Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide.Accurately predicting landslide displacement enables effective early warning and risk management.However,the limit...Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide.Accurately predicting landslide displacement enables effective early warning and risk management.However,the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models,such as state-of-the-art machine learning(ML)models.To address these challenges,this study proposes a data augmentation framework that uses generative adversarial networks(GANs),a recent advance in generative artificial intelligence(AI),to improve the accuracy of landslide displacement prediction.The framework provides effective data augmentation to enhance limited datasets.A recurrent GAN model,RGAN-LS,is proposed,specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data.A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data.Then,the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory(LSTM)networks and particle swarm optimization-support vector machine(PSO-SVM)models for landslide displacement prediction tasks.Results on two landslides in the Three Gorges Reservoir(TGR)region show a significant improvement in LSTM model prediction performance when trained on augmented data.For instance,in the case of the Baishuihe landslide,the average root mean square error(RMSE)increases by 16.11%,and the mean absolute error(MAE)by 17.59%.More importantly,the model’s responsiveness during mutational stages is enhanced for early warning purposes.However,the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM.Further analysis indicates that an optimal synthetic-to-real data ratio(50%on the illustration cases)maximizes the improvements.This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results.By using the powerful generative AI approach,RGAN-LS can generate high-fidelity synthetic landslide data.This is critical for improving the performance of advanced ML models in predicting landslide displacement,particularly when there are limited training data.Additionally,this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.展开更多
The naive, Bayes （NB） model has been successfully used to tackle spare, and is very accurate. However, there is still room for improwment. We use a train on or near error （TONE） method in online NB to enhance the ...The naive, Bayes （NB） model has been successfully used to tackle spare, and is very accurate. However, there is still room for improwment. We use a train on or near error （TONE） method in online NB to enhance the perfornmnee of NB and reduce the number of training emails. We conducted an experiment to determine the performanee of the improved algorithm by plotting （I-ROCA）% curves. The resuhs show that the proposed method improves the performanee of original NB.展开更多
Particulate matter with diameters≤2.5μm(PM_(2.5))has been identified as a significant air pollutant contributing to premature mortality.Nevertheless,the specific compositions within PM_(2.5) that play the most cruci...Particulate matter with diameters≤2.5μm(PM_(2.5))has been identified as a significant air pollutant contributing to premature mortality.Nevertheless,the specific compositions within PM_(2.5) that play the most crucial role remain unclear,especially in areas with high pollution concentrations.This study aims to investigate the individual and joint mortality risks associated with PM_(2.5) inorganic chemical compositions and identify primary contributors.In 1998,we conducted a prospective cohort study in four northern Chinese cities(Tianjin,Shenyang,Taiyuan,and Rizhao).Satellite-based machine learning models calculated PM_(2.5) inorganic chemical compositions,including sulfate(SO_(4)^(2–)),nitrate(NO_(3)^(–)),ammonium(NH_(4)^(+)),and chloride(Cl^(-)).A time-varying Cox proportional hazards model was applied to analyze associations between these compositions and cardiorespiratory mortality,encompassing nonaccidental causes,cardiovascular diseases(CVDs),nonmalignant respiratory diseases(RDs),and lung cancer.The quantile-based g-computation model evaluated joint exposure effects and relative contributions of the compositions.Stratified analysis was used to identify vulnerable subpopulations.During 785,807 person-years of follow-up,5812(15.5%)deaths occurred from nonaccidental causes,including 2932(7.8%)from all CVDs,479(1.3%)from nonmalignant RDs,and 552(1.4%)from lung cancer.Every interquartile range(IQR)increase in SO_(4)^(2–)was associated with mortality from nonaccidental causes(hazard ratio:1.860;95%confidence interval:1.809,1.911),CVDs(1.909;1.836,1.985),nonmalignant RDs(2.178;1.975,2.403),and lung cancer(1.773;1.624,1.937).In the joint exposure model,a simultaneous rise of one IQR in all four compositions increased the risk of cardiorespiratory mortality by at least 36.3%,with long-term exposure to SO_(4)^(2–)contributing the most to nonaccidental and cardiopulmonary deaths.Individuals with higher incomes and lower education levels were found to be more vulnerable.Long-term exposure to higher levels of PM_(2.5) inorganic compositions was associated with significantly increased cardiopulmonary mortality,with SO_(4)^(2–)potentially being the primary contributor.These findings offer insights into how PM_(2.5) sources impact health,aiding the development of more effective governance measures.展开更多
基金supported by the Natural Science Foundation of Jiangsu Province(Grant No.BK20220421)the State Key Program of the National Natural Science Foundation of China(Grant No.42230702)the National Natural Science Foundation of China(Grant No.82302352).
文摘Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide.Accurately predicting landslide displacement enables effective early warning and risk management.However,the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models,such as state-of-the-art machine learning(ML)models.To address these challenges,this study proposes a data augmentation framework that uses generative adversarial networks(GANs),a recent advance in generative artificial intelligence(AI),to improve the accuracy of landslide displacement prediction.The framework provides effective data augmentation to enhance limited datasets.A recurrent GAN model,RGAN-LS,is proposed,specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data.A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data.Then,the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory(LSTM)networks and particle swarm optimization-support vector machine(PSO-SVM)models for landslide displacement prediction tasks.Results on two landslides in the Three Gorges Reservoir(TGR)region show a significant improvement in LSTM model prediction performance when trained on augmented data.For instance,in the case of the Baishuihe landslide,the average root mean square error(RMSE)increases by 16.11%,and the mean absolute error(MAE)by 17.59%.More importantly,the model’s responsiveness during mutational stages is enhanced for early warning purposes.However,the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM.Further analysis indicates that an optimal synthetic-to-real data ratio(50%on the illustration cases)maximizes the improvements.This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results.By using the powerful generative AI approach,RGAN-LS can generate high-fidelity synthetic landslide data.This is critical for improving the performance of advanced ML models in predicting landslide displacement,particularly when there are limited training data.Additionally,this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.
基金supported by National Natural Science Foundation of China under Grant NO. 60903083Research fund for the doctoral program of higher education of China under Grant NO.20092303120005the Research Fund of ZTE Corporation
文摘The naive, Bayes （NB） model has been successfully used to tackle spare, and is very accurate. However, there is still room for improwment. We use a train on or near error （TONE） method in online NB to enhance the perfornmnee of NB and reduce the number of training emails. We conducted an experiment to determine the performanee of the improved algorithm by plotting （I-ROCA）% curves. The resuhs show that the proposed method improves the performanee of original NB.
基金National Key Research and Development Program of China(Grants 2017YFC0211605 and 2017YFC0211704).
文摘Particulate matter with diameters≤2.5μm(PM_(2.5))has been identified as a significant air pollutant contributing to premature mortality.Nevertheless,the specific compositions within PM_(2.5) that play the most crucial role remain unclear,especially in areas with high pollution concentrations.This study aims to investigate the individual and joint mortality risks associated with PM_(2.5) inorganic chemical compositions and identify primary contributors.In 1998,we conducted a prospective cohort study in four northern Chinese cities(Tianjin,Shenyang,Taiyuan,and Rizhao).Satellite-based machine learning models calculated PM_(2.5) inorganic chemical compositions,including sulfate(SO_(4)^(2–)),nitrate(NO_(3)^(–)),ammonium(NH_(4)^(+)),and chloride(Cl^(-)).A time-varying Cox proportional hazards model was applied to analyze associations between these compositions and cardiorespiratory mortality,encompassing nonaccidental causes,cardiovascular diseases(CVDs),nonmalignant respiratory diseases(RDs),and lung cancer.The quantile-based g-computation model evaluated joint exposure effects and relative contributions of the compositions.Stratified analysis was used to identify vulnerable subpopulations.During 785,807 person-years of follow-up,5812(15.5%)deaths occurred from nonaccidental causes,including 2932(7.8%)from all CVDs,479(1.3%)from nonmalignant RDs,and 552(1.4%)from lung cancer.Every interquartile range(IQR)increase in SO_(4)^(2–)was associated with mortality from nonaccidental causes(hazard ratio:1.860;95%confidence interval:1.809,1.911),CVDs(1.909;1.836,1.985),nonmalignant RDs(2.178;1.975,2.403),and lung cancer(1.773;1.624,1.937).In the joint exposure model,a simultaneous rise of one IQR in all four compositions increased the risk of cardiorespiratory mortality by at least 36.3%,with long-term exposure to SO_(4)^(2–)contributing the most to nonaccidental and cardiopulmonary deaths.Individuals with higher incomes and lower education levels were found to be more vulnerable.Long-term exposure to higher levels of PM_(2.5) inorganic compositions was associated with significantly increased cardiopulmonary mortality,with SO_(4)^(2–)potentially being the primary contributor.These findings offer insights into how PM_(2.5) sources impact health,aiding the development of more effective governance measures.
