What Overstory’s vegetation intelligence reveals about wildfire and outage risk.
Updated
January 15, 2026 8:03 PM
Aerial photograph of a green field. PHOTO: UNSPLASH
Managing vegetation around power lines has long been one of the biggest operational challenges for utilities. A single tree growing too close to electrical infrastructure can trigger outages or, in the worst cases, spark fires. With vast service territories, shifting weather patterns and limited visibility into changing landscape conditions, utilities often rely on inspections and broad wildfire-risk maps that provide only partial insight into where the most serious threats actually are.
Overstory, a company specializing in AI-powered vegetation intelligence, addresses this visibility gap with a platform that uses high-resolution satellite imagery and machine-learning models to interpret vegetation conditions in detail.Instead of assessing risk by region, terrain type or outdated maps, the system evaluates conditions tree by tree. This helps utilities identify precisely where hazards exist and which areas demand immediate intervention—critical in regions where small variations in vegetation density, fuel type or moisture levels can influence how quickly a spark might spread.
At the core of this technology is Overstory’s proprietary Fuel Detection Model, designed to identify vegetation most likely to ignite or accelerate wildfire spread. Unlike broad, publicly available fire-risk maps, the model analyzes the specific fuel conditions surrounding electrical infrastructure. By pinpointing exact locations where certain fuel types or densities create elevated risk, utilities can plan targeted wildfire-mitigation work rather than relying on sweeping, resource-heavy maintenance cycles.
This data-driven approach is reshaping how utilities structure vegetation-management programs. Having visibility into where risks are concentrated—and which trees or areas pose the highest threat—allows teams to prioritize work based on measurable evidence. For many utilities, this shift supports more efficient crew deployment, reduces unnecessary trims and builds clearer justification for preventive action. It also offers a path to strengthening grid reliability without expanding operational budgets.
Overstory’s recent US$43 million Series B funding round, led by Blume Equity with support from Energy Impact Partners and existing investors, reflects growing interest in AI tools that translate environmental data into actionable wildfire-prevention intelligence. The investment will support further development of Overstory’s risk models and help expand access to its vegetation-intelligence platform.
Yet the company’s focus remains consistent: giving utilities sharper, real-time visibility into the landscapes they manage. By converting satellite observations into clear and actionable insights, Overstory’s AI system provides a more informed foundation for decisions that impact grid safety and community resilience. In an environment where a single missed hazard can have far-reaching consequences, early and precise detection has become an essential tool for preventing wildfires before they start.
Keep Reading
Where smarter storage meets smarter logistics.
Updated
January 8, 2026 6:32 PM
.jpg)
Kioxia's flagship building at Yokohama Technology Campus. PHOTO: KIOXIA
E-commerce keeps growing and with it, the number of products moving through warehouses every day. Items vary more than ever — different shapes, seasonal packaging, limited editions and constantly updated designs. At the same time, many logistics centers are dealing with labour shortages and rising pressure to automate.
But today’s image-recognition AI isn’t built for this level of change. Most systems rely on deep-learning models that need to be adjusted or retrained whenever new products appear. Every update — whether it’s a new item or a packaging change — adds extra time, energy use and operational cost. And for warehouses handling huge product catalogs, these retraining cycles can slow everything down.
KIOXIA, a company known for its memory and storage technologies, is working on a different approach. In a new collaboration with Tsubakimoto Chain and EAGLYS, the team has developed an AI-based image recognition system that is designed to adapt more easily as product lines grow and shift. The idea is to help logistics sites automatically identify items moving through their workflows without constantly reworking the core AI model.
At the center of the system is KIOXIA’s AiSAQ software paired with its Memory-Centric AI technology. Instead of retraining the model each time new products appear, the system stores new product data — images, labels and feature information — directly in high-capacity storage. This allows warehouses to add new items quickly without altering the original AI model.
Because storing more data can lead to longer search times, the system also indexes the stored product information and transfers the index into SSD storage. This makes it easier for the AI to retrieve relevant features fast, using a Retrieval-Augmented Generation–style method adapted for image recognition.
The collaboration will be showcased at the 2025 International Robot Exhibition in Tokyo. Visitors will see the system classify items in real time as they move along a conveyor, drawing on stored product features to identify them instantly. The demonstration aims to illustrate how logistics sites can handle continuously changing inventories with greater accuracy and reduced friction.
Overall, as logistics networks become increasingly busy and product lines evolve faster than ever, this memory-driven approach provides a practical way to keep automation adaptable and less fragile.