hestia-earth-models 0.64.14__py3-none-any.whl → 0.65.0__py3-none-any.whl

hestia_earth/models/ipcc2019/organicCarbonPerHa_tier_1_utils.py

@@ -21,24 +21,25 @@ from hestia_earth.schema import MeasurementMethodClassification, SiteSiteType, T
 from hestia_earth.utils.model import find_term_match, filter_list_term_type
 from hestia_earth.utils.blank_node import get_node_value
 
+from hestia_earth.models.utils import split_on_condition
 from hestia_earth.models.utils.array_builders import gen_seed
 from hestia_earth.models.utils.blank_node import (
-    cumulative_nodes_match, cumulative_nodes_lookup_match, cumulative_nodes_term_match,
-    node_lookup_match, node_term_match, group_nodes_by_year, validate_start_date_end_date
+    cumulative_nodes_match, cumulative_nodes_lookup_match, cumulative_nodes_term_match, node_lookup_match,
+    node_term_match, group_nodes_by_year, validate_start_date_end_date
 )
 from hestia_earth.models.utils.ecoClimateZone import EcoClimateZone, get_eco_climate_zone_value
 from hestia_earth.models.utils.descriptive_stats import calc_descriptive_stats
 from hestia_earth.models.utils.measurement import _new_measurement
 from hestia_earth.models.utils.property import get_node_property
+from hestia_earth.models.utils.term import get_residue_removed_or_burnt_terms, get_upland_rice_land_cover_terms
 
 from .organicCarbonPerHa_utils import (
-    check_irrigation, DEPTH_LOWER, DEPTH_UPPER, get_cover_crop_property_terms_with_cache,
-    get_residue_removed_or_burnt_terms_with_cache, get_upland_rice_land_cover_terms_with_cache,
-    IPCC_SOIL_CATEGORY_TO_SOIL_TYPE_LOOKUP_VALUE, IPCC_LAND_USE_CATEGORY_TO_LAND_COVER_LOOKUP_VALUE,
-    IPCC_MANAGEMENT_CATEGORY_TO_GRASSLAND_MANAGEMENT_TERM_ID,
+    check_irrigation, DEPTH_LOWER, DEPTH_UPPER, IPCC_SOIL_CATEGORY_TO_SOIL_TYPE_LOOKUP_VALUE,
+    IPCC_LAND_USE_CATEGORY_TO_LAND_COVER_LOOKUP_VALUE, IPCC_MANAGEMENT_CATEGORY_TO_GRASSLAND_MANAGEMENT_TERM_ID,
     IPCC_MANAGEMENT_CATEGORY_TO_TILLAGE_MANAGEMENT_LOOKUP_VALUE, IpccSoilCategory, IpccCarbonInputCategory,
-    IpccLandUseCategory, IpccManagementCategory, MIN_AREA_THRESHOLD, sample_constant, sample_plus_minus_error,
-    sample_plus_minus_uncertainty, SITE_TYPE_TO_IPCC_LAND_USE_CATEGORY, SUPER_MAJORITY_AREA_THRESHOLD, STATS_DEFINITION
+    IpccLandUseCategory, IpccManagementCategory, is_cover_crop, MIN_AREA_THRESHOLD, sample_constant,
+    sample_plus_minus_error, sample_plus_minus_uncertainty, SITE_TYPE_TO_IPCC_LAND_USE_CATEGORY,
+    SUPER_MAJORITY_AREA_THRESHOLD, STATS_DEFINITION
 )
 
 _LOOKUPS = {
@@ -647,7 +648,7 @@ def should_run(site: dict) -> tuple[bool, dict, dict]:
         A tuple containing `(should_run_, inventory, kwargs, logs)`.
     """
     site_type = site.get("siteType", "")
-    management_nodes = site.get("management", [])
+    management_nodes = get_valid_management_nodes(site)
     measurement_nodes = site.get("measurements", [])
 
     eco_climate_zone = get_eco_climate_zone_value(site, as_enum=True)
@@ -695,6 +696,11 @@ def should_run(site: dict) -> tuple[bool, dict, dict]:
     return should_run_, inventory, kwargs, logs
 
 
+def get_valid_management_nodes(site: dict) -> list[dict]:
+    """Retrieve valid mangement nodes from a site."""
+    return [node for node in site.get("management", []) if validate_start_date_end_date(node)]
+
+
 def run(
     inventory: dict,
     *,
@@ -1209,22 +1215,20 @@ def _assign_ipcc_land_use_category(
     DECISION_TREE = _LAND_USE_CATEGORY_DECISION_TREE
     DEFAULT = IpccLandUseCategory.OTHER
 
-    land_cover_nodes = [
-        node for node in filter_list_term_type(management_nodes, [TermTermType.LANDCOVER])
-        if validate_start_date_end_date(node)
-    ]
-    water_regime_nodes = [
-        node for node in filter_list_term_type(management_nodes, [TermTermType.WATERREGIME])
-        if validate_start_date_end_date(node)
-    ]
+    cover_crop_nodes, land_cover_nodes = split_on_condition(
+        filter_list_term_type(management_nodes, [TermTermType.LANDCOVER]),
+        is_cover_crop
+    )
+
+    water_regime_nodes = filter_list_term_type(management_nodes, [TermTermType.WATERREGIME])
 
     has_irrigation = check_irrigation(water_regime_nodes)
     has_upland_rice = _has_upland_rice(land_cover_nodes)
     has_irrigated_upland_rice = has_upland_rice and has_irrigation
-    has_long_fallow = _has_long_fallow(land_cover_nodes)
+    has_long_fallow = _has_long_fallow(cover_crop_nodes)
     has_wetland_soils = ipcc_soil_category is IpccSoilCategory.WETLAND_SOILS
 
-    should_run_ = bool(land_cover_nodes)
+    should_run_ = land_cover_nodes or cover_crop_nodes
 
     return next(
         (
@@ -1257,7 +1261,7 @@ def _has_upland_rice(land_cover_nodes: list[dict]) -> bool:
     """
     return cumulative_nodes_term_match(
         land_cover_nodes,
-        target_term_ids=get_upland_rice_land_cover_terms_with_cache(),
+        target_term_ids=get_upland_rice_land_cover_terms(),
         cumulative_threshold=SUPER_MAJORITY_AREA_THRESHOLD
     )
 
@@ -1278,14 +1282,7 @@ def _has_long_fallow(land_cover_nodes: list[dict]) -> bool:
     bool
         `True` if long fallow is present, `False` otherwise.
     """
-    LOOKUP = _LOOKUPS["landCover"][0]
-    TARGET_LOOKUP_VALUE = "Set aside"
-    return cumulative_nodes_lookup_match(
-        land_cover_nodes,
-        lookup=LOOKUP,
-        target_lookup_values=TARGET_LOOKUP_VALUE,
-        cumulative_threshold=SUPER_MAJORITY_AREA_THRESHOLD
-    ) or cumulative_nodes_match(
+    return cumulative_nodes_match(
         lambda node: get_node_property(node, _LONG_FALLOW_CROP_TERM_ID, False).get("value", 0),
         land_cover_nodes,
         cumulative_threshold=SUPER_MAJORITY_AREA_THRESHOLD
@@ -1337,7 +1334,6 @@ def _check_ipcc_land_use_category(*, key: IpccLandUseCategory, land_cover_nodes:
 
 _IPCC_LAND_USE_CATEGORY_TO_VALIDATION_KWARGS = {
     IpccLandUseCategory.ANNUAL_CROPS_WET: {"has_wetland_soils"},
-    IpccLandUseCategory.SET_ASIDE: {"has_long_fallow"},
 }
 """
 Keyword arguments that need to be validated in addition to the `landCover` lookup match for specific
@@ -1345,6 +1341,7 @@ Keyword arguments that need to be validated in addition to the `landCover` looku
 """
 
 _IPCC_LAND_USE_CATEGORY_TO_OVERRIDE_KWARGS = {
+    IpccLandUseCategory.SET_ASIDE: {"has_long_fallow"},
     IpccLandUseCategory.PADDY_RICE_CULTIVATION: {"has_irrigated_upland_rice"}
 }
 """
@@ -1960,10 +1957,7 @@ def _get_carbon_input_kwargs(
     )
 
     has_cover_crop = cumulative_nodes_match(
-        lambda node: any(
-            get_node_property(node, term_id, False).get("value", False)
-            for term_id in get_cover_crop_property_terms_with_cache()
-        ),
+        is_cover_crop,
         land_cover_nodes,
         cumulative_threshold=MIN_AREA_THRESHOLD
     )
@@ -2007,7 +2001,7 @@ def _get_carbon_input_kwargs(
 
     has_residue_removed_or_burnt = cumulative_nodes_term_match(
         crop_residue_management_nodes,
-        target_term_ids=get_residue_removed_or_burnt_terms_with_cache(),
+        target_term_ids=get_residue_removed_or_burnt_terms(),
         cumulative_threshold=MIN_AREA_THRESHOLD
     )
 

hestia_earth/models/ipcc2019/organicCarbonPerHa_tier_2_utils.py

@@ -25,22 +25,21 @@ from hestia_earth.models.utils.array_builders import (
     avg_run_in_columnwise, gen_seed, grouped_avg, repeat_1d_array_as_columns
 )
 from hestia_earth.models.utils.blank_node import (
-    cumulative_nodes_lookup_match, cumulative_nodes_term_match, group_nodes_by_year,
-    group_nodes_by_year_and_month, GroupNodesByYearMode, node_lookup_match, node_term_match
+    cumulative_nodes_lookup_match, cumulative_nodes_term_match, group_nodes_by_year, group_nodes_by_year_and_month,
+    GroupNodesByYearMode, node_lookup_match, node_term_match
 )
 from hestia_earth.models.utils.cycle import check_cycle_site_ids_identical
 from hestia_earth.models.utils.descriptive_stats import calc_descriptive_stats
 from hestia_earth.models.utils.measurement import _new_measurement
 from hestia_earth.models.utils.property import get_node_property
 from hestia_earth.models.utils.site import related_cycles
+from hestia_earth.models.utils.term import get_upland_rice_crop_terms, get_upland_rice_land_cover_terms
 
 from .organicCarbonPerHa_utils import (
     CarbonSource, check_consecutive, DEPTH_LOWER, DEPTH_UPPER, check_irrigation,
-    get_cover_crop_property_terms_with_cache, get_upland_rice_crop_terms_with_cache,
-    get_upland_rice_land_cover_terms_with_cache, IPCC_LAND_USE_CATEGORY_TO_LAND_COVER_LOOKUP_VALUE,
-    IPCC_MANAGEMENT_CATEGORY_TO_TILLAGE_MANAGEMENT_LOOKUP_VALUE, IpccLandUseCategory, IpccManagementCategory,
-    MIN_AREA_THRESHOLD, MIN_YIELD_THRESHOLD, sample_constant, sample_plus_minus_uncertainty, sample_truncated_normal,
-    STATS_DEFINITION
+    IPCC_LAND_USE_CATEGORY_TO_LAND_COVER_LOOKUP_VALUE, IPCC_MANAGEMENT_CATEGORY_TO_TILLAGE_MANAGEMENT_LOOKUP_VALUE,
+    IpccLandUseCategory, IpccManagementCategory, is_cover_crop, MIN_AREA_THRESHOLD, MIN_YIELD_THRESHOLD,
+    sample_constant, sample_plus_minus_uncertainty, sample_truncated_normal, STATS_DEFINITION
 )
 
 _LOOKUPS = {
@@ -1410,10 +1409,7 @@ def _should_run_carbon_source_cover_crop(node: dict) -> bool:
         node_lookup_match(
             node, LOOKUP, IPCC_LAND_USE_CATEGORY_TO_LAND_COVER_LOOKUP_VALUE[IpccLandUseCategory.ANNUAL_CROPS]
         ),
-        any(
-            get_node_property(node, term_id, False).get("value", False)
-            for term_id in get_cover_crop_property_terms_with_cache()
-        )
+        is_cover_crop(node)
     ])
 
 
@@ -1744,7 +1740,7 @@ def _check_is_paddy_rice(cycles: list[dict]) -> bool:
             cycle.get("products", []) + cycle.get("practices", []),
             [TermTermType.CROP, TermTermType.FORAGE, TermTermType.LANDCOVER]
         ),
-        target_term_ids=get_upland_rice_crop_terms_with_cache() + get_upland_rice_land_cover_terms_with_cache(),
+        target_term_ids=get_upland_rice_crop_terms() + get_upland_rice_land_cover_terms(),
         cumulative_threshold=MIN_YIELD_THRESHOLD,
         default_node_value=MIN_YIELD_THRESHOLD
     ) for cycle in cycles)

hestia_earth/models/ipcc2019/organicCarbonPerHa_utils.py

@@ -1,5 +1,4 @@
 from enum import Enum
-from functools import lru_cache
 from numpy.typing import NDArray
 from typing import NamedTuple, Optional
 
@@ -8,11 +7,8 @@ from hestia_earth.schema import MeasurementStatsDefinition, SiteSiteType
 from hestia_earth.models.utils.array_builders import (
     repeat_single, plus_minus_uncertainty_to_normal_1d, truncated_normal_1d
 )
-from hestia_earth.models.utils.blank_node import cumulative_nodes_term_match
-from hestia_earth.models.utils.term import (
-    get_cover_crop_property_terms, get_irrigated_terms, get_residue_removed_or_burnt_terms, get_upland_rice_crop_terms,
-    get_upland_rice_land_cover_terms
-)
+from hestia_earth.models.utils.blank_node import cumulative_nodes_term_match, node_term_match
+from hestia_earth.models.utils.term import get_cover_crop_property_terms, get_irrigated_terms
 
 STATS_DEFINITION = MeasurementStatsDefinition.SIMULATED.value
 DEPTH_UPPER = 0
@@ -23,26 +19,6 @@ SUPER_MAJORITY_AREA_THRESHOLD = 100 - MIN_AREA_THRESHOLD
 MIN_YIELD_THRESHOLD = 1
 
 
-def get_cover_crop_property_terms_with_cache():
-    return lru_cache()(get_cover_crop_property_terms)()
-
-
-def get_irrigated_terms_with_cache():
-    return lru_cache()(get_irrigated_terms)()
-
-
-def get_residue_removed_or_burnt_terms_with_cache():
-    return lru_cache()(get_residue_removed_or_burnt_terms)()
-
-
-def get_upland_rice_crop_terms_with_cache():
-    return lru_cache()(get_upland_rice_crop_terms)()
-
-
-def get_upland_rice_land_cover_terms_with_cache():
-    return lru_cache()(get_upland_rice_land_cover_terms)()
-
-
 class IpccSoilCategory(Enum):
     """
     Enum representing IPCC Soil Categories.
@@ -106,9 +82,7 @@ IPCC_LAND_USE_CATEGORY_TO_LAND_COVER_LOOKUP_VALUE = {
     IpccLandUseCategory.PADDY_RICE_CULTIVATION: "Paddy rice cultivation",
     IpccLandUseCategory.ANNUAL_CROPS_WET: "Annual crops",
     IpccLandUseCategory.ANNUAL_CROPS: "Annual crops",
-    IpccLandUseCategory.SET_ASIDE: [
-        "Annual crops", "Paddy rice cultivation", "Perennial crops", "Set aside"
-    ],
+    IpccLandUseCategory.SET_ASIDE: "Set aside",
     IpccLandUseCategory.FOREST: "Forest",
     IpccLandUseCategory.NATIVE: "Native"
 }
@@ -236,11 +210,20 @@ def check_irrigation(water_regime_nodes: list[dict]) -> bool:
     """
     return cumulative_nodes_term_match(
         water_regime_nodes,
-        target_term_ids=get_irrigated_terms_with_cache(),
+        target_term_ids=get_irrigated_terms(),
         cumulative_threshold=MIN_AREA_THRESHOLD
     )
 
 
+def is_cover_crop(node: dict) -> bool:
+    """Check if a `landCover` node represents a cover crop."""
+    COVER_CROP_TERM_IDS = get_cover_crop_property_terms()
+    return any(
+        prop.get("value", False) for prop in node.get("properties", [])
+        if node_term_match(prop, COVER_CROP_TERM_IDS)
+    )
+
+
 def sample_truncated_normal(
     *, iterations: int, value: float, sd: float, min: float, max: float, seed: Optional[int] = None, **_
 ) -> NDArray:

hestia_earth/models/linkedImpactAssessment/{landTransformationFromCropland20YearAverageInputsProduction.py → landTransformation100YearAverageInputsProduction.py}

@@ -17,7 +17,10 @@ REQUIREMENTS = {
                     "@type": "ImpactAssessment",
                     "emissionsResourceUse": [{
                         "@type": "Indicator",
-                        "term.@id": "landTransformationFromCropland20YearAverageDuringCycle",
+                        "term.@id": [
+                            "landTransformation100YearAverageDuringCycle",
+                            "landTransformation100YearAverageInputsProduction"
+                        ],
                         "value": "> 0"
                     }]
                 }
@@ -30,7 +33,7 @@ RETURNS = {
         "value": ""
     }]
 }
-TERM_ID = 'landTransformationFromCropland20YearAverageInputsProduction'
+TERM_ID = 'landTransformation100YearAverageInputsProduction'
 
 
 def run(impact_assessment: dict): return run_inputs_production(impact_assessment, TERM_ID)

hestia_earth/models/linkedImpactAssessment/{landTransformationFromCropland100YearAverageInputsProduction.py → landTransformation20YearAverageInputsProduction.py}

@@ -17,7 +17,10 @@ REQUIREMENTS = {
                     "@type": "ImpactAssessment",
                     "emissionsResourceUse": [{
                         "@type": "Indicator",
-                        "term.@id": "landTransformationFromCropland100YearAverageDuringCycle",
+                        "term.@id": [
+                            "landTransformation20YearAverageDuringCycle",
+                            "landTransformation20YearAverageInputsProduction"
+                        ],
                         "value": "> 0"
                     }]
                 }
@@ -30,7 +33,7 @@ RETURNS = {
         "value": ""
     }]
 }
-TERM_ID = 'landTransformationFromCropland100YearAverageInputsProduction'
+TERM_ID = 'landTransformation20YearAverageInputsProduction'
 
 
 def run(impact_assessment: dict): return run_inputs_production(impact_assessment, TERM_ID)

hestia_earth/models/linkedImpactAssessment/utils.py

@@ -1,10 +1,11 @@
-from hestia_earth.utils.tools import non_empty_list
+from functools import reduce
+from hestia_earth.utils.tools import non_empty_list, flatten, list_sum
 
-from hestia_earth.models.log import debugValues, logRequirements, logShouldRun
-from hestia_earth.models.utils import sum_values
+from hestia_earth.models.log import log_as_table, logRequirements, logShouldRun
+from hestia_earth.models.utils import sum_values, _include
 from hestia_earth.models.utils.indicator import _new_indicator
 from hestia_earth.models.utils.impact_assessment import get_product, convert_value_from_cycle
-from hestia_earth.models.utils.input import sum_input_impacts
+from hestia_earth.models.utils.input import load_impacts
 from . import MODEL
 
 
@@ -14,17 +15,72 @@ def _indicator(term_id: str, value: float):
     return indicator
 
 
+def _run_indicators(product: dict, term_id: str):
+    def run(values: list):
+        indicator = values[0].get('indicator')
+        values_from_cycle = non_empty_list([
+            list_sum(value.get('input').get('value')) * value.get('indicator').get('value')
+            for value in values
+        ])
+        value = convert_value_from_cycle(product, sum_values(values_from_cycle), model=MODEL, term_id=term_id)
+        return _indicator(term_id, value) | _include(indicator, ['landCover', 'previousLandCover'])
+    return run
+
+
+def _group_indicator(group: dict, value: dict):
+    group_key = ';'.join(non_empty_list([
+        value.get('indicator').get('landCover', {}).get('@id'),
+        value.get('indicator').get('previousLandCover', {}).get('@id')
+    ]))
+    group[group_key] = group.get(group_key, []) + [value]
+    return group
+
+
 def _run_inputs_production(impact_assessment: dict, product: dict, term_id: str):
     cycle = impact_assessment.get('cycle', {})
-    values_from_cycle = non_empty_list([
-        sum_input_impacts(cycle.get('inputs', []), term_id),
-        sum_input_impacts(cycle.get('inputs', []), term_id.replace('InputsProduction', 'DuringCycle'))
+
+    # group all indicators per `landCover` and `previousLandCover`
+    all_indicators = flatten([
+        {
+            'indicator': indicator,
+            'input': input
+        }
+        for input in load_impacts(cycle.get('inputs', []))
+        for indicator in (
+            input.get('impactAssessment', {}).get('emissionsResourceUse', []) +
+            input.get('impactAssessment', {}).get('impacts', [])
+        )
+        if indicator.get('term', {}).get('@id') in [
+            term_id,
+            term_id.replace('InputsProduction', 'DuringCycle')
+        ]
     ])
-    value = convert_value_from_cycle(product, sum_values(values_from_cycle), model=MODEL, term_id=term_id)
-    debugValues(impact_assessment, model=MODEL, term=term_id,
-                has_values_from_cycle=len(values_from_cycle) > 0)
-    logShouldRun(impact_assessment, MODEL, term_id, value is not None)
-    return [] if value is None else [_indicator(term_id, value)]
+    valid_indicators = [
+        value
+        for value in all_indicators
+        if all([
+            value.get('indicator').get('value', -1) > 0,
+            list_sum(value.get('input').get('value', [-1]), 0) > 0
+        ])
+    ]
+    grouped_indicators = reduce(_group_indicator, valid_indicators, {})
+    has_indicators = bool(valid_indicators)
+
+    logRequirements(impact_assessment, model=MODEL, term=term_id,
+                    indicators=log_as_table([
+                        {
+                            'indicator-id': value.get('indicator').get('term', {}).get('@id'),
+                            'indicator-value': value.get('indicator').get('value'),
+                            'input-id': value.get('input').get('term', {}).get('@id'),
+                            'input-value': list_sum(value.get('input').get('value')),
+                        }
+                        for value in all_indicators
+                    ]))
+
+    should_run = all([has_indicators])
+    logShouldRun(impact_assessment, MODEL, term_id, should_run)
+
+    return flatten(map(_run_indicators(product, term_id), grouped_indicators.values()))
 
 
 def _should_run_inputs_production(impact_assessment: dict, term_id: str):
@@ -35,6 +91,7 @@ def _should_run_inputs_production(impact_assessment: dict, term_id: str):
                     product=product_id)
 
     should_run = all([product])
+    logShouldRun(impact_assessment, MODEL, term_id, should_run)
     return should_run, product