GPU installation, Houston. (Image source: DUG)

DUG Technology (DUG) has deployed 82 new NVIDIA H200 machines, integrating some of the most advanced AI and compute-hardware technologies into the company’s high performance computing (HPC) ecosystem

The expansion adds an impressive 41 petaflops to DUG’s global supercomputing network and will support both growing client demand and future innovation.

Each machine delivers an order-of-magnitude performance uplift relative to DUG's fastest CPU-only hardware, further reducing the company's turnaround times across both testing and production.

Each machine is configured with:

• 8 × NVIDIA H200 GPUs (141 GB each)
• Dual AMD EPYC Turin CPUs
• 4 TB of system memory and 32 TB of local flash
• 100 Gbps networking

“This upgrade significantly increases our total compute power. This translates to even faster delivery of huge datasets and more computationally intensive workloads, from AI-inference applications, to advanced seismic processing and imaging workflows, including our revolutionary DUG Elastic MP-FWI Imaging technology,” said Harry McHugh, DUG’s chief information officer.

All 82 machines are now installed and operational, delivering results for both DUG’s services clients and DUG HPC Cloud users.

DUG is an ASX-listed technology company that provides innovative processing and storage solutions for real-world applications. It delivers proprietary software (DUG Insight), cloud-based HPC as-a-service (DUG HPC Cloud), immersion-cooling (DUG Cool), and edge-computing solutions (DUG Nomad), backed by bespoke support for technology onboarding.

Decades of experience in algorithm development, optimisation and HPC craft enables DUG to solve complex problems for clients. With offices in Perth, London, Houston, Kuala Lumpur, Abu Dhabi and Rio de Janeiro, DUG designs, owns and operates a network of some of the largest supercomputers on Earth.

The new detector combines advanced gas detection, lone worker protection, and radio-quality communication in one rugged device. (Image source: Blackline Safety)

Blackline Safety has launched G8, a new connected gas detector with a rugged, IP-67 rating designed to meet the most demanding industrial environments

Building on the company's G7 line, the new detector combines advanced gas detection, lone worker protection, and radio-quality communication in one rugged device that connects workers to each other, to their safety teams, and to the broader digital worksite — with real-time data streamed to the cloud.

The detector features swappable cartridges covering more than 20 gases, dual-band GNSS/GPS (L1/L5), delivering more reliable positioning in challenging environments, and access to ZoneAware geofencing in Blackline Live.

Offering enhanced speaker and mic technology it enables loud, clear worldwide radio functionality so crews can talk across sites, regions, or even countries; emergency voice calling – connecting workers directly with a live monitoring agent when an alert is triggered; text messaging and mass notifications; an internal full-range speaker delivering up to 1W of audio power, and optional RSM with up to 1.5W output to extend sound capability even further.

A 64-colour backlit display and 35-lumen, easy-access flashlight offer reliable visibility in low-light or confined spaces.

Live data is streamed from the device to Blackline’s data and analytics platform—Blackline Live—via the cloud. This gives safety leaders real-time visibility into worker status, gas readings, and site conditions, and it gives operations teams actionable insights to prevent incidents, reduce delays, and keep projects moving.

G8 is future-ready to plug into other digital platforms from human resource management systems (HRMS) to field service management tools to hot-permitting applications and more. It will continue to evolve with new capabilities, expanded integrations, and emerging technologies like AI-driven insights.

“G8 gives workers access to the tools and information they need to confidently get the job done and get home safe,” said Cody Slater, CEO and chair, Blackline Safety. “By unifying gas detection, real-time monitoring, and communication in one connected device, we’re delivering more than incremental improvement. We’re giving every worker a direct line to the people, data, systems and support they need to make faster, safer decisions.”

The HyperSteer MX directional drill bit improves durability and maximises directional control. (Image source: Adobe Stock)

Halliburton has launched the HyperSteer MX directional drill bit, a shankless matrix-body bit that improves durability and maximises directional control, reducing well construction time and costs

The bit delivers longer runs and fewer trips, resists erosion and abrasion, and performs reliably in high-flow, abrasive environments.

HyperSteer MX directional drill bits utilise advanced matrix materials to resist erosion and abrasion, extend bit life in abrasive, high-flow environments, and improve efficiency and reliability during operations.
HyperSteer MX directional drill bits deliver precise steerability that maximises performance in vertical, curve, and lateral sections, and minimises well time and reduces well construction costs. The bit reduces trips, lowers exposure to unplanned events, and maintains directional precision in the most abrasive environments.

HyperSteer MX directional drill bits extend the HyperSteer portfolio and reflect Halliburton’s investment in innovative engineered solutions that maximise asset value.

“HyperSteer MX directional drill bits mark a major step forward in drilling. The technology combines the precise steerability of HyperSteer directional drill bits with a durable matrix body. It allows operators to drill longer in harsh environments and supports efforts to minimise well time and maximise directional performance for customers,” said Amr Hassan, vice president, Drill Bits and Services, Halliburton.

A multi-well correlation for three wells. Shown (from left to right for each well) are gamma ray, AI-predicted lithology, and far-stack seismic amplitude with the gamma ray curve in the well position. (Image source: DUG)

A multi-well correlation for three wells. Shown (from left to right for each well) are gamma ray, AI-predicted lithology, and far-stack seismic amplitude with the gamma ray curve in the well position.

Faster. Consistent. Scalable. How AI is transforming lithofacies interpretation

Lithofacies interpretation remains one of the most fundamental tasks in subsurface evaluation – and one of the most time-intensive. Despite advances in logging technology and computing power, workflows are still dominated by manual interpretation, subjective judgement and inevitable variability between interpreters. When dozens or hundreds of wells must be assessed, particularly in early-stage screening or regional studies, this inconsistency can delay decisions around reservoir presence, interval ranking and further petrophysical review.

A new deep-learning workflow developed at DUG demonstrates how that bottleneck can be significantly reduced – delivering fast, reproducible lithofacies predictions directly from standard wireline logs. Rather than replacing geological interpretation, the approach provides a consistent first-pass screening tool that allows interpreters to focus attention where it adds the most value.

A key differentiator of the workflow is its foundation in rock physics. Any supervised machine-learning model is only as reliable as its training labels, and in this case those labels are derived from carefully curated end-member lithologies. These end members represent the cleanest and most internally consistent examples of sandstones, shales, siltstones and carbonates, selected only where wireline responses align physically and geologically. By excluding intervals affected by poor borehole conditions or noisy measurements, the resulting training dataset remains objective, consistent and firmly grounded in established rock physics relationships.

The model architecture combines a transformer-based sequence model with a one-dimensional convolutional neural network, also previously developed by DUG. This enables it to capture both long-range stratigraphic trends and local log-response variability, while handling missing data through attention masking. Crucially, the workflow accepts whichever subset of common wireline curves is available for a given well, allowing lithofacies prediction even in older or incomplete datasets.

Case studies using legacy data illustrate how DUG’s workflow delivers insight beyond speed alone. Artificial intelligence (AI)-generated lithofacies predictions highlighted subtle inconsistencies caused by density spiking and sonic cycle skipping – issues that were not immediately apparent in conventional single-well analysis. By flagging these intervals, the workflow guided targeted quality control and conditional correction, improving multi-well correlation without introducing artificial geological trends.

Rather than obscuring interpretation, DUG’s workflow makes inconsistencies visible – highlighting where log behaviour departs from rock physics expectations and directing interpreter attention where it is most needed.

This work will be presented by DUG’s machine learning software engineer, Kyle Rosa, at the SEG | DGS | SPE KSA Workshop: Bridging the Gap: Geosciences to Engineering in Al Khobar, Saudi Arabia, from 10–12 February 2026.

As geoscience datasets continue to grow in size and complexity, AI-augmented interpretation workflows help enable faster, more consistent subsurface decisions – without removing the interpreter from the decision-making loop.