src/download_pm25.py
index a063c41..2fc0fa8 100644
--- a/src/download_pm25.py
+++ b/src/download_pm25.py
@@ -25,7 +25,7 @@ def main(cfg):
 
     # == setup chrome driver
     # Expand the tilde to the user's home directory
-    download_dir = f"data/input/pm25__washu__raw/"
+    download_dir = f"{cfg.datapaths.base_path}/input/raw/"
     download_dir = os.path.abspath(download_dir)
     download_zip = f"{download_dir}/{cfg.satellite_pm25[cfg.temporal_freq].zipname}.zip"
     src_dir = f"{download_dir}/{cfg.satellite_pm25[cfg.temporal_freq].zipname}"
@@ -78,16 +78,20 @@ def main(cfg):
         with zipfile.ZipFile(download_zip, "r") as zip_ref:
             zip_ref.extractall(download_dir)
 
-        # Move all files from the src_dir to dest_dir
+        # Move all files from the src_dir to dest_dir, flattening the directory structure
         os.makedirs(dest_dir, exist_ok=True)
-        for file in os.listdir(src_dir):
-            shutil.move(os.path.join(src_dir, file), dest_dir)
-
-        # Remove the zip file and the empty folder
+        for root, dirs, files in os.walk(src_dir):
+            for file in files:
+                src_file = os.path.join(root, file)
+                dest_file = os.path.join(dest_dir, file)
+                shutil.move(src_file, dest_file)
+                logger.info(f"Moved {file} to {dest_dir}")
+
+        # Remove the zip file and the source folder (including any empty subfolders)
         os.remove(download_zip)
-        os.rmdir(src_dir)
+        shutil.rmtree(src_dir)
 
-        # Remove anyfile starging with Unconfirmed (this might be a Chrome bug/artifact)
+        # Remove any file starting with Unconfirmed (this might be a Chrome bug/artifact)
         for file in os.listdir(download_dir):
             if file.startswith("Unconfirmed"):
                 os.remove(os.path.join(download_dir, file))
diff --git a/src/download_shapefile.py b/src/download_shapefile.py
deleted file mode 100644
index 492c9ca..0000000
--- a/src/download_shapefile.py
+++ /dev/null
@@ -1,38 +0,0 @@
-import logging
-import os
-import zipfile
-import hydra
-import wget
-
-@hydra.main(config_path="../conf", config_name="config", version_base=None)
-def main(cfg):
-    url = cfg.shapefiles[cfg.polygon_name][cfg.shapefile_year].url
-
-    tgt = f"data/input/shapefiles/shapefile_{cfg.polygon_name}_{cfg.shapefile_year}"
-
-    tgtdir = os.path.dirname(tgt)
-    tgtfile = os.path.basename(tgt)
-
-    tgt = f"{tgtdir}/{tgtfile}"
-    logging.info(f"Downloading {url}")
-    wget.download(url, f"{tgt}.zip")
-    logging.info("Done.")
-
-    # unzip with unzip library
-    with zipfile.ZipFile(f"{tgt}.zip", "r") as zip_ref:
-        zip_ref.extractall(tgt)
-    logging.info(f"Unzipped {tgt} with files:\n {os.listdir(tgt)}")
-
-    # remove dirty zip file
-    os.remove(f"{tgt}.zip")
-    logging.info(f"Removed {tgt}.zip")
-
-    logging.info(f"Rename files to shapefile.*")
-    files = os.listdir(tgt)
-    for f in files:
-        _, ext = os.path.splitext(f)
-        os.rename(f"{tgt}/{f}", f"{tgt}/shapefile{ext}")
-    logging.info(f"Done.")
-
-if __name__ == "__main__":
-    main()