As the main equipment of coal mining production,the anomaly detection of shearer is important to ensure production efficiency and coal mine safety.One key challenge lies in the limited or even absence of labeled monit...As the main equipment of coal mining production,the anomaly detection of shearer is important to ensure production efficiency and coal mine safety.One key challenge lies in the limited or even absence of labeled monitoring data for the equipment,coupled with the high costs associated with manual annotation.Another challenge stems from the complex structure of the mining machines,making it difficult to reflect the overall operational state through local anomaly detection.Consequently,the application of decoupled local anomaly detection for mining machines in practical production remains challenging.This paper presents an unsupervised learning-based method for detecting anomalies in shearer.The method includes a module for constructing a Multi-scale Correlation Matrix(MSCM)of mining machine operating conditions,as well as the CNN-ConvLSTM Autoencoder(C-CLA)network.The module for constructing an MSCM enhances the representation of interrelationships between various features of the equipment from different perspectives using multiple correlation analysis methods.The C-CLA network integrates convolutional and convolutional recurrent neural networks,with the convolutional structure extracting local spatial features and the ConvLSTM structure further capturing information from different time scales and feature scales,thereby enhancing the model’s perceptual capabilities towards changes in equipment status.Finally,shearer anomaly detection is achieved through the analysis of reconstructed residual matrices.The rationality and practicality of the proposed method have been validated on our dataset,and the model’s generalization capability has been verified through repeated experiments in similar scenarios.However,due to variations in the working environment of different mining faces and differences in equipment models,implementing detection on other mining faces often requires retraining the model with new data.Furthermore,we compared our method with other anomaly detection techniques,and our detection efficiency was superior by approximately 3%.This method effectively detects anomalies in the shearer.展开更多
Many types of real-world information systems, including social media and e-commerce platforms, can be modelled by means of attribute-rich, connected networks. The goal of anomaly detection in artificial intelligence i...Many types of real-world information systems, including social media and e-commerce platforms, can be modelled by means of attribute-rich, connected networks. The goal of anomaly detection in artificial intelligence is to identify illustrations that deviate significantly from the main distribution of data or that differ from known cases. Anomalous nodes in node-attributed networks can be identified with greater precision if both graph and node attributes are taken into account. Almost all of the studies in this area focus on supervised techniques for spotting outliers. While supervised algorithms for anomaly detection work well in theory, they cannot be applied to real-world applications owing to a lack of labelled data. Considering the possible data distribution, our model employs a dual variational autoencoder (VAE), while a generative adversarial network (GAN) assures that the model is robust to adversarial training. The dual VAEs are used in another capacity: as a fake-node generator. Adversarial training is used to ensure that our latent codes have a Gaussian or uniform distribution. To provide a fair presentation of the graph, the discriminator instructs the generator to generate latent variables with distributions that are more consistent with the actual distribution of the data. Once the model has been learned, the discriminator is used for anomaly detection via reconstruction loss which has been trained to distinguish between the normal and artificial distributions of data. First, using a dual VAE, our model simultaneously captures cross-modality interactions between topological structure and node characteristics and overcomes the problem of unlabeled anomalies, allowing us to better understand the network sparsity and nonlinearity. Second, the proposed model considers the regularization of the latent codes while solving the issue of unregularized embedding techniques that can quickly lead to unsatisfactory representation. Finally, we use the discriminator reconstruction loss for anomaly detection as the discriminator is well-trained to separate the normal and generated data distributions because reconstruction-based loss does not include the adversarial component. Experiments conducted on attributed networks demonstrate the effectiveness of the proposed model and show that it greatly surpasses the previous methods. The area under the curve scores of our proposed model for the BlogCatalog, Flickr, and Enron datasets are 0.83680, 0.82020, and 0.71180, respectively, proving the effectiveness of the proposed model. The result of the proposed model on the Enron dataset is slightly worse than other models;we attribute this to the dataset’s low dimensionality as the most probable explanation.展开更多
Similarity measurement has been a prevailing research topic geographic information science.Geometric similarity measurement inin scaling transformation(GSM_ST)is critical to ensure spatial data quality while balancing...Similarity measurement has been a prevailing research topic geographic information science.Geometric similarity measurement inin scaling transformation(GSM_ST)is critical to ensure spatial data quality while balancing detailed information with distinctive features.However,GSM_ST is an uncertain problem due to subjective spatial cognition,global and local concerns,and geometric complexity.Traditional rule-based methods considering multiple consistent conditions require subjective adjustments to characteristics and weights,leading to poor robustness in addressing GSM_ST.This study proposes an unsupervised representation learning framework for automated GSM_ST,using a Graph Autoencoder Network(GAE)and drainage networks as an example.The framework involves constructing a drainage graph,designing the GAE architecture for GSM_ST,and using Cosine similarity to measure similarity based on the GAE-derived drainage embeddings in different scales.We perform extensive experiments and compare methods across 71 drainage networks duringfive scaling transformations.The results show that the proposed GAE method outperforms other methods with a satisfaction ratio of around 88%and has strong robustness.Moreover,our proposed method also can be applied to other scenarios,such as measuring similarity between geographical entities at different times and data from different datasets.展开更多
In the field of infrared and visible image fusion,researchers have put increasingly complex fusion networks forward to pursue better fusion metrics.This has led to a growing number of parameters in fusion models.Addit...In the field of infrared and visible image fusion,researchers have put increasingly complex fusion networks forward to pursue better fusion metrics.This has led to a growing number of parameters in fusion models.Additionally,most fusion models rarely address the issue of preserving background details in images,while these details are vital to subsequent advanced visual tasks,such as image analysis and recognition.In response to these limitations mentioned above,this paper proposes a novel image fusion algorithm called lightweight multi-scale hierarchical dense fusion network(LMHFusion).Concisely,we propose a lightweight multi-scale encoder.It extracts multi-scale features from input images through four encoding blocks with different receptive fields.Then,a designed hierarchical dense connection method is employed to concatenate distinct scale features.Unlike traditional manual fusion strategies,our fusion network is designed to be learnable and has adjustable weights.Moreover,we have specially designed a histogram equalization loss to train LMHFusion.This new loss produces fused images that contain both prominent structures and rich details.Through comparative analysis of LMHFusion and twelve other representative fusion models,it has been proven that LMHFusion can make the model more suitable for resource-constrained scenarios apart from enhancing the quality and visual effects of fused images.Our model is nearly 5000 times smaller in size compared to RFN-Nest.展开更多
Background Cumulus clouds are important elements in creating virtual outdoor scenes.Modeling cumulus clouds that have a specific shape is difficult owing to the fluid nature of the cloud.Image-based modeling is an eff...Background Cumulus clouds are important elements in creating virtual outdoor scenes.Modeling cumulus clouds that have a specific shape is difficult owing to the fluid nature of the cloud.Image-based modeling is an efficient method to solve this problem.Because of the complexity of cloud shapes,the task of modeling the cloud from a single image remains in the development phase.Methods In this study,a deep learning-based method was developed to address the problem of modeling 3D cumulus clouds from a single image.The method employs a three-dimensional autoencoder network that combines the variational autoencoder and the generative adversarial network.First,a 3D cloud shape is mapped into a unique hidden space using the proposed autoencoder.Then,the parameters of the decoder are fixed.A shape reconstruction network is proposed for use instead of the encoder part,and it is trained with rendered images.To train the presented models,we constructed a 3D cumulus dataset that included 2003D cumulus models.These cumulus clouds were rendered under different lighting parameters.Results The qualitative experiments showed that the proposed autoencoder method can learn more structural details of 3D cumulus shapes than existing approaches.Furthermore,some modeling experiments on rendering images demonstrated the effectiveness of the reconstruction model.Conclusion The proposed autoencoder network learns the latent space of 3D cumulus cloud shapes.The presented reconstruction architecture models a cloud from a single image.Experiments demonstrated the effectiveness of the two models.展开更多
With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance s...With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.展开更多
In this article,we use a convolutional autoencoder neural network to reduce data dimensioning and rebuild soliton dynamics in a passively mode-locked fiber laser.Based on the particle characteristic in double solitons...In this article,we use a convolutional autoencoder neural network to reduce data dimensioning and rebuild soliton dynamics in a passively mode-locked fiber laser.Based on the particle characteristic in double solitons and triple solitons interactions,we found that there is a strict correspondence between the number of minimum compression parameters and the number of independent parameters of soliton interaction.This shows that our network effectively coarsens the high-dimensional data in nonlinear systems.Our work not only introduces new prospects for the laser self-optimization algorithm,but also brings new insights into the modeling of nonlinear systems and description of soliton interactions.展开更多
The health status of aero engines is very important to the flight safety.However,it is difficult for aero engines to make an effective fault diagnosis due to its complex structure and poor working environment.Therefor...The health status of aero engines is very important to the flight safety.However,it is difficult for aero engines to make an effective fault diagnosis due to its complex structure and poor working environment.Therefore,an effective fault diagnosis method for aero engines based on the gravitational search algorithm and the stack autoencoder(GSA-SAE)is proposed,and the fault diagnosis technology of a turbofan engine is studied.Firstly,the data of 17 parameters,including total inlet air temperature,high-pressure rotor speed,low-pressure rotor speed,turbine pressure ratio,total inlet air temperature of high-pressure compressor and outlet air pressure of high-pressure compressor and so on,are preprocessed,and the fault diagnosis model architecture of SAE is constructed.In order to solve the problem that the best diagnosis effect cannot be obtained due to manually setting the number of neurons in each hidden layer of SAE network,a GSA optimization algorithm for the SAE network is proposed to find and obtain the optimal number of neurons in each hidden layer of SAE network.Furthermore,an optimal fault diagnosis model based on GSA-SAE is established for aero engines.Finally,the effectiveness of the optimal GSA-SAE fault diagnosis model is demonstrated using the practical data of aero engines.The results illustrate that the proposed fault diagnosis method effectively solves the problem of the poor fault diagnosis result because of manually setting the number of neurons in each hidden layer of SAE network,and has good fault diagnosis efficiency.The fault diagnosis accuracy of the GSA-SAE model reaches 98.222%,which is significantly higher than that of SAE,the general regression neural network(GRNN)and the back propagation(BP)network fault diagnosis models.展开更多
Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration assessments.In this study,we propose an autoencoder-based mo...Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration assessments.In this study,we propose an autoencoder-based model for forest disturbance detection,which considers disturbances as anomalous events in forest temporal trajectories.The autoencoder network is established and trained to reconstruct intact forest trajectories.Then,the disturbance detection threshold is derived by Tukey’s method based on the reconstruction error of the intact forest trajectory.The assessment result shows that the model using the NBR time series performs better than the NDVIbased model,with an overall accuracy of 90.3%.The omission and commission errors of disturbed forest are 7%and 12%,respectively.Additionally,the trained NBR-based model is implemented in two test areas,with overall accuracies of 87.2%and 86.1%,indicating the robustness and scalability of the model.Moreover,comparing three common methods,the proposed model performs better,especially for intact forest detection accuracy.This study provides a novel and robust approach with acceptable accuracy for forest disturbance detection,enabling forest disturbance to be identified in regions with limited disturbance reference data.展开更多
文摘As the main equipment of coal mining production,the anomaly detection of shearer is important to ensure production efficiency and coal mine safety.One key challenge lies in the limited or even absence of labeled monitoring data for the equipment,coupled with the high costs associated with manual annotation.Another challenge stems from the complex structure of the mining machines,making it difficult to reflect the overall operational state through local anomaly detection.Consequently,the application of decoupled local anomaly detection for mining machines in practical production remains challenging.This paper presents an unsupervised learning-based method for detecting anomalies in shearer.The method includes a module for constructing a Multi-scale Correlation Matrix(MSCM)of mining machine operating conditions,as well as the CNN-ConvLSTM Autoencoder(C-CLA)network.The module for constructing an MSCM enhances the representation of interrelationships between various features of the equipment from different perspectives using multiple correlation analysis methods.The C-CLA network integrates convolutional and convolutional recurrent neural networks,with the convolutional structure extracting local spatial features and the ConvLSTM structure further capturing information from different time scales and feature scales,thereby enhancing the model’s perceptual capabilities towards changes in equipment status.Finally,shearer anomaly detection is achieved through the analysis of reconstructed residual matrices.The rationality and practicality of the proposed method have been validated on our dataset,and the model’s generalization capability has been verified through repeated experiments in similar scenarios.However,due to variations in the working environment of different mining faces and differences in equipment models,implementing detection on other mining faces often requires retraining the model with new data.Furthermore,we compared our method with other anomaly detection techniques,and our detection efficiency was superior by approximately 3%.This method effectively detects anomalies in the shearer.
文摘Many types of real-world information systems, including social media and e-commerce platforms, can be modelled by means of attribute-rich, connected networks. The goal of anomaly detection in artificial intelligence is to identify illustrations that deviate significantly from the main distribution of data or that differ from known cases. Anomalous nodes in node-attributed networks can be identified with greater precision if both graph and node attributes are taken into account. Almost all of the studies in this area focus on supervised techniques for spotting outliers. While supervised algorithms for anomaly detection work well in theory, they cannot be applied to real-world applications owing to a lack of labelled data. Considering the possible data distribution, our model employs a dual variational autoencoder (VAE), while a generative adversarial network (GAN) assures that the model is robust to adversarial training. The dual VAEs are used in another capacity: as a fake-node generator. Adversarial training is used to ensure that our latent codes have a Gaussian or uniform distribution. To provide a fair presentation of the graph, the discriminator instructs the generator to generate latent variables with distributions that are more consistent with the actual distribution of the data. Once the model has been learned, the discriminator is used for anomaly detection via reconstruction loss which has been trained to distinguish between the normal and artificial distributions of data. First, using a dual VAE, our model simultaneously captures cross-modality interactions between topological structure and node characteristics and overcomes the problem of unlabeled anomalies, allowing us to better understand the network sparsity and nonlinearity. Second, the proposed model considers the regularization of the latent codes while solving the issue of unregularized embedding techniques that can quickly lead to unsatisfactory representation. Finally, we use the discriminator reconstruction loss for anomaly detection as the discriminator is well-trained to separate the normal and generated data distributions because reconstruction-based loss does not include the adversarial component. Experiments conducted on attributed networks demonstrate the effectiveness of the proposed model and show that it greatly surpasses the previous methods. The area under the curve scores of our proposed model for the BlogCatalog, Flickr, and Enron datasets are 0.83680, 0.82020, and 0.71180, respectively, proving the effectiveness of the proposed model. The result of the proposed model on the Enron dataset is slightly worse than other models;we attribute this to the dataset’s low dimensionality as the most probable explanation.
基金supported by the National Natural Science Foundation of China[grant number 41531180]the National Natural Science Foundation of China[grant number 42071450]the China Scholarship Council(CSC)[grant number 202206270076].
文摘Similarity measurement has been a prevailing research topic geographic information science.Geometric similarity measurement inin scaling transformation(GSM_ST)is critical to ensure spatial data quality while balancing detailed information with distinctive features.However,GSM_ST is an uncertain problem due to subjective spatial cognition,global and local concerns,and geometric complexity.Traditional rule-based methods considering multiple consistent conditions require subjective adjustments to characteristics and weights,leading to poor robustness in addressing GSM_ST.This study proposes an unsupervised representation learning framework for automated GSM_ST,using a Graph Autoencoder Network(GAE)and drainage networks as an example.The framework involves constructing a drainage graph,designing the GAE architecture for GSM_ST,and using Cosine similarity to measure similarity based on the GAE-derived drainage embeddings in different scales.We perform extensive experiments and compare methods across 71 drainage networks duringfive scaling transformations.The results show that the proposed GAE method outperforms other methods with a satisfaction ratio of around 88%and has strong robustness.Moreover,our proposed method also can be applied to other scenarios,such as measuring similarity between geographical entities at different times and data from different datasets.
基金supported by the National Key Laboratory of Air-based Information Perception and Fusion and the Aeronautical Science Foundation of China(Grant No.20220001068001)。
文摘In the field of infrared and visible image fusion,researchers have put increasingly complex fusion networks forward to pursue better fusion metrics.This has led to a growing number of parameters in fusion models.Additionally,most fusion models rarely address the issue of preserving background details in images,while these details are vital to subsequent advanced visual tasks,such as image analysis and recognition.In response to these limitations mentioned above,this paper proposes a novel image fusion algorithm called lightweight multi-scale hierarchical dense fusion network(LMHFusion).Concisely,we propose a lightweight multi-scale encoder.It extracts multi-scale features from input images through four encoding blocks with different receptive fields.Then,a designed hierarchical dense connection method is employed to concatenate distinct scale features.Unlike traditional manual fusion strategies,our fusion network is designed to be learnable and has adjustable weights.Moreover,we have specially designed a histogram equalization loss to train LMHFusion.This new loss produces fused images that contain both prominent structures and rich details.Through comparative analysis of LMHFusion and twelve other representative fusion models,it has been proven that LMHFusion can make the model more suitable for resource-constrained scenarios apart from enhancing the quality and visual effects of fused images.Our model is nearly 5000 times smaller in size compared to RFN-Nest.
基金the National Key R&D Program of China(2017YFB1002702).
文摘Background Cumulus clouds are important elements in creating virtual outdoor scenes.Modeling cumulus clouds that have a specific shape is difficult owing to the fluid nature of the cloud.Image-based modeling is an efficient method to solve this problem.Because of the complexity of cloud shapes,the task of modeling the cloud from a single image remains in the development phase.Methods In this study,a deep learning-based method was developed to address the problem of modeling 3D cumulus clouds from a single image.The method employs a three-dimensional autoencoder network that combines the variational autoencoder and the generative adversarial network.First,a 3D cloud shape is mapped into a unique hidden space using the proposed autoencoder.Then,the parameters of the decoder are fixed.A shape reconstruction network is proposed for use instead of the encoder part,and it is trained with rendered images.To train the presented models,we constructed a 3D cumulus dataset that included 2003D cumulus models.These cumulus clouds were rendered under different lighting parameters.Results The qualitative experiments showed that the proposed autoencoder method can learn more structural details of 3D cumulus shapes than existing approaches.Furthermore,some modeling experiments on rendering images demonstrated the effectiveness of the reconstruction model.Conclusion The proposed autoencoder network learns the latent space of 3D cumulus cloud shapes.The presented reconstruction architecture models a cloud from a single image.Experiments demonstrated the effectiveness of the two models.
基金funded by scientific research projects under Grant JY2024B011.
文摘With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.
基金supported by the National Natural Science Foundation of China(Nos.12274238 and 61835006)the National Key Research and Development Program of China(No.2018YFB1801802)+2 种基金the Beijing-Tianjin-Hebei Basic Research Cooperation Project(No.21JCZXJC00010)the Natural Science Foundation of Tianjin City(No.19JCZDJC31200)the Tianjin Research Innovation Project for Postgraduate Students(No.2021YJSB083)。
文摘In this article,we use a convolutional autoencoder neural network to reduce data dimensioning and rebuild soliton dynamics in a passively mode-locked fiber laser.Based on the particle characteristic in double solitons and triple solitons interactions,we found that there is a strict correspondence between the number of minimum compression parameters and the number of independent parameters of soliton interaction.This shows that our network effectively coarsens the high-dimensional data in nonlinear systems.Our work not only introduces new prospects for the laser self-optimization algorithm,but also brings new insights into the modeling of nonlinear systems and description of soliton interactions.
基金supported by the National Natural Science Foundation of China(No.51605309)the Aeronautical Science Foundation of China(Nos.201933054002,20163354004)。
文摘The health status of aero engines is very important to the flight safety.However,it is difficult for aero engines to make an effective fault diagnosis due to its complex structure and poor working environment.Therefore,an effective fault diagnosis method for aero engines based on the gravitational search algorithm and the stack autoencoder(GSA-SAE)is proposed,and the fault diagnosis technology of a turbofan engine is studied.Firstly,the data of 17 parameters,including total inlet air temperature,high-pressure rotor speed,low-pressure rotor speed,turbine pressure ratio,total inlet air temperature of high-pressure compressor and outlet air pressure of high-pressure compressor and so on,are preprocessed,and the fault diagnosis model architecture of SAE is constructed.In order to solve the problem that the best diagnosis effect cannot be obtained due to manually setting the number of neurons in each hidden layer of SAE network,a GSA optimization algorithm for the SAE network is proposed to find and obtain the optimal number of neurons in each hidden layer of SAE network.Furthermore,an optimal fault diagnosis model based on GSA-SAE is established for aero engines.Finally,the effectiveness of the optimal GSA-SAE fault diagnosis model is demonstrated using the practical data of aero engines.The results illustrate that the proposed fault diagnosis method effectively solves the problem of the poor fault diagnosis result because of manually setting the number of neurons in each hidden layer of SAE network,and has good fault diagnosis efficiency.The fault diagnosis accuracy of the GSA-SAE model reaches 98.222%,which is significantly higher than that of SAE,the general regression neural network(GRNN)and the back propagation(BP)network fault diagnosis models.
基金funded by the National Natural Science Foundation of China under Grant 41871223the China Scholarship Council(CSC)(No.201806400048)for doctoral scholarship support.
文摘Monitoring and classifying disturbed forests can provide information support for not only sustainable forest management but also global carbon sequestration assessments.In this study,we propose an autoencoder-based model for forest disturbance detection,which considers disturbances as anomalous events in forest temporal trajectories.The autoencoder network is established and trained to reconstruct intact forest trajectories.Then,the disturbance detection threshold is derived by Tukey’s method based on the reconstruction error of the intact forest trajectory.The assessment result shows that the model using the NBR time series performs better than the NDVIbased model,with an overall accuracy of 90.3%.The omission and commission errors of disturbed forest are 7%and 12%,respectively.Additionally,the trained NBR-based model is implemented in two test areas,with overall accuracies of 87.2%and 86.1%,indicating the robustness and scalability of the model.Moreover,comparing three common methods,the proposed model performs better,especially for intact forest detection accuracy.This study provides a novel and robust approach with acceptable accuracy for forest disturbance detection,enabling forest disturbance to be identified in regions with limited disturbance reference data.
