scholarly journals Comparative evaluation of multi-basin production performance and application of spatio-temporal models for unconventional oil and gas production prediction

2020 ◽  
Vol 10 (8) ◽  
pp. 3091-3110 ◽  
Author(s):  
M. E. Wigwe ◽  
E. S. Bougre ◽  
M. C. Watson ◽  
A. Giussani
Keyword(s):  
Oil And Gas ◽  
Generalized Additive Models ◽  
Gas Production ◽  
Additive Models ◽  
Machine Learning Algorithms ◽  
Production Performance ◽  
Spatial And Temporal Variability ◽  
Temporal Models ◽  
Spatio Temporal ◽  
Production Prediction

Abstract Modern data analytic techniques, statistical and machine-learning algorithms have received widespread applications for solving oil and gas problems. As we face problems of parent–child well interactions, well spacing, and depletion concerns, it becomes necessary to model the effect of geology, completion design, and well parameters on production using models that can capture both spatial and temporal variability of the covariates on the response variable. We accomplish this using a well-formulated spatio-temporal (ST) model. In this paper, we present a multi-basin study of production performance evaluation and applications of ST models for oil and gas data. We analyzed dataset from 10,077 horizontal wells from 2008 to 2019 in five unconventional formations in the USA: Bakken, Marcellus, Eagleford, Wolfcamp, and Bone Spring formations. We evaluated well production performance and performance of new completions over time. Results show increased productivity of oil and gas since 2008. Also, the Bakken wells performed better for the counties evaluated. We present two methods for fitting spatio-temporal models: fixed rank kriging and ST generalized additive models using thin plate and cubic regression splines as basis functions in the spline-based smooths. Results show a significant effect on production by the smooth term, accounting for between 60 and 95% of the variability in the six-month production. Overall, we saw a better production response to completions for the gas formations compared to oil-rich plays. The results highlight the benefits of spatio-temporal models in production prediction as it implicitly accounts for geology and technological changes with time.

scholarly journals Geocoding and spatio-temporal modeling of long-term PM2.5 and NO2 exposure: the Mexican Teachers' Cohort

2021 ◽  
Author(s):  
Cervantes - Martínez Karla ◽  
Riojas - Rodríguez Horacio ◽  
Díaz - Ávalos Carlos ◽  
Moreno - Macías Hortensia ◽  
López - Ridaura Ruy ◽  
...  
Keyword(s):  
Predictive Accuracy ◽  
Generalized Additive Models ◽  
Epidemiological Studies ◽  
Additive Models ◽  
Temporal Modeling ◽  
Secondary Sources ◽  
Temporal Models ◽  
Out Of Sample ◽  
Spatio Temporal

Abstract Epidemiological studies on the effects of air pollution in Mexico often use the environmental concentrations of monitors closest to the home as exposure proxies, yet this approach disregards the space gradients of pollutants and assumes that individuals have no intra-city mobility. Our aim was to develop high-resolution spatial and temporal models for predicting long-term exposure to PM2.5 and NO2 in a population of ~ 16 500 participants from the Mexican Teachers’ Cohort study. We geocoded the home and work addresses of participants. Using information from secondary sources on geographic and meteorological variables as well as other pollutants, we fitted two generalized additive models to predict monthly PM2.5 and NO2 concentrations in the 2004–2019 period. The models were evaluated through 10-fold cross validation. Both showed high predictive accuracy with out-of-sample data and no overfitting (CV RMSE = 0.102 for PM2.5 and CV RMSE = 4.497 for NO2). Participants were exposed to a monthly average of 24.38 (6.78) µg/m3 of PM2.5 and 28.21 (8.00) ppb of NO2 during the study period. These models offer a solid alternative for estimating PM2.5 and NO2 exposure with high spatio-temporal resolution for epidemiological studies in the Valle de México region.

scholarly journals The effect of climate on the spread of the COVID-19 pandemic: A review of findings, and statistical and modelling techniques

2020 ◽  
Vol 44 (5) ◽  
pp. 591-604 ◽  
Author(s):  
Álvaro Briz-Redón ◽  
Ángel Serrano-Aroca
Keyword(s):  
Linear Models ◽  
Generalized Additive Models ◽  
Additive Models ◽  
Transmission Risk ◽  
Temporal Models ◽  
Wide Range ◽  
The World ◽  
Modelling Techniques ◽  
Spatio Temporal ◽  
Hot Weather

The new SARS-CoV-2 coronavirus has spread rapidly around the world since it was first reported in humans in Wuhan, China, in December 2019 after being contracted from a zoonotic source. This new virus produces the so-called coronavirus 2019 or COVID-19. Although several studies have supported the epidemiological hypothesis that weather patterns may affect the survival and spread of droplet-mediated viral diseases, the most recent have concluded that summer weather may offer partial or no relief of the COVID-19 pandemic to some regions of the world. Some of these studies have considered only meteorological variables, while others have included non-meteorological factors. The statistical and modelling techniques considered in this research line have included correlation analyses, generalized linear models, generalized additive models, differential equations, or spatio-temporal models, among others. In this paper we provide a systematic review of the recent literature on the effects of climate on COVID-19’s global expansion. The review focuses on both the findings and the statistical and modelling techniques used. The disparate findings reported seem to indicate that the estimated impact of hot weather on the transmission risk is not large enough to control the pandemic, although the wide range of statistical and modelling approaches considered may have partly contributed to the inconsistency of the findings. In this regard, we highlight the importance of being aware of the limitations of the different mathematical approaches, the influence of choosing geographical units and the need to analyse COVID-19 data with great caution. The review seems to indicate that governments should remain vigilant and maintain the restrictions in force against the pandemic rather than assume that warm weather and ultraviolet exposure will naturally reduce COVID-19 transmission.

scholarly journals Geocoding and spatio-temporal modeling of long-term PM2.5 and NO2 exposure: the Mexican Teachers´ Cohort

2021 ◽  
Author(s):  
KARLA CERVANTES-MARTINEZ ◽  
HORACIO RIOJAS-RODRÍGUEZ ◽  
CARLOS DÍAZ-AVALOS ◽  
HORTENSIA MORENO-MACÍAS ◽  
RUY LÓPEZ-RIDAURA ◽  
...  
Keyword(s):  
Predictive Accuracy ◽  
Human Mobility ◽  
Epidemiological Studies ◽  
Additive Models ◽  
Secondary Source ◽  
Source Information ◽  
Promising Alternative ◽  
Temporal Models ◽  
Spatio Temporal

Epidemiological studies on air pollution in Mexico often use the environmental concentrations of pollutants as measured by monitors closest to the home of participants as exposure proxies, yet this approach does not account for the space gradients of pollutants and ignores intra-city human mobility. This study aimed to develop high-resolution spatial and temporal models for predicting long-term exposure to PM2.5 and NO2 in ~16,500 participants from the Mexican Teachers’ Cohort study. We geocoded the home and work addresses of participants, and used secondary source information on geographical and meteorological variables as well as other pollutants to fit two generalized additive models capable of predicting monthly PM2.5 and NO2 concentrations during the 2004-2019 period. Both models were evaluated through 10-fold cross-validation, and showed high predictive accuracy with out-of-sample data and no overfitting (CV-RMSE=0.102 for PM2.5 and CV-RMSE=4.497 for NO2). Participants were exposed to a monthly average of 24.38 (6.78) mg/m3 of PM2.5 and 28.21 (8.00) ppb of NO2 during the study period. These models offer a promising alternative for estimating PM2.5 and NO2 exposure with high spatio-temporal resolution for epidemiological studies in the Mexico City Metropolitan Area.

scholarly journals Spatial and Temporal Variability in the Occurrence and Abundance of European Hake Larvae, Merluccius merluccius, on the Galician Shelf (NE Atlantic)

2021 ◽  
Vol 8 ◽  
Author(s):  
Cristina García-Fernández ◽  
Justin J. Suca ◽  
Joel K. Llopiz ◽  
Paula Álvarez ◽  
Rosario Domínguez-Petit ◽  
...  
Keyword(s):  
Generalized Additive Models ◽  
Additive Models ◽  
Spatial And Temporal Variability ◽  
Ne Atlantic ◽  
Merluccius Merluccius ◽  
Northeast Section ◽  
Complex Process ◽  
External Conditions ◽  
Sea Surface Heights ◽  
European Hake

The European hake (Merluccius merluccius) is represented as one of the most valuable fisheries in the Galician shelf. We analyzed the distribution, abundance, and environmental conditions of the southern-stock European hake larvae from the Galician shelf during the two main spawning peaks, winter-spring and summer, based on the data from three ichthyoplankton surveys (March 2012, March 2017, and June 2017). A total of 395 larvae in March 2012, 121 in March 2017, and 69 in June 2017 were captured. The northeast section of the study area, close to Estaca de Bares, primarily between 100 and 200 m isobaths, had the highest presence of the European hake larvae in all surveys. Generalized additive models (GAMs) indicated that the occurrence of larvae was significantly different between the surveys and was associated negatively with the temperature, while the abundance of larvae was significantly different between sampling years and was the highest at a temperature around 13.36°C and at sea surface heights of about −0.48 m. Studies of the distribution of early life stages and their relation to external conditions are essential to the understanding of the complex process of recruitment, especially in the exploited species and in highly dynamic environments like the Galician shelf.

scholarly journals Research Risk Factors in Monitoring Well Drilling—A Case Study Using Machine Learning Methods

Symmetry ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 1293
Author(s):  
Shamil Islamov ◽  
Alexey Grigoriev ◽  
Ilia Beloglazov ◽  
Sergey Savchenkov ◽  
Ove Tobias Gudmestad
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Oil And Gas ◽  
New Technologies ◽  
Learning Algorithms ◽  
Gas Production ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Drilling Process ◽  
Well Drilling

This article takes an approach to creating a machine learning model for the oil and gas industry. This task is dedicated to the most up-to-date issues of machine learning and artificial intelligence. One of the goals of this research was to build a model to predict the possible risks arising in the process of drilling wells. Drilling of wells for oil and gas production is a highly complex and expensive part of reservoir development. Thus, together with injury prevention, there is a goal to save cost expenditures on downtime and repair of drilling equipment. Nowadays, companies have begun to look for ways to improve the efficiency of drilling and minimize non-production time with the help of new technologies. To support decisions in a narrow time frame, it is valuable to have an early warning system. Such a decision support system will help an engineer to intervene in the drilling process and prevent high expenses of unproductive time and equipment repair due to a problem. This work describes a comparison of machine learning algorithms for anomaly detection during well drilling. In particular, machine learning algorithms will make it possible to make decisions when determining the geometry of the grid of wells—the nature of the relative position of production and injection wells at the production facility. Development systems are most often subdivided into the following: placement of wells along a symmetric grid, and placement of wells along a non-symmetric grid (mainly in rows). The tested models classify drilling problems based on historical data from previously drilled wells. To validate anomaly detection algorithms, we used historical logs of drilling problems for 67 wells at a large brownfield in Siberia, Russia. Wells with problems were selected and analyzed. It should be noted that out of the 67 wells, 20 wells were drilled without expenses for unproductive time. The experiential results illustrate that a model based on gradient boosting can classify the complications in the drilling process better than other models.

scholarly journals Sardine potential habitat and environmental forcing off western Portugal

2010 ◽  
Vol 67 (8) ◽  
pp. 1553-1564 ◽  
Author(s):  
Juan P. Zwolinski ◽  
Paulo B. Oliveira ◽  
Victor Quintino ◽  
Yorgos Stratoudakis
Keyword(s):  
Chlorophyll A ◽  
Seasonal Pattern ◽  
Generalized Additive Models ◽  
Additive Models ◽  
Seasonal Effect ◽  
Oceanic Circulation ◽  
Environmental Forcing ◽  
Potential Habitat ◽  
The North ◽  
Spatio Temporal

Abstract Zwolinski, J. P., Oliveira, P. B., Quintino, V., and Stratoudakis, Y. 2010. Sardine potential habitat and environmental forcing off western Portugal. – ICES Journal of Marine Science, 67: 1553–1564. Relationships between sardine (Sardina pilchardus) distribution and the environment off western Portugal were explored using data from seven acoustic surveys (spring and autumn of 2000, 2001, 2005, and spring 2006). Four environmental variables (salinity, temperature, chlorophyll a, and acoustic epipelagic backscatter other than fish) were related to the acoustic presence and density of sardine. Univariate quotient analysis revealed sardine preferences for waters with high chlorophyll a content, low temperature and salinity, and low acoustic epipelagic backscatter. Generalized additive models depicted significant relationships between the environment and sardine presence but not with sardine density. Maps of sardine potential habitat (SPH) built upon the presence/absence models revealed a clear seasonal effect in the across-bathymetry and alongshelf extension of SPH off western Portugal. During autumn, SPH covered a large part of the northern Portuguese continental shelf but was almost absent from the southern region, whereas in spring SPH extended farther south but was reduced to a narrow band of shallow coastal waters in the north. This seasonal pattern agrees with the spatio-temporal variation of primary production and oceanic circulation described for the western Iberian shelf.

scholarly journals Current characteristics of animal rabies cases in Thailand and relevant risk factors identified by a spatial modeling approach

2021 ◽  
Vol 15 (12) ◽  
pp. e0009980
Author(s):  
Weerapong Thanapongtharm ◽  
Sarin Suwanpakdee ◽  
Arun Chumkaeo ◽  
Marius Gilbert ◽  
Anuwat Wiratsudakul
Keyword(s):  
Risk Factors ◽  
Generalized Additive Models ◽  
Spatial Models ◽  
Additive Models ◽  
Human Rabies ◽  
Spatial Risk ◽  
Risk Areas ◽  
Spatio Temporal ◽  
Current Characteristics ◽  
And Control

The situation of human rabies in Thailand has gradually declined over the past four decades. However, the number of animal rabies cases has slightly increased in the last ten years. This study thus aimed to describe the characteristics of animal rabies between 2017 and 2018 in Thailand in which the prevalence was fairly high and to quantify the association between monthly rabies occurrences and explainable variables using the generalized additive models (GAMs) to predict the spatial risk areas for rabies spread. Our results indicate that the majority of animals affected by rabies in Thailand are dogs. Most of the affected dogs were owned, free or semi-free roaming, and unvaccinated. Clusters of rabies were highly distributed in the northeast, followed by the central and the south of the country. Temporally, the number of cases gradually increased after June and reached a peak in January. Based on our spatial models, human and cattle population density as well as the spatio-temporal history of rabies occurrences, and the distances from the cases to the secondary roads and country borders are identified as the risk factors. Our predictive maps are applicable for strengthening the surveillance system in high-risk areas. Nevertheless, the identified risk factors should be rigorously considered and integrated into the strategic plans for the prevention and control of animal rabies in Thailand.

scholarly journals Risk Factors Evaluation for Monitoring of Well Drilling

2021 ◽  
Author(s):  
Shamil Islamov ◽  
Alexey Grigoriev ◽  
Ilya Beloglazov ◽  
Sergey Savchenkov ◽  
Ove Tobias Gudmestad
Keyword(s):  
Anomaly Detection ◽  
Oil And Gas ◽  
New Technologies ◽  
Warning System ◽  
Time Frame ◽  
Gas Production ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Drilling Process ◽  
Well Drilling

Drilling of wells for oil and gas production is a highly complex and expensive part of reservoir development. Thus, together with injury prevention, there is a goal to save cost expenditures on downtime and repair of drilling equipment. Nowadays companies have begun to look for ways to improve the efficiency of drilling and minimize non-production time with the help of new technologies. To support decisions in a narrow time frame, it is valuable to have an early warning system. Such a decision support system will help an engineer to intervene in the drilling process and prevent high expenses of unproductive time and equipment repair due to a problem. This work is describing a comparison of machine learning algorithms for anomaly detection during well drilling. Tested models classify drilling problems based on historical data from previously drilled wells. To validate anomaly detection algorithms, we use historical logs of drilling problems for 67 wells at a large brownfield in Siberia, Russia. Wells with problems were selected and analyzed. It should be noted that out of the 67 wells, 20 wells were drilled without expenses for unproductive time. Experiential results illustrated that a model based on gradient boosting can classify the complications in the drilling process best of all.

Oil and Gas Production Prediction Based on SVM and Improved Particle Swarm Optimization

2020 ◽  
pp. 259-275
Author(s):  
Jun Peng ◽  
Yudeng Qiao ◽  
Shangzhu Jin ◽  
Dedong Tang ◽  
Lan Ge ◽  
...  
Keyword(s):  
Information Technology ◽  
Particle Swarm Optimization ◽  
Oil And Gas ◽  
Particle Swarm ◽  
Gas Production ◽  
Swarm Optimization ◽  
Improved Particle Swarm Optimization ◽  
Good Convergence ◽  
Cognitive Information ◽  
Production Prediction

Cognitive information is widely used in the field of oil and gas, where production forecasts are of great importance to companies. In this chapter, combining support vector machine and improved particle swarm optimization algorithm, a gas field production prediction model is established, and the model is validated by the actual production data of an enterprise over the years. The results show that the model has good convergence, high prediction accuracy, and training speed and can predict its output more accurately. The method adopted in this chapter is the development of cognitive information technology. The authors have reason to believe that with the continuous development of cognitive information technology, it will have a far-reaching impact on social progress.

Structure in a sea of sand: fish abundance in relation to man-made structures in the North Sea

2018 ◽  
Vol 77 (3) ◽  
pp. 1206-1218 ◽  
Author(s):  
Serena R Wright ◽  
Christopher P Lynam ◽  
David A Righton ◽  
Julian Metcalfe ◽  
Ewan Hunter ◽  
...  
Keyword(s):  
North Sea ◽  
Gadus Morhua ◽  
Oil And Gas ◽  
Generalized Additive Models ◽  
Strong Association ◽  
Additive Models ◽  
Artificial Structures ◽  
Habitat Alterations ◽  
The North ◽  
The North Sea

Abstract Artificial structures in the marine environment may have direct and/or indirect impact on the behaviour and space use of mobile foragers. This study explores whether environmental and physical features in the North Sea—including artificial structures (wrecks, wind turbines, cables, and oil and gas structures) were associated with local abundance of three fish species: cod (Gadus morhua), plaice (Pleuronectes platessa), and thornback ray (Raja clavata). Generalized additive models (GAMs) were used to compare distributions between data collected by fisheries surveys and electronic tags. Distributions of cod, plaice, and ray were correlated with environmental variables including temperature, depth, and substrate, matching findings from previous studies. All species showed seasonal increases in their abundance in areas with high densities of artificial structures, including oil and gas platforms and wrecks. Independent of whether fish purposefully associate with these features or whether structures happen to coincide with locations frequented by these populations, the strong association suggests that greater consideration needs to be given to regulation of habitat alterations, including decommissioning.

Sign in / Sign up

Export Citation Format

Share Document