Convolutional Autoencoder Research Articles

Residual squeeze-and-excitation convolutional auto-encoder for fault detection and diagnosis in complex industrial processes

Recently, deep learning has attracted increasing attention in process monitoring. However, it is still a big challenge to extract effective features of process data for fault detection and diagnosis (FDD) by using deep learning-based methods. In this study, a novel deep learning-based model, residual squeeze-and-excitation convolutional auto-encoder (RSECAE) is proposed for FDD in complex industrial processes. A hybrid structure that integrates convolution calculation and auto-encoder is proposed to construct multiple convolution layers and deconvolution layers in the encoder and decoder respectively. Thus, RSECAE can learn effective features from the process signals in an unsupervised manner. At the same time, multiple residual squeeze-and-excitation networks (RSENets) are embedded in the deep network, which effectively preserves the critical feature representations of the convolution layer and transmits them to the decoder in the form of residuals. Finally, maximum mean discrepancy (MMD) term is utilized in RSECAE to reduce the distribution difference between the process signals and the learned features. This enables RSECAE to extract effective features with prior distribution information. RSECAE provides a new solution for process FDD for complicated industrial processes. Two industrial cases are adopted to validate the effectiveness of the RSECAE in process FDD. The experimental results demonstrate the effectiveness and superiority of RSECAE in process fault detection and fault diagnosis.

Underwater multi-sensor fusion localization with visual-inertial-depth using hybrid residuals and efficient loop closing

Unmanned underwater vehicles (UUVs) need robust localization systems to complete their missions safely. To address the degradation of the localization accuracy of UUVs using visual-based simultaneous localization and mapping (SLAM) in underwater environments. A full SLAM system that fuses visual-inertial-depth measurements using hybrid residuals and efficient loop closing is proposed. Specifically, a novel visual hybrid residual is presented with an adaptive dynamic weighting factor. Reprojection and photometric double constraints are constructed simultaneously using the selected robust features. These constraints are then optimized jointly with the IMU measurements and the relative depth measurements to obtain a more accurate pose. Furthermore, a new three-step image-to-sequence strategy and a convolutional auto-encoder (CAE)-based global image representation are adopted to select candidate frames in order to improve the recall of underwater visual loop closure detection. Quantitative and qualitative analyses of real-world artificial pool and ocean experiments demonstrate the accuracy and effectiveness of the proposed system.

Automated fabric inspection system development aided with convolutional autoencoder-based defect detection

Industrial automatic fabric inspection system, a critical technology in the industry, enhances both total production quantity and quality compared to conventional inspection techniques. This study aims to create a reliable and effective real-time automated visual inspection system for fabrics, focusing on defect detection. The goals of the study can be stated as; installing a system with advanced technology for capturing and processing images swiftly, the development and deployment of a system capable of autonomously learning and scanning fabrics in use, and the creation of a smart framework for accurate fabric defect detection and classification. We focus on the development of unsupervised fabric defect detection using a convolutional autoencoder model, and defect classification using a convolutional neural network model, which takes input as the feature vector generated by the convolutional autoencoder. The experimental outcomes have displayed significant success rates in both detecting defects and classifying them, confirming the effectiveness of the framework in real-time visual inspection systems.

Cross-tokamak deployment study of plasma disruption predictors based on convolutional autoencoder

In the initial stages of operation for future tokamak, facing limited data availability, deploying data-driven disruption predictors requires optimal performance with minimal use of new device data. This paper studies the issue of data utilization in data-driven disruption predictor during cross tokamak deployment. Current predictors primarily employ supervised learning methods and require a large number of disruption and non-disruption shots for training. However, the scarcity and high cost of obtaining disruption shots for future tokamaks result in imbalanced training datasets, reducing the performance of supervised learning predictors. To solve this problem, we propose the Enhanced Convolutional Autoencoder Anomaly Detection (E-CAAD) predictor. E-CAAD can be trained only by non-disruption samples and can also be trained by disruption precursor samples when disruption shots occur. This model not only overcomes the sample imbalance in supervised learning predictors, but also overcomes the inefficient dataset utilization faced by traditional anomaly detection predictors that cannot use disruption precursor samples for training, making it more suitable for the unpredictable datasets of future tokamaks. Compared to traditional anomaly detection predictors, the E-CAAD predictor performs better in disruption prediction and is deployed faster on new devices. Additionally, we explore strategies to accelerate the deployment of the E-CAAD predictor on the new device by using data from existing devices. Two deployment strategies are presented: mixing data from existing devices and fine-tuning the predictor trained on existing devices. Our comparisons indicate that the data from existing device can accelerate the deployment of predictor on new device. Notably, the fine-tuning strategy yields the fastest deployment on new device among the designed strategies.

V-DAFT: visual technique for texture image defect recognition with denoising autoencoder and fourier transform

Texture is the surface qualities and visual attributes of an object, determined by the arrangement, size, shape, density, and proportion of its fundamental components. In the manufacturing industry, products typically have uniform textures, allowing for automated visual inspections of the product surface to recognize defects. During this process, texture defect recognition techniques can be employed. In this paper, we propose a method that combines a convolutional autoencoder architecture with Fourier transform analysis. We employ a normal reconstructed template as defined in this study. Despite its simple structure and rapid training and inference capabilities, it offers recognition performance comparable to state-of-the-art methods. Fourier transform is a powerful tool for analyzing the frequency domain of images and signals, which is essential for effective defect recognition as texture defects often exhibit characteristic changes in specific frequency ranges. The experiment evaluates the recognition performance using the AUC metric, with the proposed method showing a score of 93.7%. To compare with existing approaches, we present experimental results from previous research, an ablation study of the proposed method, and results based on the high-pass filter used in the Fourier mask.

On leveraging self-supervised learning for accurate HCV genotyping

Hepatitis C virus (HCV) is a major global health concern, affecting millions of individuals worldwide. While existing literature predominantly focuses on disease classification using clinical data, there exists a critical research gap concerning HCV genotyping based on genomic sequences. Accurate HCV genotyping is essential for patient management and treatment decisions. While the neural models excel at capturing complex patterns, they still face challenges, such as data scarcity, that exist a lot in computational genomics. To overcome this challenges, this paper introduces an advanced deep learning approach for HCV genotyping based on the graphical representation of nucleotide sequences that outperforms classical approaches. Notably, it is effective for both partial and complete HCV genomes and addresses challenges associated with imbalanced datasets. In this work, ten HCV genotypes: 1a, 1b, 2a, 2b, 2c, 3a, 3b, 4, 5, and 6 were used in the analysis. This study utilizes Chaos Game Representation for 2D mapping of genomic sequences, employing self-supervised learning using convolutional autoencoder for deep feature extraction, resulting in an outstanding performance for HCV genotyping compared to various machine learning and deep learning models. This baseline provides a benchmark against which the performance of the proposed approach and other models can be evaluated. The experimental results showcase a remarkable classification accuracy of over 99%, outperforming traditional deep learning models. This performance demonstrates the capability of the proposed model to accurately identify HCV genotypes in both partial and complete sequences and in dealing with data scarcity for certain genotypes. The results of the proposed model are compared to NCBI genotyping tool.

Deep learning model for fiber optic distributed acoustic sensing seismic data compression based on autoencoder and recurrent neural networks

Because of the extremely high sampling rate of fiber optic distributed acoustic sensing (DAS) equipment, the amount of DAS seismic data collected is enormous, which poses great challenges to the transmission and storage of DAS seismic data. Therefore, it is essential to study the compression methods of DAS seismic data. Existing data compression methods such as wavelet transform, cosine transform, and convolutional autoencoder (CAE) still have room for improvement in the compression performance and compression ratio (CR). Thus, we have proposed what we believe to be is a novel deep learning model called the recurrent autoencoder (RAE) for high-performance compression of DAS seismic data. Under different CRs, we have designed performance evaluation experiments for RAE models based on different RNN modules with different loss functions. When the CR of the RAE model is 8, the signal-to-noise ratio (SNR) of the reconstructed DAS seismic data reaches 40.60 dB, which is better than that of the CAE’s 11.58 dB. The ultimate CR was increased to 512 without reducing the compression quality, which is 4.12 times higher than the CAE model. The LSTM with a weighted loss function improves the SNR to 43.66 dB at a CR of 8, which is 3.06 dB higher than the LSTM with additive loss function. The results show that the RAE model proposed with a weighted loss function in this paper has excellent DAS seismic data compression performance and provides a high CR, which can be widely applied in large-scale DAS seismic data compression.

Convolutional autoencoder-based framework for damage localization under variable temperature

Confounding factors such as variable temperature have an impact on Lamb wave behaviour, affecting the accuracy of damage localization methods based on such waves. In this study, an innovative approach to Lamb wave prediction based on convolutional autoencoders (CAEs) is proposed and applied to an experimental dataset consisting of Lamb wave acquisitions on a Carbon Fiber Reinforced Polymer (CFRP) plate under varying temperatures. Leveraging an experimental dataset of Lamb wave signals acquired from a CFRP plate at different temperatures, this research focuses on utilizing CAEs to enhance the accuracy and reliability of damage localization. This algorithm extracts critical features from Lamb wave data, effectively recognizing subtle wave properties variations, thus significantly improving the precision of damage localization. Two different architectures of CAEs were evaluated. One which uses the temperature value as a direct input into the latent space of the autoencoder, and another that does not process the temperature value. This analysis was performed to demonstrate the actual impact of the temperature information on prediction accuracy and, furthermore, the accuracy of the CAEs at predicting Lamb wave signals for temperatures outside of their training dataset. The results obtained demonstrate that the inclusion of the temperature information into the autoencoder architecture not only increased its accuracy for temperatures within its training dataset but also increased its robustness with regards to temperature variations, displaying better performance at predicting Lamb wave signals for temperatures outside of its training dataset. The algorithm proposed here presents a way forward for increasing the robustness and reliability of damage localization methods based on Lamb waves.

Reduced-order modeling of unsteady fluid flow using neural network ensembles

The use of deep learning has become increasingly popular in reduced-order models (ROMs) to obtain low-dimensional representations of full-order models. Convolutional autoencoders (CAEs) are often used to this end as they are adept at handling data that are spatially distributed, including solutions to partial differential equations. When applied to unsteady physics problems, ROMs also require a model for time-series prediction of the low-dimensional latent variables. Long short-term memory (LSTM) networks, a type of recurrent neural network useful for modeling sequential data, are frequently employed in data-driven ROMs for autoregressive time-series prediction. When making predictions at unseen design points over long time horizons, error propagation is a frequently encountered issue, where errors made early on can compound over time and lead to large inaccuracies. In this work, we propose using bagging, a commonly used ensemble learning technique, to develop a fully data-driven ROM framework referred to as the CAE-eLSTM ROM that uses CAEs for spatial reconstruction of the full-order model and LSTM ensembles for time-series prediction. When applied to two unsteady fluid dynamics problems, our results show that the presented framework effectively reduces error propagation and leads to more accurate time-series prediction of latent variables at unseen points.

Unsupervised Feature Extraction From Raw Data for Gesture Recognition With Wearable Ultralow-Power Ultrasound.

Wearable ultrasound (US) is a novel sensing approach that shows promise in multiple application domains, and specifically in hand gesture recognition (HGR). In fact, US enables to collect information from deep musculoskeletal structures at high spatiotemporal resolution and high signal-to-noise ratio, making it a perfect candidate to complement surface electromyography for improved accuracy performance and on-the-edge classification. However, existing wearable solutions for US-based gesture recognition are not sufficiently low power for continuous, long-term operation. On top of that, practical hardware limitations of wearable US devices (limited power budget, reduced wireless throughput, and restricted computational power) set the need for the compressed size of models for feature extraction and classification. To overcome these limitations, this article presents a novel end-to-end approach for feature extraction from raw musculoskeletal US data suited for edge computing, coupled with an armband for HGR based on a truly wearable (12 cm2, 9 g), ultralow-power (ULP) (16 mW) US probe. The proposed approach uses a 1-D convolutional autoencoder (CAE) to compress raw US data by 20× while preserving the main amplitude features of the envelope signal. The latent features of the autoencoder are used to train an XGBoost classifier for HGR on datasets collected with a custom US armband, considering armband removal/repositioning in between sessions. Our approach achieves a classification accuracy of 96%. Furthermore, the proposed unsupervised feature extraction approach offers generalization capabilities for intersubject use, as demonstrated by testing the pretrained encoder on a different subject and conducting posttraining analysis, revealing that the operations performed by the encoder are subject-independent. The autoencoder is also quantized to 8-bit integers and deployed on a ULP wearable US probe along with the XGBoost classifier, allowing for a gesture recognition rate ≥ 25 Hz and leading to 21% lower power consumption [at 30 frames/s (FPS)] compared to the conventional approach (raw data transmission and remote processing).

Convolutional Autoencoders for Signal Reconstruction and their Application to Damage Signature Extraction

The utilization of Machine Learning (ML) techniques for Structural Health Monitoring (SHM) has increased in the last years. Using ML techniques for signal reconstruction has been explored in the literature of this field. In this work, a database of Ultrasonic Guided Waves (UGW), propagated through a thermoplastic composite plate, and generated and acquired with piezoelectric transducers (PZT), has been preprocessed, organized, and analyzed to reconstruct signals by using Convolutional Autoencoders (cAE) neural networks. This special type of autoencoders (AE) is based on the utilization of convolutional stages, which are formed by deep-learning layers that are especially useful for their utilization on discretized time-series signals, due to their ability to convolve different sections of the signal, thus extracting different features which are automatically learned by the network. The cAE, which have a bottleneck section in their middle part (between the encoder and the decoder sections), have the ability to reduce the dimensionality of the input data, thus allowing the extraction of a minimum number of relevant features of the signals. Summarizing, this paper presents a neural network designed as a cAE which is able to reconstruct data from a reduced number of features, reaching a correlation value between the real and the artificial data higher than 98%.

Anomaly Detection of Sensor Arrays of Underwater Methane Remote Sensing by Explainable Sparse Spatio-Temporal Transformer

The increasing discovery of underwater methane leakage underscores the importance of monitoring methane emissions for environmental protection. Underwater remote sensing of methane leakage is critical and meaningful to protect the environment. The construction of sensor arrays is recognized as the most effective technique to increase the accuracy and sensitivity of underwater remote sensing of methane leakage. With the aim of improving the reliability of underwater methane remote-sensing sensor arrays, in this work, a deep learning method, specifically an explainable sparse spatio-temporal transformer, is proposed for detecting the failures of the underwater methane remote-sensing sensor arrays. The data input into the explainable sparse block could decrease the time complexity and the computational complexity (O (n)). Spatio-temporal features are extracted on various time scales by a spatio-temporal block automatically. In order to implement the data-driven early warning system, the data-driven warning return mechanism contains a warning threshold that is associated with physically disturbing information. Results show that the explainable sparse spatio-temporal transformer improves the performance of the underwater methane remote-sensing sensor array. A balanced F score (F1 score) of the model is put forward, and the anomaly accuracy is 0.92, which is superior to other reconstructed models such as convolutional_autoencoder (CAE) (0.81) and long-short term memory_autoencoder (LSTM-AE) (0.66).

CRE-TSCAE: A Novel Classification Model Based on Stacked Convolutional Autoencoder for Dual-Target RSVP-BCI Tasks.

The Rapid Serial Visual Presentation (RSVP) paradigm facilitates target identification in a rapid picture stream, which is applied extensively in military target surveillance and police monitoring. Most researchers concentrate on the single target RSVP-BCI whereas the study of dual-target is scarcely conducted, limiting RSVP application considerably. This paper proposed a novel classification model named Common Representation Extraction-Targeted Stacked Convolutional Autoencoder (CRE-TSCAE) to detect two targets with one nontarget in RSVP tasks. CRE generated a common representation for each target class to reduce variability from different trials of the same class and distinguish the difference between two targets better. TSCAE aimed to control uncertainty in the training process while requiring less target training data. The model learned a compact and discriminative feature through the training from several learning tasks so as to distinguish each class effectively. It was validated on the World Robot Contest 2021 and 2022 ERP datasets. Experimental results showed that CRE-TSCAE outperformed the state-of-the-art RSVP decoding algorithms and the Average ACC was 71.25%, improving 6.5% at least over the rest. It demonstrated that CRE-TSCAE showed a strong ability to extract discriminative latent features in detecting the differences among two targets with nontarget, which guaranteed increased classification accuracy. CRE-TSCAE provided an innovative and effective classification model for dual-target RSVP-BCI tasks and some insights into the neurophysiological distinction between different targets.

Meta-Path Semantic and Global-Local Representation Learning Enhanced Graph Convolutional Model for Disease-Related miRNA Prediction.

Dysregulation of miRNAs is closely related to the progression of various diseases, so identifying disease-related miRNAs is crucial. Most recently proposed methods are based on graph reasoning, while they did not completely exploit the topological structure composed of the higher-order neighbor nodes and the global and local features of miRNA and disease nodes. We proposed a prediction method, MDAP, to learn semantic features of miRNA and disease nodes based on various meta-paths, as well as node features from the entire heterogeneous network perspective, and node pair attributes. Firstly, for both the miRNA and disease nodes, node category-wise meta-paths were constructed to integrate the similarity and association connection relationships. Each target node has its specific neighbor nodes for each meta-path, and the neighbors of longer meta-paths constitute its higher-order neighbor topological structure. Secondly, we constructed a meta-path specific graph convolutional network module to integrate the features of higher-order neighbors and their topology, and then learned the semantic representations of nodes. Thirdly, for the entire miRNA-disease heterogeneous network, a global-aware graph convolutional autoencoder was built to learn the network-view feature representations of nodes. We also designed semantic-level and representation-level attentions to obtain informative semantic features and node representations. Finally, the strategy based on the parallel convolutional-deconvolutional neural networks were designed to enhance the local feature learning for a pair of miRNA and disease nodes. The experiment results showed that MDAP outperformed other state-of-the-art methods, and the ablation experiments demonstrated the effectiveness of MDAP's major innovations. MDAP's ability in discovering potential disease-related miRNAs was further analyzed by the case studies over three diseases.

A knowledge-data integration framework for rolling element bearing RUL prediction across its life cycle

Prediction of Remaining Useful Life (RUL) for Rolling Element Bearings (REB) has attracted widespread attention from academia and industry. However, there are still several bottlenecks, including the effective utilization of multi-sensor data, the interpretability of prediction models, and the prediction across the entire life cycle, which limit prediction accuracy. In view of that, we propose a knowledge-based explainable life-cycle RUL prediction framework. First, considering the feature fusion of fast-changing signals, the Pearson correlation coefficient matrix and feature transformation objective function are incorporated to an Improved Graph Convolutional Autoencoder. Furthermore, to integrate the multi-source signals, a Cascaded Multi-head Self-attention Autoencoder with Characteristic Guidance is proposed to construct health indicators. Then, the whole life cycle of REB is divided into different stages based on the Continuous Gradient Recognition with Outlier Detection. With the development of Measurement-based Correction Life Formula and Bidirectional Recursive Gated Dual Attention Unit, accurate life-cycle RUL prediction is achieved. Data from self-designed test rig and PHM 2012 Prognostic challenge datasets are analyzed with the proposed framework and five existing prediction models. Compared with the strongest prediction model among the five, the proposed framework demonstrates significant improvements. For the data from self-designed test rig, there is a 1.66 % enhancement in Corrected Cumulative Relative Accuracy (CCRA) and a 49.00 % improvement in Coefficient of Determination (R2). For the PHM 2012 datasets, there is a 4.04 % increase in CCRA and a 120.72 % boost in R2.

Identifying Climate Patterns Using Clustering Autoencoder Techniques

Abstract The complexity of growing spatiotemporal resolution of climate simulations produces a variety of climate patterns under different projection scenarios. This paper proposes a new data-driven climate classification workflow via an unsupervised deep learning technique that can dimensionally reduce the vast volume of spatiotemporal numerical climate projection data into a compact representation. We aim to identify distinct zones that capture multiple climate variables as well as their future changes under different climate change scenarios. Our approach leverages convolutional autoencoders combined with k-means clustering (standard autoencoder) and online clustering based on the Sinkhorn–Knopp algorithm (clustering autoencoder) across the conterminous United States (CONUS) to capture unique climate patterns in a data-driven fashion from the Geophysical Fluid Dynamics Laboratory Earth System Model with GOLD component (GFDL-ESM2G). The developed approach compresses 70 years of GFDL-ESM2G simulation at 0.125° spatial resolution across the CONUS under multiple warming scenarios to a lower-dimensional space by a factor of 660 000 and then tested on 150 years of GFDL-ESM2G simulation data. The results show that five climate clusters capture physically reasonable and spatially stable climatological patterns matched to known climate classes defined by human experts. Results also show that using a clustering autoencoder can reduce the computational time for clustering by up to 9.2 times when compared to using a standard autoencoder. Our five unique climate patterns resulting from the deep learning–based clustering of the lower-dimensional space thereby enable us to provide insights on hydrometeorology and its spatial heterogeneity across the conterminous United States immediately without downloading large climate datasets. Significance Statement This paper presents a data-driven climate classification approach using unsupervised deep learning to dimensionally reduce climate model outputs and to identify distinct climate regions for their future changes. Our approach compresses climate information for 70 years of Geophysical Fluid Dynamics Laboratory Earth System Model data across the conterminous United States (CONUS) at 0.125° spatial resolution. The results reveal that five climate clusters capture reasonable and stable climatological patterns matched to known climate patterns. The embedded clustering process in deep learning provides ×9.2 times faster execution than the k-means clustering technique. These results give us insight about climate spatial patterns and heterogeneity of hydrological patterns across the conterminous United States without downloading large climate datasets.

ScGAAC: A graph attention autoencoder for clustering single-cell RNA-sequencing data

Single-cell RNA-sequencing (scRNA-seq) enables the investigation of intricate mechanisms governing cell heterogeneity and diversity. Clustering analysis remains a pivotal tool in scRNA-seq for discerning cell types. However, persistent challenges arise from noise, high dimensionality, and dropout in single-cell data. Despite the proliferation of scRNA-seq clustering methods, these often focus on extracting representations from individual cell expression data, neglecting potential intercellular relationships. To overcome this limitation, we introduce scGAAC, a novel clustering method based on an attention-based graph convolutional autoencoder. By leveraging structural information between cells through a graph attention autoencoder, scGAAC uncovers latent relationships while extracting representation information from single-cell gene expression patterns. An attention fusion module amalgamates the learned features of the graph attention autoencoder and the autoencoder through attention weights. Ultimately, a self-supervised learning policy guides model optimization. scGAAC, a hypothesis-free framework, performs better on four real scRNA-seq datasets than most state-of-the-art methods. The scGAAC implementation is publicly available on Github at: https://github.com/labiip/scGAAC.

A deep learning method for locating fetal heart rate decelerations during labour using crowd-sourced data

Monitoring the heart rate of a fetus is the only method for continuously monitoring fetal well-being during labour. Decelerations in the fetal heart rate, usually corresponding with contractions, provide information regarding the ability of the fetus to cope with a reduced oxygen supply caused by contractions. For this reason, visual and computer-based assessments of fetal well-being depend upon the correct identification of decelerations. Agreement between clinical professionals when identifying these features is poor. Automated methods offer a more consistent alternative, but must perform at a level comparable to a trained human observer. Collecting data to train these systems can be difficult due to time restraints on experts in fetal medicine. In this study, we designed a website to crowd-source data from clinical professionals at their convenience. This data was combined with that from other publicly available sources to produce a dataset that was used to train a convolutional auto-encoder to locate decelerations. Crowd-sourcing was found to be an effective method for collecting data that was suitable to successfully train a deep learning model to locate decelerations. The model trained using this data provided a comparable level of accuracy to users of the website and other models used for the same purpose.

Identification of Distorted Fingerprints Using Wavelet Method and Convolutional Neural Network (CNN)

Biometrics offers a valuable tool for disaster victim identification, particularly through fingerprints. However, distorted or damaged fingerprints pose a significant challenge for recognition. This study explores the potential of Wavelet and Convolutional Neural Network (CNN) techniques to enhance the accuracy of distorted fingerprint recognition. Wavelet transform addresses the non-stationary nature of images and reduces detected noise. Convolutional Autoencoder, a CNN component, generates simplified feature representations from input images and attempts to reconstruct them. Utilizing 500 fingerprint samples, the testing results demonstrate accuracy variations ranging from 11% to 59.2%. Image reconstruction achieved 7.16% to 12.47% accuracy, while fingerprint matching attained accuracies between 92.71% and 93.96%. Averaging across all damage levels, the overall accuracy reached 37.65%, with average fingerprint reconstruction at 9.31% and average matching accuracy at 93.03%. The successful reconstruction and matching of distorted fingerprints within a certain range of damage using Wavelet and Convolutional Neural Network highlights the promising potential of these techniques for improved fingerprint identification in forensic and security contexts.

Classification of compressed full-waveform airborne lidar data

ABSTRACT Airborne laser scanners produce 3D data that can be used for a range of applications, such as urban planning, facility monitoring, flood mapping, and forest management. Additional information on the surveyed area can be obtained from the backscattered waveforms recorded by modern light detection and ranging (lidar) sensors. However, the high-dimensional representation of full-waveform data has hindered progress in its use due to difficulties in processing and storage. This paper develops a quantized convolutional autoencoder network to compress lidar waveform data into a condensed feature representation, resulting in a compression rate of up to 20:1. This, together with height information, is fed into a U-net convolutional neural network that achieves an accuracy of 93.7% on six classes.