What is EVO in Geoscientific Modeling?

EVO represents a fundamental shift in geoscientific modeling—a fully managed cloud platform designed from the ground up to transform how geological data is processed, analyzed, and utilized. After four years of intensive development, this platform serves as a new operating system for geoscientific modeling, featuring cloud-native applications and data objects that underpin modern geological systems.

Announced at PDAC in March and scheduled for commercial rollout beginning July 2025, EVO doesn't simply improve existing solutions—it reimagines them entirely. As Mike Stewart, Technical Domain Expert at Seequent, emphasizes:

"EVO is the fully managed cloud platform, data objects, all the stuff that goes with that… It's going to be the game changer."

The strategic vision behind EVO is ambitious, with Stewart noting they've "approached the idea of obsoleting ourselves by moving to the cloud from the ground up."

Understanding Seequent's Game-Changing Platform

EVO goes beyond being just another software update. It represents a complete architectural transformation in how geoscientific data is structured, accessed, and manipulated. By shifting to a cloud-first approach, Seequent has created an environment where previously impossible workflows become not only possible but streamlined.

This fully managed platform eliminates many traditional limitations of desktop geological software. Rather than working with isolated data silos and locally-constrained processing power, users can leverage cloud infrastructure for more sophisticated analysis while maintaining consistent data access across projects and teams.

Key Components of the EVO Ecosystem

The platform incorporates several critical elements that work together to create a comprehensive ecosystem:

• Cloud-native applications: Purpose-built software designed to leverage distributed computing resources
• Standardized data objects: Consistent data structures ensuring compatibility across tools
• Fully managed infrastructure: Automatic updates and maintenance without user intervention
• Python scripting integration: Direct programmatic access to geological data and modeling processes
• Advanced geostatistical tools: Cloud-optimized algorithms for sophisticated analysis

This ecosystem enables seamless integration between different modeling tools while providing the foundation for future innovations in geological modeling and analysis. The standardized data objects are particularly important as they establish a common language for different applications to share information without loss of fidelity or context.

How Does EVO Transform Geoscientific Modeling?

EVO represents a paradigm shift in how geoscientists work with complex geological data. The platform transforms traditional modeling approaches through its cloud-native architecture and standardized data structures. This evolution addresses longstanding industry challenges around collaboration, computational limitations, and data consistency.

Cloud-Native Architecture Advantages

EVO's cloud-native architecture eliminates traditional software limitations by providing fully managed infrastructure. This approach delivers several measurable benefits:

• Enhanced accessibility: Multiple users can access the same datasets simultaneously from any location
• Unlimited computational resources: Cloud scaling eliminates the processing constraints of desktop solutions
• Simplified collaboration: Teams can work concurrently on models without version control issues
• Automatic maintenance: Updates and system management happen transparently in the background
• Scalable processing: Complex modeling tasks leverage distributed computing resources as needed

As Stewart explains, the shift to cloud computing fundamentally changes what's possible:

"We've approached the idea of obsoleting ourselves by moving to the cloud from the ground up."

This architectural transformation enables workflows that would be impractical or impossible in traditional desktop environments. By removing local hardware limitations, EVO allows geoscientists to focus on analysis rather than computational constraints.

Data Objects and Interoperability

The platform's data object system represents a significant advancement in how geological information is stored and accessed. Unlike traditional file-based approaches, EVO's data objects provide:

• Standardized structures: Consistent data formats maintain integrity across applications
• Enhanced governance: Improved version control and audit trails for regulatory compliance
• Seamless exchange: Different modeling tools access the same underlying data without conversion
• Reduced duplication: Single-source data objects eliminate redundant copies and associated errors
• Comprehensive metadata: Improved traceability documents the full data lineage

These data objects serve as the foundation for interoperability between tools, enabling workflows that previously required cumbersome import/export processes. The standardized structures also improve data quality by enforcing consistency across the modeling pipeline.

What New Capabilities Does EVO Enable?

EVO introduces transformative capabilities that extend well beyond traditional desktop geological modeling. The platform's architecture enables new approaches to data analysis, structural modeling, and computational workflows that were previously impractical or impossible.

Python Scripting Integration

One of EVO's most revolutionary features is its robust support for Python scripting. This capability addresses a longstanding limitation in dynamic geological modeling environments. As Stewart explains:

"We've always resisted scripting inside Leapfrog because it's very difficult in that dynamic environment… that becomes entirely possible within EVO as a workspace."

This integration enables several powerful capabilities:

• Direct data access: Scripts can interact directly with underlying geological data objects
• Custom workflows: Organizations can develop tailored analysis pipelines for specific needs
• Data science integration: Seamless connectivity with popular libraries like NumPy, pandas, and scikit-learn
• Automation: Repetitive modeling tasks can be programmatically executed and standardized
• Specialized tools: Development of organization-specific analytical tools beyond standard offerings

Python scripting effectively transforms EVO from a closed system to an extensible platform where geoscientists and data scientists can collaborate using industry-standard tools and techniques.

Driver: Advanced Structural Continuity Modeling

The platform introduces Driver, a sophisticated tool for structural and grade continuity analysis. Originally developed by a company acquired by Seequent "2.5-3 years ago" according to Stewart, Driver brings powerful new capabilities to geological modeling:

• Local-scale analysis: Detailed modeling of grade continuity using triaxial ellipsoids
• Structural feature extraction: Automated identification of lineations, foliations, and structural patterns
• Leapfrog integration: Direct incorporation of Driver outputs into broader geological models
• Enhanced visualization: Clearer representation of complex structural trends and relationships
• Process transparency: Exposure of previously opaque modeling parameters and decisions

Driver represents a significant advancement in how geologists understand and model structural continuity. By examining grade continuity at local scales and developing triaxial ellipsoids to represent directional trends, it provides more nuanced insights than traditional approaches.

How Will EVO Impact Current Leapfrog Users?

The introduction of EVO represents a significant evolution for Seequent's product ecosystem, but the company has planned a thoughtful transition path for existing users. Rather than forcing an abrupt change, Seequent is implementing a gradual rollout strategy that allows users to adopt new capabilities at their own pace.

Evolution of Structural Trend Modeling

EVO significantly enhances structural trend modeling capabilities, an area where many Leapfrog users have requested greater control and transparency. The improvements include:

• Enhanced visualization: Clearer representation of structural trends and relationships
• Transparent clustering: Exposed clustering processes that were previously hidden "black boxes"
• Parameter access: Visibility into modeling parameters that affect structural interpretations
• Problem decomposition: Better explanation of how complex problems are broken down and reconstructed
• Directional control: Enhanced influence over linearity and other structural properties

These improvements address longstanding user feedback about the opacity of structural modeling in previous versions. By exposing the underlying processes and parameters, EVO gives geologists greater confidence in their structural interpretations and more control over the modern mine planning trends.

Transition Path for Existing Users

Current Leapfrog users can expect a carefully managed transition to EVO's capabilities. According to Stewart, this includes:

• Gradual rollout: Beginning July 2025 with a phased approach rather than an abrupt transition
• Early access programs: Limited availability for select customers to provide feedback
• Familiar interfaces: Integration of EVO capabilities into recognizable Leapfrog environments
• Workflow continuity: Backward compatibility with existing projects and processes
• Comprehensive training: Resources to facilitate adoption of new capabilities

Stewart emphasizes that the transition will be deliberate: "It's not a splash launch… We need to bring people into that system. It's going to take time." This approach acknowledges the complexity of the platform and the importance of user comfort with new workflows.

The next Leapfrog release (version 24.2) has already touched "2.5 million lines of code" according to Stewart, demonstrating the scale of the technical transition underway.

What Advanced Geostatistical Tools Will EVO Offer?

EVO significantly expands Seequent's geostatistical capabilities through cloud-optimized algorithms and intuitive interfaces. These tools democratize advanced geostatistical techniques by making them more accessible to geologists without specialized statistical backgrounds.

Cloud-Based Geostatistical Algorithms

EVO provides access to a comprehensive suite of cloud-optimized geostatistical tools that leverage the platform's distributed computing capabilities:

• Integrated algorithms: Full incorporation of techniques developed by renowned geostatistician Alex Boucher
• Cloud optimization: Algorithms redesigned to leverage distributed processing environments
• Standardized implementations: Consistent approaches to common geostatistical methods
• Unified interfaces: Coherent user experience across different statistical techniques
• Accessible analytics: Complex statistical methods presented in geologically meaningful contexts

The cloud-based implementation allows these algorithms to process larger datasets more efficiently than desktop equivalents. This enables more sophisticated analyses while maintaining responsive performance.

Simulation and Uncertainty Analysis

The platform includes sophisticated simulation capabilities designed for accessibility and practical application. Stewart emphasizes that the focus is on the value of simulation rather than its technical implementation:

"Focus on why people want to use simulation—uncertainty is intuitive to geologists… Not how you make them."

Key features of the simulation toolkit include:

• Turning bands conditional simulation: Robust numerical analysis for resource estimation
• Simplified workflow: Streamlined process for creating reliable simulations
• Validation system: "Traffic light" approach ensuring output quality and reliability
• Uncertainty quantification: Tools focused on practical applications of uncertainty information
• Decision support: Methods to leverage simulation outputs for improved business decisions

This approach transforms simulation from a specialized technical exercise to an intuitive tool for understanding geological uncertainty. By focusing on the practical applications of uncertainty analysis, EVO makes these techniques more relevant to everyday geological decision-making.

How Does Seequent Labs Accelerate Innovation?

To maintain a rapid pace of innovation while managing a complex product ecosystem, Seequent has established a dedicated research arm that operates independently from main product development. This structure enables experimentation and rapid prototyping without disrupting core product stability.

Research and Development Structure

Seequent has created a specialized innovation center called Seequent Labs:

• Dedicated team: Approximately eight specialists focused exclusively on innovation
• Operational independence: Separated from main product development to enable nimble operation
• Rapid experimentation: Ability to test new concepts without affecting production systems
• Fail-fast methodology: Quick validation of ideas to identify promising directions
• Direct platform access: Seamless integration with the cloud environment for prototyping

As Stewart explains, this separation is crucial for innovation velocity:

"Seequent Labs gives us the ability to innovate and iterate quickly… Separated from the behemoth that is Leapfrog."

This structure allows specialists to explore new approaches without the constraints of existing product architectures or release schedules. The result is accelerated innovation that can then be incorporated into main product lines when mature.

Development Velocity and Feature Implementation

The combination of Seequent Labs and the EVO platform architecture enables significantly faster development cycles:

• Rapid response: Quicker reaction to emerging industry needs and user feedback
• Agile development: More flexible development cycles compared to traditional software
• Focused solutions: Targeted tools addressing specific geological challenges
• Compressed timelines: Reduced interval between concept and implementation
• Specialized capabilities: Ability to address niche requirements more effectively

This approach has already yielded results, with innovations like Driver moving from acquisition to integration within a compressed timeframe. The cloud platform further accelerates this process by providing a consistent environment for development and deployment.

What Role Will AI Play in EVO's Future?

Artificial intelligence represents a significant opportunity for geoscientific modeling, and EVO has been architected with AI in mining technology integration in mind. The platform's data structures and extensible design create an ideal foundation for incorporating machine learning and other AI technologies.

Artificial Intelligence Integration Potential

EVO creates a foundation for incorporating AI into geoscientific modeling through several key architectural choices:

• ML-optimized data structures: Organization of geological information compatible with machine learning models
• Deployment infrastructure: Platform architecture supporting AI model integration and execution
• Automated interpretation: Framework for feature recognition and pattern analysis
• Predictive capabilities: Foundation for forecasting geological properties and relationships
• Integration framework: Structure for incorporating third-party AI solutions seamlessly

Stewart acknowledges the transformative potential of AI while emphasizing EVO's role as an enabling platform:

"The potential for AI… [EVO] will enable other people to build functionality on top of that platform."

This approach positions EVO as both a direct solution for current modeling needs and a foundation for future AI-enhanced capabilities. The standardized data objects are particularly important for AI applications, as they provide consistent, well-structured information for training and inference.

Collaborative Development Ecosystem

The platform is designed to foster collaboration and third-party development, creating an ecosystem where specialized tools can build on EVO's foundation:

• Open architecture: Technical framework allowing others to extend core capabilities
• Specialized extensions: Opportunity for niche tools addressing specific geological domains
• Partnership framework: Structure for industry and academic collaboration
• Standardized interfaces: Consistent APIs for plugin and extension development
• Innovation marketplace: Potential for ecosystem of specialized geological applications

This collaborative approach multiplies innovation potential by enabling specialists across the industry to contribute their expertise. Rather than attempting to solve every geological modeling challenge internally, Seequent has created an environment where the broader community can participate in extending the platform's capabilities.

How Will EVO Address Current Industry Challenges?

The geoscientific modeling industry faces several persistent challenges that EVO's architecture and capabilities are specifically designed to address. From data integration issues to uncertainty quantification, the platform tackles fundamental problems that have limited the effectiveness of geological modeling.

Data Integration and Workflow Optimization

EVO tackles several persistent industry problems related to data management and workflow efficiency:

• Integration gaps: Bridging disconnections between data collection and model implementation
• Manual processing: Reducing labor-intensive intervention in data preparation workflows
• Consistency issues: Improving uniformity between different modeling stages and applications
• Traceability limitations: Enhancing audit trails throughout the modeling process
• Complexity barriers: Simplifying advanced geostatistical processes for broader adoption

These improvements address fundamental pain points in current geological modeling workflows. By creating a cohesive data environment with standardized objects and seamless tool integration, EVO reduces the friction that currently exists between different stages of the modeling process.

Uncertainty Quantification and Decision Support

The platform provides enhanced tools for understanding and communicating geological uncertainty:

• Intuitive simulation: More accessible approaches to probability analysis and scenario modeling
• Practical application: Focus on using uncertainty information for decision-making
• Actionable insights: Tools that translate technical outputs into business-relevant information
• Effective visualization: Techniques that communicate confidence levels clearly to stakeholders
• Integrated risk assessment: Uncertainty quantification throughout the modeling process

This emphasis on practical uncertainty quantification transforms simulation from a technical exercise to a decision support tool. By making these techniques more accessible and focusing on their business applications, EVO helps organizations make better-informed decisions based on a realistic understanding of geological uncertainty.

FAQ: Common Questions About EVO

When will EVO be available to users?

EVO will begin commercial rollout in July 2025, with a phased approach rather than an immediate full launch. As Mike Stewart explains, "It's not a splash launch… We need to bring people into that system. It's going to take time." Limited availability programs are already underway with select customers providing feedback on the platform.

Will EVO replace existing Leapfrog software?

Rather than an immediate replacement, EVO represents an evolution of Seequent's technology stack. The next Leapfrog release will include EVO subscription options, allowing users to access new capabilities while maintaining workflow continuity. This gradual transition ensures users can adopt new features at their own pace without disrupting existing projects.

How does EVO compare to competing platforms?

EVO represents Seequent's strategic vision rather than a reaction to competitors. The platform's focus on cloud-native architecture, data objects, and Python scripting integration creates a distinct approach to geoscientific modeling challenges. Its emphasis on accessibility, collaboration, and extensibility sets it apart from traditional desktop-focused solutions.

What hardware requirements will EVO have?

As a cloud-based platform, EVO shifts computational requirements from local hardware to remote servers, potentially reducing the need for specialized workstations. Users will primarily need reliable internet connectivity rather than powerful local machines. This change democratizes access to sophisticated modeling capabilities by removing hardware barriers.

How will EVO handle large geological datasets?

The cloud architecture enables scalable processing capabilities, allowing the system to handle substantially larger datasets than desktop-based solutions. By leveraging distributed computing resources, EVO can efficiently process complex models that would overwhelm traditional systems. This scalability is particularly valuable for comprehensive resource estimation and [mineral deposit tiers guide](https://discoveryalert.com.au/news/mineral

Ready to Catch the Next Major Mineral Discovery?

Discovery Alert's proprietary Discovery IQ model instantly notifies investors of significant ASX mineral discoveries, transforming complex data into actionable insights that could lead to substantial returns. Explore why historic discoveries can generate exceptional market outcomes by visiting Discovery Alert's dedicated discoveries page and begin your 30-day free trial today to position yourself ahead of the market.