Summary Decline–curve analysis (DCA) is an easy and fast empirical regression method for predicting future well production. However, applying DCA to shale–gas wells limited by long transient flow, a unique completion design, high–density drilling. Recently, short-term-memory (LSTM) algorithm has been widely applied the prediction of time–series data. Because shale–gas–production data are data, LSTM can be predict After information 332 in Alberta, Canada, obtained from commercial database,...

Due to environmental and economic constraints on their acquisition, seismic data are always irregularly sampled include bad or missing traces, which can cause problems for processing. Recently, many researchers have attempted improve reconstruction using machine learning (ML) techniques, such as convolutional neural networks, inspired by computer vision imaging In this letter, we propose a novel approach reconstructing traces in ML especially recurrent network (RNN) algorithms. Instead of...

Due to the rapid development and spread of deep learning technologies, potential applications artificial intelligence technology in field geophysical inversion are being explored. In this study, we applied a neural network (DNN) reconstruct one-dimensional electrical resistivity structures from airborne electromagnetic (AEM) data for varying sensor heights. We used numerical models their simulated AEM responses train DNN be an operator, determined that it was possible without use stabilisers...

One of the major problems in modeling and inversion marine controlled-source electromagnetic (CSEM) data is related to need for accurate representation very complex geoelectrical models typical environment. At same time, corresponding forward-modeling algorithms should be powerful fast enough suitable repeated use hundreds iterations multiple transmitter/receiver positions. To this end, we have developed a novel 3D approach, which combines advantages finite-difference (FD) integral-equation...

One of the critical problems in interpretation marine controlled-source electromagnetic geophysical data is taking into account anisotropy rock formations. We evaluated a 3D anisotropic inversion method based on integral equation method. applied this to full towed-streamer (EM) data. The EM system makes it possible collect with high production rate and over very large survey areas. At same time, has become challenging problem because huge number transmitter positions moving system, and,...

With recent advances in machine learning, convolutional neural networks (CNNs) have been successfully applied many fields, and several attempts made the field of geophysics. In this letter, we investigated mapping subsurface electrical resistivity distributions from electromagnetic (EM) data with CNNs. To begin imaging using CNNs, carried out precise delineation a salt structure, which is indispensable for identification offshore hydrocarbon reservoirs, towed streamer EM data. For training...

Deep learning (DL) methods are recently used as a powerful tool in seismic signal processing. Most of trace reconstruction governed by the superresolution based on convolutional neural network (CNN). The performances these kinds depend not only how training model is constructed but also what learned from data, especially field data application. In this study, we propose two sequences interpolation through t-SNE and U-Net to provide guide optimal organization sets successful missing traces....

This letter introduces a novel approach to the optimal design of synthetic aperture method for marine controlled-source electromagnetic (MCSEM) surveys. We demonstrate that sensitivity MCSEM survey specific geological target could be enhanced by selecting appropriate amplitude and phase coefficients corresponding aperture. have developed general optimization technique find parameters method. makes it possible increase ratio between total background fields within area an expected reservoir...

Quantitative facies classification is the key to linking seismic data lithology evaluate important reservoir properties. During past several years, size of volumes has piled up extent that it challenging for experts examine every volume classify facies. This motivated machine learning approach predicting in an efficient way. However, labeled (well data) limited by various constraints and very expensive obtain, whereas, there a plethora unlabeled (seismic data). Geophysicists are tasked...

Clays in fault zones have low electrical resistivity, making resistivity tomography (ERT) effective for investigations. However, traditional ERT inversion methods struggle to find a unique solution and produce unstable results owing the ill-posed nature of problem. To address this, workflow integrating deep-learning (DL) technology with is proposed. First, model named DL-ERT that maps apparent data subsurface models developed. create target-oriented training data, we use approximately 150...

This paper addresses the metrics required for generating multi-scene videos based on a continuous scenario, as opposed to traditional short video generation. Scenario-based require comprehensive evaluation that considers multiple factors such character consistency, artistic coherence, aesthetic quality, and alignment of generated content with intended prompt. Additionally, in generation, unlike single images, movement characters across frames introduces potential issues like distortion or...

Machine learning algorithms have been widely used for the quantitative seismic interpretation to delineate distribution of oil-saturated reservoir. Especially, unsupervised clustering has more favored than supervised in early stage exploration due lack labeled data such as well logs. However, method performs only grouping unlabeled data, and requires labeling facies by human interpreters, so results can be error-prone biased depending on interpreter's ability. To overcome shortcomings, we...

The mainstream approach to the interpretation of towed streamer electromagnetic (EM) data is based on 2.5-D and/or 3-D inversions observed into resistivity models subsurface formations. However, rigorous and even require large amounts computational power time. synthetic aperture (SA) method one key techniques in remote sensing using radio frequency signals. During recent years, this was also applied low-frequency EM fields used for geophysical exploration. This letter demonstrates that...

Salt structure imaging is one of the most important problems in field hydrocarbon exploration. To resolve this issue, integration diverse geophysical data has emerged. In study, we proposed cooperative inversion with seismic and controlled-source electromagnetic (CSEM) based on supervised deep learning (DL) technique for precise salt delineation. CSEM data, which are effective distinguishing a body high electrical resistivity from surrounding media, were used as inversion, high-resolution...

We introduce the concept of controlled sensitivities which enable a geophysical survey to be focused on specific volume interest. In particular, this method increases sensitivity within interest in subsurface, where potential geological targets (e.g., hydrocarbon‐bearing reservoirs) may located. have developed numerical for constructing given priori resistivity model. demonstrate approach with 3D model study marine controlled‐source electromagnetic (CSEM) surveys.

This paper introduces a novel approach to the optimal design of synthetic aperture method for marine controlled source electromagnetic (MCSEM) surveys. We demonstrate that sensitivity MCSEM survey specific geological target could be enhanced by selecting appropriate amplitude and phase coefficients corresponding aperture. have developed general optimization technique find parameters method. makes it possible increase ratio between total background fields within area an expected reservoir...

As one of the most vulnerable countries to floods, there should be an increased necessity for accurate and reliable flood forecasting in Indonesia.Therefore, a new prediction model using machine learning algorithm is proposed provide daily Indonesia.Data crawling was conducted obtain rainfall, streamflow, land cover, data from 2008 2021.The built Random Forest (RF) classification predict future floods by inputting three days rainfall rate, forest ratio, stream flow.The accuracy, specificity,...

Trace interpolation using machine learning (ML) has been actively studied recently. Especially, crossline in towed streamer system is an important task due to the sparsity of data compared dense inline data. The key successful ML application trace how similar training are target data, which be interpolated. Considering similarity, we use for model, and then apply trained model interpolation. In this way, can train fill gaps on sparse same seismic without additional datasets. For based...