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

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.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-18
DOI
https://doi.org/10.1038/s41598-026-79263-x
Primary Topic
Drilling and Well Engineering
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Javad Mahdavi Kalatehno, Ehsan Khamehchi, Saber Saffar, Alireza Ahmadi
6 links
Scientific Reports
Drilling and Well Engineering
article

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

Javad Mahdavi Kalatehno, Ehsan Khamehchi, Saber Saffar, Alireza Ahmadi
article en

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.

Scientific Reports
Amirkabir University of Technology (IR)
Iran National Science Foundation
Drilling and Well Engineering
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon