Make sense of your farm records
PFD is TPS’s aquaculture production-data analysis platform. It compares fish numbers, growth and feed records to highlight potential stock discrepancies.
Request a Free One-Cage Analysis
No subscription commitment or mandatory sales call.
Three practical outcomes
Identify potential missing fish
Investigate whether recorded fish numbers fit biological performance.
Validate growth and feeding performance
Review sample weights, biological FCR, feed and mortality together.
Improve farm decisions
Prioritise sampling, record reconciliation and production-planning checks.
How it works
Share the question and one cage’s records.
Check data quality and model suitability.
Compare biological signals and alternative explanations.
Validate estimates with separate farm evidence.
What you need
Stocking numbers and weights, dated weight samples, feed and mortality records. Temperature, transfers and harvests add context. Models described here cover sea bream, sea bass and tilapia; suitability must be assessed for your farm.
Aquaculture AI, with human review
PFD Wingman uses artificial intelligence to explain unusual patterns, possible causes and uncertainty. Review its interpretation alongside the calculations and farm observations.
Important limits
PFD estimates discrepancies; it does not directly count fish. Sampling, recording errors, environment, health and model assumptions can affect results. Model agreement or AI interpretation does not prove losses. Independently validate estimates before changing official stock figures.
Explore the supporting modules below, or ask us about your farm’s requirements.
Explore PFD tools
29 supporting modules, organised around six farm tasks. Open a category for details.
Check stock recordsImports, data quality and fish movements
- Production Data Uploader
- Ingests full production history to reconstruct the cycle: starting/closing biomass, mortality biomass, reported/model/adjusted FCR, and estimated missing fish.
- Data Quality Intelligence
- Checks for missing feed/mortality/harvest events, duplicates, impossible biomass changes and stale samples.
- Merged Population Handling
- Handles transferred, combined, partially harvested or topped-up populations with lineage tracking.
- Open- and Closed-Cage Analysis
- Open cage: review current signals and verification needs. Closed cage: reconcile recorded outcomes and assess what can be learned for the next cycle.
Understand growthSamples, growth curves and biological models
- Growth vs Model
- Compares actual growth against expected biological trajectory (direction, magnitude, persistence, timing).
- Actual Growth Reconstruction
- Reconstructs the likely growth path between physical samples and re-anchors on each new one.
- Incorrect / Suspect Sample Detection
- Flags samples inconsistent with trajectory, subsequent samples, feed, mortality and harvest.
- SGR / Growth Performance
- Gives SGR equal weight to FCR — fewer production turns is a hidden economic cost.
- Temperature-Driven Biological Models
- Daily temperature feeds SGR calculations. Regional profiles installed; farms can upload custom thermal models.
- Species-Specific Models
- Separate biological modelling for sea bream, sea bass and tilapia (user-model architecture supports expansion).
- User-Uploaded Biological Models
- Farms can move beyond generic industry curves and use their own biological assumptions.
Review feeding & planningFCR, feeding patterns and forecasts
- FCR Intelligence
- Reported biological FCR vs model vs adjusted FCR — interpreted alongside SGR, growth and feeding history.
- Relative Feeding Index
- Feed delivered vs model expectations, distinguishing daily vs cumulative feeding behaviour.
- Misfeeding & No-Feed Day Analysis
- Examines the timing and duration of feed restriction alongside growth and feeding records. Effects depend on life stage, conditions and subsequent compensatory growth.
- Growth Prognosis
- Extends corrected biological assumptions forward for harvest timing, biomass and feed requirement.
- SFR Calculator
- Rapid Specific Feeding Rate calculator for operational feed sizing.
Assess the evidenceDiscrepancy signals, uncertainty and validation
- Multi-Signal Biological Reconciliation
- Combines fish numbers, feed, growth, FCR, mortality and environment. Agreement across indicators can strengthen an investigation, but indicators sharing growth, feed or stock inputs are not independent validation. No single metric establishes fish loss.
- Loss Window Estimation
- Highlights a possible discrepancy interval for comparison with storms, transfers, treatments or oxygen events. Timing and cause remain provisional until supported by separate evidence.
- Model Sensitivity Testing
- Tests alternative growth assumptions to assess how model suitability affects a stock estimate. Sensitivity testing alone cannot establish which explanation is correct.
- Confidence-Based Decision States
- Organises evidence into MONITOR_ONLY / VALIDATION_REQUIRED / ACTIONABLE states. These are decision-support indicators, not calibrated probabilities or independent confirmation; review the underlying evidence before action.
- Harvest Reconciliation
- Compares earlier estimates with final recovery records. Validation requires reliable, separately obtained counts and reconciliation of movements and mortality; agreement is not guaranteed.
- Pre-Harvest Risk Analysis
- Increases emphasis on discrepancy signals as cages approach market size.
Compare & reportCage overviews, benchmarking and reports
- Snapshot Analysis
- Rapid-entry biological reasonableness check for triaging cages before uploading full history.
- Live Cage KPI Overview
- Multi-cage triage layer showing biomass, RFI, FCR gaps, missing-fish estimate and sample recency at a glance.
- Historical Like-for-Like Benchmarking
- Compares against comparable historical cycles (species, hatchery, month, initial weight, site) rather than generic industry norms.
- Summary & Full Reports
- Exportable reports for communicating findings to managers, veterinarians and owners.
Interpret & integrateAI explanations and existing farm systems
- PFD Wingman AI
- Explains what appears abnormal, what may explain it, what evidence supports each option and what remains uncertain; explanations should be checked against source records and reviewed by the farm team.
- No New Farm Hardware Required
- Core analysis uses production data farms already collect — no cameras, sonar or dedicated cage hardware.
- Complements Rather Than Replaces Hardware
- Sits alongside biomass cameras, feeders and health-monitoring tools, identifying inconsistencies each system alone can miss.
Illustrative AI-generated placeholder — replace with your farm photograph.