Artificial Intelligence in Geosciences最新文献

Geophysicists interpreting seismic reflection data aim for the highest resolution possible as this facilitates the interpretation and discrimination of subtle geological features. Various deterministic methods based on Wiener filtering exist to increase the temporal frequency bandwidth and compress the seismic wavelet in a process called spectral shaping. Auto-encoder neural networks with convolutional layers have been applied to this problem, with encouraging results, but the problem of generalization to unseen data remains. Most published works have used supervised learning with training data constructed from field seismic data or synthetic seismic data generated based on measured well logs or based on seismic wavefield modelling. This leads to satisfactory results on datasets similar to the training data but requires re-training of the networks for unseen data with different characteristics. In this work seek to improve the generalization, not by experimenting with network architecture (we use a conventional U-net with some small modifications), but by adopting a different approach to creating the training data for the supervised learning process. Although the network is important, at this stage of development we see more improvement in prediction results by altering the design of the training data than by architectural changes. The approach we take is to create synthetic training data consisting of simple geometric shapes convolved with a seismic wavelet. We created a very diverse training dataset consisting of 9000 seismic images with between 5 and 300 seismic events resembling seismic reflections that have geophysically motived perturbations in terms of shape and character. The 2D U-net we have trained can boost robustly and recursively the dominant frequency by 50%. We demonstrate this on unseen field data with different bandwidths and signal-to-noise ratios. Additionally, this 2D U-net can handle non-stationary wavelets and overlapping events of different bandwidth without creating excessive ringing. It is also robust in the presence of noise. The significance of this result is that it simplifies the effort of bandwidth extension and demonstrates the usefulness of auto-encoder neural network for geophysical data processing.

This research aim to evaluate hydro-meteorological data from the Yamuna River Basin, Uttarakhand, India, utilizing Extreme Value Distribution of Frequency Analysis and the Markov Chain Approach. This method assesses persistence and allows for combinatorial probability estimations such as initial and transitional probabilities. The hydrologic data was generated (in-situ) and received from Uttarakhand Jal Vidut Nigam Limited (UJVNL), and meteorological data was acquired from NASA's archives MERRA-2 product. A total of sixteen years (2005–2020) of data was used to foresee daily Precipitation from 2020 to 2022. MERRA-2 products are utilized as observed and forecast values for daily Precipitation throughout the monsoon season, which runs from July to September. Markov Chain and Long Short-Term Memory (LSTM) findings for 2020, 2021, and 2022 were observed, and anticipated values for daily rainfall during the monsoon season between July and September. According to test findings, the artificial intelligence technique cannot anticipate future regional meteorological formations; the correlation coefficient R² is around 0.12. According to the randomly verified precipitation data findings, the Markov Chain model has a success rate of 79.17 percent. The results suggest that extended return periods should be a warning sign for drought and flood risk in the Himalayan region. This study gives a better knowledge of the water budget, climate change variability, and impact of global warming, ultimately leading to improved water resource management and better emergency planning to the establishment of the Early Warning System (EWS) for extreme occurrences such as cloudbursts, flash floods, landslides hazards in the complex Himalayan region.

We propose a novel machine learning approach to improve the formation evaluation from logs by integrating petrophysical information with neural networks using a loss function. The petrophysical information can either be specific logging response equations or abstract relationships between logging data and reservoir parameters. We compare our method's performances using two datasets and evaluate the influences of multi-task learning, model structure, transfer learning, and petrophysics informed machine learning (PIML). Our experiments demonstrate that PIML significantly enhances the performance of formation evaluation, and the structure of residual neural network is optimal for incorporating petrophysical constraints. Moreover, PIML is less sensitive to noise. These findings indicate that it is crucial to integrate data-driven machine learning with petrophysical mechanism for the application of artificial intelligence in oil and gas exploration.

The vertical profile of the ionosphere density plays a significant role in the development of low-latitude Equatorial Plasma Bubbles (EPBs), that in turn lead to ionospheric scintillation which can severely degrade precision and availability of critical users of the Global Navigation Satellite System (GNSS). Accurate estimation of ionospheric delays through vertical electron density profiles is vital for mitigating GNSS errors and enhancing location-based services. The objective of this study is to propose a neural network, trained with radio occultation data from the COSMIC-1 mission, that generates average ionospheric electron density profiles during dusk, focusing on the pre-reversal enhancement of the zonal electric field. Results show that the estimated profiles exhibit a clear seasonal pattern, and reproduce adequately the climatological behavior of the ionosphere, thus presenting strong appeal on ionospheric error attenuation.

In recent years, convolutional neural networks (CNNs) have demonstrated their effectiveness in predicting bulk parameters, such as effective diffusion, directly from pore-space geometries. CNNs offer significant computational advantages over traditional methods, making them particularly appealing. However, the current literature primarily focuses on fully saturated porous media, while the partially saturated case is also of high interest for various applications. Partially saturated conditions present more complex geometries for diffusive transport, making the prediction task more challenging. Traditional CNNs tend to lose robustness and accuracy with lower saturation rates. In this paper, we overcome this limitation by introducing a CNN, which conveniently fuses diffusion prediction and a well-established morphological model that describes phase distributions in partially saturated porous media. We demonstrate the ability of our CNN to perform accurate predictions of relative diffusion directly from full pore-space geometries. Finally, we compare our predictions with well-established relations such as the one by Millington–Quirk.

Logs are valuable information for oil and gas fields as they help to determine the lithology of the formations surrounding the borehole and the location and reserves of subsurface oil and gas reservoirs. However, important logs are often missing in horizontal or old wells, which poses a challenge in field applications. To address this issue, conventional methods involve supplementing the missing logs by either combining geological experience and referring data from nearby boreholes or reconstructing them directly using the remaining logs in the same borehole. Nevertheless, there is currently no quantitative evaluation for the quality and rationality of the constructed log. In this paper, we utilize data from the 2020 machine learning competition of the Society of Petrophysicists and Logging Analysts (SPWLA), which aims to predict the missing compressional wave slowness (DTC) and shear wave slowness (DTS) logs using other logs in the same borehole. We employ the natural gradient boosting (NGBoost) algorithm to construct an Ensemble Learning model that can predicate the results as well as their uncertainty. Furthermore, we combine the SHAP (SHapley Additive exPlanations) method to investigate the interpretability of the machine learning model. We compare the performance of the NGBosst model with four other commonly used Ensemble Learning methods, including Random Forest, GBDT, XGBoost, LightGBM. The results show that the NGBoost model performs well in the testing set and can provide a probability distribution for the prediction results. This distribution allows petrophysicists to quantitatively analyze the confidence interval of the constructed log. In addition, the variance of the probability distribution of the predicted log can be used to justify the quality of the constructed log. Using the SHAP explainable machine learning model, we calculate the importance of each input log to the predicted results as well as the coupling relationship among input logs. Our findings reveal that the NGBoost model tends to provide greater slowness prediction results when the neutron porosity (CNC) and gamma ray (GR) are large, which is consistent with the cognition of petrophysical models. Furthermore, the machine learning model can capture the influence of the changing borehole caliper on slowness, where the influence of borehole caliper on slowness is complex and not easy to establish a direct relationship. These findings are in line with the physical principle of borehole acoustics. Finally, by using the explainable machine learning model, we observe that although we did not correct the effect of borehole caliper on the neutron porosity log through preprocessing, the machine learning model assigned a greater importance to the influence of the caliper, achieving the same effect as caliper correction.

Frosts are one of the atmospheric phenomena with one of the larger negative effects on the agricultural sector in the southern region of Brazil, therefore, an earlier forecast can minimize their impacts. In the present work, artificial neural networks (ANNs) techniques were applied in order to improve the predicting capabilities of frost events in southern Brazil. In the study, two multilayer perceptron (MLP) ANNs were built, one with ADAM optimizer and the other with SGD. The input parameters MLP-ANNs were numerical predictions of the Eta model. The ANNs were trained using four years (2012–2015), while validation and testing were performed using 2016 and 2017, respectively. An episode of frost that occurred on May 21st, 2018, related to an intense cold air mass, was also utilized to evaluate the performance of the ANNs. The best configurations (topologies and hyperparameters) of the ANNs were identified through experiments, using the highest accuracy obtained during the validation period as a metric. The results of the ANNs with ADAM and SGD optimizers were compared with the predictions of the Eta model. For the case study, an additional comparison against the operational frost index (IG) from the National Institute for Space Research (INPE) was also included. The performance of both ANNs (properly configured) with ADAM and SGD optimizers are comparable one to the other. And both are significantly better compared to the Eta model. The ANNs were able to drastically reduce the underestimation trends of frost events caused by the warm bias of the Eta model. The ANNs also indicated more satisfactory performances when compared to the INPE IG. In general, the ANNs were able to identify deficiencies in Eta predictions, and consequently improve their results. In this sense, the use of ANNs to predict frost events can be a very useful tool in an operational environment.

The Hindu Kush-Pamir region (HKPR) is characterized by complex ongoing deformation, unique slab geometry, and intermediate seismic activity. The availability of extensive seismological data in recent decades has prompted the use of deep learning algorithms to extract valuable insights. In this study, we present a fully automated approach for augmenting earthquake catalogue within the HKPR. Our method leverages an attention mechanism-based deep learning architecture to simultaneously detect events, perform phase picking, and estimate magnitudes. We applied this model to a ten-month dataset (January 2013–October 2013) from 83 stations in the region. Utilizing a robust criterion to evaluate the model's probabilities, we associated phases at different stations and pinpointed earthquake locations in the region. Our results demonstrate a significant enhancement, revealing nearly four and a half times more earthquakes than previously documented in the International Seismological Center (ISC) catalogue. A notable portion of these newly detected events falls within the category of very low-magnitude earthquakes (<3), which were absent in the ISC catalogue. Notably, our spatiotemporal analysis reveals a concentration of crustal seismicity along poorly mapped neotectonic north and northeast-oriented faults in the western Pamir, as well as the Vakhsh Thrust System and the Darvaz Karakul Fault. These findings underscore potential sources of future seismic hazards. Furthermore, our expanded earthquake catalogue facilitates a deeper understanding of the interplay between crustal and intermediate seismic activity in the HKPR, shedding light on the deformation and active faulting resulting from Eurasian-Indian plate interactions.

Evolution in geoscientific data provides the mineral industry with new opportunities. A direction of geochemical data generation evolution is towards big data to meet the demands of data-driven usage scenarios that rely on data velocity. This direction is more significant where traditional geochemical data are not ideal, which is the case for evaluating unconventional resources, such as tailing storage facilities (TSFs), because they are not static due to sedimentation, compaction and changes associated with hydrospheric and lithospheric processes (e.g., erosion, saltation and mobility of chemical constituents). In this paper, we generate big secondary geochemical data derived from Sentinel-2 satellite-remote sensing data to showcase the benefits of big geochemical data using TSFs from the Witwatersrand Basin (South Africa). Using spatially fused remote sensing and legacy geochemical data on the Dump 20 TSF, we trained a machine learning model to predict in-situ gold grades. Subsequently, we deployed the model to the Lindum TSF, which is 3 km away, over a period of a few years (2015-2019). We were able to visualize and analyze the temporal variation in the spatial distributions of the gold grade of the Lindum TSF. Additionally, we were able to infer extraction sequencing (to the resolution of the data), acid mine drainage formation and seasonal migration. These findings suggest that dynamic mineral resource models and live geochemical monitoring (e.g., of elemental mobility and structural changes) are possible without additional physical sampling.