NASA CSDA hosts OroraTech OT-NRT guide: 8-satellite onboard-AI wildfire product in closed beta

OroraTech (product guide hosted on NASA Science / CSDA) · Commercial wildfire satellite detection / civil Earth observation · Global product with North America among covered regions; vendor Germany/EU-based constellation ops

Emergency Services

Publisher: NASA Science (CSDA vendor materials) / OroraTech Product User Guide
Original publication: 2026-09-02
Source retrieved: 2026-10-01
Event date: 2026-09-02

Read original source

What happened

OroraTech’s 2 Sep 2026 OT-NRT Product User Guide (v1.0.2), hosted on NASA Science CSDA paths, describes an eight-satellite thermal constellation (OTC-P1) with 200 m GSD SAFIRE instruments that run onboard AI hotspot detection and deliver up to two daily scans (~4 am/4 pm local) via Wildfire Solution WFS/API. Product maturity is labeled Closed Beta. A June 2026 ESA OPT-MPC assessment cited joint detection rates of 77.8% vs VIIRS and 96.1% vs MTG on a limited dataset still subject to change. The guide states industrial heat and solar-farm reflections can create false positives and that small/cool/obscured fires or missed overpasses can cause omissions.

Why it matters

Gives U.S. SLED fire/EM buyers a concrete wildfire-satellite AI product spec—resolution, revisit, onboard AI, confidence metadata, and FP/FN modes—distinct from already-archived ALERTCalifornia/ALERTWest camera and FireSat first-light coverage. Why now: Sept 2026 NASA-hosted guide and June 2026 ESA CCM metrics were not in the emergency-services archive and are newly relevant as Western agencies compare camera nets to commercial thermal constellations.

Evidence and measured results

Opened the NASA-hosted PDF via curl (SLED-research-bot/1.0) and extracted text with pdftotext. Confirmed v1.0.2 date 02 Sep 2026; 8 satellites; 200 m; onboard AI wording; joint detection 77.8%/96.1%; closed beta; industrial/solar FP and small/cool miss limitations.

Limitations and uncertainty

Vendor product guide; ESA joint-detection figures are preliminary on a limited dataset and may change; Closed Beta; not an independent U.S. fire-agency outcome evaluation; NASA hosting is distribution, not NASA endorsement of operational readiness.

Put this evidence to work

Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-09-29; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.

Sales

Role takeaway

Customer problem: Agencies need earlier wildfire cues in the afternoon burn window when many public satellites are sparse.
Stakeholders: Fire chiefs
Wildfire intel/aviation
ECC/dispatch
County EM
GIS/IT
Discovery questions: What is current VIIRS/FIRMS latency for your AOI?
Who verifies AI/camera alerts before engines?
Where are camera-network gaps?
What FP rate is operationally tolerable?
Value hypothesis: A 200 m thermal constellation with onboard AI may cue detections when cameras/911 are late—if humans still verify and beta limits are accepted.
Potential engagement: One-season Closed Beta pilot with cue-time and FP KPIs versus current detection stack.
Unsupported claims: Every ignition detected
NASA certified operational readiness
Replaces cameras or lookouts
Fixed 20-minute global revisit today

Pre-sales engineering

Role takeaway

Fit: NRT hotspot/cluster feed into wildfire COP with human-verify gates.
Architecture and integration: OT-NRT WFS/API → cluster/confidence filter → CAD/COP layer → duty-officer verify → optional public alert.
Prerequisites: AOI tasking
API credentials
Multi-source fire layer
Verify SOP
Constraints: Closed Beta
~2 scans/day
Industrial/solar FP modes
ESA metrics may change
Security: Protect WFS keys and tasked AOIs; log access; avoid leaking sensitive monitoring polygons.
Proof of value: Median cue lead vs 911/camera
FP rate after human filter
Missed fires found later by other means

Delivery

Role takeaway

Work: Configure AOIs, train intel/dispatch on confidence/cluster types, and stand up FP review.
Dependencies: Fire intel
ECC
GIS
Vendor beta support
Ownership: Fire duty officer owns verify-before-alert; GIS owns feed health.
Skills and adoption: Teach interpreters to treat confidence as triage, not truth.
Governance checkpoints: Monthly FP/FN review
Beta metric change notice
Public-alert policy check
Acceptance criteria: 100% human verify before public warning
Logged acquisition/detection times
Documented solar/industry handling
Risks: Beta over-trust
Missed small/cool fires
Unannounced model updates

Implementation considerations

Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.

Architecture and integration

What must connect, and where does the AI sit in the workflow?

Treat OT-NRT as a NRT hotspot/cluster feed into CAD/wildfire common operating pictures via WFS API—not as standalone dispatch authority. Plan for ~0.5-day revisit, afternoon-burn orbit niche, and multi-source cluster fusion with public VIIRS/MODIS/GOES.

Governance

Who approves, reviews and stays accountable for outcomes?

Require written acceptance of Closed Beta status, published confidence thresholds for auto-notify vs human verify, and change-control when ESA metrics or onboard models update.

Security and privacy

What data, permissions and controls need testing?

API keys and monitored AOIs are operationally sensitive; apply least-privilege WFS credentials, logging, and no public exposure of tasked emergency AOIs beyond intentional public feeds.

Accessibility and workforce

Who is affected, and what skills or accommodations follow?

Dispatchers/fire intel still need training to interpret confidence, cluster types (e.g., industry vs vegetation), and when to wait for corroborating 911/camera reports.

Procurement

What should contracts, pricing and exit terms secure?

Compete thermal constellation subscriptions against camera networks using revisit, GSD, FP handling (solar farms), data rights, and beta exit criteria—not marketing ‘AI onboard’ alone.

Operating model

Which teams own the service once it runs?

Keep human verification before public alerts/evacuations; use OT-NRT to cue lookouts/aircraft, not to replace them.

Publication history

2026-09-29Emergency Services · Issue 255 resources

Read preserved resource versions (JSON)

Stable resource ID: ororatech-ot-nrt-nasa-guide-20260902