Frequently asked questions

DXPLR ingests orbital hyperspectral data cubes (VNIR/SWIR/TIR) and applies physics-informed AI to isolate subsurface harmonic frequency responses from crustal noise. These signals are cross-referenced against DXPLR's proprietary reference database of calibrated mineral and hydrocarbon resonance signatures to confirm the target commodity's identity. Once verified, our inversion models calculate target depth, thickness, and intensity down to +3,000 meters within a ±30 m tolerance.

Very little. Depending on the engagement, DXPLR can begin with a defined area of interest and target commodity. Because the process is remote and non-invasive, physical site access is generally not required.

DXPLR results can be validated against independent subsurface data—including drill results, well logs, assays, seismic, geological, geophysical and geochemical information. In blind tests, predictions are established before DXPLR receives the corresponding validation data, allowing results to be objectively compared against what is subsequently observed.

DXPLR works across minerals and hydrocarbons, onshore and offshore. Because the technology is space-based and remotely deployed, it can evaluate opportunities across geographic regions and operating environments without requiring physical access.

A typical DXPLR intelligence cycle can be completed in approximately four weeks, depending on the size, complexity and objectives of the project. This allows exploration decisions to be advanced in weeks rather than the months or years often associated with conventional workflows.

Yes. DXPLR works through flexible partnership structures, including project-level co-investment, exploration partnerships, intelligence and data licensing, and technology or service alliances. The appropriate structure depends on the opportunity and the objectives of the partner.

No. DXPLR is designed to complement conventional exploration intelligence, not replace it. Traditional methods help determine where hydrocarbons or mineralization could occur; DXPLR adds independent direct-detection intelligence to help assess whether the targeted signature is actually present. Together, they support higher-conviction exploration decisions.

DXPLR converts its analysis into decision-ready intelligence, which may include opportunity maps, exploration fairways, virtual boreholes, target ranking, prospect prioritization and drill recommendations all validate against conventional exploration data. Deliverables are designed to move from technical interpretation to investment decision.

DXPLR has demonstrated detection capability beyond 3,000 meters. Actual project capability depends on the target, geological setting and engagement parameters.

DXPLR has achieved 90%+ results in selected blind validation programs across mineralization and hydrocarbons, using pre-agreed validation criteria and comparison against independent subsurface data. Results vary by project, geology, target and validation methodology.

Conventional satellite and remote-sensing approaches generally characterize surface conditions or use indirect indicators. DXPLR's proprietary approach is designed to identify frequency-resonance signatures associated with targeted subsurface mineralization and hydrocarbons, providing an additional layer of intelligence before drilling.

Because drilling remains the ultimate physical test of the subsurface. DXPLR is designed to improve the decision before capital is committed to drilling—helping identify, rank and validate the opportunities that warrant further investment. The objective is not to eliminate drilling, but to drill to validate the best opportunities rather than drill to discover where they might be. Drill to validate, not to discover.