pure and applied geophysics最新文献

{"title":"Integration of Deep Learning with the Discrete Element Method for Porosity Prediction in Gravel-Bed Rivers","authors":"Phong Nguyen Thanh,&nbsp;Duong Tran Anh,&nbsp;Ahad Hasan Tanim,&nbsp;Bang Tran,&nbsp;Quoc Bao Pham,&nbsp;Son T. Mai,&nbsp;Hung Phan Duy,&nbsp;Van Hieu Bui","doi":"10.1007/s00024-026-04069-x","DOIUrl":"10.1007/s00024-026-04069-x","url":null,"abstract":"<div><p>Porosity is a key parameter governing the hydraulic, geomorphic, and ecological functions of gravel-bed rivers. Although the discrete element method (DEM) can reproduce particle-scale packing structures with high accuracy, its computational cost limits its application for rapid porosity assessment. To address this limitation, this study proposes an integrated framework that combines DEM simulations with deep learning (DL) models, including a two-dimensional convolutional neural network (2D-CNN) and a long short-term memory (LSTM) network. DEM-generated grayscale images and grain-size distributions (GSDs) were used to train the 2D-CNN and LSTM models, respectively, under clogging and penetration scenarios. The results show that the 2D-CNN achieved the highest predictive accuracy, with R values of 0.9712 and 0.9509 for the penetration and clogging cases, respectively, outperforming both the LSTM model and the empirical Yu model. Although the LSTM model also provided satisfactory predictions, its accuracy was generally lower than that of the 2D-CNN. These findings demonstrate that integrating DEM-generated datasets with DL provides an efficient surrogate framework for rapid porosity prediction over the range of GSDs considered in this study, thereby reducing the need for computationally intensive DEM simulations.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 9","pages":"4585 - 4606"},"PeriodicalIF":2.1,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148986828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gap Filling and Anomaly Separation Using Inverse Principal Components Analysis","authors":"Qingmou Li,&nbsp;Xiaojun Liu","doi":"10.1007/s00024-026-04053-5","DOIUrl":"10.1007/s00024-026-04053-5","url":null,"abstract":"<div><p>Gap filling in geophysical time series is particularly challenging when observed data is non-stationarity and has sharp temporal transitions. Many existing approaches rely on global functional representations or stationarity assumptions, which can compromise the preservation and identification of physically meaningful local features. In this study, we introduce EigenSig, an eigenspace-based framework that reformulates gap filling as a coordinate-recovery problem in a reduced eigenspace. The method partitions a time series into epochs, embeds them in a vector space, and constructs an eigenspace using principal component analysis, where dominant eigenvectors capture within-epoch variability and eigenspace coordinates represent large-scale coherence across epochs. Missing epochs are addressed by estimating and analyzing these coordinates from neighboring epochs and projecting them back into the original data space. Unlike least-squares harmonic estimation (LSHE), which uses global Fourier series representation, EigenSig uses a fully data-driven orthogonal basis as the base of eigenspace and designed to preserve signal shape without stationary assumption. We also incorporate the widely used LSHE method to estimate coordinates of unknown epochs in eigenspace to enhance its robustness and uncertainty quantification. EigenSig is further extended for anomaly separation using a leave-one-out strategy, in which each epoch is reconstructed from all remaining data in eigenspace, and anomalies are quantified as the residual between the observed and reconstructed epochs. Applications to synthetic data gaps and geomagnetic time series demonstrate that EigenSig effectively reconstructs data gaps, separates localized anomalies while maintaining global structure, and has calculation efficiency, highlighting its methodological novelty and practical relevance for geophysical signal analysis.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 8","pages":"3977 - 4001"},"PeriodicalIF":2.1,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s00024-026-04053-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis and Simulation of Anisotropic Thin-Layered Structures in the Atmosphere","authors":"S. P. Kshevetskii,&nbsp;S. N. Kulichkov,&nbsp;Yu. A. Kurdyaeva,&nbsp;N. M. Gavrilov","doi":"10.1007/s00024-026-04065-1","DOIUrl":"10.1007/s00024-026-04065-1","url":null,"abstract":"<div><p>Anisotropic thin-layered structures in the atmosphere are investigated both theoretically and numerically. These formations may be interpreted as internal gravity waves (IGWs) with vertical lengths significantly smaller than the horizontal wavelengths and vertical stratification scales. Approximate analytical expressions describing the spatial configuration of such waves are derived. A novel method is proposed for using these fine-scale structures for initialization of a high-resolution nonlinear numerical atmospheric model in the form of effective wave sources. These sources generate anisotropic turbulence over a finite time interval and are deactivated when the target structures are established. Consequently, the resulting fine-scale formations are fully governed by nonlinear hydrodynamic equations. Examples of simulations of various thin-layered structures are presented. The results provide a robust framework for conducting numerical studies of fine-scale layers caused by IGW propagation in the atmosphere.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 9","pages":"4707 - 4728"},"PeriodicalIF":2.1,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148986829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Robust Hybrid Deep Learning Model for GHI Forecasting Incorporating EEMD, CSA Optimization, and Transformer–GRU Networks","authors":"Girijapati Sharma,&nbsp;Subhash Chandra,&nbsp;Arvind Kumar Yadav","doi":"10.1007/s00024-026-04054-4","DOIUrl":"10.1007/s00024-026-04054-4","url":null,"abstract":"<div><p>Solar energy is a sustainable and environmentally friendly energy source; however, its intermittent and highly dynamic nature makes accurate Global Horizontal Irradiance (GHI) forecasting a challenging task. Reliable GHI prediction is crucial for efficient photovoltaic power generation, grid stability, and renewable energy integration. To address this challenge, this study proposes a hybrid EEMD-CSA-VTX-GRU forecasting framework that combines Ensemble Empirical Mode Decomposition (EEMD), Cuckoo Search Algorithm (CSA)-based hyperparameter optimization, and a Transformer-enhanced Gated Recurrent Unit (VTX-GRU) model for solar irradiance prediction. The EEMD technique is employed to decompose nonlinear and non-stationary irradiance signals into intrinsic mode functions, improving feature representation and reducing noise effects. The Transformer module captures long-range temporal dependencies using an attention mechanism, while the GRU network effectively models short-term sequential patterns. Furthermore, CSA is utilized to optimize model hyperparameters, enhancing convergence stability and forecasting accuracy. The proposed framework was evaluated using the Jodhpur solar irradiance dataset under different forecasting scenarios. Its performance was compared with conventional GRU and other benchmark models using RMSE, MAE, nRMSE, MAPE, and R² metrics. Experimental results demonstrated superior forecasting performance, achieving an MAE of 31.48, RMSE of 46.64, nRMSE of 0.0442, and MAPE of 10.56%. Sensitivity and statistical analyses further confirmed the robustness and stability of the proposed model across varying training configurations and forecasting horizons. Although the framework was validated on a single geographical region, the results indicate its effectiveness for short-term solar irradiance forecasting. Future work will focus on multi-regional validation, lightweight optimization strategies, and improved forecasting robustness under highly dynamic atmospheric conditions.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 9","pages":"4627 - 4663"},"PeriodicalIF":2.1,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148986275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Evaluation of Hybrid ARIMA-XGBoost and Machine Learning Models for SO2 Forecasting in Gaziantep City","authors":"Efdal Kaya,&nbsp;Halil Baris Ozel,&nbsp;Muge Agca,&nbsp;Ilknur Zeren Cetin,&nbsp;Riza Altunay,&nbsp;Dilek Birgul Zeren","doi":"10.1007/s00024-026-04063-3","DOIUrl":"10.1007/s00024-026-04063-3","url":null,"abstract":"<div><p>Air pollution represents a major public health challenge, particularly in rapidly developing urban environments. Accurate forecasting of sudden fluctuations in air pollutant concentrations is therefore essential for effective air quality management and environmental decision-making. In this study, SO₂ concentrations (µg/m³) were forecast using four categories of forecasting approaches: statistical forecasting models, including Auto-Regressive Integrated Moving Average (ARIMA), Exponential Smoothing (ETS), and Prophet; standard machine-learning models, including linear regression (LR), k-nearest neighbours (KNN), multilayer perceptron neural networks (MLP), and support vector regression (SVR); ensemble-learning models, including Random Forest (RF) and Extreme Gradient Boosting (XGBoost); and hybrid forecasting models, including ARIMA-Boost and Prophet-Boost. A comprehensive comparative framework integrating statistical, machine-learning, ensemble-learning, and hybrid forecasting approaches was developed and systematically evaluated. Daily SO₂ concentration data collected between 01/01/2020 and 31/07/2024 were obtained from the official air quality monitoring station operated by the Ministry of Environment, Urbanization and Climate Change in Gaziantep Province, Türkiye. Model performance was evaluated using mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE). Among the evaluated models, the hybrid ARIMA-Boost framework achieved the best overall forecasting performance, producing the lowest MAE (2.61) and RMSE (3.71) values, whereas the ARIMA model yielded the lowest MAPE value (26.51). The findings demonstrate that hybrid statistical-machine-learning forecasting frameworks can substantially improve SO₂ prediction accuracy compared with conventional statistical methods and standalone machine-learning approaches.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 9","pages":"4665 - 4684"},"PeriodicalIF":2.1,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148986119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Climatic Extreme in a High-Resolution Dataset over Densely Populated Cities of Middle Gangetic Plain, India","authors":"Prabhat Kumar,&nbsp;P. Parth Sarthi,&nbsp;Archisman Barat,&nbsp;Sunny Kumar","doi":"10.1007/s00024-026-04049-1","DOIUrl":"10.1007/s00024-026-04049-1","url":null,"abstract":"<div><p>The current study investigates the climatic extremes using high-resolution datasets over densely populated cities of the Middle Gangetic Plain, India. Extreme weather events significantly impact urban infrastructure, public health, and the economy, with these effects intensifying due to climate change. The Climpact2 package was used to analyse nine temperature-based and six precipitation-based indices from high-resolution Climate Hazards Center datasets (CHIRTS and CHIRPS) spanning from 1983 to 2016. The Mann–Kendall test and Sen’s slope estimator were employed to evaluate trends in extreme climatic events. Results reveal a significant increase in warm temperature indices and a decrease in cold temperature indices across most cities. Warm days (TX90P) increased up to 0.406% days/year over Bhagalpur, while warm nights (TN90P) increased by 0.509% days/year, indicating comparatively stronger nighttime warming. The Warm Spell Duration Indicator (WSDI) and Heatwave Frequency (HWF) also showed increasing trends, reaching 0.561 days/year and 0.548 days/year, respectively. In contrast, cool nights (TN10P) decreased significantly by − 0.489% days/year over Muzaffarpur, while the Cold Spell Duration Indicator (CSDI) declined by − 0.592 days/year, suggesting shorter and less frequent cold conditions. These trends indicate intensified urban warming and increasing thermal stress over the selected cities, particularly after 2005, possibly associated with rapid urban expansion, increasing built-up areas, urban heat island effects, and aerosol interactions. Precipitation indices exhibited mixed but statistically non-significant trends across the study region. Annual total wet-day precipitation (PRCPTOT) showed increasing tendencies over Muzaffarpur (2.887 mm/year) and Patna (2.087 mm/year), while maximum 5-day precipitation (RX5day) increased by 0.301 mm/year over Patna. However, the Simple Daily Intensity Index (SDII) generally exhibited decreasing trends across all cities, indicating reduced rainfall intensity in several urban locations. These heterogeneous precipitation patterns may be influenced by variations in urban morphology, land cover, topography, moisture availability, aerosol loading, and regional monsoon variability, leading to differing city-scale climatic responses. The findings further suggest that neighbouring cities sharing similar physiographic settings may still exhibit substantially different climatic behaviour due to variations in urban structure and local meteorological conditions. Overall, the study provides new insights into urban-scale climatic extremes over the Middle Gangetic Plain and highlights the urgent need for city-specific climate adaptation strategies, resilient urban planning, and improved infrastructure to minimise climate-related risks and support sustainable urban development.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 8","pages":"4291 - 4306"},"PeriodicalIF":2.1,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148751972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Coupled Eulerian–Lagrangian Based Nonlinear Seismic Sloshing Analysis of Reinforced Concrete Elevated Circular Water Tanks","authors":"G. S. Arun Kumar,&nbsp;Amit S. Waddar,&nbsp;M. B. Niyaz Ahamed,&nbsp;Gururaj Hatti,&nbsp;Saleemsab Doddamani","doi":"10.1007/s00024-026-04048-2","DOIUrl":"10.1007/s00024-026-04048-2","url":null,"abstract":"<div><p>Elevated reinforced concrete (RC) water tanks are highly susceptible to seismic loading due to hydrodynamic sloshing effects, which can significantly increase structural responses and compromise operational safety. This study presents a nonlinear fluid–structure interaction (FSI)-based numerical investigation of the seismic behaviour of an elevated RC circular water tank, with particular emphasis on the effectiveness of baffle walls in mitigating sloshing-induced demands. Three-dimensional dynamic simulations were performed in ABAQUS using a coupled Eulerian–Lagrangian (CEL) framework, incorporating material nonlinearity and realistic interaction between the contained water and the tank structure. The 2001 Bhuj earthquake ground motion was applied as horizontal base excitation to evaluate the tank response under half-filled conditions for configurations with and without baffle walls. The seismic performance was assessed in terms of fluid displacement, velocity, acceleration, structural displacement, base shear, and S11 stress distribution. The results demonstrate that the incorporation of baffle walls significantly suppresses sloshing activity and improves the overall seismic response of the tank. Compared with the unbaffled configuration, the baffled tank exhibited reductions of approximately 83% in maximum water displacement, 50% in fluid velocity, and 44% in fluid acceleration. Furthermore, the base shear was reduced by approximately 36%, while the S11 stress distribution showed lower stress concentrations and a more uniform stress pattern in the tank wall and staging system. Structural displacement, velocity, and acceleration responses were also significantly reduced in the presence of baffles.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 8","pages":"3921 - 3938"},"PeriodicalIF":2.1,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148751973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatiotemporal Assessment of Agricultural Drought in Semiarid Northern Nigeria Using MODIS Data and Explainable Random Forest (2000–2025)","authors":"Muhammad Lawal Abubakar,&nbsp;Asmau M. Ahmed,&nbsp;Sidikatu Aliyu,&nbsp;Saadatu Umaru Baba,&nbsp;Muhammad Sambo Ahmed,&nbsp;Khalid Ibrahim Richifa","doi":"10.1007/s00024-026-04046-4","DOIUrl":"10.1007/s00024-026-04046-4","url":null,"abstract":"<div><p>Agricultural drought poses a persistent threat to food security in Katsina State, a semiarid region of northern Nigeria, yet the relative contributions of thermal stress and moisture deficit to vegetation health remain poorly understood. In this study, spatiotemporal agricultural drought dynamics from 2000 to 2025 were assessed using the vegetation health index (VHI), integrating MODIS-derived NDVI and land surface temperature (LST), CHIRPS rainfall, ERA5-Land soil moisture, and SRTM topographic data. A random forest regression model, interpreted with SHAP values, was employed to quantify the influence of biophysical drivers on vegetation health. The results indicate severe drought conditions in the early 2000s, with marked improvement after 2015 associated with lower thermal stress and improved vegetation conditions. The model demonstrated strong predictive performance (R² = 0.89; root mean square error (RMSE) = 8.29), identifying the LST as the dominant predictor of the VHI (59.3%), whereas rainfall exerted weaker direct effects (14.9%), reflecting the mediating role of soil moisture and temperature interactions in this semiarid system. These results suggest that early warning and adaptation strategies for drought in semiarid northern Nigeria should prioritize thermal stress indicators alongside conventional rainfall metrics.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 8","pages":"4397 - 4410"},"PeriodicalIF":2.1,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148751969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D Structural and Petrophysical Modelling for Reservoir Characterization of the Poseidon Gas Field, Browse Basin, NW Shelf, Australia","authors":"Maryam Dahiru Usman,&nbsp;John Oluwadamilola Olutoki,&nbsp;Mohamed Elsaadany,&nbsp;Hassan Salisu Mohammed","doi":"10.1007/s00024-026-04038-4","DOIUrl":"10.1007/s00024-026-04038-4","url":null,"abstract":"<div><p>This study presents an integrated reservoir characterization of the Poseidon Gas Field, located in the Browse Basin, offshore northwestern Australia. The field, known for its complex geological structure, was investigated using a multi-disciplinary approach that combined petrophysical analysis, 3D seismic interpretation, and structural modelling to delineate key reservoir properties and improve understanding of subsurface architecture to support hydrocarbon exploration and development strategies. Petrophysical analysis of well log data, including gamma-ray, resistivity, density, and neutron logs, was conducted to estimate porosity, permeability, and fluid saturation. Results revealed significant spatial variability in porosity (2–26%) and permeability (300–1700 mD), with higher porosity zones concentrated in the northeastern part of the field. These findings provided essential insights into the reservoir's storage and flow potential. Key structural features, including faults and horizon surfaces, were mapped to understand reservoir compartmentalization and identify potential hydrocarbon traps. Structural analysis indicated the presence of normal fault systems that significantly influence reservoir continuity and trap configurations. A 3D stochastic model incorporating seismic, petrophysical, and well log data was developed to visualize the spatial distribution and heterogeneity of the Plover Formation reservoirs. The model highlights the dominance of sand and silt facies with high hydrocarbon saturation (~ 80%). The integrated analysis confirms the presence of laterally continuous yet heterogeneous reservoirs between 4000 and 5500 feet, with promising hydrocarbon potential. The study enhances the geological understanding of the Poseidon Field and offers valuable input for reducing exploration risk, optimizing well placement, and improving recovery efficiency in similar deepwater gas reservoirs.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 8","pages":"4113 - 4132"},"PeriodicalIF":2.1,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148751971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting and Identifying Geomagnetic Anomalies Caused by Diversified Interferences with Ground Observations","authors":"Busheng Xie,&nbsp;Lixin Wu,&nbsp;Wenfei Mao","doi":"10.1007/s00024-026-04043-7","DOIUrl":"10.1007/s00024-026-04043-7","url":null,"abstract":"<div><p>Multi-source geomagnetic interferences have detrimental impacts on the magnetic field of geomagnetic observatories, resulting in reduced data availability and reliability. The detection and identification of potential magnetic disturbances with clear or unknown causes contributes to enhancing the anti-interference capability of international geomagnetic networks. In this study, we presented an integrated framework for detecting and identifying some typical magnetic interferences, which includes signal characteristic discrimination, detection algorithm design, correlation verification, and performance evaluation. Two INTERMAGNET stations in Japan and one geomagnetic observatory in China are used in this study. We analyzed the characteristics of magnetic disturbances caused by solar activity, climate activity, and human activities on ground observations referring to mechanisms. Considering three basic characteristics (amplitude, frequency, and morphology), various algorithms for interferences are developed for detecting geomagnetic anomalies. The detected anomalies are further identified using the verification of spatiotemporal correlation between the anomalies and interferences. The performance of the presented algorithms was evaluated using recall rate, precision, and accuracy, demonstrating their accuracy and effectiveness. Accordingly, the two-step method, sliding window method, time–frequency analysis method, and one-dimensional convolutional neural network model (1D CNN) are considered the optimal algorithms for identifying the anomalies caused by geomagnetic storms, thunderstorms, subway operations, and high-voltage direct current transmission (HVDC), respectively. This study provides a reference paradigm for addressing diversified interferences, facilitating the screening of weak magnetic disturbances generated by unknown factors such as geophysical activities, and providing a potential solution for pioneering applications.</p></div>","PeriodicalId":21078,"journal":{"name":"pure and applied geophysics","volume":"183 8","pages":"4003 - 4024"},"PeriodicalIF":2.1,"publicationDate":"2026-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148751199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}