Digital Rock Patents: Top Companies & Filing Trends 2026
- 66.5% of all 173 records sit with just five assignees, and 85.5% with ten — this is a field with a short, well-defended top table.
- Filings fell 69% from 36 in 2021 to 11 in 2024, the last year the data can treat as complete.
- G01N and G06T dominate material analysis (59.0%) and image processing (39.9%) classes anchor most filings, while AI-based computing (G06N, 6.9%) is still thin.
Filing growth compares 2021 (36 records) with 2024 (11) — 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 173 records in scope (CR5), not by the ranked leaders only.
What this landscape covers
This dataset tracks patent families combining digital rock physics and pore network modelling with imaging and simulation elements such as pore space segmentation, representative elementary volume, lattice Boltzmann simulation, image resolution handling, multiscale image fusion and simulated permeability. It spans 173 published records filed or published between 2015 and mid-2026, drawn from filings at the US, WIPO (PCT), EPO, Australian, Canadian and UAE offices.
The field sits at the intersection of core analysis, computational imaging and reservoir simulation. Petrophysics-heavy filers dominate the IPC composition alongside imaging and general-purpose computing classes, which signals that claims are being written as much around image workflows as around the physical measurement itself.
Filing trend and technology composition
Two views of the same 173-record dataset: filing activity by year, and the IPC subclasses that carry the claims.
Filing trend: a 2023 peak followed by an incomplete tail
Filings rose to a peak of 39 in 2023 before falling to 11 in 2024 — a 69% drop from the 36 filed in 2021, the last comparison the data supports. 2025 and 2026 numbers are still low because publication lags filing by roughly 18 months; they should not be read as a genuine slowdown yet.
IPC composition: material testing and imaging lead
G01N (material analysis & testing) appears on 59.0% of records and G06T (image data processing) on 39.9%, with G06F, G01V and E21B each in the high-teens to low-twenties. AI-based computing under G06N sits at just 6.9%, and pattern/data recognition under G06K at 7.5% — both comparatively open relative to the imaging and petrophysics core.
Shares are the percentage of the 173 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Digital Rock and Pore Scale Imaging with Eureka
This page is one run against one query. Ask Eureka your own question about digital rock and pore scale imaging and every answer comes back with the patent numbers behind it.
Try EurekaThe most-cited records in this space
Method and System for Pore-Scale Modeling of a Multi-Phase Hydrocarbon Extraction Process
A computer system models a hydrocarbon extraction process using a dynamic pore network model representing a subterranean reservoir as pores connected by throats. Solvent is injected to mobilize hydrocarbons, and an iterative process tracks molar balance of components over time. A first set of pore characteristics is defined, from which a second set is derived for two-phase pores to compute extraction outcomes.Filed by the government of Canada's natural resources ministry — a reminder that national labs and public research bodies are active filers in pore-scale modelling, not only oilfield service majors.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20090259446A1 | Method to generate numerical pseudocores using borehole images, digital rock samples, and multi-point statist… | 208 |
| 2 | US20130259190A1 | Method And System For Estimating Properties Of Porous Media Such As Fine Pore Or Tight Rocks | 130 |
| 3 | US20190154597A1 | System and Methods for Computing Physical Properties of Materials Using Imaging Data | 66 |
| 4 | WO2009126881A2 | Method to generate numerical pseudocores using borehole images, digital rock samples, and multi-point statist… | 57 |
| 5 | US8725477B2 | Method to generate numerical pseudocores using borehole images, digital rock samples, and multi-point statist… | 44 |
| 6 | US20210190664A1 | System and method for estimation of rock properties from core images | 30 |
| 7 | US20210116354A1 | Method of determining absolute permeability | 30 |
| 8 | US20180003786A1 | Cuttings Analysis For Improved Downhole NMR Characterisation | 28 |
| 9 | WO2013148632A1 | A method and system for estimating properties of porous media such as fine PORE or tight rocks | 27 |
| 10 | US20150345267A1 | Method of Forming Directionally Controlled Wormholes in a Subterranean Formation | 25 |
Citation counts reflect age as much as importance — older families like the numerical pseudocore patents have had more time to accumulate citations, so treat this as a signal of influence rather than current relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Put your own technology through the same analysis
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 →MCP server & REST API
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 →What the numbers mean for a filing decision
Three findings a reader would not get from browsing the table alone.
The top of the field is narrow and well established
Five assignees account for 66.5% of all records in scope, and the top ten hold 85.5%. New entrants are filing into a space where the dominant petrophysics and oilfield-service groups already hold dense prior art around core imaging and simulation workflows.
Filing pace has cooled from its 2023 peak
Activity peaked at 39 filings in 2023, then fell to 11 by 2024 — down 69% from the 36 filed in 2021. Because publication lags filing by around 18 months, 2025-2026 figures are still incomplete and should not be read as confirming a continued decline.
AI-native claims are still a minority
Material analysis (G01N, 59.0%) and image processing (G06T, 39.9%) are the backbone of this field's claims, but AI-based computing (G06N) appears on only 6.9% of records and data recognition (G06K) on 7.5%. Machine-learning-driven segmentation and property prediction are patented far less densely than the imaging and simulation steps around them.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to digital rock and pore scale imaging, with the prior art for and against each one.
Who is filing, and where the room still is
The ranking below covers all 38 assignees the dataset returns — not a curated top 50 or top 100 — so the drop-off after the leaders is real, not an artefact of truncation.
One filer sits well clear of the field
The leading assignee's count of 38 is more than three times the fifth-place total of 11, indicating a filer that has treated digital rock imaging as a core, sustained programme rather than an occasional filing area.
A compact group of steady filers below the leader
Places five through ten hold between 11 and 5 records each — oilfield service majors and specialist imaging firms with sustained but smaller programmes. Together with the leader they take 85.5% of all 173 records.
Co-filing is limited and mostly internal to one group
Only six co-assignee pairs appear in the data, and the strongest is between two entities within the same corporate family, alongside a named inventor pair with five joint filings. Cross-company joint filing is not a notable pattern in this field.
| Assignee | Recent year | YoY |
|---|---|---|
| Shell Internationale Research Maatschappij BV | 0 | — |
| University of Wyoming | 0 | -100% |
| Ingrain Inc | 0 | — |
| Shell Oil Co | 0 | — |
| Eni SpA | 0 | — |
| DigiM Solution LLC | 0 | — |
| MODAVI ABDOLLAH | 0 | — |
| BECKHAM RICHARD E | 0 | — |
Where to take this next
The dataset points to a narrow set of dominant filers and a technology mix still light on AI-native claims — both are starting points for deeper work.
Run a freedom-to-operate check against the leader
With one assignee holding more than triple the fifth-place count, any new filing in pore-scale imaging should be checked against that filer's claim set first.
Search assignee portfolios in EurekaProbe the AI-segmentation gap
G06N appears on only 6.9% of records despite machine-learning segmentation being widely discussed in the technical literature — worth a targeted prior-art search before drafting.
Explore white space in EurekaWatch the 2023-2024 filing drop for signal, not noise
The fall from 39 to 11 filings could reflect consolidation, a shift to trade secrecy, or simply publication lag. Track 2025-2026 as they backfill before drawing conclusions.
Monitor filing trends in EurekaCommon questions about this landscape
The dataset's leading assignee holds 38 of the 173 records in scope, well ahead of the fifth-place holder at 11. The top five assignees combined account for 66.5% of all records, and the top ten for 85.5%, so the field is concentrated among a small group of oilfield service majors, major operators and specialist imaging firms rather than spread across many small filers. Anyone entering this space should expect to run into that leader's claims first.
Filings peaked at 39 in 2023 and fell to 11 by 2024, a 69% drop from the 36 filed in 2021. Because patent publication typically lags filing by about 18 months, the apparent decline in 2025 and 2026 figures is partly an artefact of records not yet published, not confirmed evidence of a shrinking field. 2024 is the most recent year that can be treated as a complete count.
Material analysis and testing (IPC class G01N) appears on 59.0% of the 173 records, and image data processing (G06T) on 39.9%, making these the two anchor classes. Electric digital data processing (G06F), geophysics (G01V) and drilling (E21B) each cover roughly a fifth of records, while AI-based computing (G06N) and image recognition (G06V) remain comparatively thin at under 11%.
The clearest gap is between the imaging and simulation core, which is densely claimed, and AI-native processing, where G06N appears on only 6.9% of records. Sub-areas such as automated representative elementary volume determination, multiscale image fusion workflows and AI-driven pore segmentation show comparatively light claim density relative to their prominence in the technical literature, making them worth a targeted search before drafting new claims.
Collaboration is limited: the dataset shows only six co-assignee pairs across 173 records, and the strongest of these is between two entities inside the same corporate group rather than an arm's-length partnership. Most protection in digital rock and pore-scale imaging is being built by single assignees filing independently, which means competitive mapping should focus on individual company portfolios rather than joint ventures or consortia.
Research Digital Rock and Pore Scale Imaging in depth with Eureka
Go past this page: query the whole digital rock and pore scale imaging 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.