diff --git a/data/data-pipeline/data_pipeline/etl/sources/dot_travel_composite/etl.py b/data/data-pipeline/data_pipeline/etl/sources/dot_travel_composite/etl.py
index 2a99f76f..9e9d0f3f 100644
--- a/data/data-pipeline/data_pipeline/etl/sources/dot_travel_composite/etl.py
+++ b/data/data-pipeline/data_pipeline/etl/sources/dot_travel_composite/etl.py
@@ -16,6 +16,7 @@ class TravelCompositeETL(ExtractTransformLoad):
     NAME = "travel_composite"
     SOURCE_URL = "https://www.transportation.gov/sites/dot.gov/files/Shapefile_and_Metadata.zip"
     GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
+    PUERTO_RICO_EXPECTED_IN_DATA = False
 
     # Output score variables (values set on datasets.yml) for linting purposes
     TRAVEL_BURDEN_FIELD_NAME: str
diff --git a/data/data-pipeline/data_pipeline/etl/sources/fsf_wildfire_risk/etl.py b/data/data-pipeline/data_pipeline/etl/sources/fsf_wildfire_risk/etl.py
index 2a26370e..99aaa8fe 100644
--- a/data/data-pipeline/data_pipeline/etl/sources/fsf_wildfire_risk/etl.py
+++ b/data/data-pipeline/data_pipeline/etl/sources/fsf_wildfire_risk/etl.py
@@ -16,6 +16,8 @@ class WildfireRiskETL(ExtractTransformLoad):
     NAME = "fsf_wildfire_risk"
     SOURCE_URL = settings.AWS_JUSTICE40_DATASOURCES_URL + "/fsf_fire.zip"
     GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
+    PUERTO_RICO_EXPECTED_IN_DATA = False
+    EXPECTED_MISSING_STATES = ['02', '15']
 
     # Output score variables (values set on datasets.yml) for linting purposes
     COUNT_PROPERTIES: str
diff --git a/data/data-pipeline/data_pipeline/etl/sources/ncld_nature_deprived/etl.py b/data/data-pipeline/data_pipeline/etl/sources/ncld_nature_deprived/etl.py
index 14d49c52..acd6eae0 100644
--- a/data/data-pipeline/data_pipeline/etl/sources/ncld_nature_deprived/etl.py
+++ b/data/data-pipeline/data_pipeline/etl/sources/ncld_nature_deprived/etl.py
@@ -19,6 +19,7 @@ class NatureDeprivedETL(ExtractTransformLoad):
         + "/usa_conus_nat_dep__compiled_by_TPL.csv.zip"
     )
     GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
+    PUERTO_RICO_EXPECTED_IN_DATA = False
 
     # Output score variables (values set on datasets.yml) for linting purposes
     ELIGIBLE_FOR_NATURE_DEPRIVED_FIELD_NAME: str