AI MODELS

Summit.OS ships with eleven production-ready ONNX models custom-built and trained by BigMT.ai — domain-expert feature engineering, purpose-built training pipelines, and real-world public datasets blended with scenario-specific synthetic data. They run entirely on your hardware — no cloud, no API calls, no data leaves your network.

[✓]

ZERO DATA COLLECTION

If you download and run this repo, no data is sent anywhere. Summit.OS has no telemetry, no analytics, no crash reporting, no ping-home behavior of any kind. Your sensor feeds, entity tracks, operator decisions, and mission history never leave your deployment.

The only optional outbound network calls are the three external feeds listed in the External API Calls section below — all disabled by default and opt-in via environment variable.

VISUAL DETECTOR

Real-time object detection from drone cameras, CCTV feeds, and satellite imagery. YOLOv8-architecture ONNX model with 18 mission-critical detection classes.

summit_detector.onnx

YOLOv8n-based · 640×640 input · 18 detection classes · <15ms inference on CPU

00smoke
01fire
02fire_front
03person
04person_water
05life_raft
06oil_spill
07pipeline_damage
08chemical_plume
09crop_disease
10pest_damage
11dry_field
12vessel
13vessel_distress
14power_line_damage
15structural_crack
16solar_defect
17dangerous_animal

ALL 11 MODELS

All eleven models were designed, trained, and exported by BigMT.ai — not fine-tuned from third-party checkpoints. Training scripts live in packages/ml/ and are fully open. Every model ships as ONNX — no PyTorch, no GPU required at runtime.

// mission planning

MISSION CLASSIFIER

mission_classifier.onnx  ·  HistGradientBoosting · sklearn → ONNX

Given a detected event (class + coordinates + risk level), predicts the optimal mission type to dispatch. Feeds the tasking engine to auto-generate missions from sensor detections. Supports progressive fine-tuning from real operator-approved mission history.

outputs
SURVEY MONITOR SEARCH PERIMETER ORBIT DELIVER INSPECT
// threat assessment

RISK SCORER

risk_scorer.onnx  ·  HistGradientBoosting · sklearn → ONNX

Assigns a threat level to any detected event based on class, confidence, location context, and environmental factors. Drives alert severity and PENDING_APPROVAL gating for high-stakes missions.

outputs
LOW MEDIUM HIGH CRITICAL
// alert quality

FALSE POSITIVE FILTER

false_positive_filter.onnx

Binary classifier that suppresses noisy detections before they reach the operator alert queue. Trained on historical confirmed vs. discarded alert patterns. Reduces operator alert fatigue.

outputs
CONFIRMED FALSE_POSITIVE
// alert triage

ESCALATION PREDICTOR

escalation_predictor.onnx

Predicts whether an active alert will escalate in severity within the next observation window. Used to pre-position assets and alert commanders before a situation worsens.

outputs
STABLE ESCALATING CRITICAL_ESCALATION
// pattern recognition

INCIDENT CORRELATOR

incident_correlator.onnx

Groups spatially and temporally related alerts into unified incidents. Prevents operators from being flooded with duplicate alerts for the same underlying event (e.g., fire spread across multiple sensor zones).

outputs
CLUSTER_ID CORRELATION_SCORE
// mission intelligence

OUTCOME PREDICTOR

outcome_predictor.onnx

Estimates the probability of mission success before launch. Considers asset capabilities, environmental conditions, mission type, and target characteristics. Informs human-in-the-loop DISPATCH decisions.

outputs
SUCCESS_PROBABILITY RECOMMENDED / CAUTION / ABORT
// resource optimization

ASSET ASSIGNMENT

asset_assignment.onnx

Optimal asset-to-mission matching. Given available assets (drones, ground units, sensors) and pending missions, scores each pairing and surfaces the best allocation. Accounts for proximity, fuel, payload, and capability.

outputs
ASSIGNMENT_SCORE RANKED_ASSET_LIST
// anomaly detection

SEQUENCE ANOMALY

sequence_anomaly.onnx  ·  LSTM · PyTorch → ONNX

LSTM-based model that detects anomalous entity behavior in time-series tracks. Flags unusual movement patterns, loitering, erratic flight paths, or unexpected sensor dropouts that rule-based filters miss.

outputs
NORMAL ANOMALY ANOMALY_SCORE
// environmental risk

WEATHER RISK SCORER

weather_risk_scorer.onnx

Assesses operational risk from weather conditions: wind speed, precipitation, visibility, temperature, and lightning proximity. Used to auto-hold missions when conditions exceed safe operating thresholds.

outputs
GO MARGINAL NO_GO RISK_SCORE
// visual intelligence

RE-ID EMBEDDER

reid_embedder.onnx  ·  custom CNN · Colab notebook

Generates 128-dimensional visual embeddings for detected objects. Enables cross-camera entity re-identification — track a person or vehicle as they move between non-overlapping camera fields of view.

outputs
128-DIM EMBEDDING VECTOR
// flagship · visual detection

SUMMIT DETECTOR

summit_detector.onnx  ·  YOLOv8n · custom trained · Colab notebook

YOLOv8-based visual detector with 18 mission-critical classes. See full class list above. Primary inference engine for video feeds from drones, CCTV, and aerial imagery. Runs at real-time frame rates on CPU.

outputs
BBOX CLASS CONFIDENCE

TRAINING DATA

BigMT.ai built custom training pipelines and domain-expert synthetic data generators covering 10+ operational domains — wildfire, search & rescue, maritime, infrastructure, agriculture, hazmat, and more. Public real-world datasets were downloaded, preprocessed, and blended with scenario-specific synthetic samples to cover edge cases and low-frequency events. No proprietary data, no user data, no scraped content.

NASA FIRMS

Active Fire Detections

Global wildfire and fire front detections updated every 10 minutes from MODIS and VIIRS satellite instruments. Primary source for smoke/fire/fire_front training samples.

NOAA Storm Events

Severe Weather 1950–Present

1.5M+ severe weather records including floods, tornadoes, hurricanes, and hail. Primary source for weather risk and escalation predictor training.

PHMSA

Pipeline & Hazmat Incidents

Pipeline failure and hazardous materials incident reports from 2010–present. Source for pipeline_damage, oil_spill, and chemical_plume detection labels.

GBIF

Wildlife Occurrences

Global Biodiversity Information Facility — 2B+ wildlife occurrence observations. Used for dangerous_animal and wildlife-related detection class training.

USGS

Earthquake Catalog M2.5+

Real-time global earthquake feed. Used for structural risk scoring and incident correlation training data for ground movement events.

NASA EONET

Natural Events

Earth Observatory Natural Event Tracker — volcanoes, floods, wildfires, landslides, dust storms, and sea/lake ice events with georeferenced coordinates.

iNaturalist

100M+ Observations

Crowd-sourced wildlife observations including threatened and endangered species. Supplementary source for ecological detection classes and rare event distributions.

OpenAQ

Air Quality Readings

Global air quality monitoring data used as a proxy for fire smoke concentration and chemical plume dispersion during training.

GDACS

Global Disaster Alerts

Global Disaster Alert and Coordination System — earthquakes, cyclones, floods, volcanoes, and tsunamis with severity scoring. Used for risk scorer calibration.

ReliefWeb

Humanitarian Crisis Events

UN OCHA humanitarian reporting database — floods, earthquakes, epidemics, conflicts. Used for high-level incident type classification training.

Synthetic

Edge Case Generation

Low-frequency scenarios (e.g., simultaneous multi-hazard events, extreme sensor noise) generated via generate_data.py to ensure model robustness at the margins.

EXTERNAL API CALLS

Summit.OS makes no outbound calls by default. The following are opt-in integrations, all disabled unless you set the corresponding env var. None of these calls send your operational data — they only pull in public reference feeds.

Service What it does Enabled by What's sent
OpenSky
OPTIONAL
Live ADS-B aircraft positions for the spatial intelligence overlay OPENSKY_ENABLED=true Your bounding box coordinates (or nothing for worldwide). No entity data sent outbound.
CelesTrak
OPTIONAL
TLE orbital elements for satellite position propagation on the 3D globe CELESTRAK_ENABLED=true HTTP GET request for TLE data file only. No user data sent.
MaxMind
OPTIONAL
GeoIP database auto-update for geoblocking enforcement MAXMIND_LICENSE_KEY= set Authenticated download of GeoLite2-Country.mmdb. No user IP addresses sent.
YubiCloud
OPTIONAL
OTP validation for YubiKey hardware authentication (Yubico OTP protocol) YUBICO_CLIENT_ID= set YubiKey OTP token sent to Yubico's validation servers. No user data. Can be replaced with self-hosted YK-VAL server.
Infisical / Vault
OPTIONAL
Secrets management backend for production deployments INFISICAL_TOKEN= or VAULT_ADDR= set Secret key names only — no operational data, no user data.
S3
OPTIONAL
Audit log shipping for SOC2 compliance retention AWS_AUDIT_BUCKET= set Append-only audit log entries (operator actions, auth events). Only your own bucket — Anthropic/BigMT never receives this data.

RETRAIN WITH YOUR DATA

All training scripts are open source in packages/ml/. Fine-tune any model on your own operator history for higher accuracy in your specific environment.

COLLECT OPERATOR FEEDBACK

Every alert confirm/discard and mission outcome is logged to the audit trail in NDJSON format. Export your deployment's history or label new samples using your own sensor data.

DOWNLOAD PUBLIC DATA (OPTIONAL)

Run the public data downloader to augment your dataset with fresh global event data.

cd packages/ml && python download_real_data.py

TRAIN THE MODEL

Each model has its own training script. Example for the risk scorer:

python train_risk_scorer.py

Visual detector and re-ID embedder training are Colab notebooks (GPU recommended):

packages/ml/colab/colab_visual_detector.ipynb
packages/ml/colab/colab_reid_embedder.ipynb

DROP IN THE NEW MODEL

Replace the corresponding .onnx file in packages/ml/models/ and restart the intelligence service. No code changes required — all services load models from the path in PLANNER_MODEL_PATH or the default models directory.

docker compose restart intelligence
# Run all tabular model training scripts in sequence
for script in train_risk_scorer train_mission_classifier train_false_positive_filter \
              train_escalation_predictor train_incident_correlator train_outcome_predictor \
              train_asset_assignment train_sequence_anomaly train_weather_risk_scorer; do
  echo "=== Training $script ==="
  python packages/ml/${script}.py
done