Warning Of Events Research Articles

Anomaly Detection over Streaming Graphs with Finger-Based Higher-Order Graph Sketch

A streaming graph is a constantly growing sequence of edges, which forms a dynamic graph that changes with every edge in the stream. An anomalous behavior in a streaming graph can be modeled as an edge or a subgraph that is unusual compared to the rest of the graph. Identifying anomalous behaviors in real time is essential to the early warning of abnormal or notable events. Due to the complexity of the problem, little work has been reported so far to solve the problem. In this paper, we propose Finger-based Higher-order Graph Sketch (FHGS for short), which is an approximate data structure for streaming graphs with linear memory usage, high update speed, and high accuracy and supports both edge and subgraph anomaly detection. FHGS first maps each edge into a matrix based on hash functions, and then counts its frequency in a time window with unique fingerprints for detecting anomalies. Extensive experiments confirm that our approach generate high-quality results compared to baseline methods.

The 2023/24 El Niño and the Feasibility of Long-Lead ENSO Forecasting

Abstract Through its atmospheric teleconnections, El Niño–Southern Oscillation (ENSO) shifts and disrupts weather and climate patterns far beyond the equatorial Pacific where it occurs often resulting in catastrophic consequences in many countries of the world. It is also the largest source of seasonal and interannual climate predictability. Despite its huge importance, ENSO forecasting is still not performed operationally at longer leads than about 6 months ahead. At the same time, there is mounting scientific evidence that forecasts are possible even more than a year in advance. Early warning of ENSO events could substantially mitigate some of the most damaging impacts, such as floods, droughts, and harvest failure and help avoid famine, migration, and disease outbreaks. Here, we present forecasts from a statistical ENSO model of the next El Niño predicted to occur in the winter of 2023/24, at lead times between 11 and 17 months ahead of an expected peak in December 2023. We use a statistical unobserved dynamic components model (EDCM) based on subsurface ocean temperatures as well as sea surface temperatures and zonal wind stress. EDCM has been previously validated through hindcasts of the major El Niños since 1970 and through real-time forecasts of the 2015/16 and 2018/19 El Niños. Our statistical framework and results indicate that there is potential for doubling the operational predictive lead time of ENSO to at least 12 months, with additional promise for even earlier anticipation of 19 months. Such longer-lead forecasts could be of high value, because decision-making and management in a number of key socioeconomic sectors could be greatly improved.

Deep Learning-Based Flood Detection for Bridge Monitoring Using Accelerometer Data

Flooding and consequential scouring are the primary causes of bridge failures, making the detection of such events crucial for structural safety. This study investigates the characteristics of accelerometer data from bridge pier vibrations and proposes a flood detection method with deep learning-based models based on ResNet18 and 1D Convolution architectures. These models were comprehensively evaluated for (1) detecting vehicles passing on bridges and (2) detecting flood events based on axis-specific accelerometer data under various traffic conditions. Continuous Wavelet Transform (CWT) was employed to convert the accelerometer data into richer time-frequency representations, enhancing the detection of passing vehicles. Notably, when vehicles are passing over bridges, the vertical direction exhibits a magnified and more sustained energy distribution across a wider frequency range. Additionally, under flooding conditions, time-frequency representations from the bridge direction reveal a significant increase in energy intensity and continuity compared with non-flooding conditions. For detection of vehicles passing, ResNet18 outperformed the 1D Convolution model, achieving an accuracy of 97.2% compared with 91.4%. For flood detection without vehicles passing, the two models performed similarly well, with accuracies of 97.3% and 98.3%, respectively. However, in scenarios with vehicles passing, the 1D Convolution model excelled, achieving an accuracy of 98.6%, significantly higher than that of ResNet18 (81.6%). This suggests that high-frequency signals, such as vertical vibrations induced by passing vehicles, are better captured by more complex representations (CWT) and models (e.g., ResNet18), while relatively low-frequency signals, such as longitudinal vibrations caused by flooding, can be effectively captured by simpler 1D Convolution over the original signals. Consequentially, the two model types are deployed in a pipeline where the ResNet18 model is used for classifying whether vehicles are passing the bridge, followed by two 1D Convolution models: one trained for detecting flood events under vehicles-passing conditions and the other trained for detecting flood events under no-vehicles-passing conditions. This hierarchical approach provides a robust framework for real-time monitoring of bridge response to vehicle passing and timely warning of flood events, enhancing the potential to reduce bridge collapses and improve public safety.

High-dimensional process monitoring under time-varying operating conditions via covariate-regulated principal component analysis

High-dimensional process monitoring, which aims to raise warnings for faulty events, is a fundamental tool in ensuring the safety of large-scale industrial systems. Over the last few decades, there has been significant interest in Principal Component Analysis (PCA)-based Statistical Process Control (SPC) charts. However, most of them rely on PCA’s optimal properties in homogeneous data, which often fails when dealing with heterogeneous data from industrial processes under time-varying operating conditions. To address this issue, this study proposes a Covariate-regulated PCA model (CrPCA) seamlessly integrated into a process monitoring framework. The main idea is to adjust the principal component directions smoothly according to the time-varying operating conditions, resulting in significantly less information loss in the principal component scores compared to existing methods. This approach further yields a low-dimensional feature vector that follows a distribution with fixed parameters, regardless of covariates, for real-time surveillance. We validate the performance of our methodology through a comprehensive numerical study and two real-world applications: wind turbine condition monitoring and hot rolling process monitoring.

Prediction of Solar Wind Speed Through Machine Learning From Extrapolated Solar Coronal Magnetic Field

AbstractAn accurate solar wind (SW) speed model is important for space weather predictions, catastrophic event warnings, and other issues concerning SW—magnetosphere interaction. In this work, we construct a model based on convolutional neural network (CNN) and Potential Field Source Surface (PFSS) magnetic field maps, considering a SW source surface of RSS = 2.5R⊙, aiming to predict the SW speed at the Lagrange‐1 (L1) point of the Sun‐Earth system. The input of our model consists of four PFSS magnetic field maps at RSS, which are three, four, five, and six days before the target epoch. Reduced maps are used to promote the model's efficiency. We use the Global Oscillation Network Group (GONG) photospheric magnetograms and the potential field extrapolation model to generate PFSS magnetic field maps at the source surface. The model provides predictions of the quasi‐continuous test data set, which is generated by randomly assigning 120 data segments that are individually continuous in time, with an averaged correlation coefficient (CC) of 0.53 ± 0.07 and a root mean square error (RMSE) of 80.8 ± 4.8 km/s in an eight‐fold validation training scheme with the time resolution of the data as small as one hour. The model also has the potential to forecast high speed streams of the SW, which can be quantified with a general threat score of 0.39.

Demonstrating the Potential of Low-Cost GNSS Receiver for tidal monitoring, storms, and flood detecting: example of 2022 Noru Storm in Thua Thien Hue province, Vietnam

Extreme hydrological events such as tsunamis, high tides, or storm surges seriously threaten coastal communities. These events result in flooding, property damage, loss of life, and long-term economic and social impacts. Therefore, monitoring and detecting extreme hydrological events significantly affect coastal areas in disaster response efforts. However, the cost of installing and maintaining these stations can be a significant challenge for developing countries. The objective of this study is to use a low-cost GNSS receiver to monitor tides and detect extreme coastal hydrological phenomena by analyzing changes in water level, using analysis of the signal-to-noise ratio (SNR) data. Data used in this study were collected from a GNSS station located in the Tam Giang Lagoon area, Thua Thien Hue, Vietnam, from September to October 2022. The water level based on GNSS-R is compared with the sensor's measured water level, with the Pearson correlation coefficient reaching 0.96 and RMSE of 0.08m. Continuous Wavelet Transform analysis demonstrated the relationship between water levels and extreme hydrological events. The results show that distinct signatures in the data correspond to the Noru typhoon from September 27-29, 2022, and the inundation from October 14-19, 2022, in Thua Thien Hue. This information is the basis for forecasting and early warning of extreme events and informing disaster response and management efforts.

Reservoir computing-based advance warning of extreme events

Physics-based computing exploits nonlinear or disorder-induced complexity, for example, to realize energy-efficient and high-throughput computing tasks. A particularly difficult but useful task is the prediction of extreme events that can occur in a wide range of complex systems. We prepare an experiment based on a microcavity semiconductor laser that produces statistically rare extreme events resulting from the interplay of deterministic nonlinear dynamics and spontaneous emission noise. We then evaluate the performance of three reservoir computing training approaches in predicting the occurrence of extreme events. We show that Dual Training Reservoir Computing (which in turn can be implemented with fast semiconductor laser dynamics) can provide meaningful early warnings up to 15 times the typical linear correlation time of the dynamics.

Design of New Media Event Warning Method Based on K-means and Seasonal Optimization Algorithm

INTRODUCTION: Timely and effective early warning of new media events not only provides academic value to the study of new media events, but also can play a positive role in promoting the resolution of public opinion. OBJECTIVES: Aiming at the current research on early warning of new media events, there are problems such as the theoretical research is not in-depth and the early warning model is not comprehensive. METHOD: In this paper, K-means and seasonal optimization algorithm are used to construct new media event early warning method. Firstly, by analyzing the construction process of new media event early warning system, extracting text feature vector and carrying out text feature dimensionality reduction; then, combining with the random forest algorithm, the new media event early warning method based on intelligent optimization algorithm optimizing K-means clustering algorithm is proposed; finally, the validity and superiority of the proposed method is verified through the analysis of simulation experiments. RESULTS: The method developed in this paper improves the accuracy, time performance of new media event warning techniques. CONCLUSION: Addresses the lack of comprehensiveness of current approaches to early warning of new media events.

The Impact of Non‐Equilibrium Plasma Distributions on Solar Wind Measurements by Vigil's Plasma Analyser

AbstractIn order to protect society from space weather impacts, we must monitor space weather and obtain early warnings for extreme events if possible. For this purpose, the European Space Agency is currently preparing to launch the Vigil mission toward the end of this decade as a space‐weather monitor at the fifth Lagrange point of the Sun–Earth system. Vigil will carry, amongst other instruments, the Plasma Analyser (PLA) to provide quasi‐continuous measurements of solar wind ions. We model the performance of the PLA instrument, considering typical solar wind plasma conditions, to compare the expected observations of PLA with the assumed input conditions of the solar wind. We evaluate the instrument performance under realistic, non‐equilibrium plasma conditions, accounting for temperature anisotropies, proton beams, and the contributions from α‐particles. We examine the accuracy of the instrument's performance over a range of input solar wind moments. We identify sources of potential errors due to non‐equilibrium plasma conditions and link these to instrument characteristics such as its angular and energy resolution and its field of view. We demonstrate the limitations of the instrument and potential improvements such as applying ground‐based fitting techniques to obtain more accurate measurements of the solar wind even under non‐equilibrium plasma conditions. The use of ground processing of plasma moments instead of on‐board processing is crucial for the extraction of reliable measurements.

Evaluation of Daily Temperature Extremes in the ECMWF Operational Weather Forecasts and ERA5 Reanalysis

In weather forecasting and climate monitoring, daily maximum and minimum air temperatures (TMAX and TMIN) are fundamental for operational and research purposes, from early warning of extreme events to climate change studies. This study provides an integrated evaluation of TMAX and TMIN from two European Centre for Medium-range Weather Forecasts (ECMWF) products: ERA5 reanalysis (1980–2019) and operational weather forecasts (2017–2021). Both products are evaluated using in situ observations from the Global Historical Climatology Network (GHCN). While the analyses span globally, emphasis is given to four key regions: Europe, East and West United States, and Australia. Results reveal a general underestimation of TMAX and overestimation of TMIN in both operational forecasts and ERA5, highlighting the limitation of the ECMWF model in estimating the amplitude of the diurnal cycle of air temperature. ERA5′s accuracy has improved over the past decade, due to enhanced constrain of land–atmosphere analysis streaming from more and higher-quality satellite data. Furthermore, ERA5 outperforms one-day-ahead weather forecasts, indicating that non-real-time dependent studies should rely on ERA5 instead of real-time operational forecasts. This study underscores the importance of ongoing research in model and data assimilation, considering the relevance of daily temperature extremes forecasting and reanalysis for operational meteorology and climate monitoring.

Intelligent identification and real-time warning method of diverse complex events in horizontal well fracturing

The existing approaches for identifying events in horizontal well fracturing are difficult, time-consuming, inaccurate, and incapable of real-time warning. Through improvement of data analysis and deep learning algorithm, together with the analysis on data and information of horizontal well fracturing in shale gas reservoirs, this paper presents a method for intelligent identification and real-time warning of diverse complex events in horizontal well fracturing. An identification model for “point” events in fracturing is established based on the Att-BiLSTM neural network, along with the broad learning system (BLS) and the BP neural network, and it realizes the intelligent identification of the start/end of fracturing, formation breakdown, instantaneous shut-in, and other events, with an accuracy of over 97%. An identification model for “phase” events in fracturing is established based on enhanced Unet++ network, and it realizes the intelligent identification of pump ball, pre-acid treatment, temporary plugging fracturing, sand plugging, and other events, with an error of less than 0.002. Moreover, a real-time prediction model for fracturing pressure is built based on the Att-BiLSTM neural network, and it realizes the real-time warning of diverse events in fracturing. The proposed method can provide an intelligent, efficient and accurate identification of events in fracturing to support the decision-making.

Lag Time and Cumulative Effects of Climate Factors on Drought in North China Plain

The growing concern surrounding climate change has gradually drawn attention to the influence of climate factors on drought occurrence. In order to effectively prevent the occurrence of drought and reasonably utilize water resources, the vegetation health index (VHI) was used to characterize drought in North China Plain (NCP) in this study. Furthermore, six climate factors: air temperature (AT), precipitation (P), evapotranspiration (ET), specific humidity (SH), soil moisture (SM), and soil temperature (ST) were selected. The pole symmetric mode decomposition (PSMD) and improved gridded trend test (IGT) were used to analyze the spatial–temporal characteristics of drought and climate factors in NCP from 1982 to 2020. By calculating the cumulative climatic factors of 0 months, 1 month, 2 months, and 3 months, the correlation between drought and the climatic factors with different cumulative scales was analyzed. The results showed that: (1) from 1982 to 2020, the drought in NCP showed a downward trend and the climate factors showed an upward trend; (2) with the increase in AT, P, ET, SH, SM, and ST, VHI showed an upward trend, and SM showed the strongest correlation with VHI; (3) the optimal cumulative lag time (CLT) for AT, P, ET, SH, SM, and ST were 1.67 months, 1.48 months, 1.95 months, 1.69 months, 0.89 months, and 1.81 months, respectively; and (4) AT was the main driving factor of drought in NCP. This study contributes to the early warning and prediction of drought events, providing a scientific basis for water management authorities in drought management and decision making, and mitigating the negative impacts of drought on socio-economic aspects.

Application of Hybrid ANN Techniques for Drought Forecasting in the Semi-Arid Region of India.

The intensity and frequency of diverse hydro-meteorological disasters viz., extreme droughts, severe floods, and cyclones have increasing trends due to unsustainable management of land and water resources, coupled with increasing industrialization, urbanization and climate change. This study focuses on the forecasting of drought using selected Artificial Neural Network (ANN)-based models to enable decision-makers to improve regional water management plans and disaster mitigation/reduction plans. Four ANN models were developed in this study, viz., one conventional ANN model and three hybrid ANN models: (a) Wavelet based-ANN (WANN), (b) Bootstrap based-ANN (BANN), and (c) Wavelet-Bootstrap based-ANN (WBANN). The Standardized Precipitation Evapotranspiration Index (SPEI), the best drought index identified for the study area, was used as a variable for drought forecasting. Three drought indices, such as SPEI-3, SPEI-6 and SPEI-12 respectively representing "short-term", "intermediate-term", and "long-term" drought conditions, were forecasted for 1-month to 3-month lead times for six weather stations over the study area. Both statistical and graphical indicators were considered to assess the performance of the developed models. For the hybrid wavelet model, the performance was evaluated for different vanishing moments of Daubechies wavelets and decomposition levels. The best-performing bootstrap-based model was further used for analysing the uncertainty associated with different drought forecasts. Among the models developed for drought forecasting for 1 to 3 months, the performances of the WANN and WBANN models are superior to the simple ANN and BANN models for the SPEI-3, SPEI-6, and SPEI-12 up to the 3-month lead time. The performance of the WANN and WBANN models is the best for SPEI-12 (MAE = 0.091-0.347, NSE = 0.873-0.982) followed by SPEI-6 (MAE = 0.258-0.593; NSE = 0.487-0.848) and SPEI-3 (MAE = 0.332-0.787, NSE = 0.196-0.825) for all the stations up to 3-month lead time. This finding is supported by the WBANN analyze uncertainties as narrower band width for SPEI-12 (0.240-0.898) as compared to SPEI-6 (0.402-1.62) and SPEI-3 (0.474-2.304). Therefore, the WBANN model is recommended for the early warning of drought events as it facilitates the uncertainty analysis of drought forecasting results.

Regional aerosol forecasts based on deep learning and numerical weather prediction

Atmospheric chemistry transport models have been extensively applied in aerosol forecasts over recent decades, whereas they are facing challenges from uncertainties in emission rates, meteorological data, and over-simplified chemical parameterizations. Here, we developed a spatial-temporal deep learning framework, named PPN (Pollution-Predicting Net for PM2.5), to accurately and efficiently predict regional PM2.5 concentrations. It has an encoder-decoder architecture and combines the preceding PM2.5 observations and numerical weather prediction. Besides, the model proposes a weighted loss function to promote the forecasting performance in extreme events. We applied the proposed model to forecast 3-day PM2.5 concentrations over the Beijing-Tianjin-Hebei region in China on a three-hour-by-three-hour basis. Overall, the model showed good performance with R2 and RMSE values of 0.7 and 17.7 μg m−3, respectively. It could capture the high PM2.5 concentration in the south and relatively low concentration in the north and exhibit better performance within the next 24 h. The use of the weighted loss function decreased the level of “high values underestimation, low values overestimation”, while incorporating the preceding PM2.5 observations into the encoder phase improved the predictive accuracy within 24 h. We also compared the model result with that from a state-of-the-art numerical model (WRF-Chem with pollutant data assimilation). The temporal R2 and RMSE from the WRF-Chem were 0.30−0.77 and 19−45 μg m−3 while those from the PPN model were 0.42−0.84 and 15−42 μg m−3. The proposed model shows powerful capacity in aerosol forecasts and provides an efficient and accurate tool for early warning and management of regional pollution events.

Battery-free and AI-enabled multiplexed sensor patches for wound monitoring.

Wound healing is a dynamic process with multiple phases. Rapid profiling and quantitative characterization of inflammation and infection remain challenging. We report a paper-like battery-free in situ AI-enabled multiplexed (PETAL) sensor for holistic wound assessment by leveraging deep learning algorithms. This sensor consists of a wax-printed paper panel with five colorimetric sensors for temperature, pH, trimethylamine, uric acid, and moisture. Sensor images captured by a mobile phone were analyzed by neural network-based machine learning algorithms to determine healing status. For ex situ detection via exudates collected from rat perturbed wounds and burn wounds, the PETAL sensor can classify healing versus nonhealing status with an accuracy as high as 97%. With the sensor patches attached on rat burn wound models, in situ monitoring of wound progression or severity is demonstrated. This PETAL sensor allows early warning of adverse events, which could trigger immediate clinical intervention to facilitate wound care management.

Interannual Variation in Earth’s Rotation Rate and Its Role as a Climate Change Indicator

Exploring the relationship between climate phenomena and anomalies in Earth’s rotation during a corresponding period is helpful for constraining the assessment of global change, even for the early warning of climate events. This study selected the latest length of day changes (ΔLOD) observations, and extracted the interannual terms solely related to climatic variations, employing a difference plus frequency domain stepwise regression (Difference+FDSR) method. Afterward, we calculated the correlations of different data compositions between surface fluid contributions (AAM, OAM and HAM) and the climate-related ΔLOD. Finally, the anomalies during the period of 1993–2023 were focused on, by comparing the high-precision fluid forcing and the climate-related ΔLOD with El Niño–Southern Oscillation (ENSO) indices. Our results show that superimposing the HAM can improve fluid correlations ~5% with climate-related ΔLOD, but the OAM contribution is not obvious. Additionally, we detected a triple-dip La Niña in the last 3 years, and the corresponding minimum values of climate-related ΔLOD were between −0.11 and −0.23 ms. Furthermore, we investigated the short-term forecast of a climate event with ΔLOD predictions based on the climate change information on Earth‘s rotation rate, wherein a follow-up El Niño is indicated.

Brightness Temperature Characteristics of Short-Duration Heavy Rainfall in the Chengdu–Chongqing Railway Region in China

In this study, we analyzed the brightness temperature characteristics of short-duration heavy rainfall (SDHR) along the Chengdu–Chongqing Railway (CCR), an important corridor of economic and transportation activity in southwest China. Our findings could prove useful in the monitoring and advance warning of SDHR events: (1) SDHR predominantly occurred from July to August, with a peak frequency in July in the CCR area. In terms of diurnal variation, SDHR was mainly observed at night, particularly between 22:00–05:00 and 06:00–09:00 (local time), with a peak at 01:00; (2) The relationship between SDHR and equivalent blackbody temperature (TBB) further showed that the occurrence of SDHR was accompanied by TBB decreasing to its minimum value, after which it increased, and SDHR ceased. In cases where TBB approached its minimum value after 1 h but continued to decrease slightly, SDHR continued. When SDHR occurred, the majority of the TBB values were recorded in the range 190–230 K; within this range, values between 190 and 200 K were most frequently recorded. In general, lower TBB values are associated with more intense SDHR. Based on this finding, we used linear regression to establish an estimating equation for SDHR.

Electronic nose application for detecting different odorants in source water: Possibility and scenario

The problem of taste and odor (T&O) in drinking water is a widespread societal concern and highlights substantial challenges related to the detection and evaluation of odor in water. In this study, the portable electronic nose PEN3, which is equipped with ten different heated metal sensors, was applied to analyze its applicability, feasibility and application scenarios for the detection of typical odorants, such as 2-methylisobornel (2-MIB), geosmin (GSM), β-cyclocitral, β-ionone, and other T&O compounds in source water, while avoiding uncertainties and instability related to manual inspection. All the T&O compounds could be effectively differentiated by principal component analysis (PCA). Linear discriminant analysis (LDA) showed that the odors varied greatly between different samples and could be effectively distinguished. As the odorant concentration increased, the sensor response intensity of the primary identification sensors R6 and R8 increased with a significant positive correlation. For Microcystis aeruginosa, an algae that produces odorants, PCA could distinguish the odors of algae at a series of densities at different concentrations. The responses of R10 showed a significant increase with increasing algae density, implying the production of more aliphatic hydrocarbons and other odor compounds. The results indicated that the electronic nose could provide a promising alternative to traditional unstable and complex detection methods for the detection of odorous substances in surface water and early warning of odor events. This study aimed to provide technical support for rapid monitoring and early warning of odorants in source water management.

Disruption event characterization and forecasting in tokamaks

Disruption prediction and avoidance is a critical need for next-step tokamaks, such as ITER. Disruption Event Characterization and Forecasting (DECAF) research fully automates analysis of tokamak data to determine chains of events that lead to disruptions and to forecast their evolution allowing sufficient time for mitigation or complete avoidance of the disruption. Disruption event chains related to local rotating or global magnetohydrodynamic (MHD) modes and vertical instability are examined with warnings issued for many off-normal physics events, including density limits, plasma dynamics, confinement transitions, and profile variations. Along with Greenwald density limit evaluation, a local radiative island power balance theory is evaluated and compared to the observation of island growth. Automated decomposition and analysis of rotating tearing modes produce physical event chains leading to disruptions. A total MHD state warning model comprised of 15 separate criteria produces a disruption forecast about 180 ms before a standard locked mode detector warning. Single DECAF event analyses have begun on KSTAR, MAST, and NSTX/-U databases with thousands of shot seconds of device operation using from 0.5 to 1 × 106 tested sample times per device. An initial multi-device database comparison illustrates a highly important result that plasma disruptivity does not need to increase as βN increases. Global MHD instabilities, such as resistive wall modes (RWMs), can give the briefest time period of warning before disruption compared to other physics events. In an NSTX database with unstable RWMs, the mode onset, loss of boundary and current control, and disruption event warnings are found in all cases and vertical displacement events are found in 91% of cases. An initial time-dependent reduced physics model of kinetic RWM stabilization created to forecast the disruption chain predicts instability 84% of the time for experimentally unstable cases with a relatively low false positive rate. Instances of the disruption event chain analysis illustrate dynamics including H–L back transitions for rotating MHD and global RWM triggering events. Disruption warnings are issued with sufficient time before the disruption (on transport timescales) to potentially allow active profile control for disruption avoidance, active mode control, or mitigation.

A Rapid Identification Technique of Moving Loads Based on MobileNetV2 and Transfer Learning

Rapid and accurate identification of moving load is crucial for bridge operation management and early warning of overload events. However, it is hard to obtain them rapidly via traditional machine learning methods, due to their massive model parameters and complex network structure. To this end, this paper proposes a novel method to perform moving loads identification using MobileNetV2 and transfer learning. Specifically, the dynamic responses of a vehicle–bridge interaction system are firstly transformed into a two-dimensional time-frequency image by continuous wavelet transform to construct the database. Secondly, a pre-trained MobileNetV2 model based on ImageNet is transferred to the moving load identification task by transfer learning strategy for describing the mapping relationship between structural response and these specified moving loads. Then, load identification can be performed through inputting bridge responses into the established relationship. Finally, the effectiveness of the method is verified by numerical simulation. The results show that it can accurately identify the vehicle weight, vehicle speed information, and presents excellent strong robustness. In addition, MobileNetV2 has faster identification speed and requires less computational resources than several traditional deep convolutional neural network models in moving load identification, which can provide a novel idea for the rapid identification of moving loads.