ARXIV:2604.04916 · PREDICTIVE MAINTENANCE AI · SUBMITTED 07 APR · 20:11 UTC · FRESHNESS UNKNOWN

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning

Xuyang Shen · Zijie Pan · Diego Cerrai · Xinxuan Zhang · Christopher Colorio · Emmanouil N. Anagnostou · +1 at arXiv

A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.

Ship in 2-4 weeks›Score7.0Evidence unverified

Opportunity summary

Pain A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.

Evidence 0 refs | 0 sources | 0% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events. These outages halt industrial operations, impact communities, damage critical infrastructure, profoundly disrupt economies, and have…

METHOD

Full abstract

Extreme weather events, such as severe storms, hurricanes, snowstorms, and ice storms, which are exacerbated by climate change, frequently cause widespread power outages. These outages halt industrial operations, impact communities, damage critical infrastructure, profoundly disrupt economies, and have far-reaching effects across various sectors. To mitigate these effects, the University of Connecticut and Eversource Energy Center have developed an outage prediction modeling (OPM) system to provide pre-emptive forecasts for electric distribution networks before such weather events occur. However, existing predictive models in the system do not incorporate the spatial effect of extreme weather events. To this end, we develop Spatially Aware Hybrid Graph Neural Networks (SA-HGNN) with contrastive learning to enhance the OPM predictions for extreme weather-induced power outages. Specifically, we first encode spatial relationships of both static features (e.g., land cover, infrastructure) and event-specific dynamic features (e.g., wind speed, precipitation) via Spatially Aware Hybrid Graph Neural Networks (SA-HGNN). Next, we leverage contrastive learning to handle the imbalance problem associated with different types of extreme weather events and generate location-specific embeddings by minimizing intra-event distances between similar locations while maximizing inter-event distances across all locations. Thorough empirical studies in four utility service territories, i.e., Connecticut, Western Massachusetts, Eastern Massachusetts, and New Hampshire, demonstrate that SA-HGNN can achieve state-of-the-art performance for power outage prediction.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. Thorough empirical studies in four utility service territories, i.e., Connecticut, Western Massachusetts, Eastern Massachusetts, and New Hampshire, demonstrate that SA-HGNN can achieve state-of-the-art performance…

WHY NOW

Predictive Maintenance AI moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainA hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.

Evidence0 refs | 0 sources | 0% coverage

Blockerno shell-level blocker reported

Analysis summary

A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Competitive landscape

A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.

Segment

Predictive Maintenance AI

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "d7fffb65-9675-4777-aeee-13a175fcf885", "arxiv_id": "2604.04916", "canonical_route": "/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning", "endpoints": { "paper_pack": "/api/v1/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning/paper-pack", "build_passport": "/api/v1/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning", "normalized_query": "2604.04916", "route": "/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning", "paper_ref": "empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning#webpage", "url": "https://sciencetostartup.com/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning", "name": "Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning", "description": "A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning#scholarlyArticle", "headline": "Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning", "description": "A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.", "url": "https://sciencetostartup.com/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning", "sameAs": "https://arxiv.org/abs/2604.04916", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2604.04916" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-04-06T17:56:03.000Z", "author": [ { "@type": "Person", "name": "Xuyang Shen" }, { "@type": "Person", "name": "Zijie Pan" }, { "@type": "Person", "name": "Diego Cerrai" }, { "@type": "Person", "name": "Xinxuan Zhang" }, { "@type": "Person", "name": "Christopher Colorio" }, { "@type": "Person", "name": "Emmanouil N. Anagnostou" }, { "@type": "Person", "name": "Dongjin Song" } ], "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 7 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "Predictive Maintenance AI" }, { "@type": "PropertyValue", "propertyID": "commercialReadiness", "value": "code" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "Predictive Maintenance AI", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "Empowering Power Outage Prediction with Spatially Aware Hybr", "item": "https://sciencetostartup.com/paper/empowering-power-outage-prediction-with-spatially-aware-hybrid-graph-neural-networks-and-contrastive-learning" } ] } ] }

Competitive landscape

A hybrid graph neural network with contrastive learning to significantly improve power outage prediction accuracy for extreme weather events.

Segment

Predictive Maintenance AI

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning

Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline