GridCORTEX Live · Wildfire & Vegetation  ·  ← All Demos
On this page What you are watching The business case Run this at your utility Where you see it and how you say yes

The Ignition Forecast Synthetic Data · Simulation

Utilities don't start most wildfires, but the ones they start happen at predictable places on predictable days. This is the full fusion your wildfire plan promises and your systems can't compute: fire-weather forecasts, km-scale wind physics, soil and terrain, fuel type, live fuel moisture from satellite, and LiDAR strike-tree analytics, blended into a per-span Fire Potential Index that runs four days ahead. Watch it drive three decisions in one red-flag event: the vegetation strike team cutting the 14 spans that matter (not the ones the trim cycle says are due), sensitive relay settings arming on exactly nine feeders as the index crosses threshold, and a surgical PSPS that de-energizes 4,100 customers instead of 38,000. Then the gust hits the limb, and nothing burns.

HOUR 0
SEASONAL RISK PICTURE
⏳ DECISION POINT: TIME SLOWED
SYNTHETIC DATA
Grass Chaparral Timber LiDAR strike-tree span EPSS / fast-trip armed PSPS de-energized Contact event

The gust hit the limb. Nothing burned.

What the fusion is worth on the day the wind comes, ignition risk as a computed number, not a season of dread
,
Utility ignitions
,
PSPS customers dark
,
Strike-tree spans cleared pre-event
The Event
WithoutWith GridCORTEXΔ
The Program
WithoutWith GridCORTEXΔ
Illustrative simulation on synthetic data; territory, weather, and outcomes are fictional; no real fire, utility, or event is depicted. In a GridCORTEX pilot, the ignition twin runs on YOUR LiDAR, YOUR fuel and weather data, and YOUR protection settings, backtested against your worst historical fire-weather days. See UC 8.4 "Demo and Proof Plan."
31
Fire Potential Index (0–100)
9%
Dead fuel moisture (10-hr)
0 / 9
Feeders on fast-trip (EPSS)
0
Customers de-energized
Fire Ops Feed, weather · LiDAR · satellite · protection · human-in-the-loop
Risk map
Red flag
PSPS call
The gust
All clear
The Validated Use Cases Behind This Scenario
UC 8.4
Wildfire Ignition Risk Twin
The per-span Fire Potential Index: weather physics × fuel × terrain × asset condition, four days ahead.
UC 9.1
LiDAR & Satellite Encroachment
Every strike tree ranked by what it can hit and what's under it, the cut list the trim cycle can't see.
UC 8.10
Adaptive Protection Designer
Fast-trip settings armed by computed risk, feeder by feeder; the reliability cost paid only where the index demands it.
UC 8.5
PSPS Scope Minimizer
4,100 customers dark instead of 38,000, sectionalizing and DER islanding turned a blackout into a scalpel.
UC 8.9
Ignition Detection Network
Cameras, satellite, and hourly IR drone patrols over the flagged corridors, a heat hit reaches the control center in seconds and pre-arms the lines in the fire's path.
UC 16.1
IR Drone Patrols
The airframes flying the hourly hotspot sweeps, the same fleet from The Fleet Above, on fire watch until the red flag lifts.
Inside the Demo
What you are watching, and what it proves

The stage is a fictional utility territory heading into four days of dangerous fire weather; the simulation clock runs 96 hours, Day 1 through Day 4. The stakes are simple: a wildfire started by utility equipment can mean burned homes, lawsuits, and years of liability, so one prevented ignition is worth the whole program. The opening picture is the seasonal risk map. It layers aerial laser scans (LiDAR) that have located 2,300 individual trees tall enough to strike a power line if they fall, satellite readings of vegetation dryness, soil and slope data, and vegetation types. The northeast hills are the danger zone: the brush there holds only 61% of the moisture level considered safe, and it is still drying. GridCORTEX blends all of it into one Fire Potential Index, a 0 to 100 risk score computed for every span of wire and projected four days ahead. The dashboard opens with the index at 31 and the small dead twigs on the ground at 9% moisture.

The first decision point comes at hour 3. The fused data ranks 14 spans of line as this week's real ignition risk; three of them were not scheduled for tree trimming for another two years. The software asks a human operator to approve pulling two contractor crews off routine trimming for 72 hours to cut those 14 spans, worst consequences first. A person decides because it means real crews and real budget. By the end of Day 1 six spans are cleared, including a leaning gray pine over the line called FDR-118 that the normal schedule would not reach until 2028; all 14 are cleared and verified by hour 26. At hour 30 a red flag warning arrives, the weather service's formal alert for dangerous fire weather: dry wind from inland, gusts forecast above 45 mph, humidity at 8%. The second decision point asks the operator to arm fast-trip settings on exactly 9 power lines: extra-sensitive breaker settings that cut power at the first flicker of trouble, with automatic re-energizing switched off so a line is never powered back into a fallen branch. Protection engineers review every setting before it goes live. The trade-off shows up at hour 40, when a squirrel touches line FDR-131 and 220 customers lose power for 40 minutes over a harmless contact the normal settings would have ridden through. That small outage is the honest price of the protection.

Day 3 is the peak. The wind model puts gusts of 47 to 48 mph through the Cedar Ridge canyons from 14:00 to 20:00, and the fire index crosses 90 on three hillside segments. The third decision point is the hardest call in wildfire operations: a Public Safety Power Shutoff, or PSPS, a planned blackout in which the utility turns lines off before the wind can knock them into dry fuel. Drawn with a blunt weather-zone boundary, the shutoff would darken 38,000 customers. GridCORTEX computes the boundary switch by switch instead and recommends turning off 4,100, keeping the Cedar Ridge community microgrid, a neighborhood of 610 homes with its own local power supply, lit, and contacting customers who depend on medical equipment first. A review board of people, not the software, owns that call. Then at hour 63 the gust arrives: 47 mph wind drops a limb across line FDR-115. The fast-trip settings cut power in 0.08 seconds and the line stays dead, so no spark reaches ground fuel that is at 4% moisture, dry enough for one spark to become a fire. A patrol finds the limb 22 minutes later. At hour 68 an hourly heat-sensing drone patrol spots a smolder in the hills, left by a lightning strike from last week. The control center is alerted in 40 seconds, the fire department gets exact coordinates, one line section in the fire's modeled path is switched off as a precaution, and the smolder is put out at 0.2 acres.

With all three approvals, the wind breaks after hour 76. The sensitive settings come off line by line as the index falls, the shutoff areas are patrolled and re-energized, and every customer is back by 06:00 on Day 4. The wrap at hour 90 is the whole story: zero utility-caused ignitions, 4,100 customers dark for 19 hours instead of 38,000 for 24, one 40-minute nuisance outage, and 14 dangerous trees gone for good, with the reasoning behind every decision recorded. Decline the recommendations and the same gust starts a wind-driven fire that reaches 1,850 acres and destroys 11 buildings by Day 4.

Without GridCORTEX

Every input exists, but nothing combines them. The 14 dangerous spans stay on the routine 2027-2028 trimming schedule, because the schedule ranks work by calendar date, not by risk. Breakers keep their normal settings everywhere, because nobody can say which lines need the sensitive ones. The shutoff debate, facing only a blunt 38,000-customer outline with schools and a hospital inside, stalls at "monitor conditions," because the cost of the blackout is obvious and the risk is a guess. At hour 63 the limb drops across line FDR-115, and the breaker automatically re-powers the line twice, straight into the fallen branch, throwing sparks into tinder-dry fuel on a 47 mph wind.

The camera network confirms a fire 9 minutes later, moving toward Cedar Ridge; evacuations begin. With no drone patrols, the lightning smolder in the hills is found by a 911 caller three hours later, a second fire front on a day that already has one. By Day 4 the tally is 1,850 acres and 11 buildings, and the cause investigation opens on the breaker's own records. The utility's data becomes the other side's best evidence in court.

With GridCORTEX

The software fuses seven data sources into one fire risk score for every span of wire, four days ahead, and turns the score into three recommendations that people approve: cut the 14 spans that matter most, ranked by risk instead of by calendar; arm the extra-sensitive breaker settings on exactly 9 lines, with automatic re-powering blocked; and shrink the safety shutoff to a surgical 4,100 customers instead of 38,000, with the neighborhood microgrid kept lit. Every gate has a person in charge: managers approve the crews, protection engineers approve the settings, and a review board owns the shutoff.

The payoff: the limb strike is cut off in 0.08 seconds with no re-powering and no fire, the reliability cost is one 220-customer nuisance outage, the drone patrols catch a lightning smolder at 0.2 acres, and the event closes with zero utility ignitions and an automatically kept record of the justification behind every setting, cut, and boundary.

The results, side by side
MeasureWithout GridCORTEXWith GridCORTEXThe difference
Utility ignitionsfires started by the utility's own equipment, the number the whole program exists to keep at zero1; wind-driven, 1,850 acres0the whole ballgame
The FDR-115 limb strikewhat happened when the gust dropped a tree limb onto the power line named FDR-115breaker re-powered the fallen line twicepower cut in 0.08 seconds, stayed offarmed by the index
Strike-tree spansthe 14 stretches of line where a tree tall enough to hit the wire stood over dry fuelwaiting on the 2027-28 schedulecut 3 weeks earlyranked by risk, not calendar
PSPS scopePSPS is a Public Safety Power Shutoff, a planned blackout ahead of dangerous wind; scope is how many customers it darkens38,000 blunt (never called)4,100 surgical + microgrid lit89% fewer customers dark
PSPS customers dark (headline)the shutoff as the public experienced it0; then evacuations4,100 × 19 hrsrisk retired, lights mostly on
Nuisance-trip costthe price of extra-sensitive settings: harmless contacts, like a squirrel, now cause small outagesn/a1 outage, 220 customers, 40 minthe honest price
Detection to patrolhow quickly someone laid eyes on the spot where the limb hit the linecamera at +9 min (a fire)patrol at +22 min (no fire)crews staged in advance
Lightning smolder in the hillsa small fire left by last week's lightning, nothing to do with the utility's lines, but burning in its territoryfound by a 911 caller, 3 hours laterdrone heat camera; out at 0.2 acreshourly patrols + lines pre-armed
Event outcomehow the four days endburned buildings, evacuations, lawsuitsa logbook entryeverything
Liability recordwhat the utility can show in court about the choices it madebreaker record is the plaintiff's best evidenceevery setting justified, traceddefensible
Veg budget effectwhat the tree-trimming budget actually bought80% spent on low-risk spansevery crew-hour aimed at real risksame money, real risk cut
Reliability cost of fire opshow much everyday reliability was given up to run in fire-safe mode, which causes more small outagessensitive settings all season long9 lines, 52 hours, only while the index demanded itsurgical
WMP / regulator filingthe WMP is the Wildfire Mitigation Plan, the safety plan the utility must file with its regulator every yearwritten narrativescomputed evidence, every step loggedwrites itself
Community trusthow customers feel about the shutoff once it is over"why was my power off?"microgrid lit, notice earlyearned
The live numbers on the dashboard
Fire Potential Index (0-100)The single risk score every decision runs on, computed for each span of wire. Readings near 31 mean calm conditions; readings near 90 mean a spark can become a fire. Watch it climb with the wind and the dryness, arming protections as it crosses thresholds.
Dead fuel moisture (10-hr)How much moisture is left in the small dead twigs that catch fire first ("10-hour" fuels change dryness within about ten hours of a weather shift). Higher is safer. It opens at 9%, already dry, and heads toward the 4% measured at the contact site, which is tinder.
Feeders on fast-trip (EPSS)How many of the 9 flagged lines have the extra-sensitive breaker settings armed, with automatic re-powering blocked (EPSS stands for Enhanced Powerline Safety Settings). 0 of 9 is normal in calm weather; 9 of 9 through the windstorm is the goal.
Customers de-energizedHow many customers the safety shutoff has turned off. It reads 0 until the shutoff runs, then 4,100, a fraction of the 38,000 a blunt boundary would darken. On the failure path this tile becomes the fire's size in acres instead.

The Business Case: Safety, Hours, and Cost

A utility does not buy a demo. It buys a safety exposure that goes away and a cost that goes down. Below is that case for every use case behind The Ignition Forecast, written the way a plant manager, a safety lead, and a CFO each need to read it. Every hour and every dollar is a formula you run with your own rates and volumes. There are no vendor benchmarks in here and no invented percentages. If a number is not yours, it is not a number.
UC 8.4 Wildfire Ignition Risk Twin

What happens today, without this

The wildfire duty officer builds the daily risk picture by hand every morning through fire season. They read the National Weather Service forecast and any red flag warnings, pull fuel moisture readings from the stations that report them, look at wind forecasts by district, and combine all of that with whatever they can recall about which circuits carry open vegetation findings or old conductor. The result is a district level risk call recorded in a spreadsheet. Operating posture, patrol targeting, and PSPS pre-planning all get set off a picture that is far coarser than the grid it is meant to protect.

What it replaces or shrinks

  • The daily manual assembly of weather, fuel moisture, and wind data into a risk index
  • Cross referencing circuits against open vegetation findings and conductor condition records by hand
  • District wide risk calls applied uniformly to circuits with very different exposure, which shrinks to circuit and span level
  • Manual selection of which circuits get an inspection or a patrol ahead of a wind event
  • Rebuilding the risk picture from scratch each forecast cycle instead of updating it
  • After the fact reconstruction of what the risk picture said on a given day

Why it is safer

The exposure that changes is patrol exposure during wind events. Instead of patrolling a whole district because the district sits under a warning, crews patrol the circuits the model ranks highest, which cuts driving in high wind and after dark and cuts the operating posture changes that put people in the field at the worst hours.

Counted in units you already track:

  • Road miles driven on pre-event and during-event patrols in high wind conditions
  • Night driving hours during red flag periods
  • Switching operations performed for protective setting changes and de-energization across a whole district rather than selected circuits
  • Energized area entries by patrollers during declared fire weather

Man-hours it gives back

The duty officer's daily assembly hours come back and the wildfire team's inspection targeting is produced rather than debated, while the risk call itself stays with the duty officer.

HOURS AVOIDED PER YEAR = fire season days per year x hours per day the duty officer and supporting analysts spend assembling the risk picture x forecast cycles per day, plus circuits patrolled per event x patrol hours per circuit x wind events per season, minus the review time the duty officer still spends accepting or overriding the model each cycle.

The numbers we need from you to run that formula:

  • Fire season length in days and forecast cycles per day
  • Hours per cycle the duty officer and supporting analysts spend building the current risk picture
  • Circuits typically patrolled per wind event and patrol hours per circuit
  • Loaded hourly rates for the duty officer, the analysts, and the patrollers
  • Wind or red flag events in an average season

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Duty officer and analyst laborassembly hours avoided x your loaded rates x fire season days x cycles per day
Targeted patrol laborpatrol hours avoided by patrolling ranked circuits instead of whole districts x your loaded patroller rate x events per season
Vehicle and travelpatrol miles avoided x your fleet cost per mile
Avoided PSPS scopecustomers not de-energized because their circuit scored below threshold x hours of the event x 60 x your value per customer minute. This one counts only if you actually use the twin to inform the call, and the call stays yours
Avoided ignitionyour own modeled cost per ignition event x the share you believe circuit level targeting would prevent, which is your number and one you should keep conservative

Reliability and maintenance

Reliability
The direct reliability effect runs through PSPS. A circuit level risk score lets you leave circuits energized that a district level call would have taken out, and every circuit left up is SAIFI and SAIDI you did not incur. It does not change the physical condition of the grid.
Maintenance
Inspection and vegetation work gets aimed at circuits whose risk score is being driven by asset or vegetation condition rather than by weather, which is the part you can actually fix. Over a season the score breakdown tells the maintenance planner which findings are moving risk and which are not.

What else it moves

ComplianceA dated, circuit level record of the risk picture that informed each operating decision, which is the core evidentiary ask of a wildfire mitigation plan and of any post ignition investigation.
CustomerFewer customers de-energized on a district wide basis when their own circuit was never above threshold.
Insurance and riskDemonstrable circuit level risk management is the posture underwriters look for, and its absence is what makes a geography based program expensive to insure.

What it costs you, stated honestly

You pay for the weather modeling and the twin, for integration to your vegetation findings, conductor condition records, GIS, and outage history, and for your team's time validating the score against actual near misses and ignitions over at least one season. The quality of your conductor and vegetation records will decide how much of year one goes to data cleanup.

How to build the payback case

The payback a reviewer will accept is driven by duty officer and patrol labor and by PSPS customer minutes avoided. Avoided ignition is the largest number and the least auditable, so keep it out of the base case.

This is a planning model driven by your season length, staffing, patrol rates, and customer minute valuation, not a vendor claim. Re-run it with your own season actuals and validated near miss record before you extend the program.
UC 9.1 LiDAR and Satellite Encroachment Analytics at Scale

What happens today, without this

Territory scale vegetation data arrives on a long cycle. You fly light detection and ranging, or LiDAR, over part of the system, send the point cloud to a service bureau, and get a clearance violation report back months later, by which time the fastest growing spans have moved. In between, encroachment is judged by a forester patrolling right of way, or ROW, on foot or by truck, spot measuring conductor to canopy with a range finder one span at a time, and typing findings into the geographic information system, or GIS, back at the office. The program manager plans a season from data that is a processing cycle old and a patrol sample wide.

What it replaces or shrinks

  • Months of service bureau turnaround between data capture and a usable violation list
  • Ground patrol walked or driven purely to measure clearance on routine spans
  • Hand keying of measured violations into GIS and into the work management system
  • The annual spreadsheet reconciliation of violations found against spans actually trimmed
  • Shrinks the separate re fly or re walk done just to establish how fast a given corridor is growing

Why it is safer

Part of this benefit is indirect and it is fair to say so. The direct piece is real: routine clearance measurement puts a forester under energized conductor, in brush, on ROW access roads and highway shoulders, for hours at a time, and a measurement taken from the point cloud does not. The indirect piece is that violations found sooner are trimmed as scheduled work rather than as an emergency response after a contact.

Counted in units you already track:

  • Road miles driven on ROW access roads and shoulders for routine clearance patrol
  • Energized area entries by foresters working directly beneath conductor to take a measurement
  • Permits to work and landowner access permits pulled for routine survey visits rather than for actual trim work

Man-hours it gives back

Forester field hours and GIS data entry hours come back to the vegetation program, and the forester's remaining field time goes to verifying flagged spans and talking to landowners instead of measuring spans that turn out to be fine.

HOURS AVOIDED PER YEAR = ROW miles in the program x forester hours per mile of ground clearance survey x surveys per year, plus violations recorded per year x minutes per violation to key into GIS and the work system, plus data refreshes per year x staff hours spent expediting and quality checking service bureau deliverables, minus the field time a forester still spends confirming flagged spans before a crew is scheduled.

The numbers we need from you to run that formula:

  • ROW miles in the vegetation program, split by transmission and distribution
  • Forester hours per mile of ground survey and loaded hourly rate for a forester
  • Violations recorded per year and minutes per record to enter into GIS
  • Current data acquisition and service bureau processing cost, and the turnaround you get today
  • Loaded hourly rate for the GIS analyst who maintains the vegetation layer

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Forester field laborground survey hours avoided x your loaded forester rate, plus miles avoided x your fleet cost per mile
Data processingyour current service bureau processing fee per mile or per square mile x the volume you process per year, compared against processing the same volume in house
GIS data entryrecords keyed per year x minutes each x your loaded GIS analyst rate
Rework and mobilizationcrew mobilizations sent against a stale span list x your contractor mobilization cost, which is the cost of finding the tree already gone or the wrong span flagged
Avoided outageyour own cost per tree caused distribution outage x the share of them you believe a current inventory would have caught in time, which you set, not us

Reliability and maintenance

Reliability
Vegetation contact is one of the cause codes in your own outage records, and you already know what share of your SAIFI, the average number of interruptions per customer, it drives. This use case does not change how you trim, it changes how current the list is when you decide what to trim, so the reliability gain is proportional to how many of your vegetation outages happened on spans that were not yet on anyone's list.
Maintenance
Repeat passes over the same corridor give a growth rate per span rather than a growth rate per region, which is what lets you stretch the interval on slow growing spans and tighten it where growth is fast. That is the difference between a calendar cycle and a condition based one, and it needs at least two data cycles before you should trust it.

What else it moves

ComplianceFor transmission ROW, a repeatable, dated, measurable clearance record across the whole portfolio is what a vegetation management standard audit asks to see, and a sample patrol is not that.
WorkforceExperienced foresters stop spending the season measuring and start spending it on the judgment calls and the landowner conversations, which is the part that does not transfer to a point cloud.
EnvironmentFewer survey trips on unimproved ROW roads means less soil disturbance and fewer access events in sensitive corridors, and targeting means less removal on spans that never needed it.

What it costs you, stated honestly

The dominant cost is data acquisition, the flights or the satellite tasking, and you are largely paying that today. On top of it you pay for the GPU processing capacity or the hosted service, for the GridCORTEX analytics layer, for integration into GIS and the work management system, and for your program staff to validate the first inventory against known ground truth spans before anyone plans a season from it.

How to build the payback case

Payback is driven by processing turnaround and ground survey labor, not by avoided outages, because acquisition cost stays roughly flat either way. If the pilot only proves you can refresh the inventory in the same season you captured it, that alone is usually the case.

These are planning models built from your ROW mileage, your forester rates, and your current processing fees, not vendor claims. Re run them after the first full territory refresh, using what the validation actually found.
UC 8.10 Wildfire Operation Zone and Adaptive Protection Designer

What happens today, without this

A protection and control engineer builds fire mode settings by hand, one device at a time, in the relay setting software, and proves coordination by drawing time current characteristic curves in a study tool. Because fire mode changes the protection, typically more sensitive earth fault pickup and reclosing blocked, coordination has to hold in both the normal state and the fire state, so every device pair gets checked twice. A territory has a handful of people who can do this work, it takes months per district, and it goes stale the first time the network model changes. Wildfire Operation Zone boundaries, meanwhile, get drawn once in a GIS workshop and revisited about as often as a rate case.

What it replaces or shrinks

  • Device pair by device pair coordination checking in both the normal and the fire mode state
  • Hand drawn zone boundaries produced in a one time GIS workshop
  • Re checking affected setting groups by hand every time the network model changes
  • The spreadsheet that tracks which device carries which setting group and which revision
  • Shrinks the manual assembly of the design basis narrative that the commission asks for, because the rationale is produced with the design

Why it is safer

The public safety effect is the point: fewer utility ignitions from faults that fire mode is designed to catch. There is a workforce exposure effect too, and it comes from a mechanism people miss. Because fire mode blocks reclosing, every trip becomes a locked out circuit that has to be patrolled end to end before it can be re energized, often at night in bad conditions. Tighter zones and validated coordination mean fewer devices lock out for a given fault, so fewer circuit miles get patrolled.

Counted in units you already track:

  • Road miles driven on full circuit patrols after a fire mode lockout
  • Night driving hours on those patrols, which is when most of them happen
  • Energized area entries by patrol crews walking a locked out circuit to find a fault before re energizing
  • Switching operations required to sectionalize, isolate, and restore around a fire mode lockout

Man-hours it gives back

Scarce protection engineering hours come back, and the engineer moves from producing settings to judging the ones that were flagged, which is the correct place for that expertise.

HOURS AVOIDED PER YEAR = districts in the program x engineer weeks per district x hours per week x engineers assigned, plus network model changes per year x device pairs affected x minutes per manual re validation, plus filing or program cycles per year x hours to assemble the design basis, minus the engineer review hours spent adjudicating flagged coordination conflicts and approving each setting group, which do not go away.

The numbers we need from you to run that formula:

  • Districts or zones to design and how long a district takes your team today
  • Protection engineers available for this work and their loaded hourly rate, plus any outside consultant rate you pay
  • Protective devices in scope and the device pairs that require coordination checking
  • Network model changes per year that force re validation
  • Circuit miles patrolled and crew hours per patrol after a fire mode lockout

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Protection engineering laborengineer hours avoided x your loaded protection engineer rate, and separately x your outside consultant rate for the portion you contract out, which is usually the higher of the two
Patrol labor and travelcircuit miles not patrolled after avoidable lockouts x your patrol hours per mile x loaded crew rate, plus miles x your fleet cost per mile
Design basis documentationhours to assemble the documented rationale per zone x your loaded rate or your consultant rate x zones per cycle
Customer interruption from fire modecustomers de energized by fire mode lockouts that better coordination avoids x hours out x your own value of customer interruption
Avoided ignitionyour own modeled cost per utility ignition x the share you attribute to faults fire mode settings would have caught, which you set, not us

Reliability and maintenance

Reliability
This one needs an honest answer rather than a flattering one. Fire mode deliberately trades reliability for ignition risk: sensitive settings and blocked reclosing mean more sustained interruptions and worse SAIFI and SAIDI inside the zone, and that is the intended bargain. What this use case does is contain the price, by drawing zones tightly enough that only the spans that need fire mode are in it, and by proving the coordination so a fault does not trip a device further upstream than it should. The effect is a smaller, shorter footprint for a cost you have already decided to accept.
Maintenance
Setting groups stay tied to the current network model instead of drifting away from it, so the gap between as designed and as deployed relay settings gets found on a schedule rather than during an event investigation. Re scoring zones every season with current fuel and weather converts a rate case sized project into routine maintenance of the design.

What else it moves

ComplianceA documented design basis per zone, regenerated when inputs change, which is what a commission asks for and what a hand built package cannot keep current.
WorkforceProtection and control engineering is one of the thinnest benches in the industry and the people who can do dual state coordination by hand are often the closest to retiring. This puts their time on judgment and captures their logic in something reviewable.
CustomerA tightly drawn zone means fewer customers living with fire mode settings and the longer outages that come with them, on days when it is not warranted for them.

What it costs you, stated honestly

You pay for the scoped engagement that builds and runs this and for integration into your protection settings management system, but the cost that decides whether this works is network model quality. Your model has to be accurate and complete, with current load, fault duty, and device data, and closing those gaps is real engineering time. Your protection engineers also review and approve every setting group, and that review does not shrink much, because it should not.

How to build the payback case

Payback here is usually measured in districts completed per season rather than in dollars, because protection engineering capacity is the binding constraint and you cannot buy more of it quickly. If you want a dollar figure, use the consultant rate you would otherwise pay for the same design volume.

This is a planning model built from your device counts, your engineer and consultant rates, and your own patrol costs, not a vendor claim. Re run it after the first district, using how long the engineer review actually took.
UC 8.5 PSPS Decision Support and Scope Minimizer

What happens today, without this

When a wind event approaches, the PSPS decision team meets and draws the de-energization scope on a map, usually by zone, because zones are what the switching plans and the customer notification lists are already built around. Engineers then work out by hand which switches isolate that footprint, and someone checks the medical baseline and critical facility lists against it. The scope ends up wider than the risk, because time is short and a broad cut is easier to explain than a narrow one. Every customer inside that footprint loses power, and every de-energized mile has to be patrolled before it can be restored.

What it replaces or shrinks

  • Hand drawing of the de-energization footprint on a zone map in a war room
  • Manual engineering work to find the switch sections that isolate a proposed scope
  • Cross checking medical baseline and critical facility lists against a proposed footprint by hand
  • Rebuilding the switching plan by hand every time leadership asks to see a narrower option, which shrinks to a re-run measured in minutes
  • Post event patrol of de-energized miles that never needed to be de-energized in the first place
  • After the fact justification of the scope, assembled from meeting notes

Why it is safer

The safety change is mostly in the restoration tail. Every de-energized mile must be patrolled before it is re-energized, so a smaller scope is directly fewer patrol miles, fewer switching operations, and fewer field entries during and after a high wind event. There is also the exposure a de-energization creates for customers running backup generation, which a narrower scope reduces.

Counted in units you already track:

  • Switching operations performed to de-energize and then restore the PSPS footprint
  • Road miles driven on mandatory patrol of de-energized circuits before restoration
  • Night driving hours during restoration patrols once the wind subsides
  • Energized area entries by patrol and switching crews during and immediately after the event

Man-hours it gives back

Engineering and restoration patrol hours come back, and the PSPS decision authority gets scope options with their risk and customer impact already priced instead of waiting on an engineer to build one.

HOURS AVOIDED PER YEAR = PSPS events per season x engineering hours per event to build and rebuild scope options, plus de-energized circuit miles avoided x patrol hours per circuit mile x patrollers, plus switching operations avoided x hours per switching operation, minus the review time the decision authority and the control room spend validating the proposed plan in the ADMS, your advanced distribution management system.

The numbers we need from you to run that formula:

  • PSPS events in an average season and engineering hours spent per event building scope options
  • Circuit miles typically de-energized per event and patrol hours per circuit mile before restoration
  • Customers per de-energized circuit mile and your value per customer minute of interruption
  • Loaded hourly rates for planning engineers, patrollers, and switching crews
  • Your per event cost for customer notification, community resource centers, and PSPS related claims

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Customer minutescustomers spared x hours de-energized x 60 x whatever value your commission or your own case places on a customer minute. This is the dominant driver and it is your number, not ours
Restoration patrol laborpatrol hours avoided on miles never de-energized x your loaded patroller rate
Engineering laborscope building hours avoided per event x your loaded planning engineer rate x events per season
Event support costreduction in customer notification volume, community resource center staffing, and PSPS related claims x your own per event cost for each
Switching laborswitching operations avoided x hours per operation x your loaded crew rate

Reliability and maintenance

Reliability
PSPS is self inflicted SAIFI and SAIDI, and in fire prone territory it can be the single largest contributor to both. Narrowing scope to the switch sections that actually carry the risk is the most direct lever a utility has on those numbers, and unlike storm damage it is entirely within your control.
Maintenance
The switch sections that keep landing inside the minimum defensible scope, event after event, are your hardening and vegetation priority list. That is a maintenance targeting output the current zone based process cannot produce at all.

What else it moves

ComplianceA documented, quantified basis for the scope chosen and the scope rejected, including the risk reduction retained, which is the answer a commission asks for when it challenges a broad de-energization.
CustomerFewer customers de-energized, and fewer medical baseline and critical facility customers caught inside a footprint their own circuit risk did not justify.
Insurance and riskThe record shows risk reduction was held while impact was narrowed, which is the position that defends both against an ignition claim and against criticism of over de-energizing.

What it costs you, stated honestly

You pay for the modeling service, for the ADMS and GIS integration that lets a proposed scope be expressed as a real switching plan, and for a serious amount of your own engineering and control room time validating proposed scopes against plans your operators would actually execute. Expect that validation to run a full season before anyone signs off on a narrower scope during a live event.

How to build the payback case

Payback is dominated by customer minutes not interrupted, and everything else is rounding. That makes the whole case rest on your own value per customer minute, so settle that number internally before you model anything else.

This is a planning model driven by your event history, circuit miles, customer counts, and your value per customer minute, not a vendor claim. Re-run it with the actuals from a full season of events before you rely on it during a live call.
UC 8.9 Real-Time Wildfire Ignition Detection Network

What happens today, without this

Ignition detection today is mostly a phone call. A member of the public, a fire agency dispatcher, or a lineman sees smoke and calls it in, and then the wildfire duty officer tries to confirm it, sometimes by scanning a wall of camera feeds during red flag conditions, sometimes by sending a truck. One duty officer watches far more cameras than a person can actually watch. Meanwhile Public Safety Power Shutoff, or PSPS, decisions are made hours or a day ahead on forecast, so whole circuits get de energized for a whole day because nobody can tell which span is the problem.

What it replaces or shrinks

  • Continuous human staring at camera walls through red flag operational periods
  • The phone tree used to confirm a public smoke report against a location and a circuit
  • Truck rolls sent purely to confirm whether a reported smoke column is on your line or somebody else's
  • Shrinks the manual hunt through archived imagery when a cause and origin investigation asks what your equipment was doing
  • Shrinks the eyeball estimate of which circuit and which span a plume belongs to, which is what makes the switching order slow

Why it is safer

The exposure removed is a crew driving toward a smoke column to find out what it is, in wind, in poor visibility, often at night, on the same roads the fire agencies need. Faster and more precise de energization also narrows the footprint that has to be patrolled and re energized afterward.

Counted in units you already track:

  • Road miles driven on confirmation truck rolls for unverified smoke reports
  • Night driving hours during red flag operational periods
  • Energized area entries by patrol crews sent to a span before the ignition is confirmed
  • Switching operations, which shift from broad precautionary PSPS scope to targeted de energization of the circuit actually involved

Man-hours it gives back

Duty officer watch hours and confirmation patrol hours come back to wildfire operations, and the duty officer stops scanning and starts adjudicating alerts, which is the part only a person should do.

HOURS AVOIDED PER YEAR = red flag days per year x camera watch staffing hours per day x staff on watch, plus smoke reports per season x hours per confirmation truck roll x crew size, plus cause investigations per year x hours spent retrieving imagery, minus the duty officer time still spent verifying every alert before a de energization is proposed, which does not go away and should not.

The numbers we need from you to run that formula:

  • Red flag or elevated fire risk operational days per year and staff assigned to camera watch
  • Smoke reports investigated per season and average crew hours and miles per confirmation trip
  • Loaded hourly rate for a duty officer, a system operator, and a patrol crew
  • Your fleet cost per mile for patrol vehicles
  • Cameras in service or planned, and the spans each one covers

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Watch laborcamera watch hours avoided x your loaded duty officer rate x red flag days per year
Confirmation truck rollsconfirmation trips avoided x your loaded crew rate per trip, plus miles x your fleet cost per mile
PSPS scopecustomers kept energized because scope narrowed x hours de energized x your own cost per customer hour of PSPS interruption, using whatever value you already apply in your PSPS cost benefit work
Patrol and re energizationcircuit miles not patrolled because the de energized footprint is smaller x your patrol hours per mile x loaded crew rate
Avoided fire lossyour own modeled cost per grid ignition that reaches reportable size x the share you believe seconds level detection would have kept small, which you set, not us

Reliability and maintenance

Reliability
The reliability effect runs through PSPS scope. Every customer you do not de energize precautionarily is customer minutes you do not lose, and in most jurisdictions those minutes land in SAIFI and SAIDI or in a parallel PSPS metric the commission watches just as closely. A targeted de energization also shortens the patrol and re energization sequence, which is what drives the duration side, CAIDI.
Maintenance
The same cameras that see smoke also see arcing at night, conductor slap in wind, and equipment flashes, so a span that keeps flashing becomes a work order instead of an unexplained momentary. That converts a class of emergent, cause unknown failures into scoped planned repair on a named structure.

What else it moves

ComplianceTimestamped, imagery backed detection and response times for every alert, which is exactly the evidence a wildfire mitigation plan commitment and a post incident inquiry ask for.
CustomerNarrower and shorter PSPS events, and a defensible answer when a customer asks why their circuit was shut off and the one next door was not.
Insurance and riskA documented detection to de energization interval is the single most useful fact in a liability posture, and it is either recorded or it is testimony.
EnvironmentAcres burned is the outcome everything else is a proxy for, and detection time is the lever you actually control.

What it costs you, stated honestly

The dominant cost is the field build, poles or mounts, power, and backhaul to the camera sites, not the inference. On top of that you pay for the edge devices, the GridCORTEX detection layer, integration into your ADMS switching queue, and duty officer time through the first fire season tuning thresholds. Be ready for false positives early. The honest way to run that period is to keep every alert human adjudicated and measure how the false positive rate falls, rather than promising it starts low.

How to build the payback case

Payback is dominated by narrowed PSPS scope and by avoided fire loss, and only the first of those is auditable from your own records, so build the case on PSPS customer minutes and watch labor and treat avoided loss as upside.

These are planning models built from your camera counts, your PSPS cost values, and your patrol rates, not vendor claims. Re run them with the actuals from your first fire season before you size the buildout.
UC 16.1 Autonomous Transmission Line Inspection Drone Fleet

What happens today, without this

Transmission lines are inspected on a calendar cycle by patrol crews driving right of way roads and by manned helicopter flights. A patroller covers a set number of structures a day, records findings on paper or a tablet, and the findings are typed into the asset system later. Anything above ground gets judged from below with binoculars, or a climber goes up.

What it replaces or shrinks

  • Ground patrol driving of accessible right of way for routine condition checks
  • Manned helicopter passes flown purely to look at hardware
  • Climbing a structure to confirm a suspected finding before scoping the repair
  • Manual transcription of field notes into the asset management system
  • The separate desk review where an engineer sorts patrol findings into priority order

Why it is safer

The two highest consequence exposures in line inspection are low altitude manned flight and climbing energized structures. Both are replaced for routine condition assessment, and the climber only goes up once the defect is already confirmed and the repair is scoped.

Counted in units you already track:

  • Low altitude manned flight hours flown for inspection purposes
  • Structure climbs performed for inspection rather than for repair
  • Right of way road miles driven, including on unimproved and seasonal roads
  • Energized area entries by ground crews on routine patrol

Man-hours it gives back

Patrol hours and desk triage hours come back to the line department, and the inspection engineer stops reading every image and starts reading only the flagged ones.

HOURS AVOIDED PER YEAR = structures inspected per year x patrol hours per structure, plus helicopter hours per year x crew size, plus findings per year x desk triage minutes per finding, minus the review time an engineer still spends confirming flagged detections.

The numbers we need from you to run that formula:

  • Structures in the inspection program and the current cycle length
  • Patrol hours per structure and crew size on a patrol
  • Manned helicopter hours flown per year for inspection and the hourly cost
  • Average findings per year and the desk minutes spent triaging each one
  • Loaded hourly rate for a patroller and for an inspection engineer

Where the dollars come from

Cost driverHow it is calculated, from a rate you supply
Patrol laborpatrol hours avoided x your loaded patroller rate
Aviationmanned inspection hours avoided x your all-in helicopter hourly cost, whether owned or contracted
Engineering triagetriage hours avoided x your loaded engineer rate
Avoided failureyour own cost per unplanned transmission outage x the share of failures you believe earlier detection would have caught, which you set, not us
Vehicle and travelroad miles avoided x your fleet cost per mile, plus per diem on remote patrols

Reliability and maintenance

Reliability
Defects are found between calendar cycles rather than at the next scheduled patrol, so hardware failures get repaired as planned work instead of becoming an unplanned line outage. The reliability benefit is real but it depends on how many of your outages trace to conditions a visual or thermal inspection could have seen, which is a number you already have in your outage cause coding.
Maintenance
Findings arrive already sorted by severity and already attached to a structure identifier, so the work planner scopes the job once instead of sending someone back to confirm. Repeat imagery of the same structure across cycles shows whether a finding is stable or getting worse, which is what lets you defer safely instead of guessing.

What else it moves

ComplianceA defensible, timestamped, image-backed inspection record for every structure, which is what an audit of your inspection and maintenance program actually asks for.
WorkforceExperienced patrollers stop spending their day driving and start spending it on judgment calls, which matters when the ones who can read a structure by eye are the ones closest to retirement.
EnvironmentFewer vehicle miles on unimproved right of way roads means less soil disturbance and fewer access permits in sensitive habitat.

What it costs you, stated honestly

You pay for the flight operations, whether you own the fleet or contract it, for the GridCORTEX intelligence layer that turns imagery into ranked findings, for the integration into your asset and work systems, and for your own staff time to validate detections during the first inspection season. The intelligence layer is the smaller line item. The flight operations dominate.

How to build the payback case

Payback is usually driven by aviation and patrol labor, not by avoided failures, because avoided failure is the number you will trust least. Build the case on the two you can audit and treat avoided failure as upside.

These are planning models you drive with your own rates and volumes, not vendor claims. Re-run them with the actuals from your first inspection season before you size the program.
Each of these opens in full on the use case page, alongside the integration plan, the data ask, the path to production, and the operator console. Open the use case library.
For Your Architects and Data Owners
Run this at your utility

What is this, exactly? It is AI software: intelligent agents and models built and delivered by SoftServe, running on NVIDIA accelerated computing. It is not a hardware appliance and it does not replace the systems you run today. It deploys in your own cloud or on your premises, connects read-only to your existing systems, and recommends; your people approve every action, starting in shadow mode until it earns trust.

A continuously updated risk model for wildfire and operations leadership: a circuit-and-span-level ignition risk map, refreshed each forecast cycle, that feeds PSPS calls and inspection targeting. The demo above uses synthetic data; everything below describes what the real deployment needs from your organization.

Systems it connects to

Your systemTypical productsHow we connect
Weather and environmentNational Weather Service feeds, commercial forecast services, satellite and LiDAR imageryread-only API
Geographic Information System (GIS)Esri ArcGIS Utility Network, GE Smallworldscheduled file export (CSV or CIM XML)
SCADA historianAVEVA PI System, GE Proficyhistorian mirror (one-way feed)
Asset / work management (EAM/CMMS)IBM Maximo, SAP PM, Oracle WAMdatabase replica refreshed nightly
Outage Management System (OMS)GE PowerOn, Oracle NMS, ADMS outage moduledatabase replica refreshed nightly
Planning and study toolsCYME, Synergi, WindMilscheduled file export (CSV or CIM XML)
Protection settings managementASPEN OneLiner, CAPE, relay settings databasesscheduled file export (CSV or CIM XML)

Data it needs from you

How it runs on your systems

Runs in your cloud account on GPU instances to handle weather model downscaling, with an on-premises option; all feeds are read-only with no connection to control systems, and PSPS decisions stay with your wildfire leadership. The 30-day pilot runs in shadow against actual conditions.

Path to production

Data access and model build (Weeks 1-6)
Weather, asset, vegetation, and event history are connected; assembling ignition and fault history is the usual gate.
Shadow pilot (Weeks 7-11)
The twin runs for 30 days and its predicted high-risk periods are compared against actual ignitions, faults, and PSPS events.
Evaluation (Weeks 12-14)
Prediction skill versus the current risk process drives the go or no-go decision.
Production hardening (Months 4-6)
Security review, monitoring, fire-season readiness drills, and team training.
Production and scaling (Months 6-9)
The wildfire team opens the risk map every fire-season morning, feeding PSPS deliberations and inspection targeting territory-wide.

What we need from your team

Full integration, data, and timeline detail for each use case in this scenario: UC 8.4 · UC 9.1 · UC 8.10 · UC 8.5
For Your Operators and Dispatchers
Where you will see it and how you say yes

The Approve button you just clicked in the demo above is the real workflow. This is what it looks like on the screen of the wildfire duty officer in the GridCORTEX console:

GridCORTEX ConsoleSigned in: the wildfire duty officer
Notifications
Red flag Thursday: 6 circuits exceed ignition risk 8.0 of 10; circuit C-77 peaks at 9.2 with 51 mph gusts forecast
Daily model refresh complete; all connected feeds healthy
Recommendation
Accept Thursday's circuit-level ignition risk forecast
  • 6 circuits above the 8.0 threshold serve 23,000 customers
  • C-77 combines 51 mph gusts, 4 percent fuel moisture, 12 open vegetation findings
  • Model matched 3 of 3 verified near-misses last month
✓ Accept risk forecastModifyDecline
After you approve: The accepted forecast publishes to the PSPS planning workspace and drafts inspection tasks in the work management system, and an audit entry records who approved it and why.
Computed from data as of 17:42:10 local; every card shows the timestamp of the data behind it.

What happens when you hit approve

Approve publishes the accepted forecast to the PSPS planning workspace and creates draft inspection tasks in your work management system in pending status; your wildfire team confirms and assigns them. PSPS calls remain with the decision authority; the twin only informs them.

How you tell it what it cannot see

The trigger is automatic from weather, fuel, and asset feeds; the duty officer enters nothing. Field observations logged in the work system feed back into the score.

Live data, not stale data

Rescored each forecast cycle, with weather every 15 minutes and SCADA continuously; every circuit card shows the forecast run time it came from.

Where it lives day to day

Lives as a console risk map refreshed each forecast cycle; mobile push when a circuit crosses the threshold. The console runs in a browser beside your existing screens on day one; embedding into your own systems is a roadmap step once the read-only phase has earned trust. Approve, Modify, and Decline are all captured in an audit trail your compliance team can pull, and GridCORTEX never blocks or overrides anything in the systems you run today.

The Gap: Why Your Existing Systems Don't Already Do This

The fair question from any wildfire officer: "We buy fire-weather forecasts, we fly LiDAR, we have a wildfire mitigation plan and PSPS criteria, what's new here?" Here's the honest answer.

What you own keeps doing its job

  • Fire-weather services, the forecasts keep coming; they become one input among seven.
  • LiDAR & satellite programs, the flights and imagery continue; the analytics finally consume ALL of them.
  • The wildfire mitigation plan, the regulatory commitments stand; the twin becomes their evidence engine.
  • Protection engineers & the PSPS board, every setting change and every de-energization you watched was a human decision with the math attached.

The gap GridCORTEX fills, above them, not instead of them

  • The inputs exist; the fusion doesn't. Fire weather lives in one portal, LiDAR in a contractor's deliverable, fuel moisture in a federal dataset, soil and terrain in GIS, asset condition in the EAM. Nobody's system multiplies them into ONE number per span per hour. That number is the product.
  • The trim cycle is a calendar; risk is not. Cutting every span on a 4-year rotation spends 80% of the veg budget on spans that can't start a fire. The 14 spans that mattered this week were found by LiDAR × dryness × wind exposure × what's downwind, three of them weren't due for two years.
  • Fast-trip is a blunt instrument today. Season-long sensitive settings punish reliability everywhere. Arming EPSS feeder-by-feeder, hour-by-hour, off the computed index pays the reliability cost only where and when the risk is real.
  • PSPS scope is drawn with a highlighter. Weather zones make blunt shapes; the twin makes surgical ones, sectionalizer-level scope, DER islands kept lit, 89% fewer customers dark for the same risk retired.
  • The liability case is the same math. Every armed setting, every cut span, every PSPS boundary carries its computed justification, the defensible record regulators and courts now expect.
Accent, don't replace: GridCORTEX fuses your weather feeds, LiDAR, satellite, soil, fuel, and asset data into a per-span ignition index · hands the cut list to your veg contractors, the arming schedule to your protection engineers, and the scope map to your PSPS board · and keeps the receipts for the regulator. The wind still comes. The fire doesn't.
Under the Hood: What GridCORTEX Took Into Account in This Scenario

When someone asks "what did it actually calculate?", this is the list. In the simulation these factors drive the storyline; in a pilot they are computed from your LiDAR, weather, fuel, and protection data.

🌡 The Fuel & Weather Physics

  • Km-scale wind and humidity forecasting (Earth-2 class), gusts modeled through YOUR canyons, not a county-wide number
  • Live and dead fuel moisture: satellite NDVI/NDWI trends per fuel polygon, 10-hr and 100-hr dead fuel from weather history
  • Fuel typing from imagery: grass, chaparral, timber, with soil type and slope shaping spread behavior downwind of every span

🌲 The Vegetation Intelligence

  • LiDAR strike-tree analytics: every tree tall enough to reach a conductor, scored by lean, health (satellite stress), species failure rates, and wind exposure
  • Consequence weighting: what's downwind (fuel load, terrain funneling, structures) decides which encroachment matters
  • Risk-based cut lists ranked by ignition-consequence per contractor-hour, with work verification when crews close out (UC 9.3)

⚡ The Grid Response

  • Per-feeder Fire Potential Index thresholds arming fast-trip/EPSS settings and blocking reclosing, protection changes recommended, engineer-approved, auto-logged
  • PSPS scope optimization at sectionalizer granularity: risk retired per customer-hour dark, with DER/microgrid islanding keeping critical loads lit
  • Patrol-verified re-energization sequencing when the weather breaks

🧾 The Record

  • Every armed setting, cut span, and scope boundary carries its computed justification, Relay-traced for the wildfire mitigation plan and any proceeding after
  • Ignition detection network (UC 8.9): cameras, satellite, and hourly IR drone patrols over the corridors the fusion flags, flying until the threat passes; a heat signature notifies the control center in seconds and pre-arms de-energization along the modeled fire path (UC 16.1)
  • Runs always-on via the NVIDIA Agent Toolkit; the twin was watching the forecast before anyone asked it to

Presenter's one-liner: "Seven data sources nobody had ever multiplied together became one number per span, four days ahead. The number sent the tree crews to fourteen spans, armed fast-trip on nine feeders, and drew a PSPS boundary around four thousand customers instead of thirty-eight. Then the 47-mile-an-hour gust put the limb on the wire, the feeder cleared in 80 milliseconds, nothing reclosed into it, and nothing burned. That's ignition risk as engineering instead of dread."

GridCORTEX Live Scenario Demo · Synthetic data throughout, no real fire, utility, or event is depicted · Protection engineers approve all settings; the PSPS board decides scope · SoftServe + NVIDIA · Created by Ronnie Mauldin, NVIDIA Solutions Director, Power & Utilities, SoftServe · JUL 2026