LIVEdataset aec-bench@releasetasks 552models 18last submission … · built …
civilboth

Pollutant Load Estimate

Estimates annual Total Suspended Solids (TSS), Total Phosphorus (TP), and Total Nitrogen (TN) pollutant loads from urban catchments using the Event Mean Concentration (EMC) method. Computes annual runoff volume as V = C*P*A*10 and multiplies by EMC values per MUSIC guidelines and Australian Runoff Quality to support water-sensitive urban design.

both: The model must reason numerically unaided.

Standards

Australian Runoff Quality (ARQ)MUSIC guidelines

Tags

EMCTSScivilnitrogenphosphoruspollutantstormwaterwater-quality

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

  1. 01

    Template

    The reusable contract shown on this page.

  2. 02

    Scenario

    An archetype and site context are sampled.

  3. 03

    Difficulty tier

    Inputs may be hidden at harder tiers.

  4. 04

    Task prompt

    The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

6 inputs

Always given

Included directly in every task prompt.

1

  • Catchment area

    catchment_area_ha

    Contributing catchment area A

    0.5 – 500 ha

Derived from scenario

Sampled from the scenario and inferable from its description.

5

  • Annual rainfall

    annual_rainfall_mm

    Mean annual rainfall P

    Derived from the archetype scenario.

    200 – 3000 mm

  • Runoff coefficient

    runoff_coefficient

    Volumetric runoff coefficient C (fraction of rainfall that becomes runoff)

    Derived from the archetype scenario.

    0.05 – 0.95

  • Emc tss

    emc_tss_mg_l

    Event mean concentration of Total Suspended Solids

    Derived from the archetype scenario. Hidden at hard difficulty.

    10 – 400 mg/L

  • Emc tp

    emc_tp_mg_l

    Event mean concentration of Total Phosphorus

    Derived from the archetype scenario. Hidden at hard difficulty.

    0.05 – 1 mg/L

  • Emc tn

    emc_tn_mg_l

    Event mean concentration of Total Nitrogen

    Derived from the archetype scenario. Hidden at hard difficulty.

    0.3 – 5 mg/L

Scored outputs

4 outputs

Annual runoff volume m3

annual_runoff_volume_m3

Annual runoff volume V (m³/yr)

Scores if within ±3% of the reference value.

Tss load kg yr

tss_load_kg_yr

Annual Total Suspended Solids load (kg/yr)

Scores if within ±3% of the reference value.

Tp load kg yr

tp_load_kg_yr

Annual Total Phosphorus load (kg/yr)

Scores if within ±3% of the reference value.

Tn load kg yr

tn_load_kg_yr

Annual Total Nitrogen load (kg/yr)

Scores if within ±3% of the reference value.

Difficulty

Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.

easy

All inputs given

All parameters given directly — straightforward EMC load calculation

medium

All inputs given

All parameters given but industrial or commercial land use with higher EMC values — agent must handle larger numbers carefully

hard

Some inputs hidden

EMC values hidden — agent must infer typical concentrations from land use type and site description

Hidden inputs

  • Emc tss mg lemc_tss_mg_l
  • Emc tp mg lemc_tp_mg_l
  • Emc tn mg lemc_tn_mg_l

Prompt replacement text

The catchment is a {{ archetype.description }} ({{ archetype.site_context }})

Task bundle

The exact instruction and parameter contract used to generate this task, pinned to the published library source.

/workspace

  • instruction.md

Teal lines show Jinja input conditions, not task visibility policy. A line renders only when that input or tool is visible.

1You are a senior civil engineer specializing in stormwater quality management and WSUD (Water Sensitive Urban Design).2 3## Problem4 5Estimate the annual pollutant loads from a catchment using the Event Mean Concentration (EMC) method, consistent with MUSIC modelling guidelines.6 7## Given8 9| Parameter | Value | Unit |10|-----------|-------|------|11| Catchment area (A) | {{ catchment_area_ha }} | ha |12| Mean annual rainfall (P) | {{ annual_rainfall_mm }} | mm |13| Runoff coefficient (C) | {{ runoff_coefficient }} | - |14{%- if emc_tss_mg_l is defined %}15| EMC — Total Suspended Solids | {{ emc_tss_mg_l }} | mg/L |16{%- endif %}17{%- if emc_tp_mg_l is defined %}18| EMC — Total Phosphorus | {{ emc_tp_mg_l }} | mg/L |19{%- endif %}20{%- if emc_tn_mg_l is defined %}21| EMC — Total Nitrogen | {{ emc_tn_mg_l }} | mg/L |22{%- endif %}23{% if archetype_description is defined %}24 25### Site Conditions26 27{{ archetype_description }}28{% endif %}29 30{% if tool_available %}31## Available Tool32 33A pollutant load calculation tool is available at `/workspace/{{ meta.name }}_calc.py`. Run it with:34 35```bash36python3 /workspace/{{ meta.name }}_calc.py --help37```38 39You may use this tool to verify your calculations or compute values directly.40{% endif %}41 42## Required43 44Calculate the following:45 461. Annual runoff volume V (m³/yr)472. Annual Total Suspended Solids load (kg/yr)483. Annual Total Phosphorus load (kg/yr)494. Annual Total Nitrogen load (kg/yr)50 51## Applicable Standards52 53- MUSIC (Model for Urban Stormwater Improvement Conceptualisation) guidelines54- Australian Runoff Quality (ARQ)55 56## Constraints57 58- No internet access is available. Work from engineering knowledge and the provided tool.59- Use the simple EMC method for pollutant load estimation:60 - **Annual runoff volume:** V = C × P × A × 10 (m³/yr)61 - C is the volumetric runoff coefficient (dimensionless, 0 to 1)62 - P is mean annual rainfall in mm63 - A is catchment area in ha64 - The factor 10 converts ha·mm to m³65 - **Pollutant load:** L = EMC × V / 1000 (kg/yr)66 - EMC is the event mean concentration in mg/L67 - V is the annual runoff volume in m³68 - The division by 1000 converts mg/L × m³ to kg69- Typical EMC values for Australian urban catchments (if not given directly):70 - Residential: TSS ≈ 150 mg/L, TP ≈ 0.35 mg/L, TN ≈ 2.0 mg/L71 - Commercial: TSS ≈ 170 mg/L, TP ≈ 0.40 mg/L, TN ≈ 2.5 mg/L72 - Industrial: TSS ≈ 200 mg/L, TP ≈ 0.45 mg/L, TN ≈ 3.0 mg/L73 - Parkland/open space: TSS ≈ 50 mg/L, TP ≈ 0.10 mg/L, TN ≈ 0.8 mg/L74 75## Output Format76 77Show your step-by-step working in Markdown, including formulas and intermediate calculations. At the end of your solution, include a JSON block with your final answers in exactly this format:78 79```json80{81 "annual_runoff_volume_m3": <numeric_value>,82 "tss_load_kg_yr": <numeric_value>,83 "tp_load_kg_yr": <numeric_value>,84 "tn_load_kg_yr": <numeric_value>85}86```87 88Write your complete solution to `/workspace/output.md`.89

Scenario archetypes

Each generated task is drawn from one of these realistic scenario bands.

Site contexts ground each scenario in a real locale the model can use to infer hidden values.

Residential suburb

residential_suburb

Residential suburban catchment with moderate impervious fraction and typical domestic pollutant sources

sydney-western-suburbsmelbourne-southeast-growthbrisbane-northern-suburbsperth-southern-corridor
Parameter ranges
catchment_area_ha
5 – 100
annual_rainfall_mm
600 – 1200
runoff_coefficient
0.4 – 0.7
emc_tss_mg_l
100 – 200
emc_tp_mg_l
0.25 – 0.45
emc_tn_mg_l
1.5 – 2.5

Commercial centre

commercial_centre

Commercial or mixed-use town centre with high impervious fraction and heavy traffic

sydney-cbd-fringemelbourne-docklandsbrisbane-fortitude-valleyadelaide-north-terrace
Parameter ranges
catchment_area_ha
1 – 50
annual_rainfall_mm
600 – 1400
runoff_coefficient
0.7 – 0.95
emc_tss_mg_l
120 – 250
emc_tp_mg_l
0.3 – 0.55
emc_tn_mg_l
2 – 3

Industrial estate

industrial_estate

Industrial estate with high impervious cover and elevated pollutant concentrations from warehousing and logistics

sydney-smithfield-industrialmelbourne-western-ringbrisbane-eagle-farmperth-kwinana-strip
Parameter ranges
catchment_area_ha
2 – 200
annual_rainfall_mm
400 – 1200
runoff_coefficient
0.6 – 0.9
emc_tss_mg_l
150 – 400
emc_tp_mg_l
0.35 – 0.65
emc_tn_mg_l
2 – 4

Parkland open space

parkland_open_space

Parkland or open space catchment with low impervious fraction and minimal pollutant sources

sydney-centennial-parkmelbourne-yarra-bendbrisbane-south-bankcanberra-lake-burley-griffin
Parameter ranges
catchment_area_ha
5 – 500
annual_rainfall_mm
400 – 2000
runoff_coefficient
0.05 – 0.3
emc_tss_mg_l
10 – 80
emc_tp_mg_l
0.05 – 0.15
emc_tn_mg_l
0.3 – 1.2

Example task

sydney-western-suburbs-residential-suburb-preview — hard difficulty, some inputs hidden.

Residential suburban catchment with moderate impervious fraction and typical domestic pollutant sources. sydney-western-suburbs. Required outputs: annual_runoff_volume_m3, tss_load_kg_yr, tp_load_kg_yr, tn_load_kg_yr

The model sees

Scenario context and visible inputs.

catchment_area_ha
5 to 100 ha
annual_rainfall_mm
600 to 1200 mm
runoff_coefficient
0.4 to 0.7 -

Executable tool: pollutant-load-estimate_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Emc tp mg l

    emc_tp_mg_l

  • Emc tss mg l

    emc_tss_mg_l

  • Emc tn mg l

    emc_tn_mg_l

Stand-in text in the prompt

The catchment is a {{ archetype.description }} ({{ archetype.site_context }})

The model must produce

The scored JSON answer schema.

{
  "annual_runoff_volume_m3": <number>,
  "tss_load_kg_yr": <number>,
  "tp_load_kg_yr": <number>,
  "tn_load_kg_yr": <number>
}
  • annual_runoff_volume_m3 · scored within ±3%
  • tss_load_kg_yr · scored within ±3%
  • tp_load_kg_yr · scored within ±3%
  • tn_load_kg_yr · scored within ±3%