Sensor Observations Research Articles

Spatial correction of low‐cost sensors observations for fusion of air quality measurements

AbstractThe context for this article is the statistical fusion of several pollutant measurement networks: a reference one of fixed sensors of high quality and others of fixed or mobile micro‐sensors of heterogeneous quality. The challenge is to use together the measurements of such different networks to obtain a better air quality map. Since pollution maps are often obtained from the correction of numerical model outputs by the measurements provided by the monitoring stations of air quality networks, the quality of the reconstructed map may be improved by increasing the density of sensors by adding low‐cost micro‐sensors. A geostatistical approach is very often used for the fusion of measurements. But the first step is to correct micro‐sensors measures using those given by the reference sensors. Usually, this preprocessing is performed during an offline preliminary study for which reference and micro‐sensor are located at the same position, which does not allow to adapt quickly to changes and to cope with time‐related nonstationarities. We propose in this article to complement these approaches by a simple online spatial correction of micro‐sensors. The principle is to use the reference measurements to correct the network of micro‐sensors. More precisely, by kriging only the measurements from micro‐sensors, the reference measurements are estimated; allowing to calculate a correction by kriging the differences, finally applied to the micro‐sensors. Then one can iterate this fundamental sequence of steps. Numerical experiments exploring the proposed algorithm by simulation and an application to a real‐world dataset are provided.

Monitoring Mountain Weather Variabilities Based on Decadal Observations of the Present Weather Sensor in the Highland of Central Japan

山岳域の天候変動を特徴付ける雲・霧・強雨や降雪の発現に関する統計的傾向を明らかにした研究例は日本では少ない。本研究では，長野県菅平高原（標高1,320 m）に設置された現在天気計（バイサラ社）で2010年11月から2020年10月にかけ取得したデータを使用し，視程により区分される霧と靄，降水形態，降雨強度の季節変化・日変化の特徴を明らかにした。靄は霧に比べて高頻度で出現し，両者とも夜間に頻度が増加した。霧は春季・秋季に，靄は夏季に頻度が増加した。これに比べて，長野地方気象台（標高418 m）では，靄は寒候期・早朝に増加傾向が見られた。降雪とみぞれは日中に発生頻度が低下した。みぞれの発生はまれで，12月と3月に南岸低気圧・二つ玉低気圧通過時に出現しやすかった。非常にまれであるが，過冷却水滴が集中して観測される期間が存在した。強い降雨の頻度は7-9月，夕方に増加する傾向があり，中程度もしくは弱い降雨の頻度は6月や10月といった梅雨・台風の卓越する時期に増加した。降雪は強度に明瞭な季節・日変化の違いは見られなかったが，強い強度の割合は南岸低気圧や二つ玉低気圧の通過時に増加した。従来の目視による低頻度の観測に代わり，今回示された高時間分解で長期データに基づく特性は，衛星観測や数値実験の検証データとしても有用となると考えられる。

Three-dimensional wind field reconstruction using tucker decomposition with optimal sensor placement

Short-term wind prediction is of great significance for wind power trading strategy, equipment protection, and effective control. Physical models can provide accurate and detailed wind speed data but require a large amount of time for calculation. To solve this problem, based on Tucker decomposition, a sensor and CFD (Computational Fluid Dynamics) data fusion technique is proposed, which allows us to readily obtain an estimation of the ‘actual’ three-dimensional wind field from sensor observations. Moreover, a new greedy algorithm based on minimum condition is developed to stabilize the inverse process and derive optimal sensor placement. In the simulation, the ‘actual’ wind field can be reconstructed with reasonable accuracy for different wind shear characteristics, and the relative errors of absolute velocity is less than 0.2%. Additionally, the reconstruction time is much less than ultra-short-term forecasting and accounting for only 0.2%–3.2% of the CFD calculation time. The experimental results show that the optimal placement is much more effective than random placement in terms of minimizing the relative error (the relative error can be controlled within 6%). In general, the innovative approach combines the advantages of both statistical and physical approaches while compensating for their shortcomings, making it potentially valuable in short-term wind forecasting.

Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection

The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone annotation process or sensor observation noise. Current public object detection datasets only provide deterministic object labels without considering their inherent uncertainty, as does the common training process or evaluation metrics for object detectors. As a result, an in-depth evaluation among different object detection methods remains challenging, and the training process of object detectors is sub-optimal, especially in probabilistic object detection. In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model, and define a new representation of the probabilistic bounding box through a spatial uncertainty distribution. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. Furthermore, we propose Jaccard IoU (JIoU) as a new evaluation metric that extends IoU by incorporating label uncertainty. We conduct an in-depth comparison among several LiDAR-based object detectors using the JIoU metric. Finally, we incorporate the proposed label uncertainty in a loss function to train a probabilistic object detector and to improve its detection accuracy. We verify our proposed methods on two public datasets (KITTI, Waymo), as well as on simulation data. Code is released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/</uri> ZiningWang/Inferring-Spatial-Uncertainty-in-Object-Detection.

Research on motion distortion optimization algorithm of laser SLAM

Aiming at the problems of inaccurate laser point cloud matching, large reference pose error and insufficient utilization of sensor observation data during 2D laser SLAM positioning and mapping, which lead to the motion distortion of lidar, a piecewise linear interpolation based method is proposed. Fusion of radar motion distortion optimization strategy and PL-ICP algorithm. The optimization algorithm first uses the piecewise linear interpolation method to fuse the data of the wheel odometer and the lidar, solve the robot pose corresponding to each laser point in the current frame of laser data, then convert all the laser points to the same coordinate system according to the solved pose, and finally the laser data scan matching is performed by the PL-ICP algorithm. In the experiment, the ICP and PL-ICP algorithms were compared for the radar data, and the SLAM algorithm equipped with the motion distortion optimization module was used for localization and mapping. The experimental results show that the motion distortion optimization algorithm effectively removes the motion distortion of low-precision lidar and improves the accuracy of mobile robot positioning and mapping.

An Adaptive Filtering Method for Cooperative Localization in Leader-Follower AUVs.

In the complex and variable marine environment, the navigation and localization of autonomous underwater vehicles (AUVs) are very important and challenging. When the conventional Kalman filter (KF) is applied to the cooperative localization of leader–follower AUVs, the outliers in the sensor observations will have a substantial adverse effect on the localization accuracy of the AUVs. Meanwhile, inaccurate noise covariance matrices may result in significant estimation errors. In this paper, we proposed an improved Sage–Husa adaptive extended Kalman filter (improved SHAEKF) for the cooperative localization of multi-AUVs. Firstly, the measurement anomalies were evaluated by calculating the Chi-square test statistics based on the innovation. The detection threshold was determined according to the confidence level of the Chi-square test, and the Chi-square test statistics exceeding the threshold were regarded as measurement abnormalities. When measurement anomalies occurred, the Sage–Husa adaptive extended Kalman filter algorithm was improved by suboptimal maximum a posterior estimation using weighted exponential fading memory, and the measurement noise covariance matrix was adjusted online. The numerical simulation of leader–follower multi-AUV cooperative localization verified the effectiveness of the improved SHAEKF and demonstrated that the average root mean square and the average standard deviation of the localization errors based on the improved SHAEKF were significantly reduced in the case of the presence of measurement abnormalities.

Selection Optimal Method of Evaporation Duct Model Based on Sensitivity Analysis

Abstract The evaporation duct is an abnormal refractive phenomenon with wide distribution and frequency occurrence at the boundary between the atmosphere and the ocean, which directly affects electromagnetic wave propagation. In recent years, the use of meteorological and hydrological data to predict the evaporation duct height has become an emerging and promising approach. There are some evaporation duct models that have been proposed based on the Monin–Obukhov similarity theory. However, each model adopts different stability functions and roughness length parameterization methods, so the prediction accuracies are different under different environmental conditions. To improve the prediction accuracy of the evaporation duct under different environmental conditions, a model selection optimization method (MSOM) of the evaporation duct model is proposed based on sensitivity analysis. According to the sensitivity of each model to input parameters analyzed by the sensor observation accuracy, curve graph, and Sobol sensitivity, the model input parameters are divided into several intervals. Then the optimization model is selected in different intervals. The model was established using numerical simulation data from local areas in the South China Sea, and its accuracy was verified by the observational data from the offshore observation platform located in the South China Sea. The results show that the MSOM can effectively improve the prediction accuracy of the evaporation duct height. Under unstable conditions, the maximum relative error is reduced by 7.1%, and under stable conditions, the relative error is reduced by 10.7%. Significance Statement The evaporation duct height has a significant effect on marine radar or wireless apparatus applications. To obtain the evaporation duct height, there are some evaporation duct models that have been proposed. However, different evaporation duct models are applicable to different meteorological and hydrological environments. A single model cannot achieve accurate evaporation duct height predictions in all environments. We propose a model selection optimization method of the evaporation duct model based on sensitivity analysis. This method can dynamically select the optimal model according to different meteorological and hydrological environment, and improve the prediction accuracy of the evaporation duct height. Under unstable conditions, the maximum relative error is reduced by 7.1%, and under stable conditions, the relative error is reduced by 10.7%.

Dynamic Displacement using DInSAR of Sentinel-1 in Sunda Strait

Sunda Strait’s geographical condition makes it experience many tectonic and seismic events. Deformation monitoring has been carried out with various methods ranging from terrestrial and non-terrestrial surveys. This study aimed to monitor the dynamics of deformation in the Sunda Strait region in 2019 using Differential Interferometric Synthetic Aperture Radar (DInSAR). DInSAR principle analyzes the paired SAR images that have been co-registered with different acquisition times to detect changes along the sensor observation line to the target or Line of Sight (LOS). The SAR data used are Sentinel-1 acquisition on June 1, and October 23, 2019. The results show that the coherence value of the image pair is low due to differences in the phase and intensity values. The maximum uplift value is 0.54 m located in the West Lampung Regency, and the subsidence is −0.3 m in the Pesisir Barat Regency. Uplift results are located in various geological conditions and do not affect by seismic phenomena, whereas subsidence shows its location in the potential area of land subsidence. The dynamics of uplift and subsidence in the Lampung regency are mostly affected by the geological and land use conditions of the locations.&#x0D; HIGHLIGHTS&#x0D; &#x0D; DInSAR provides deformation measurements with a high level of data precision over a large area&#x0D; The selection of image pairs is essential for analyzing ground deformation using DInSAR&#x0D; Lampung Province has experienced uplift and subsidence in several locations&#x0D; The dynamic of uplift and subsidence in the Lampung Province is mostly affected by the conditions of the geological and land-cover condition&#x0D; &#x0D; GRAPHICAL ABSTRACT

Multiple model AUV navigation methodology with adaptivity and robustness

Autonomous Underwater Vehicle (AUV) navigation and localization in the complex and changeable marine environment is crucial and challenging. The inaccurate noise covariance matrix may result in significant prediction errors or even filtering divergence for traditional navigation algorithms. Meanwhile, the outliers in sensor observations also have a substantial adverse effect on the AUV positioning accuracy. Therefore, in this paper, we propose an Improved Interacting Multiple Model-Unscented Kalman Filter (IIMM-UKF) with both adaptivity and robustness for AUV navigation. Firstly, the Variational Bayesian (VB) based UKF algorithm is proposed as adaptive sub-models of IIMM to estimate the time-varying measurement noise covariance adaptively. Secondly, an outliers detector sub-model is proposed to enhance the robustness of IIMM. Gaussian Process Regression (GPR) is used to regress state pseudo values for each sub-model as estimations of the filtering process when the outliers are detected by the residual χ2 detector. Multiple models work in parallel to achieve high-precision and robust AUV navigation. The performance of the IIMM-UKF algorithm has been evaluated on AUV with simulation and actual experimental data. In sea trials, the average AUV navigation accuracy of the IIMM-UKF is improved by 61.02% compared to EKF, 43.44% compared to UKF, and 35.54% compared to the IMM-UKF.

A Framework of Generating Land Surface Reflectance of China Early Landsat MSS Images by Visibility Data and Its Evaluation

The Landsat time-series dataset is one of the most widely used datasets for land surface research due to its long time-series and Land Surface Reflectance (LSR) product. Though the United States Geological Survey (USGS) provides Landsat LSR products for later Landsat 4–5 Thematic Mapper (TM), Landsat 7 Enhanced Thematic Mapper Plus (ETM+), and Landsat 8 Operational Land Imager (OLI), no early Landsat 1–5 Multispectral Scanner System (MSS) LSR product is generated currently, limiting the research traced back to the 1970s. Atmospheric correction is one of the necessary preprocesses for generating LSR products. However, it is challenging for MSS images, not only because the image quality is lower and bands are different compared with the current sensors, but also because of the multiple effects of other preprocesses, such as radiometric calibration. Based on the Second Simulation of a Satellite Signal in the Solar Spectrum Vector (6SV) model, we propose a novel framework for generating Landsat 1–5 MSS LSR data of China. Ground-based visibility records are introduced to replace the images-based aerosol optical depth (AOD) to effectively generate MSS LSR data of the 1970s. We evaluate the generated MSS LSR data by the cross-validation of the simultaneous observation of MSS and TM sensors in Landsat 4 and Landsat 5 using Landsat Ecosystem Disturbance Adaptive Processing System (LEDAPS) surface reflectance product as the truth value. The evaluation result shows that the generated MSS LSR data is comparable with the later Landsat TM LSR product, with slightly larger uncertainties. In addition, it shows that the non-atmospheric factors (e.g., the difference of relative spectral responses of TM and MSS, the georegistration errors, the radiometric calibration uncertainty, and image noises) bring larger uncertainties than the atmospheric factors (e.g., the AOD retrieval method by visibility) to the cross-validation results. We apply the MSS LSR data generated by the proposed framework on time series analysis in the regions of interest (ROIs) of the spectral-stable land cover in China for all the MSS sensors. The application demonstrates the potential and promise of the MSS LSR data generated by the proposed framework.

Autonomous Cave Surveying With an Aerial Robot

This paper presents a method for cave surveying in total darkness using an autonomous aerial vehicle equipped with a depth camera for mapping, downward-facing camera for state estimation, and forward and downward lights. Traditional methods of cave surveying are labor-intensive and dangerous due to the risk of hypothermia when collecting data over extended periods of time in cold and damp environments, the risk of injury when operating in darkness in rocky or muddy environments, and the potential structural instability of the subterranean environment. Although these dangers can be mitigated by deploying robots to map dangerous passages and voids, real-time feedback is often needed to operate robots safely and efficiently. Few state-of-the-art, high-resolution perceptual modeling techniques attempt to reduce their high bandwidth requirements to work well with low bandwidth communication channels. To bridge this gap in the state of the art, this work compactly represents sensor observations as Gaussian mixture models and maintains a local occupancy grid map for a motion planner that greedily maximizes an information-theoretic objective function. The approach accommodates both limited field of view depth cameras and larger field of view LiDAR sensors and is extensively evaluated in long duration simulations on an embedded PC. An aerial system is leveraged to demonstrate the repeatability of the approach in a flight arena as well as the effects of communication dropouts. Finally, the system is deployed in Laurel Caverns, a commercially owned and operated cave in southwestern Pennsylvania, USA, and a wild cave in West Virginia, USA.

Unsteady flow prediction from sparse measurements by compressed sensing reduced order modeling

Prediction of complex fluid flows from sparse and noisy sensor measurements is widely applied to many engineering fields. In the present study, a novel compressed sensing reduced-order modeling framework has been proposed to predict unsteady flow fields from sparse and noisy sensor observations, which includes offline learning and online forecasting. In the offline learning stage, the Long Short Term Memory (LSTM) model is used for modeling the dynamic evolution of the sensor signals. Moreover, the sparsity-promoting Dynamic Mode Decomposition (DMD) algorithm is applied to extract spatio-temporal coherent structures from high-dimensional fluid dynamic system and choose optimal DMD modes for flow reconstruction. In order to establish the correlation between sensor space and feature-based coherent structures space, the Deep Neural Network (DNN) is employed. In the online forecasting stage, the trained framework is applied to predict the flow fields from limited sensor measurements in the actual experiment setup. In the current work, the proposed framework is applied in two numerical examples, including the flow past a circle cylinder at Re=100 characterized by laminar flow and at Re=3900 characterized by turbulent flow. It is shown that the proposed framework performs accurately and robustly in both prediction of sensor measurements and unsteady flow fields. Especially, the important physical features and quantities can be well maintained for both laminar and turbulent flow, even if high level noise is involved. Therefore, the proposed framework is a promising tool for sparse representation from complex flow fields in realistic experiments.

Speech Localization at Low Bitrates in Wireless Acoustics Sensor Networks

The use of speech source localization (SSL) and its applications offer great possibilities for the design of speaker local positioning systems with wireless acoustic sensor networks (WASNs). Recent works have shown that data-driven front-ends can outperform traditional algorithms for SSL when trained to work in specific domains, depending on factors like reverberation and noise levels. However, such localization models consider localization directly from raw sensor observations, without consideration for transmission losses in WASNs. In contrast, when sensors reside in separate real-life devices, we need to quantize, encode and transmit sensor data, decreasing the performance of localization, especially when the transmission bitrate is low. In this work, we investigate the effect of low bitrate transmission on a Direction of Arrival (DoA) estimator. We analyze a deep neural network (DNN) based framework performance as a function of the audio encoding bitrate for compressed signals by employing recent communication codecs including PyAWNeS, Opus, EVS, and Lyra. Experimental results show that training the DNN on input encoded with the PyAWNeS codec at 16.4 kB/s can improve the accuracy significantly, and up to 50% of accuracy degradation at a low bitrate for almost all codecs can be recovered. Our results further show that for the best accuracy of the trained model when one of the two channels can be encoded with a bitrate higher than 32 kB/s, it is optimal to have the raw data for the second channel. However, for a lower bitrate, it is preferable to similarly encode the two channels. More importantly, for practical applications, a more generalized model trained with a randomly selected codec for each channel, shows a large accuracy gain when at least one of the two channels is encoded with PyAWNeS.

Improving obstacle boundary representations in predictive occupancy mapping

Predictive, inference-based occupancy mapping has been used successfully in many instances to create accurate and descriptive maps from sparse data, defining occupied space in a manner suitable to support autonomous navigation. However, one key drawback of inferring occupancy based largely on the proximity of range sensor observations is inaccuracy at the boundary between occupied and free space, where sparse coverage by the sensor data can be misinterpreted. To obtain a more accurate representation of the boundary between free and occupied space, we propose several modifications to a recently published occupancy mapping algorithm that uses Bayesian generalized kernel inference. In particular, our proposed algorithm distinguishes between unknown map cells with insufficient observations, and those which are uncertain due to disagreement among numerous observations, in a predictive, inference-based occupancy map. This distinction is key to our improved ability to capture ambiguities arising at the boundary between free and occupied space. We validate our approach using synthetic range data from a simulated environment and demonstrate real-time mapping performance using range data acquired by a ground robot operating in an underground mine.

Solar Flare Irradiance: Observations and Physical Modeling

Abstract We examine Solar Dynamics Observatory (SDO)/EUV Variability Experiment (EVE) data to better understand solar flare irradiance, and how that irradiance may vary for large events. We measure scaling laws relating Geostationary Orbital Environmental Satellites (GOES) flare classes to irradiance in 21 lines measured with SDO/EVE, formed across a wide range of temperatures, and find that this scaling depends on the line-formation temperature. We extrapolate these irradiance values to large events, exceeding X10. In order to create full spectra, however, we need a physical model of the irradiance. We present the first results of a new physical model of solar flare irradiance, NRLFLARE, that sums together a series of flare loops to calculate the spectral irradiance ranging from the X-rays through the far-UV (≈0 to 1250 Å), constrained only by GOES/X-ray Sensors observations. We test this model against SDO/EVE data. The model spectra and time evolution compares well in high-temperature emission, but cooler lines show large discrepancies. We speculate that the discrepancies are likely due to both a nonuniform cross-section of the flaring loops as well as opacity effects. We then show that allowing the cross-sectional area to vary with height significantly improves agreement with observations, and is therefore a crucial parameter needed to accurately model the intensity of spectral lines, particularly in the transition region from 4.7 ≲ log T ≲ 6 .

Map completion from partial observation using the global structure of multiple environmental maps

Using the spatial structure of various indoor environments as prior knowledge, the robot would construct the map more efficiently. Autonomous mobile robots generally apply simultaneous localization and mapping (SLAM) methods to understand the reachable area in newly visited environments. However, conventional mapping approaches are limited by only considering sensor observation and control signals to estimate the current environment map. This paper proposes a novel SLAM method, map completion network-based SLAM (MCN-SLAM), based on a probabilistic generative model incorporating deep neural networks for map completion. These map completion networks are primarily trained in the framework of generative adversarial networks (GANs) to extract the global structure of large amounts of existing map data. We show in experiments that the proposed method can estimate the environment map 1.3 times better than the previous SLAM methods in the situation of partial observation.

Big Data Analytics and Visualization in Traffic Monitoring

This paper presents a system that employs information visualization techniques to analyze urban traffic data and the impact of traffic emissions on urban air quality. Effective visualizations allow citizens and public authorities to identify trends, detect congested road sections at specific times, and perform monitoring and maintenance of traffic sensors. Since road transport is a major source of air pollution, also the impact of traffic on air quality has emerged as a new issue that traffic visualizations should address. Trafair Traffic Dashboard exploits traffic sensor data and traffic flow simulations to create an interactive layout focused on investigating the evolution of traffic in the urban area over time and space. The dashboard is the last step of a complex data framework that starts from the ingestion of traffic sensor observations, anomaly detection, traffic modeling, and also air quality impact analysis. We present the results of applying our proposed framework on two cities (Modena, in Italy, and Santiago de Compostela, in Spain) demonstrating the potential of the dashboard in identifying trends, seasonal events, abnormal behaviors, and understanding how urban vehicle fleet affects air quality. We believe that the framework provides a powerful environment that may guide the public decision-makers through effective analysis of traffic trends devoted to reducing traffic issues and mitigating the polluting effect of transportation.

Design of False Data Injection Attack on Distributed Process Estimation

Herein, design of false data injection attack on a distributed cyber-physical system is considered. A stochastic process with linear dynamics and Gaussian noise is measured by multiple agent nodes, each equipped with multiple sensors. The agent nodes form a multi-hop network among themselves. Each agent node computes an estimate of the process by using its sensor observation and messages obtained from neighboring nodes, via Kalman-consensus filtering. An external attacker, capable of arbitrarily manipulating the sensor observations of some or all agent nodes, injects errors into those sensor observations. The goal of the attacker is to steer the estimates at the agent nodes as close as possible to a pre-specified value, while respecting a constraint on the attack detection probability. To this end, a constrained optimization problem is formulated to find the optimal parameter values of a certain class of linear attacks. The parameters of linear attack are learnt on-line via a combination of stochastic approximation based update of a Lagrange multiplier, and an optimization technique involving either the Karush-Kuhn-Tucker (KKT) conditions or online stochastic gradient descent. The problem turns out to be convex for some special cases. Desired convergence of the proposed algorithms are proved by exploiting the convexity and properties of stochastic approximation algorithms. Finally, numerical results demonstrate the efficacy of the attack.

A hybrid cooperative navigation method for UAV swarm based on factor graph and Kalman filter

Navigation plays an important role in the task execution of the micro-unmanned aerial vehicle (UAV) swarm. The Cooperative Navigation (CN) method that fuses the observation of onboard sensors and relative information between UAVs is a research hotspot. Aiming at the efficiency and accuracy problems of previous studies, this article proposes a hybrid-CN method for UAV swarm based on Factor Graph and Kalman filter. A global Factor Graph is used to combine Global Navigation Satellite System (GNSS) and ranging information to provide position estimations for modifying the distributed Kalman filter; distributed Kalman filter is established on each UAV to fuse inertial information and optimized position estimation to modify the navigation states. In order to provide time-consistent GNSS position information for the Factor Graph, a time synchronization filter is designed. The proposed method is tested and verified using standard Monte Carlo simulations, simulation results show that it can provide a more precise and efficient CN solution than traditional CN methods.

A case study in smart manufacturing: predictive analysis of cure cycle results for a composite component

Aim: This work proposes a workflow monitoring sensor observations over time to identify and predict relevant changes or anomalies in the cure cycle (CC) industrial process. CC is a procedure developed in an autoclave consisting of applying high temperatures to provide composite materials. Knowing anomalies in advance could improve efficiency and avoid product discard due to poor quality, benefiting sustainability and the environment. Methods: The proposed workflow exploits machine learning techniques for monitoring and early validating the CC process according to the time-temperature constraints in a real industrial case study. It uses CC's data produced by the thermocouples in the autoclave along the cycle to train an LSTM model. Fast Low-cost Online Semantic Segmentation algorithm is used for better characterizing the time series of temperature. The final objective is predicting future temperatures minute by minute to forecast if the cure will satisfy the constraints of quality control or raise the alerts for eventually recovering the process. Results: Experimentation, conducted on 142 time series (of 550 measurements, on average), shows that the framework identifies invalid CCs with significant precision and recall values after the first 2 hours of the process. Conclusion: By acting as an early-alerting system for the quality control office, the proposal aims to reduce defect rates and resource usage, bringing positive environmental impacts. Moreover, the framework could be adapted to other manufacturing targets by adopting specific datasets and tuning thresholds.