Artificial neural network assisted prediction of dissolution spatial distribution in the volcanic weathered crust: A case study from Chepaizi Bulge of Junggar Basin, northwestern China

Miao, Tian; Xu, Huaimin; Cai, Jun; Wang, Jun; Wang, Zhizhang

doi:10.1016/j.marpetgeo.2019.08.045

Cited by 15 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…En adición, investigadores como Tian y otros [43] realizan la predicción asistida de disolución en la corteza volcánica, en su investigación titulada "Artificial neural network assisted prediction of dissolution spatial distribution in the volcanic weathered crust: A case study from Chepaizi Bulge of Junggar Basin, northwestern China", estableciendo parámetros de entrenamiento previo y, realizando la validación correspondiente con el modelo de disolución volcánica geológica proporcionado por la entidad geológica correspondiente. Otro caso de estudio asociado a la temática, es el realizado por Lara y otros [19] con su investigación titulada "A deep learning approach for automatic recognition of seismo-volcanic events at the Cotopaxi volcano", en donde, por medio de reconocimiento automático de microterremotos, se realizan predicción en tiempo cercano al real, con base en requerimientos del Instituto Geofísico de la Escuela Politécnica Nacional, con precisión teórica del 97 % en la etapa de clasificación.…”

Section: Reconocimiento De Señales De Eventos Sismo-volcánicos Con Re...unclassified

Predicción de la deformación en la corteza del Volcán – Nevado del Ruíz en el año 2020 mediante información troposférica TROPOMI, técnica DInsar y redes neuronales

Santana

2022

rev.digit.educ.ing

View full text Add to dashboard Cite

El Volcán Nevado del Ruíz situado entre los límites de los Departamentos del Caldas y Tolima en Colombia presentó un comportamiento inestable en el trascurso del año 2020, dicha actividad volcánica conllevó a efectos secundarios en la corteza, es por ello que la predicción de deformaciones se torna como menester de los geocientíficos. En el transcurso de la investigación presentada se dispuso el uso de variables troposféricas, tales como evapotranspiración, índice de aerosoles UV, monóxido de carbono, dióxido de nitrógeno, metano, temperatura superficial, entre otros; para entrenar un conjunto de redes neuronales que puedan predecir el comportamiento de la fase resultante de un interferograma sin desenrollar con la técnica DInSAR, cuyo objetivo principal sea identificar y caracterizar el comportamiento de la corteza con base en las condiciones del entorno. Para lo anterior, se realizó la recolección de variables, la conformación de un modelo lineal generalizado y el conjunto de redes neuronales. Posterior al entrenamiento de la red, se realizó la validación con los datos de testeo, otorgando un MSE de 0,17598 y, un r – cuadrado asociado de aproximadamente 0,88454. El modelo resultante permitió la obtención de un conjunto de datos con exactitud temática buena, reflejando el comportamiento del volcán en el año 2020 dado un conjunto de características del ambiente.

show abstract

Section: Reconocimiento De Señales De Eventos Sismo-volcánicos Con Re...unclassified

Predicción de la deformación en la corteza del Volcán – Nevado del Ruíz en el año 2020 mediante información troposférica TROPOMI, técnica DInsar y redes neuronales

Santana

2022

rev.digit.educ.ing

View full text Add to dashboard Cite

show abstract

“…Owing to the limited data and the coarse resolution of observations, conventional identification approaches such as the semi‐quantitative description based on core analyses and the qualitative description based on tectonic stress field analyses fail to provide satisfactory results. Proposed mathematical models based on the geophysical data contribute to the fracture identification in decades (Tian et al ., 2019b). However, most models that take each sample as a spatial independent event and recognize fractures just with the corresponding one‐site measurements are unable to predict clear boundaries and reasonable thickness for fractured zones.…”

Section: Problem Definition and Notationmentioning

confidence: 99%

Deep learning assisted well log inversion for fracture identification

Miao

Li²,

et al. 2020

Geophysical Prospecting

Self Cite

View full text Add to dashboard Cite

Manual fracture identification methods based on cores and image logging pseudopictures are limited by the expense and the amount of data. In this paper, we propose an integrated workflow, which takes the fracture identification as an end-to-end project, to combine the boundary detection and the deep learning classification to recognize fractured zones with accurate locations and reasonable thickness. We first apply the discrete wavelet transform algorithm and a boundary detection method named changing point detection to enhance the fracture sensibility of acoustic logs and segment the whole logging interval into non-overlapping subsections by estimating boundaries. The deep neural network based auto-encoders and the convolutional neural network classifier are then implemented to extract the hidden information from logs and categorize the subsections as the fractured or non-fractured zones. To validate the feasibility of this workflow, we apply it to the logging data from a real well. Compare with the benchmarks provided by the support vector machine , random forest and Adaboost model, the one-dimensional well profile predicted by the proposed changing point detection-deep learning classifier is more consistent with the manual identification result.

show abstract

“…Some areas are limited by the strong heterogeneity of volcanic rocks, which makes their study difficult, and the effect on exploration and development is not ideal. In recent years, it has been gradually realized that the formation of volcanic rock reservoirs depends on late reconstruction, so the research direction has gradually changed to research on weathering, leaching, and the controlling range of tectonic fractures, and some achievements have been made [28][29][30][31][32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

Reservoir Characteristics and Main Factors Controlling Carboniferous Volcanic Rocks in the Well CH471 Area of the Hongche Fault Zone: Northwest Margin of Junggar Basin, China

Chen,

Qin,

et al. 2023

Minerals

View full text Add to dashboard Cite

Nearly 100 million tons of reserves have been explored in the Well 471 area of the Hongche Fault zone. The Carboniferous volcanic rock reservoir is the main oil-bearing reservoir in the well CH471 area and is the main target of exploration and development. The characteristics of the Carboniferous volcanic rock reservoir are studied through core, thin section, physical property, logging, and other data, and its main controlling factors are analyzed in combination with actual means of production. The lithologies of the volcanic reservoir in the study area are mainly volcanic breccia, andesite, and basalt. The matrix physical properties of volcanic rock reservoirs are medium-porosity and ultralow-permeability, among which volcanic breccia has the best physical properties. The reservoir space mainly comprises primary pores, secondary dissolution pores, and fractures, resulting in a dual medium pore-fracture-type reservoir. Combined with production data analysis, the lateral distribution of oil and gas is controlled by lithology and lithofacies, with explosive volcanic breccia being the best, followed by the basalt and andesite of overflow facies, which are vertically affected by weathering and leaching and distributed within 50~300 m from the top of the Carboniferous system. The area with densely developed fractures was conducive to developing high-quality reservoirs. The tectonic movement promoted the formation of weathering and controlled the development of faults. Based on a comprehensive analysis, it is believed that the formation of Carboniferous volcanic oil and gas reservoirs in the study area was controlled and influenced by the lithology, lithofacies, weathering, leaching, faults (fractures), and tectonics.

show abstract

Artificial neural network assisted prediction of dissolution spatial distribution in the volcanic weathered crust: A case study from Chepaizi Bulge of Junggar Basin, northwestern China

Cited by 15 publications

References 49 publications

Predicción de la deformación en la corteza del Volcán – Nevado del Ruíz en el año 2020 mediante información troposférica TROPOMI, técnica DInsar y redes neuronales

Predicción de la deformación en la corteza del Volcán – Nevado del Ruíz en el año 2020 mediante información troposférica TROPOMI, técnica DInsar y redes neuronales

Deep learning assisted well log inversion for fracture identification

Reservoir Characteristics and Main Factors Controlling Carboniferous Volcanic Rocks in the Well CH471 Area of the Hongche Fault Zone: Northwest Margin of Junggar Basin, China

Contact Info

Product

Resources

About