Design a bioelectrochemical resource-recovery system
Start with a wastewater stream. Get a ranked design from the lab catalog via the 5-physics-family router, open its dossier and P&ID sheet, and see a real ML prediction with its interval and an OOD flag. Every number traces to a source artifact or is stated as a baseline assumption.
- /api/ml/predict — 15-block response
- holdout-coverage-2026-05-21.json — 940 OOS obs
- calibration.json — random split, not paper-disjoint (when generated)
- wastewater/*-baseline.json — 6 process-TEAs
- @messai/component-catalog — 6 lab-catalog twins
- @messai/pid-schematic — ISA-5.1 sheets per twin
Section 1 · Influent characterisation
Define the wastewater stream
Six industrial archetypes or set parameters within their literature ranges. Each slider shows hard bounds, typical band, sub-ranges by facility type, and the active preset's target value.
Section 2 · System suggestion · lab catalog designs
Pick a coupled architecture
Ranked by influent fit using the 5-physics-family router. Every card is a digital twin from the lab catalog; click one to drive every downstream panel.
Section 2b · System dossier · from the lab catalog
MFC + Anaerobic Digester (electricity from wastewater)
The Bio-Battery Train
A two-stage flowsheet that pairs an anaerobic digester (for bulk COD reduction + biogas recovery) with a downstream microbial fuel cell that polishes residual COD into direct electrical current. The AD does the thermodynamic heavy lifting; the MFC monetises what’s left as electrons rather than gas, with no biogas-handling burden on the back end.
Key differentiator
AD alone leaves 25–50 % of the influent COD behind in the digestate. An MFC polish step recovers a portion of that residual COD as electricity at electrode-surface efficiencies that exceed dark-fermentation H2 routes. The full-flowsheet TEA is meant to take the parameter-sweep page’s Butler-Volmer + Monod outputs; that link is not wired yet, so the baseline uses literature midpoints.
How it works
Influent enters the AD; biogas exits the dome to CHP; digestate flows by gravity into the MFC anode chamber where exoelectrogens (Geobacter / mixed consortia) attach to a carbon-cloth or graphite-felt anode. Substrate oxidation releases electrons that travel through an external circuit to an air cathode (typical) and protons migrate through a separator. Power is dumped to a buck-boost charger that conditions the MFC output to grid-tie or battery voltage.
Performance envelope
Research status
MFCs remain at TRL 4–5 outside niche sensor applications. The MFC+AD combination is published, but no pilot plants are continuously operated. Active research: scaling anode area while preserving CE, cheaper cathode catalysts, hybrid AD-MFC operating strategies.
Key parameters
Reactor geometry
Left: cylindrical AD tank (see "wastewater-ad" for sizing). Right: rectangular MFC chamber with planar anode (left wall) and air cathode (right wall, typically Pt/C on carbon cloth or activated-carbon-on-stainless-mesh). Top: external circuit with adjustable load resistor; LED indicator on the wire visualises current.
Applications
- Wastewater treatment with energy recovery (food / dairy / brewery effluents)
- Decentralised treatment at sites without grid access
- BOD sensors at WWTP outfalls (MFC voltage tracks BOD)
- Educational / public-engagement reactors
- Combined heat (AD biogas) + power (MFC) micro-grids
Scale
Pilotscale
TRL
4–5
Active volume
0.5 – 50 m³ MFC stack downstream of a 10 000 m³ AD
Loading 3D reactor scene…
Section 4 · Live prediction · /api/ml/predict
Live ML prediction
Typical error on the paper-disjoint benchmark (bes-benchmark-v1) is about 0.8 orders of magnitude (×6) for power density, so the bands are wide by design. Assumed operating point, not yet an input: 100 Ω external load, Nafion 117 membrane, Pt/C cathode at the anode’s area.
Section 5 · Recovery balance
What this system actually recovers
Daily recovered products from a first-principles balance on the influent and the live prediction. Band widths are not to scale; values marked “—” lack the inputs to compute.
- · COD removal from the archetype baseline (60 %).
- · Biogas at the theoretical (Buswell) CH₄ yield — an upper bound.
- · Electrode electricity: insufficient inputs (no power prediction).
Section 7 · Design recommendations
No change the corpus can vouch for yet
Each card is a fitted corpus effect with its n and 95 % CI. A change counts as recommended only when the CI’s lower bound clears a 5 % gain; the rest are shown as candidates whose direction the corpus hasn’t established. Stage one to see it as a ghost overlay in 3D.
live prediction unavailable — lifts shown as relative % only
Section 7b · Raise confidence
33 evidence gaps for MFC + Anaerobic Digestion
Each row is a design lever the corpus cannot yet quantify with high confidence, the study that would close it, and the literature search that looks for it.
- external resistance → power density128 papers · cross-paper · effect not distinguishable from zero · lowSuggested study: vary external resistance; hold temperature, pH, HRT, COD_in, anode material fixed; measure power density + coulombic efficiency; ≥ 3 conditions per study.openalex: external resistance "microbial fuel cell" power density
- pH → power density110 papers · cross-paper · effect not distinguishable from zero · lowSuggested study: vary anolyte pH; hold temperature, HRT, COD_in, R_ext, anode material fixed; measure power density + coulombic efficiency; ≥ 3 conditions per study.openalex: anolyte pH "microbial fuel cell" power density
- temperature → COD removal108 papers · cross-paper · effect not distinguishable from zero · mediumSuggested study: vary reactor temperature; hold pH, HRT, COD_in, R_ext, anode material fixed; measure COD removal + coulombic efficiency; ≥ 3 conditions per study.openalex: reactor temperature "microbial fuel cell" COD removal
- pH → COD removal105 papers · cross-paper · effect not distinguishable from zero · lowSuggested study: vary anolyte pH; hold temperature, HRT, COD_in, R_ext, anode material fixed; measure COD removal + coulombic efficiency; ≥ 3 conditions per study.openalex: anolyte pH "microbial fuel cell" COD removal
- influent COD → COD removal94 papers · cross-paper · effect not distinguishable from zero · lowSuggested study: vary influent COD concentration; hold temperature, pH, HRT, R_ext, anode material fixed; measure COD removal + coulombic efficiency; ≥ 3 conditions per study.openalex: influent COD concentration "microbial fuel cell" COD removal
- influent COD → coulombic efficiency62 papers · cross-paper · effect not distinguishable from zero · lowSuggested study: vary influent COD concentration; hold temperature, pH, HRT, R_ext, anode material fixed; measure coulombic efficiency + power density; ≥ 3 conditions per study.openalex: influent COD concentration "microbial fuel cell" coulombic efficiency
Section 7c · What to measure
Measurement plan for MFC + Anaerobic Digestion
Ranked from 263 MFC papers that report a recovery target: levers a study should vary, the context variables the corpus expects alongside them, and the outcomes to report. Coverage and correlation are descriptive; only the effect column is a fitted causal-grade estimate.
| parameter | role | reported in | fitted effect | gaps it closes | ρ vs targetpooled |
|---|---|---|---|---|---|
| anode material | lever | 0% · 0 | +0.017 → power density · low · n=5 | 64 · hold in 64 | — |
| hydraulic retention timeh | lever | 12% · 31 | −0.029 → COD removal · low · n=43 | 15 · hold in 113 | -0.25 (11) |
| pH | lever | 34% · 88 | −0.086 → ammonium removal · medium · n=10 | 14 · hold in 114 | +0.55 (15) |
| temperature°C | lever | 22% · 59 | +0.0087 → COD removal · medium · n=108 | 14 · hold in 114 | -0.25 (103) |
| COD Concentrationmg/L | lever | 33% · 87 | +4.6e-7 → COD removal · low · n=94 | 13 · hold in 115 | +0.43 (69) |
| External LoadΩ | lever | 29% · 75 | −0.0000037 → coulombic efficiency · medium · n=60 | 8 · hold in 120 | +0.78 (8) |
| Power DensitymW/cm² | covariate | 54% · 141 | — | — | +0.74 (30) |
| voltageV | covariate | 43% · 114 | — | — | +0.48 (13) |
| Open Circuit VoltageV | covariate | 35% · 91 | — | — | -0.45 (10) |
| Current DensitymA/cm² | covariate | 34% · 88 | — | — | +0.56 (26) |
| Reactor VolumemL | covariate | 32% · 83 | — | — | -0.20 (73) |
| Internal ResistanceΩ | covariate | 30% · 78 | — | — | -0.71 (12) |
| Cod Removal% | outcome | 83% · 219 | — | — | — |
| coulombic efficiency% | outcome | 44% · 116 | — | — | — |
| Ammonium-N Removed% | outcome | 8% · 21 | — | — | — |
| Phosphorus Removal% | outcome | 4% · 11 | — | — | — |
source: apps/web/public/data/computed/research/measure-priorities.json · 2026-10-07
Section 8 · Sensitivity ladder
Which knob moves the needle
Corpus effects from within-paper-effects.json, for this archetype. Within-paper fits partial out paper-level confounds; cross-paper fits don’t, and are labelled. Green raises, red lowers the target — but only where the 95 % CI excludes zero; grey bars are directions the corpus hasn’t established. β units differ by knob (per °C, per pH, per hour, per level), so compare signs and intervals, not bar lengths.
Mechanistic closure · direction-validated levers
Does the physics closure predict the direction (sign) of a within-design change better than a coin flip (50 %)? Only where the 95 % interval stays above 50 % — so far, substrate → power, narrowly. Direction agreement only, not magnitude.
Not shown: current↔substrate and current↔pH are anti-skillful (the closure predicts the wrong direction), so we exclude them rather than surface a misleading bar. The richer interactive version lives at /lab/design.
Section 9 · Calibration · honest caveats
What this model is — and isn't — calibrated for
⚠ Conformal coverage guarantee is provisional
The split-conformal q̂ were calibrated against holdout-priors-2026-05-21, but the served predictor is v2-sota-2026-05-15. The interval math (log-space + physical clamp) is correct, but the marginal-coverage guarantee holds only once the constants are regenerated against the served fit. Every /api/ml/predict response carries this same version_check.ok = false.
What we don't claim
- •MDC, MES, MNRC, MMRC, MBES are not in the held-out coverage check — analytical predictors only.
- •TEA numbers are straight-line literature midpoints, not a contracted quote; site engineering adds cost on top.
- •COD removal predictions are coarse for high-strength industrial streams with toxic shocks.
- •No predictions of micropollutant removal, antibiotic resistance, or pathogen fate.
- •Long-term biofouling, electrode degradation > 12 months are absent from the corpus.
Section 10 · Mini-TEA · MFC + Anaerobic Digestion
What it costs
From the archetype's Process-TEA baseline. Discount rate 0.1, lifetime 15 yr. Honest disclaimer: literature midpoints, not a contracted quote.
- · Electrode capex $1,200/m² (carbon-cloth, Logan 2008 inflated).
- · Performance inputs are stub literature midpoints — wire to a sweep export for real numbers.
- · Higher 10 % discount rate reflects MFC scale-up risk (Santoro 2017).
Section 11 · For industrial partners · your stream in, value out
What your stream could become
Pick the row that matches what you discharge or emit. Each wastewater row is a modeled system with a published baseline and selects that design above; each prediction comes with an interval and an honest flag when your stream sits outside the data we have.
| Your input | System | What comes out | Notes |
|---|---|---|---|
MFC + anaerobic digestion The Bio-Battery Train · TRL 4–5 | waterelectricitybiogas | Brewery, dairy, food processing. MFC is the most data-rich system class in the corpus. | |
MEC + anaerobic digestion The Hydrogen Train · TRL 3–4 | waterH₂biogas | 0.6 V applied; hydrogen instead of power. Corpus evidence for MEC H₂ is thin (2 papers with a specific H₂ production). | |
MFC + struvite side-stream The Phosphorus Mine · TRL 8–9 | waterelectricitystruvite (P) | MgCl₂ dosing; 90% P recovery in the baseline model (a 200 mg P/L centrate). | |
MFC + NH₃ stripping The Ammonia Stripper · TRL 8–9 | waterelectricityNH₃ (N) | N-fertilizer feedstock; 80% N recovery in the baseline model (a 600 mg N/L stream). | |
MFC + electrochemical polishing The Color Eater · TRL 7–8 | waterelectricitymetals | Mining, plating, electronics effluent. Electrocoagulation removes metals into the floc sludge — removal, not recovery. | |
Conventional activated sludge The Industry Workhorse · TRL 9 | water only | The incumbent baseline every case is priced against. | |
| Ambient air ↗ | Bipolar-membrane electrodialysis DAC | CO₂ streamcompressed CO₂ | Presets at 0.15 t/yr bench, 1 kt/yr pilot, 100 kt/yr commercial. Same core, different inlet. |
| Mine ventilation methane ↗ | Methanotrophic biofilter | CH₄ oxidized | Early model, not yet calibrated. Ask if relevant. |
What a feasibility study looks like
Six to eight weeks from stream data to a screening-grade answer with its uncertainty stated. The output is not a brochure; it is the number, its interval, the plant economics, and the one or two bench measurements that would move the answer most.
Weeks 1–2
Characterize
You share flow, COD, N, P, metals, temperature, and what you pay today. We map it to the corpus and flag where your stream is outside the data.
Weeks 2–4
Route and predict
The stream is routed to the right physics family and archetype. Each prediction comes with its interval and an out-of-distribution flag.
Weeks 4–6
Price it
CAPEX, OPEX, levelized cost or net present value over the plant life (15 years for MES trains, 25 for activated sludge), against your incumbent. Assumptions are listed in each baseline’s notes.
Weeks 6–8
Name the test
A ranked measurement plan: the one or two bench measurements that would move the answer most, with the variance each one explains.
What we will tell you before you ask
- Waste-to-value predictions are strongest for MFC systems, where held-out coverage was measured. Sparse archetypes carry a visible out-of-distribution flag in the prediction strip above.
- Recovery fractions in the balance are baseline-model constants, not measurements of your stream: 90% P as struvite and 80% N as NH₃ until a partner sample replaces them.
- Cost inputs are labeled literature or assumed, line by line in the mini-TEA. A partner quote replaces an assumption with a fact.
- The DAC and mine-methane models have not been calibrated against a running plant. They are listed so you know they exist, and they say so on their own pages.
Partners are the calibration. The first studies are priced accordingly.
Start with one stream
Send a flow rate and a lab sheet. Within a week you get a routed archetype, a first interval, and a scope for the study.