Automating Reservoir Pressure Measurement Insights from Deep Water Carbonate Formations in Brazil

Abstract The primary objective is to achieve consistent pressure measurement acquisition while optimizing the time required for high-quality data collection. Specifically, for carbonate formations in deep water Brazil, where reservoir intervals often exceed 200 meters, the aim is to streamline wireline formation tester programs, which can typically take less than a day up to a few days depending on formation thickness and type. To achieve desired efficiency in pretesting acquisition, we implemented an automated workflow and AI classification of pretests. Automation reduces human intervention in tasks at the pretest station. The AI, a supervised algorithm trained on a generalist dataset of pressure build-ups, predicts valid or invalid pretests within the first 60 seconds. This enables rapid decision-making to either wait for pressure stabilization or abort and retry with different parameters. We measure total station time and time between events/pretests, comparing these metrics with other wells in the same reservoir to evaluate efficiency. The proposed solution was successfully implemented in three carbonate formation fields in Brazil. The results, compared with previous manual pressure measurement sequences, demonstrated significant improvements. The total time required to complete the pressure campaigns was reduced, and the measurement sequence was optimized at all stations. A standardized protocol for pressure measurement was established, with consistent pressure stabilization criteria applied across the entire reservoir intervals. Automation in WFT pressure measurements yielded positive outcomes. The WFT probe set and retract times were optimized at all pressure stations, and the build-up pressure behavior was evaluated within a 60-second window, enabling quick decision-making within minutes. These advancements highlight the efficiency and effectiveness of automated pressure measurement in deep water carbonate formations. For over 50 years, WFT pressure measurements have been integral to formation evaluation programs, typically relying on experienced professionals for high-quality data acquisition. This paper introduces a novel automated solution that complements traditional methods, enhancing data quality and significantly reducing rig time, thereby advancing the current state of knowledge in the petroleum industry.

Authors

Publication Details

Published
2024-10-20
DOI
https://doi.org/10.2118/223228-ms
Primary Topic
Reservoir Engineering and Simulation Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Automating Reservoir Pressure Measurement Insights from Deep Water Carbonate Formations in Brazil

A. Bertolini, Mário A. R. Dantas, E. Haik
Reservoir Engineering and Simulation Methods
article

Automating Reservoir Pressure Measurement Insights from Deep Water Carbonate Formations in Brazil

A. Bertolini, Mário A. R. Dantas, E. Haik
article en

Abstract

Abstract The primary objective is to achieve consistent pressure measurement acquisition while optimizing the time required for high-quality data collection. Specifically, for carbonate formations in deep water Brazil, where reservoir intervals often exceed 200 meters, the aim is to streamline wireline formation tester programs, which can typically take less than a day up to a few days depending on formation thickness and type. To achieve desired efficiency in pretesting acquisition, we implemented an automated workflow and AI classification of pretests. Automation reduces human intervention in tasks at the pretest station. The AI, a supervised algorithm trained on a generalist dataset of pressure build-ups, predicts valid or invalid pretests within the first 60 seconds. This enables rapid decision-making to either wait for pressure stabilization or abort and retry with different parameters. We measure total station time and time between events/pretests, comparing these metrics with other wells in the same reservoir to evaluate efficiency. The proposed solution was successfully implemented in three carbonate formation fields in Brazil. The results, compared with previous manual pressure measurement sequences, demonstrated significant improvements. The total time required to complete the pressure campaigns was reduced, and the measurement sequence was optimized at all stations. A standardized protocol for pressure measurement was established, with consistent pressure stabilization criteria applied across the entire reservoir intervals. Automation in WFT pressure measurements yielded positive outcomes. The WFT probe set and retract times were optimized at all pressure stations, and the build-up pressure behavior was evaluated within a 60-second window, enabling quick decision-making within minutes. These advancements highlight the efficiency and effectiveness of automated pressure measurement in deep water carbonate formations. For over 50 years, WFT pressure measurements have been integral to formation evaluation programs, typically relying on experienced professionals for high-quality data acquisition. This paper introduces a novel automated solution that complements traditional methods, enhancing data quality and significantly reducing rig time, thereby advancing the current state of knowledge in the petroleum industry.

Openalex Percentile: Top 76%
Reservoir Engineering and Simulation Methods
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.

Automating Reservoir Pressure Measurement Insights from Deep Water Carbonate Formations in Brazil — A. Bertolini, Mário A. R. Dantas, et al. · (2024) | TGRS Research Map | TGRS