Work

Design and optimization of high-density calcium nitrate completion fluids for HPHT applications: an integrated experimental and machine learning approach

Year: 2026
Type: article
Abstract: Exploring hydrocarbon resources in High-Pressure/High-Temperature (HPHT) environments requires advanced, solids-free completion fluids to maximize productivity and mitigate formation damage. This study presents an integrated approach combining laboratory experimentation and machine learning (ML) to design high-density, thermally stable completion fluids. The experimental phase evaluated the incorporation of polyols (MEG, DEG, TEG) into calcium nitrate brines. Results established that while all polyols enhanced density and thermal stability, MEG provided the optimal equilibrium between density, rheology, and clarity, avoiding the excessive viscosity induced by heavier glycols. Leveraging the experimental dataset, predictive ML models were subsequently developed to forecast critical fluid properties. A comparative analysis of five algorithms revealed a task-specific optimal hierarchy: the Random Forest algorithm best captured the complex non-linearities of viscosity, whereas the Extra Trees algorithm demonstrated superior precision in modeling deterministic, thermodynamic density variations. Ultimately, this research delivers a validated fluid formulation for HPHT operations and establishes robust computational frameworks to streamline the future design and optimization of advanced completion fluids.
Language: English
Subfield: Fuel Technology
Field: Energy
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7236377663
FWCI:
Cites: 40
Cited by:
Related to: 10