Back to results
US 2026/0120219 A1Published application
Wildfire Risk Mitigation Planning with Decision Support
AssigneeXylo Risk, Inc.
InventorsScott Farley, David Winnacker
Life of this patent
Estimating the term…
Abstract
Machine-learning-based methods and systems for vegetation treatment project design. The approach autonomously creates, evaluates, and optimizes wildfire risk mitigation activities to intelligently reduce wildfire risk to communities in a resource-constrained environment. The methods and/or systems are accompanied by a cloud-enabled user interface that provides decision support to vegetation management specialists charged with implementing wildfire risk reduction measures.
Claims18
A decision support system for wildfire risk mitigation, the system comprising:
- one or more processors;
- a non-transitory memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:
- (i) receive and store a plurality of candidate treatment plans for a geographic region, each treatment plan comprising a set of treatment actions associated with a geographic footprint, an implementation cost, and an anticipated effect on fire spread;
- (ii) access a directed graph representation of filtered fire spread pathways, the directed graph comprising nodes corresponding to cell and time states and edges corresponding to transitions with associated propagation likelihoods and incremental losses;
- (iii) simulate, for each treatment plan, a modified set of fire spread pathways by applying an effect model that adjusts propagation likelihoods and incremental losses for edges intersecting the treatment actions of the treatment plan;
- (iv) compute, for each treatment plan, a suitability score based on
- (a) an expected risk reduction derived from the modified set of fire spread pathways, and/or
- (b) implementation cost of the treatment plan;
- (v) rank the plurality of treatment plans based on the suitability scores to produce ranked treatment plans;
- (vi) generate a decision support output comprising the ranked treatment plans and corresponding geospatial overlays for display in a user interface;
- and
- (vii) receive user adjustments to one or more decision parameters, the decision parameters comprising at least a budget constraint, a risk-reduction weighting factor, or a geographic priority, wherein the one or more processors are further configured to recompute the suitability scores and the ranked treatment plans in response to the user adjustments.
9 more elements
A computer-implemented method for wildfire risk mitigation planning, the method comprising:
- (a) receiving, by one or more processors, multi-source geospatial and temporal data for a geographic region divided into cells, the data comprising at least weather fields, topography, vegetation data, fuel condition data, and asset exposure data;
- (b) simulating, given candidate ignition locations and over a time-indexed directed graph, a plurality of fire spread pathways using a fire spread model to produce, for each such pathway, an ordered sequence of cell transitions with associated propagation likelihoods and intensity estimates;
- (c) computing, for each fire spread pathway, an impact score based at least on the associated propagation likelihoods and exposure of assets intersected by the respective pathway;
- (d) defining a library of candidate treatment actions, each treatment action comprising a geographic footprint mapped to a subset of nodes or edges in the directed graph, an effect model specifying at least a reduction in propagation likelihood on affected edges, and an implementation cost;
- (e) evaluating, for each candidate treatment action and at least one combination of candidate treatment actions, a risk-reduction value computed as a change in expected loss on the directed graph when applying the effect model to the subset of nodes or edges associated with the candidate treatment action(s);
- (f) selecting, from the candidate treatment actions, a treatment plan comprising a subset of the candidate treatment actions that maximizes a risk-reduction objective subject to one or more constraints comprising a budget constraint and at least one resource, geographic, or timing constraint;
- (g) generating, from the data, a time-indexed spatial representation of the geographic region comprising a plurality of cells at a temporal resolution and identifying a set of candidate ignition locations for a selectable forecast horizon;
- and
- (h) outputting the treatment plan together with geospatial identifiers and scheduling information to a planning interface for execution.
6 more elements
Dependencies are inferred from the claim text.