Risking seismic amplitude anomaly prospects based on database trends

Forrest, Mike; Roden, Rocky; Holeywell, Roger

doi:10.1190/1.3422455

Cited by 19 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the presence of DHIs can prove to be a decisive factor in terms of the final evaluation of the prospect, it is commonly known that seismic amplitude anomalies may be caused by other than the presence of hydrocarbons. It is therefore also important to adequately rate and integrate the qualities of the various geophysical data into the risking process (Forrest et al, 2010). The database, presently consisting of over 360 prospects, contains wells from a variety of AVO classes (Roden et al, 2014) and geographical locations.…”

Section: Hydrocarbon Risk Assessmentmentioning

confidence: 99%

Explainable Machine Learning for Hydrocarbon Prospect Risking

Mustafa¹,

AlRegib²,

Koster³

2023

Preprint

View full text Add to dashboard Cite

Hydrocarbon prospect risking integrates information from multiple geophysical data and modalities to arrive at a probability of success for a given prospect. The DHI database of drilled prospects gathers data from prospects drilled around the world in multiple geologic settings in one central knowledge base. A major goal of interest to geophysicists is to understand the impact of various seismic amplitude anomalies, that are interpreted as direct hydrocarbon indicators, on the risking process. The individual correlation-based analysis typically carried out for this purpose misses out on complex feature interactions governing the physical phenomena. Data-driven machine learning techniques have the potential to sift through large, multidimensional datasets to learn mappings from feature spaces to outcome classes. LIME is a model explainability technique that explains decisions by black-box models by locally approximating their behavior. We propose a novel method whereby LIME is used in conjunction with various machine learning models to learn mappings from feature spaces in the DHI database to respective prospect outcomes. Consequently, we are able to highlight seismic amplitude anomalies considered most important by the models to the risking process and we show that our insights agree with geophysical intuition. Moreover, we use LIME explanations to demonstrate a case study of bias detection with machine learning models for the application of prospect risking. A limitation with LIME is that it only explains model behavior around solitary datapoints. Towards this end, we propose novel metrics summarizing a model's global understanding of a dataset by aggregating local explanations over individual examples. To the best of our knowledge, this is the first work using explainable machine learning for the purpose of bringing novel insights to prospect risk assessment.

show abstract

Section: Hydrocarbon Risk Assessmentmentioning

confidence: 99%

Explainable Machine Learning for Hydrocarbon Prospect Risking

Mustafa¹,

AlRegib²,

Koster³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…В конце 60-х годов прошлого столетия американский геофизик Майк Форрест установил, что наличие насыщенных углеводородами пород в разрезе часто проявляется в виде сильных амплитудных и, соответственно, энергетических аномалий в сейсмических данных [10].…”

Section: методика и анализ результатов динамической интерпретацииunclassified

Интеграция Данных Гис И 3d-Сейсморазведки Для Прогноза Флюидонасыщения Породного Массива

Тезиков,

Трапезникова

2022

Гор. эхо

View full text Add to dashboard Cite

“…However, it is often not clear whether an amplitude anomaly is in fact due to the presence of hydrocarbons. High-porosity wet sands (23% of all prospects) or low-saturation gas sands (11% of all prospects) are the most common reasons for the failure of DHI-located prospects (Forrest et al, 2010). The identification of individual DHIs on seismic profiles may be unsatisfactory, but the presence of multiple indicators may point to the presence of a prospect.…”

Section: Introductionmentioning

confidence: 99%

Seismic Events in the Upper Miocene – Pliocene Sedimentary Succession in the Gulf of İzmi̇r (Western Anatolia): Implications for Hydrocarbon Prospectivity

Altan

Ocakoğlu

Böhm

et al. 2020

Journal of Petroleum Geology

View full text Add to dashboard Cite

An analysis of multi‐channel seismic reflection data integrating reflection tomography, pre‐stack depth migration, AVO analysis, seismic modelling and seismic attribute analysis was used to investigate the Miocene – Quaternary stratigraphy of the Gulf of İzmir, western Anatolia. In this area, the east‐west oriented Gediz graben intersects with the NE‐SW oriented Bakırçay Graben. A velocity‐depth model together with pre‐stack depth migration allowed two seismic stratigraphic units (SSU1 and SSU2) to be distinguished. These units can be correlated with the stratigraphic succession at the offshore Foça‐1 well and correspond to the Upper Miocene to Recent Bozköy, Ularca and Bayramiç Formations with a combined thickness of 1.75 km. The units rest on acoustic basement (SSU3) which has a basin‐and‐ridge morphology, and which corresponds to the Lower‐Middle Miocene Yuntdağ Volcanics. A number of lateral velocity variations were identified. In particular, a ~90 m wide and ~500 m long lenticular‐shaped low‐velocity zone with an interval velocity of 1.68 km/s was identified in the Quaternary Bayramiç Formation. The structure is bounded by negative reflections whose amplitude increases with offset at the top and by strong positive reflections whose amplitude increases with offset at the base, interpreted as possible bright and flat spots respectively. These amplitude events point to the presence of gas‐saturated sediments within the study area. The lenticular structure is bounded by strike‐slip faults on either side, and by a Miocene – Pliocene unconformity surface below and by shales of the Bayramiç Formations above. It is therefore interpreted as a possible structural – stratigraphic trap. The strike‐slip faults may allow the migration of hydrocarbons from source rocks located at greater depths. The presence of a low‐velocity zone above the lenticular structure reaching up to seafloor may indicate the upward leakage of hydrocarbons from the trap. These observations will contribute to future hydrocarbon exploration activities in the study area.

show abstract

Risking seismic amplitude anomaly prospects based on database trends

Cited by 19 publications

References 5 publications

Explainable Machine Learning for Hydrocarbon Prospect Risking

Explainable Machine Learning for Hydrocarbon Prospect Risking

Интеграция Данных Гис И 3d-Сейсморазведки Для Прогноза Флюидонасыщения Породного Массива

Seismic Events in the Upper Miocene – Pliocene Sedimentary Succession in the Gulf of İzmi̇r (Western Anatolia): Implications for Hydrocarbon Prospectivity

Contact Info

Product

Resources

About