Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →Filing growth compares 2021 (5 records) with 2024 (9) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 169 records in scope (CR5), not by the ranked leaders only.
This dataset tracks 169 published records at the intersection of solar forecasting, solar resource assessment and related technical parameters such as irradiance modelling, cell efficiency and process controls. Coverage runs from 2015 through the 2026-08-31 cut-off, spanning a period where solar output prediction moved from statistical weather models toward machine-learning-assisted grid integration. The scope captures both meteorological forecasting methods and the downstream power-system applications that consume those forecasts.
Records here span standalone irradiance-prediction methods, cloud-detection techniques tied to distributed solar assets, and forecasting pipelines feeding grid dispatch or commerce systems. Because publication lags filing by roughly 18 months, the most recent one to two years in any trend chart will understate real filing activity.
Pick a task. Every answer cites the patents behind it.
The filing curve and the IPC composition together show where solar forecasting patent activity concentrates and how the technology mix has shifted.
Filings peaked in 2019 at 22 records, dipped through the early 2020s, then recovered: 2021 to 2024 rose from 5 to 9 records, an 80% increase over that three-year span. 2026 figures (8 so far) are partial and will rise as later filings publish.
G01W meteorology methods appear in 43.8% of the 169 records, ahead of G06N AI-model computing (30.2%) and H02J power-grid systems (29.6%). G06F data processing and G06Q business/administrative processing each sit at 26.0%, while H02S photovoltaic generation (22.5%), F24S solar heat collectors (13.6%) and G06T image processing (12.4%) round out the mix — note these shares sum to well over 100% because most records carry multiple IPC classes.
Shares are the percentage of the 169 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
This page is one run against one query. Ask Eureka your own question about solar forecasting & resource assessment patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaA wireless mesh network of nodes records voltage fluctuations at distributed solar sites and correlates them across sites to detect advancing cloud cover. By computing the time offset between correlated fluctuations, the system infers cloud movement speed and direction without dedicated irradiance sensors, using existing grid-connected voltage telemetry instead.Filed by Itron Networked Solutions; published 2020-05-14.


| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20100198420A1 | Dynamic management of power production in a power system subject to weather-related factors | 284 |
| 2 | US20050039787A1 | Method and system for predicting solar energy production | 111 |
| 3 | US20130166266A1 | Weather and satellite model for estimating solar irradiance | 110 |
| 4 | US20130054662A1 | Methods of using generalized order differentiation and integration of input variables to forecast trends | 99 |
| 5 | US20160306906A1 | Solar irradiance modeling augmented with atmospheric water vapor data | 70 |
| 6 | US20170031056A1 | Solar Energy Forecasting | 69 |
| 7 | US20190158011A1 | Solar power forecasting | 68 |
| 8 | US7580817B2 | Method and system for predicting solar energy production | 68 |
| 9 | US20120191351A1 | Estimating solar irradiance components from plane of array irradiance and global horizontal irradiance | 55 |
| 10 | US20140196761A1 | Solar tracker and related methods, devices, and systems | 53 |
Citation counts reflect influence within the searched corpus and skew toward older filings; treat them as a signal of prior-art density, not of current commercial importance.
Each row carries its publication number; clicking a row searches Eureka by that number.
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →Three patterns stand out once concentration, technology mix and citation data are read together.
The five leading assignees hold 60 of 169 records (35.5%), and the top ten extend that to 92 records (54.4%). That leaves nearly half the field spread across a long tail of single- and few-filing entrants — room to build a position without displacing an incumbent directly.
G01W meteorology classes appear in more records than any AI-model class, including G06N at 30.2%. Forecasting patents that pair a meteorological method with a specific downstream application — grid dispatch, cell-efficiency correction — sit across more claim territory than model-only filings.
The most-cited record in scope, on dynamic power-production management tied to weather factors, has drawn 284 citations — far ahead of the next tier. That density suggests foundational forecasting-to-dispatch claims are well mapped, and later filers have mostly built narrower, application-specific claims around them rather than re-claiming the core method.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to solar forecasting & resource assessment patent landscape, with the prior art for and against each one.
| Assignee | Co-assignee | Shared families |
|---|---|---|
| NEO VIRTUS ENG | BING JAMES M | 2 |
| The Regents of the University of California | COIMBRA CARLOS F M | 2 |
Only two co-assignee pairs appear across the dataset, indicating most records here are filed by a single assignee rather than through joint development arrangements.
Filing activity concentrates among a handful of established players, but recent-year momentum data shows even the leader has gone quiet in the latest year, and named branches remain thinly claimed.
The leading assignee holds 21 of 169 records, well ahead of fifth place at 8. Yet recent-year momentum data shows this same leader at 0 filings in the latest year, a -100% year-over-year change — a reminder that a strong historical position can still leave room for a new entrant to move.
The United States receives the largest share of filings (71), followed by India (32) and WIPO/PCT filings (22). Europe, Australia and Canada each receive single-digit-to-teens counts, suggesting protection strategies outside the US-India-PCT corridor remain comparatively thin.
Only two co-assignee pairs recur in the dataset, each appearing twice. Most solar forecasting patent activity here is filed by a single organisation working alone, rather than through university-industry or multi-party collaboration structures common in some adjacent energy fields.
| Assignee | Recent year | YoY |
|---|---|---|
| EAGLEVIEW TECHNOLOGIES INC | 0 | -100% |
| Commonwealth Scientific and Industrial Research Organisation (CSIRO) | 0 | — |
| Qatar Foundation for Education, Science and Community Development | 0 | — |
| Itron, Inc. | 0 | — |
| DRIFT MARKETPLACE INC | 0 | — |
| NEO VIRTUS ENG | 0 | — |
| LOCUS ENERGY | 0 | — |
| Green Power Labs Inc. | 0 | — |
The dataset points to specific next steps depending on whether the goal is freedom-to-operate, portfolio positioning, or identifying acquisition targets.
Start with the records carrying the deepest citation counts, particularly the dynamic power-production management filing at 284 citations, to understand what core claim territory is already occupied before drafting new applications.
Explore citation trees in EurekaThe gate chips above point to sub-areas with thinner filing density than the core meteorology and AI classes. Running a draft claim against these branches in Eureka can surface whether the gap is real or simply unindexed.
Run a claim check in EurekaSeveral top assignees show zero filings in the latest year, which given publication lag may reflect pending applications not yet published rather than reduced activity. Monitoring newly published families against this baseline will clarify which.
Set up assignee monitoring in EurekaThe dataset shows a leader-plus-long-tail structure: one assignee holds 21 of the 169 records in scope, and the top five combined hold 60 records, or 35.5% of the field. The top ten extend that to 92 records (54.4%), which leaves nearly half of all records spread across many smaller filers. This means the field has clear leaders but is not fully locked up — there is meaningful room for new entrants outside the top ten.
Meteorology methods (IPC class G01W) appear in 43.8% of the 169 records, more than any other class, followed by AI-model computing (G06N) at 30.2% and power-grid systems (H02J) at 29.6%. Because a single patent can carry multiple IPC classes, these shares add up to well over 100%. The pattern suggests that forecasting patents most often combine a meteorological method with a specific application, rather than claiming a model architecture alone.
Filings grew from 5 in 2021 to 9 in 2024, an 80% increase over that three-year span, after peaking earlier at 22 in 2019. The 2025 and 2026 figures in the dataset are still partial because patent publication typically lags filing by around 18 months, so the most recent years will rise as more applications publish. On the evidence available, the trend since 2021 is upward, not declining.
US20200150309A1, assigned to Itron Networked Solutions, covers a wireless mesh network that detects cloud movement by correlating voltage fluctuations recorded at multiple distributed solar sites, rather than using dedicated irradiance sensors. It computes the time offset between correlated voltage dips at different nodes to infer cloud speed and direction. This approach is notable because it repurposes existing grid voltage telemetry for forecasting rather than requiring new sensor hardware, which narrows the field for anyone trying to design a similar sensorless cloud-detection method.
The IPC composition shows meteorology, AI and grid classes are the most heavily claimed, while narrower branches such as solar heat collector geometry tied to forecasting (F24S, 13.6% of records) and image-based resource assessment (G06T, 12.4%) carry comparatively less density. Co-assignee filings are also rare, with only two pairs identified across the dataset, suggesting joint university-industry filing strategies are underused. Both signals point to openings for applicants willing to combine an underused technical branch with a specific downstream application.
Go past this page: query the whole solar forecasting & resource assessment patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company's registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.