A Step by Step Approach to Improving Data Quality in Drilling Operations: Field Trials in North America

2016 ◽  
Author(s):  
Pradeepkumar Ashok ◽  
Adrian Ambrus ◽  
Dawson Ramos ◽  
John Lutteringer ◽  
Michael Behounek ◽  
...  
Keyword(s):  
North America ◽  
Data Quality ◽  
Field Trials ◽  
Drilling Operations

Improving Real-Time Drilling Data Quality Using Artificial Intelligence and Machine Learning Techniques

2021 ◽  
Author(s):  
S. H. Al Gharbi ◽  
A. A. Al-Majed ◽  
A. Abdulraheem ◽  
S. Patil ◽  
S. M. Elkatatny
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Data Quality ◽  
Real Time ◽  
Input Data ◽  
Support Vector ◽  
The Real ◽  
Drilling Data ◽  
Drilling Operations

Abstract Due to high demand for energy, oil and gas companies started to drill wells in remote areas and unconventional environments. This raised the complexity of drilling operations, which were already challenging and complex. To adapt, drilling companies expanded their use of the real-time operation center (RTOC) concept, in which real-time drilling data are transmitted from remote sites to companies’ headquarters. In RTOC, groups of subject matter experts monitor the drilling live and provide real-time advice to improve operations. With the increase of drilling operations, processing the volume of generated data is beyond a human's capability, limiting the RTOC impact on certain components of drilling operations. To overcome this limitation, artificial intelligence and machine learning (AI/ML) technologies were introduced to monitor and analyze the real-time drilling data, discover hidden patterns, and provide fast decision-support responses. AI/ML technologies are data-driven technologies, and their quality relies on the quality of the input data: if the quality of the input data is good, the generated output will be good; if not, the generated output will be bad. Unfortunately, due to the harsh environments of drilling sites and the transmission setups, not all of the drilling data is good, which negatively affects the AI/ML results. The objective of this paper is to utilize AI/ML technologies to improve the quality of real-time drilling data. The paper fed a large real-time drilling dataset, consisting of over 150,000 raw data points, into Artificial Neural Network (ANN), Support Vector Machine (SVM) and Decision Tree (DT) models. The models were trained on the valid and not-valid datapoints. The confusion matrix was used to evaluate the different AI/ML models including different internal architectures. Despite the slowness of ANN, it achieved the best result with an accuracy of 78%, compared to 73% and 41% for DT and SVM, respectively. The paper concludes by presenting a process for using AI technology to improve real-time drilling data quality. To the author's knowledge based on literature in the public domain, this paper is one of the first to compare the use of multiple AI/ML techniques for quality improvement of real-time drilling data. The paper provides a guide for improving the quality of real-time drilling data.

Impact of Data Quality on Well Operations: Case Study of Work-over Operations

2016 ◽  
Author(s):  
Alfred Enyekwe ◽  
Osahon Urubusi ◽  
Raufu Yekini ◽  
Iorkam Azoom ◽  
Oloruntoba Isehunwa
Keyword(s):  
Data Quality ◽  
Data Management ◽  
Real Time ◽  
Data Management System ◽  
Quality Data ◽  
Process Safety ◽  
Well Control ◽  
Drilling Operations ◽  
Short Time

ABSTRACT Significant emphasis on data quality is placed on real-time drilling data for the optimization of drilling operations and on logging data for quality lithological and petrophysical description of a field. This is evidenced by huge sums spent on real time MWD/LWD tools, broadband services, wireline logging tools, etc. However, a lot more needs to be done to harness quality data for future workover and or abandonment operations where data being relied on is data that must have been entered decades ago and costs and time spent are critically linked to already known and certified information. In some cases, data relied on has been migrated across different data management platforms, during which relevant data might have been lost, mis-interpreted or mis-placed. Another common cause of wrong data is improperly documented well intervention operations which have been done in such a short time, that there is no pressure to document the operation properly. This leads to confusion over simple issues such as what depth a plug was set, or what junk was left in hole. The relative lack of emphasis on this type of data quality has led to high costs of workover and abandonment operations. In some cases, well control incidents and process safety incidents have arisen. This paper looks at over 20 workover operations carried out in a span of 10 years. An analysis is done on the wells’ original timeline of operation. The data management system is generally analyzed and a categorization of issues experienced during the workover operations is outlined. Bottlenecks in data management are defined and solutions currently being implemented to manage these problems are listed as recommended good practices.

scholarly journals Survival and Growth of Amur maackia Seedlings Across North America

HortScience ◽  
1997 ◽  
Vol 32 (3) ◽  
pp. 508B-508
Author(s):  
Anthony S. Aiello ◽  
William R. Graves
Keyword(s):  
North America ◽  
Field Trials ◽  
Stem Length ◽  
Site Location ◽  
Growing Seasons ◽  
Survival And Growth ◽  
Sibling Group ◽  
Selection Of ◽  
Half Sibling ◽  
Sibling Groups

Amur maackia (Maackia amurensis Rupr. & Maxim.) has potential for use in small, urban, or cold landscapes. Although Amur maackia is becoming increasingly popular, plants are currently grown from open-pollinated seed populations, and there has been no selection of cultivars. We have addressed the effects of climate on growth and have begun field trials for selection of horticulturally superior genotypes. In May 1995, a field trial near Ames was begun with 337 plants. These were selected from more than 2000 greenhouse-grown seedlings to represent 32 half-sibling seed groups from 16 arboreta across North America. After two growing seasons, the increase in stem length among seed groups ranged from 3% to 75%. Survival rate did not vary with seed group. In a related study, 30 plants from six half-sibling groups have been established at each of 10 sites in the U.S. and four in Canada to assess effects of location on survival and growth. The influence of seed group on survival after 1 year varied with the trial site location. Survival among combinations of half-sibling group and trial location ranged from 0% to 100% (mean = 54%). Half-sibling group and trial location affected growth without interaction. The greatest growth across locations, an 83% increase in stem length, was shown by seeds that originated from a tree at the Arnold Arboretum. At the 14 locations, changes in stem length over half-sibling groups varied from <0% in Ithaca, N.Y., to 179% in Puyallup, Wash.

Field Test of the WeevilHadroplonthus trimaculatusand the FleabeetlePsylliodes chalcomeraAgainst Musk Thistle (Carduus nutans)

Weed Science ◽  
1993 ◽  
Vol 41 (4) ◽  
pp. 656-663 ◽  
Author(s):  
Paul H. Dunn ◽  
Gaetano Campobasso
Keyword(s):  
Biological Control ◽  
North America ◽  
Field Test ◽  
Host Plants ◽  
Free Choice ◽  
Natural Populations ◽  
Field Trials ◽  
Biological Control Of Weeds ◽  
Carduus Nutans ◽  
Test Plants

This study was conducted to determine if field evaluations could be used to select insects for biological control of musk thistle. Host specificity and larval development of a weevil,Hadroplonthus trimaculatus, and a fleabeetle,Psylliodes chalcomera, were studied in field trials near Rome, Italy, in which insects were allowed free choice of several hosts. Natural populations of these two insects, which do not occur in North America, were exposed to North American species ofCirsium, Carduus, and selected crops. Adult insects and larvae on host plants were identified and counted on test plants from North America and native attraction plants. In addition to infesting musk thistle, weevil adults and larvae were recorded on flodman thistle, wavyleaf thistle, and spinosissimum thistle. Consequently, this insect was not suitable for introduction into North America. The fleabeetle would be satisfactory for biological control since no adults or larvae were recorded onCirsiumspp. or economic plants. These studies show that field trials are a valid method for identifying specific and nonspecific candidate insects for biological control of weeds.

scholarly journals Underreporting COVID-19: the curious case of the Indian subcontinent

2020 ◽  
Vol 148 ◽  
Author(s):  
Raaj Kishore Biswas ◽  
Awan Afiaz ◽  
Samin Huq
Keyword(s):  
North America ◽  
Data Quality ◽  
Indian Subcontinent ◽  
Systematic Bias ◽  
Test Coverage ◽  
Quality Test ◽  
Middle Income ◽  
Middle Income Countries ◽  
Cross Country ◽  
Existing Data

Abstract COVID-19 has spread across the globe with higher burden placed in Europe and North America. However, the rate of transmission has recently picked up in low- and middle-income countries, particularly in the Indian subcontinent. There is a severe underreporting bias in the existing data available from these countries mostly due to the limitation of resources and accessibility. Most studies comparing cross-country cases or fatalities could fail to account for this systematic bias and reach erroneous conclusions. This paper provides several recommendations on how to effectively tackle these issues regarding data quality, test coverage and case counts.

Cochylis hospes (Lepidoptera: Tortricidae) damage to male lines varies significantly and inbred susceptibility predicts damage to hybrids

2019 ◽  
Vol 151 (6) ◽  
pp. 817-823 ◽  
Author(s):  
Jarrad R. Prasifka
Keyword(s):  
North America ◽  
Predictive Power ◽  
Primary Source ◽  
Field Trials ◽  
Inbred Lines ◽  
Insect Damage ◽  
Seed Damage ◽  
Damage Data ◽  
Cochylis Hospes ◽  
Sunflower Moth

AbstractLarvae of Cochylis hospes (Walsingham) (Lepidoptera: Tortricidae) (banded sunflower moth) are a primary source of insect damage to seeds of cultivated sunflower, Helianthus annuus Linnaeus (Asteraceae), in North America. Field trials were used to evaluate seed damage under natural infestations for panels of publicly released male lines, publicly derived hybrids (females crossed to one common male parent), and commercial hybrids over a total of four years. For trials in 2013–2014 including 17 male lines, seed damage ranged from 3% to 19%. The least damaged male, RHA 266, was statistically similar to one other male, RHA 455. Three commercial hybrids used as checks also received very little seed damage (< 5%). In trials during 2016–2017, hybrids created by pollinating 15 different female lines with RHA 266 showed 4–14% damage. Data from female parents explained about 28% of variation in seed damage for the hybrids. Results confirm cultivated sunflower has greater variation in susceptibility to C. hospes than previously believed, and that seed damage to inbred lines provides some predictive power for hybrids. Though breeding for resistance to C. hospes seems possible, it may be too labour-intensive without relating resistance to more easily measurable traits or genetic markers.

A Tool for Derivation of Real Time Lithological Information from Drill Bit Sound

2021 ◽  
Author(s):  
Yunlai Yang ◽  
Wei Li ◽  
Fahd A. Almalki ◽  
Maher I. Almarhoon
Keyword(s):  
Real Time ◽  
Sound Transmission ◽  
Field Trials ◽  
Drill String ◽  
Drive Shaft ◽  
Drill Bit ◽  
Acoustic Sensors ◽  
Preliminary Results ◽  
Drilling Operations ◽  
Real Time Applications

Abstract Real time lithological information at the drill bit is required for some important drilling operations, such as geo-steering and casing shoe positioning. This paper presents a novel tool "Petro-phone" for recording and processing drill bit sounds, which are generated by the drill bit cutting the rock, in order to provide real time lithological information for the rock at the drill bit. A prototype and a preliminary professional version of Petro-phone have been developed and field trialed. Petro-phone is a surface tool with its acoustic sensors attached to the top drive of a drill rig at some strategical locations for maximally picking up drill bit sounds. The drill bit sounds generated at the drill bit transmit along drill string and drive shaft to reach to the acoustic sensors. Since all the parts along the drill bit sound transmission pathway are made of steel, the drill bit sounds transmit efficiently from the source (drill bit) to the sensors. Preliminary results from two field trials show that drill bit sound patterns correlate with lithologies. The results also indicate that a parameter "Apparent Power" of drill bit sounds negatively correlates with gamma log. Due to its true real time nature, Petro-phone potentially has some real time applications, such as geo-steering, casing shoes positioning. Recorded drill bit sound can also potentially be used to derive lithological information, such as lithology type.

scholarly journals Genetic Diversity, Cytogenetics, and Biomass Yields among Taxa of Giant Reeds (Arundo Species)

2016 ◽  
Vol 141 (3) ◽  
pp. 256-263 ◽  
Author(s):  
Darren H. Touchell ◽  
Thomas G. Ranney ◽  
Dilip R. Panthee ◽  
Ronald J. Gehl ◽  
Alexander Krings
Keyword(s):  
Genetic Diversity ◽  
North America ◽  
South Asia ◽  
Field Trials ◽  
Issr Markers ◽  
Genetic Distances ◽  
Arundo Donax ◽  
Ploidy Levels ◽  
Biomass Yields ◽  
Principle Coordinate Analysis

Genetic diversity and cytogenetics of 31 accessions of Arundo L., collected from North America and South Asia, were characterized using 20 intersimple sequence repeat (ISSR) markers, flow cytometry, and cytology. In addition, field trials of 23 Arundo donax L. accessions were established in 2011 and harvested in 2012 to 2013 to assess annual biomass yields. Cluster analysis, based on Jaccard’s similarity coefficient method, clearly differentiated Arundo formasana Hack. from A. donax and a third unidentified Arundo taxon. Arundo donax further contained two subgroups representing North American (naturalized and cultivated) and South Asian collections. Within each A. donax subgroup, genetic distances were very low (0.03 for North America and 0.07 for South Asia). Principle coordinate analysis further supported distinct clusters. Relative genome sizes were determined using Pisum sativum L. as the reference genome and 6-diamidino-2-phenylindole (DAPI) fluorochrome. Chromosome numbers (2n), ploidy levels, and 2C relative genome sizes ranged from ≈62 to 105, near 12x to near 18x, and 2.78 to 4.13 pg, respectively, and were similar within each taxa/subgroup. While there was a low level of genetic variability among A. donax accession, dry biomass yields varied significantly ranging from 6.5 to 65 Mg·ha−1 per year for the third growing season.

Sign in / Sign up

Export Citation Format

Share Document