Multiscale Monitoring Research Articles

High Performance Conductive Composites and E-skins with Large-scale Manufacturing for Wearable Electronic Sensor Systems

Objective: High performance wearable sensors for biological and bio-technological recognition of human epidermal movements and muscle tissue deformations are attracting widespread attention and demonstrate fascinating potential for future wearable electronics. Methods: This work demonstrates conductive networks and film cracks-based stretchable strain sensors using carbonic sensing layers / mold star silicone elastomer nanocomposites. Results: The as-fabricated stretchable strain sensors demonstrate captivating superiority, including simplicity in the fabrication steps and ultra-high strain sensitivity far exceeding recently reported state-of-the-art strain sensors. Prominently, the stretchable strain sensors exhibit dazzling piezoresistivity with a high gauge factor of 2,185 and a wide sensing range of 30% strain. The working mechanism depends on the electrical resistance variations, which is strikingly altered by a percolating network crack surface microstructure due to strain concentration during tensile deformations. The ultra-sensitive sensing performance in conjunction with a wide sensing range, prominent linearity (R2>0.99 in the strain range of 15-30%), excellent reversibility characteristics and remarkable durability (more than 1,300 stretch-release cycles under a large-scale strain of 30%) for large-scale tensile deformations. Conclusion: The stretchable strain sensors to be employed as wearable strain monitoring devices for the diverse-range of practical applications, including but not confined to multi-scale monitoring, electronic skins, smart robotics, human-machine / computer interfaces, as well as sports performance monitoring.

Multiscale monitoring and analysis of complex rupture and source mechanisms of mining-related seismicity on fault networks

Mining-related seismicity poses significant challenges in underground coal mining due to its complex rupture mechanisms and associated hazards. To bridge gaps in understanding these intricate processes, this study employed a multi-local seismic monitoring network, integrating both in-mine and local instruments at overlapping length scales. We specifically focused on a damaging local magnitude (ML) 2.6 event and its aftershocks that occurred on 10 September 2022 in the vicinity of the 3308 working face of the Yangcheng coal mine in Shandong Province, China. Moment tensor (MT) inversion revealed a complex cascading rupture mechanism: an initial moment magnitude (Mw) 2.2 normal fault slip along the DF60 fault in an ESE–WNW direction, transitioning to a Mw 3.0 event as the FD24 and DF60 faults unclamped. The scale-independent self-similarity and stress heterogeneity of mining-related seismicity were investigated through source parameter calculations, providing valuable insights into the driving mechanism of these seismic sequences. The in-mine network, constrained by its low dynamic changes, captured only the nucleation phase of the DF60 fault. Furthermore, standard decomposition of the MT solution from the seismic network proved inadequate for accurately identifying the complex nature of the rupture. To enhance safety and risk management in mining environments, we examined the implications of source reactivation within the cluster area post-stress-adjustment. This comprehensive multiscale analysis offers crucial insights into the complex rupture mechanisms and hazards associated with mining-related seismicity. The results underscore the importance of continuous multi-local network monitoring and advanced analytical techniques for improved disaster assessment and risk mitigation in mining operations.

Multi-Scale Dynamics and Spatial Consistency of Economy and Population Based on NPP/VIIRS Nighttime Light Data and Population Imagery: A Case Study of the Yangtze River Delta

Population and economy are crucial factors contributing to regional disparities. Studying the patterns and relationships between these two elements is essential for promoting sustainable development in regions and cities. This study constructs multi-scale geographic concentration indices and inconsistency indices, utilizing NPP/VIIRS and LandScan data to quantitatively analyze the spatial pattern changes of population and economy in the Yangtze River Delta across various spatial scales, revealing the matching relationships between population and economic elements within cities. The results indicate that the economy in the Yangtze River Delta is spreading outward from the core areas, with the average population–nightlight inconsistency index decreasing from 1.57 to 1.33. This suggests that the imbalance between population and economy within the urban agglomeration is gradually improving, consistent with trends observed in statistical survey data. Within individual cities, there is a noticeable spatial mismatch between population and nightlight intensity, with the population primarily concentrated in urban core areas. As urban spaces expand, the areas where population concentration is significantly lower than nightlight concentration are gradually diminishing. By 2022, the land area where population and economic concentration are coordinated within the Yangtze River Delta urban areas increased from 9.13% to 16.24%. Population concentration in these coordinated regions rose from 11.33% to 16.33%, while nightlight concentration increased from 9.98% to 13.63%. The improved geographic concentration and inconsistency indices are effective indicators for multi-scale monitoring of population and economic spatial changes. The integration of NPP/VIIRS nighttime light data and LandScan data provides an effective method for uncovering different spatial patterns of population and socio-economic element aggregation in urban structures. This can offer insights for promoting sustainable regional and urban development.

An Integrated Multisource and Multiscale Monitoring Technique for Assessing the Health Status of High-Speed Railway Subgrade

An Integrated Multisource and Multiscale Monitoring Technique for Assessing the Health Status of High-Speed Railway Subgrade

Monitoring framework development for a network of multiple laboratory structures

The stadium structures have unique structural features increasing the significance of structural monitoring systems specifically designed for them. Aside from vibrations serviceability concerns and human-induced excitations, the development and propagation of structural damage under all possible atmospheric and seismic conditions need to be closely monitored for structural resiliency and integrity of the stadia. As such, Structural Health Monitoring (SHM) methods combined with effective data evaluation methodologies need to be deployed to monitor the structural performance of stadiums. Even though stadia monitoring has been performed at multiple locations in the world, a web based and real-time SHM network of stadia is not known to authors. As a preliminary study for the network implementation of stadia monitoring with acceleration measurements, the presented work focuses on the fundamental steps to accomplish this goal, with a collaborative research effort between Qatar University, the University of Central Florida, and University of Alberta. The authors performed analytical investigations and experimental testing on stadium-type structures built in laboratory environments for the development of the SHM framework. Specialized signal processing algorithms, sensing suites and approaches considering multi-scale monitoring were used on collected acceleration measurements. The novelty of the work presented in this manuscript are the following items which exist simultaneously in the developed SHM framework. The developed framework is a web-based monitoring application where structural damage is detected in real-time. The proposed methodology operates directly on raw acceleration signals and runs at a network level. With that, the damage detection, damage localization, and damage quantification tasks are performed simultaneously, while the feature extraction and classification stages are combined in one learning body.

Fiber optic-based integrated system for in vivo multiscale pharmacokinetic monitoring.

This paper presents the development of a fiber-optic-based fluorescence detection system for multi-scale monitoring of drug distribution in living animals. The integrated system utilized dual laser sources at the wavelengths of 488 nm and 650 nm and three photomultiplier channels for multi-color fluorescence detection. The emission spectra of fluorescent substances were tracked using the time-resolved fluorescence spectroscopy module to continuously monitor their blood kinetics. The fiber bundle, consisting of 30,000 optic filaments, was designed for wide-field mesoscopic imaging of the drug's interactions within organs. The inclusion of a gradient refractive index (GRIN) lens within the setup enabled fluorescence confocal laser scanning microscopy to visualize the drug distribution at the cellular level. The system performance was verified by imaging hepatic and renal tissues in mice using cadmium telluride quantum dots (CdTe QDs) and R3. By acquiring multi-level images and real-time data, our integrated system underscores its potential as a potent tool for drug assessment, specifically within the realms of pharmacokinetic and pharmacodynamic investigations.

Assessing the potential impact of assimilating total surface current velocities in the Met Office’s global ocean forecasting system

Accurate prediction of ocean surface currents is important for marine safety, ship routing, tracking of pollutants and in coupled forecasting. Presently, velocity observations are not routinely assimilated in global ocean forecasting systems, largely due to the sparsity of the observation network. Several satellite missions are now being proposed with the capability to measure Total Surface Current Velocities (TSCV). If successful, these would substantially increase the coverage of ocean current observations and could improve accuracy of ocean current forecasts through data assimilation. In this paper, Observing System Simulation Experiments (OSSEs) are used to assess the impact of assimilating TSCV in the Met Office’s global ocean forecasting system. Synthetic observations are generated from a high-resolution model run for all standard observation types (sea surface temperature, profiles of temperature and salinity, sea level anomaly and sea ice concentration) as well as TSCV observations from a Sea surface KInematics Multiscale monitoring (SKIM) like satellite. The assimilation of SKIM like TSCV observations is tested over an 11 month period. Preliminary experiments assimilating idealised single TSCV observations demonstrate that ageostrophic velocity corrections are not well retained in the model. We propose a method for improving ageostrophic currents through TSCV assimilation by initialising Near Inertial Oscillations with a rotated incremental analysis update (IAU) scheme. The OSSEs show that TSCV assimilation has the potential to significantly improve the prediction of velocities, particularly in the Western Boundary Currents, Antarctic Circumpolar Current and in the near surface equatorial currents. For global surface velocity the analysis root-mean-square-errors (RMSEs) are reduced by 23% and there is a 4-day gain in forecast RMSE. There are some degradations to the subsurface in the tropics, generally in regions with complex vertical salinity structures. However, outside of the tropics, improvements are seen to velocities throughout the water column. Globally there are also improvements to temperature and sea surface height when TSCV are assimilated. The TSCV assimilation largely corrects the geostrophic ocean currents, but results using the rotated IAU method show that the energy at inertial frequencies can be improved with this method. Overall, the experiments demonstrate significant potential benefit of assimilating TSCV observations in a global ocean forecasting system.

Mechanical tough and stretchable quaternized cellulose nanofibrils/MXene conductive hydrogel for flexible strain sensor with multi-scale monitoring

For advanced conductive hydrogels, adaptable mechanical properties and high conductivity are essential requirements for practical application, e.g., soft electronic devices. Here, a straightforward strategy to develop a mechanically robust hydrogel with high conductivity by constructing complicated 3D structures composed of covalently cross-linked polymer network and two nanofillers with distinguishing dimensions is reported. The combination of one-dimensional quaternized cellulose nanofibrils (QACNF) and two-dimensional MXene nanosheets not only provides prominent and tunable mechanical properties modulated by materials composition, but results in electronically conductive path with high conductivity (1281 mS m–1). Owing to the uniform interconnectivity of network structure attributed to the strong macromolecular interaction and nano-reinforced effect, the resultant hydrogel exhibits a balanced mechanical feature, i.e., high tensile strength (449 kPa), remarkable stretchability (> 1700 %), and ultra-high toughness (5.46 MJ m–3), outperforming those of virgin one. Additionally, the enhanced conductive characteristic with the aid of QACNF enables hydrogels with impressive electromechanical behavior, containing high sensitivity (maximum gauge factor: 2.24), wide working range (0–1465 %), and fast response performance (response time: 141 ms, recover time: 140 ms). Benefiting from the excellent mechanical performance, a flexible strain sensor based on such conductive hydrogel can deliver an appealing sensing performance of monitoring multi-scale deformations, from large and monotonous mechanical deformation to tiny and complex physiological motions (e.g., joint movement and signature/vocal recognition). Together, the hydrogel material in this work opens up opportunities in the design and fabrication of advanced gel-based materials for emerging wearable electronics.

Corrigendum: Development of a multi-scale monitoring programme: approaches for the Arctic and lessons learned from the Circumpolar Biodiversity Monitoring Programme 2002-2022

Corrigendum: Development of a multi-scale monitoring programme: approaches for the Arctic and lessons learned from the Circumpolar Biodiversity Monitoring Programme 2002-2022

Assessing the Environmental Performances of Nature-Based Solutions Implementation in Urban Environments through Visible and Near-Infrared Spectroscopy: A Combined Approach of Proximal and Remote Sensing for Monitoring and Evaluation

The implementation of Nature-based Solutions (NbS) in urban environments is gaining momentum as a means to address environmental challenges and promote sustainable development. However, effective monitoring and evaluation are essential to assess the performance of NbS interventions and to guide decision-making. This research paper introduces a combined approach of proximal and remote sensing, based on visible and near-infrared spectroscopy, to monitor and evaluate NbS implementation in urban areas. The study focuses on the case of the UPPER (Urban Productive Parks for Sustainable Urban Regeneration) project and aims to establish urban Productive Parks as a novel NbS approach in the town of Latina (Italy). Field-based proximal sensing techniques (i.e., near-infrared spectroscopy, NIR) and satellite-based remote sensing data from the Sentinel-2 mission are employed. By integrating these techniques, the study enables comprehensive and multi-scale monitoring of vegetation health and assessment of vegetated areas. Various band ratio indices are calculated to assess vegetation coverage, water content, and urbanization. Temporal variations in these indices are analyzed to evaluate the effectiveness of NbS interventions and their impact on the urban environment. The combined approach of proximal and remote sensing demonstrates the potential for comprehensive and multi-scale monitoring of NbS in urban environments. The research findings contribute to the existing knowledge on NbS monitoring and evaluation, providing valuable insights for sustainable urban development and evidence-based decision-making.

Multiscale monitoring of industrial chemical process using wavelet-entropy aided machine learning approach

In recent decades, machine learning (ML) techniques have been effectively applied for industrial process monitoring to assure safety and high-quality yield. Traditional process fault detection, identification, and diagnosis (FDI&D) approaches are insufficiently smart to address the modern complex challenges of real-time industrial chemical processes. The detection and diagnostic resolution of the traditional monitoring approach are less robust, inefficient, and produce the wrong interpretation of actual fault information. These approaches are based on a single-scale fault illustration and cannot effectively address multiple fault depiction roots. This study introduces a novel ML-aided methodological framework for industrial and manufacturing monitoring systems. The proposed ML framework is developed using Principal component analysis (PCA), Shannon information entropy (IE), wavelet transformation (WT), and signed directed graph (SDG). It includes fault detection, identification, and diagnostic propagation root-path interpretation to address the safety challenges of modern, real-time industrial chemical processes. The proposed methodological framework is validated using the Tennessee Eastman process (TEP) benchmark to highlight their performance and efficiency. The results of this study determined that the new proposed approach is more efficient in terms of accuracy, robustness, and actual propagation root cause than traditional techniques. It has a high fault detection rate (FDR), low fault alarm rate (FAR) that identifies and recognizes the actual faulty-correlated variables to establish the SDG model framework for determining the actual diagnostic propagation root path. It initially enables operators to react to unusual incidents, ensuring industrial safety, minimizing economic loss, and avoiding disasters.

Prior knowledge and active learning enable hybrid method for estimating leaf chlorophyll content from multi-scale canopy reflectance

Real-time and accurate assessment of leaf chlorophyll content (Cab) will be significant for monitoring plant physiological status. Development of hybrid methods advances the assessment of Cab with the advantages of both physical mechanism and calculation capability, while the estimation accuracies were constrained by the lacking of prior knowledge and representative real samples. This study explored the use of prior knowledge and active learning to enable the development of efficient hybrid methods for assessing Cab from multi-scale canopy reflectance. The hybrid method was established by using the simulated dataset from the PROSAIL model to train the Gaussian process regression (GPR) model. We used two measured crop datasets and three publicly-available grassland, herbaceous, and tree species datasets collected from near-ground, unmanned aerial vehicle, and airborne platforms to examine the model performances. Prior knowledge for model parameters was obtained from ground measurements, and an active learning method, namely improved Greedy sampling (iGS), was employed to select new representative samples. The results showed that performance of the hybrid method in Cab estimations varied with leaf structure parameter, carotenoid content, anthocyanin content, carbon-based constituents, average leaf angle, leaf area index, and hot-spot size parameter. When prior knowledge for the ranges of model parameters was available, the hybrid method better estimated Cab with the root mean square error (RMSE) reduced by 7.59%–65.96%. Compared with the random selection, iGS was able to select representative samples to update the estimation models with only 10% of the measured samples, and a higher ratio (e.g., 20%) may be needed for small datasets. The hybrid method coupled with prior knowledge and active learning obtained satisfied estimations of Cab across different datasets with the relative RMSE of 12.30%–27.24%. The proposed method will contribute to improving the applicability and robustness of hybrid modeling for multi-scale monitoring of leaf biochemical traits.

Development of a multi-scale monitoring programme: approaches for the Arctic and lessons learned from the Circumpolar Biodiversity Monitoring Programme 2002-2022

The Arctic Council working group, the Conservation of Arctic Flora and Fauna (CAFF) established the Circumpolar Biodiversity Monitoring Programme (CBMP), an international network of scientists, governments, Indigenous organizations, and conservation groups working to harmonize and integrate efforts to extend and develop monitoring and assessment of the Arctic’s biodiversity. Its relevance stretches beyond the Arctic to a broad range of regional and global initiatives and agreements. This paper describes the process and approach taken in the last two decades to develop and implement the CBMP. It documents challenges encountered, lessons learnt, and solutions, and considers how it has been a model for national, regional, and global monitoring programmes; explores how it has impacted Arctic biodiversity monitoring, assessment, and policy and concludes with observations on key issues and next steps. The following are overarching prerequisites identified in the implementation of the CBMP: effective coordination, sufficient and sustained funding, improved standards and protocols, co-production of knowledge and equitable involvement of IK approaches, data management to facilitating regional analysis and comparisons, communication and outreach to raising awareness and engagement in the programme, ensuring resources to engage in international fora to ensuring programme implementation.

Risk Assessment of Single-Gully Debris Flow Based on Dynamic Changes in Provenance in the Wenchuan Earthquake Zone: A Case Study of the Qipan Gully

After the Wenchuan earthquake on 12 May 2008, a huge amount of loose deposits was generated on the mountain surface in the earthquake zone, and vegetation was severely damaged, providing a rich source of material for debris flow, greatly increasing the danger. For many years, researchers have mainly considered the recovery of slope vegetation in assessing the risk of debris flow post-earthquake. However, field investigations have found that large amounts of the dynamic reserve materials in the gully have an important impact on the risk. Thus, based on field survey data, this paper takes the Qipan gully in Wenchuan County as an object and uses multi-source and multi-scale monitoring methods (Landsat series, Quickbird, and Unmanned Air Vehicle) to analyze and statistically study the provenance of the slope and gully both pre- and post- the earthquake. By comprehensively using game theory combination weighting and the cloud model, a dynamic risk assessment model for debris flow was constructed to evaluate the risk of debris flow from 2005 to 2019. The results show that the slope provenance post-earthquake was 7.7 times that of pre-earthquake, and by 2019 the slope provenance had recovered to the pre-earthquake level. Based on the statistical estimation of the amount of debris flow outbreak and the dredging of the blocking dam recorded in relevant data, the dynamic provenance of debris flow had decreased by about 781.3 × 104 m3 by 2019. Compared with considering slope provenance only, the assessment result of debris flow risk considering both slope and gully provenance is more realistic. The results are expected to provide reference and guidance for dynamic assessment of the risk of debris flow faced by increasing projects in high-seismic-intensity mountainous areas and to ensure the safety of people’s lives and property effectively.

The Grande Ronde Model Watershed: Integrating Science into Restoration Implementation and Adaptive Management.

Watershed conservation groups throughout the Pacific Northwest coordinate and implement watershed and habitat restoration to recover Pacific salmon Oncorhynchus spp. Many watershed organizations struggle with implementing an adaptive management process that integrates monitoring data and the latest science into their restoration programs. We describe the evolution and lessons learned from the Grande Ronde Model Watershed (GRMW), one of the longest running watershed organizations coordinating fish habitat restoration projects. Since 1992, the GRMW has initiated nearly 300 habitat restoration projects and their partners more than 600 projects. These projects have evolved from an opportunistic approach, focusing on small-scale riparian fencing and instream structures to a data driven, collaborative processes for identifying, ranking, and implementing large process-based floodplain projects using the latest science. The GRMW recently developed an adaptive management process to assess restoration goals and priorities, and a multi-scale monitoring program that leverages the extensive data collected by partners, and periodic collection of LiDAR to evaluate past, current, and future restoration projects. These recently developed components, which are based on the collective history of the GRMW, provide important lessons for other watershed restoration organizations. These include partnering with local organizations to collect monitoring data; use of a transparent multi-scale process for prioritizing restoration; development of a stepwise process for design and implementation of priority projects; a formal adaptive management process with a designated lead to use the latest science to modify goals, priorities, project selection, and design; and use of remotely sensed data to assist with multi-scale monitoring of project success.

In Situ Experimental Study of Cloud-Precipitation Interference by Low-Frequency Acoustic Waves

Since acoustic agglomeration is an effective pre-treatment technique for removing fine particles, it can be considered as a potential technology for applications in aerosol pollution control, industrial dust and mist removal, and cloud and precipitation interference. In this study, the cloud-precipitation interference effect was evaluated in situ based on a multi-dimensional multi-scale monitoring system. The variations in the spatial and temporal distribution of rainfall near the surface and the characteristics of precipitation droplets in the air were investigated. The results indicate that strong low-frequency acoustic waves had a significant impact on the macro-characteristics of rainfall clouds, the microphysical structure of rain droplets and near-surface precipitation, and various microwave parameters. In terms of physical structure, the precipitation cloud’s base height decreased significantly upon opening the acoustic device, while agglomeration and de-agglomeration of raindrops were in a dynamic equilibrium. When the sound generator was on, the particle concentration at a sampling attitude of 500−1700 m and the proportion of particles with diameters of 1–1.5 mm decreased significantly (by 1–5 ln [1/m3·mm]). In contrast, the particle concentration increased by 1–3 ln [1/m3·mm] at a sampling attitude below 400 m. Moreover, during acoustic interference, the reflectivity factor surged by 2.71 dBZ within 1200 m of the operation centre. Overall, the spatial and temporal distributions of rainfall rates and cumulative precipitation within 5 km of acoustic operation were uneven and influenced by local terrain and background winds.

The future of coastal monitoring through satellite remote sensing

AbstractSatellite remote sensing is transforming coastal science from a “data-poor” field into a “data-rich” field. Sandy beaches are dynamic landscapes that change in response to long-term pressures, short-term pulses, and anthropogenic interventions. Until recently, the rate and breadth of beach change have outpaced our ability to monitor those changes, due to the spatiotemporal limitations of our observational capacity. Over the past several decades, only a handful of beaches worldwide have been regularly monitored with accurate yet expensive in situ surveys. The long-term coastal-change data of these few well-monitored beaches have led to in-depth understanding of many site-specific coastal processes. However, because the best-monitored beaches are not representative of all beaches, much remains unknown about the processes and fate of the other >99% of unmonitored beaches worldwide. The fleet of Earth-observing satellites has enabled multiscale monitoring of beaches, for the very first time, by providing imagery with global coverage and up to daily frequency. The long-standing and ever-expanding archive of satellite imagery will enable coastal scientists to investigate coastal change at sites vulnerable to future sea-level rise, that is, (almost) everywhere. In the past decade, our capability to observe coastal change from space has grown substantially with computing and algorithmic power. Yet, further advances are needed in automating monitoring using machine learning, deep learning, and computer vision to fully leverage this massive treasure trove of data. Extensive monitoring and investigation of the causes and effects of coastal change at the requisite spatiotemporal scales will provide coastal managers with additional, valuable information to evaluate problems and solutions, addressing the potential for widespread beach loss due to accelerated sea-level rise, development, and reduced sediment supply. Monitoring from Earth-observing satellites is currently the only means of providing seamless data with high spatiotemporal resolution at the global scale of the impending impacts of climate change on coastal systems.

Fourier ptychographic microscope allows multi-scale monitoring of cells layout onto micropatterned substrates

Patterned microstructures are commonly used for investigating cells proliferation, guiding cell fate and promoting adhesion and differentiation. Analyzing the behavior of cells layered onto functionalized micropatterned substrates ideally requires large Field of View (FoV), depth of focus, and spatial resolution. Managing the trade-off among these features is pretentious with standard microscopy. Furthermore, patterned substrates have often very complex geometries. Thus, optical systems should be able to get rid of artefacts due to light scattering/diffraction from both the cells’ layer and the underneath structure whose pitches typically have dimensions at the visible wavelength scale. Moreover, the layers are seen as coupled by transmission imaging systems. Decoupling them is pivotal to understand their own properties and related dependences and for interpreting how the structure geometry, point-by-point, addresses the behavior and the functions of the living cells. Here we show the successful use of Fourier Ptychographic Microscopy (FPM) for investigating cell-substrate interaction on micropatterned substrates, solving in full the issue of the layers decoupling. In fact, we demonstrate that it is possible to extract paired but separate clear images of both layers, by computationally decoupling them in FPM reconstruction. In order to test the proposed modality, we chose fibroblast cells in adhesion on a complex substrate consisting of irregular micro-wrinkles on a thin layer of Au. We rely on a numerical multi-look approach, which is capable of restoring quantitative phase-contrast maps of the label-free cells unaffected by artefacts, over a 3.3 mm2 FoV with 0.5 µm resolution. Moreover, from one single FPM map, we demonstrate separate extraction of cells’ morphometry and the underneath wrinkled patterns. Two parameters characterizing the cell-substrate interaction are defined, showing correlation that paves the way to future exploitations of this processing protocol in the fields of mechanobiology and cells and tissue engineering.

Multiscale Monitoring Using Machine Learning Methods: New Methodology and an Industrial Application to a Photovoltaic System

In this study, a multiscale monitoring method for nonlinear processes was developed. We introduced a machine learning tool for fault detection and isolation based on the kernel principal component analysis (PCA) and discrete wavelet transform. The principle of our proposal involved decomposing multivariate data into wavelet coefficients by employing the discrete wavelet transform. Then, the kernel PCA was applied on every matrix of coefficients to detect defects. Only those scales that manifest overruns of the squared prediction errors in control limits were considered in the data reconstruction phase. Thus, the kernel PCA was approached on the reconstructed matrix for detecting defects and isolation. This approach exploits the kernel PCA performance for nonlinear process monitoring in combination with multiscale analysis when processing time-frequency scales. The proposed method was validated on a photovoltaic system related to a complex industrial process. A data matrix was determined from the variables that characterize this process corresponding to motor current, angular speed, convertor output voltage, and power voltage system output. We tested the developed methodology on 1000 observations of photovoltaic variables. A comparison with monitoring methods based on neural PCA was established, proving the efficiency of the developed methodology.

Multiscale imaging of therapeutic anti-PD-L1 antibody localization using molecularly defined imaging agents

BackgroundWhile immune checkpoint inhibitors such as anti-PD-L1 antibodies have revolutionized cancer treatment, only subgroups of patients show durable responses. Insight in the relation between clinical response, PD-L1 expression and intratumoral localization of PD-L1 therapeutics could improve patient stratification. Therefore, we present the modular synthesis of multimodal antibody-based imaging tools for multiscale imaging of PD-L1 to study intratumoral distribution of PD-L1 therapeutics.ResultsTo introduce imaging modalities, a peptide containing a near-infrared dye (sulfo-Cy5), a chelator (DTPA), an azide, and a sortase-recognition motif was synthesized. This peptide and a non-fluorescent intermediate were used for site-specific functionalization of c-terminally sortaggable mouse IgG1 (mIgG1) and Fab anti-PD-L1. To increase the half-life of the Fab fragment, a 20 kDa PEG chain was attached via strain-promoted azide-alkyne cycloaddition (SPAAC). Biodistribution and imaging studies were performed with 111In-labeled constructs in 4T1 tumor-bearing mice. Comparing our site-specific antibody-conjugates with randomly conjugated antibodies, we found that antibody clone, isotype and method of DTPA conjugation did not change tumor uptake. Furthermore, addition of sulfo-Cy5 did not affect the biodistribution. PEGylated Fab fragment displayed a significantly longer half-life compared to unPEGylated Fab and demonstrated the highest overall tumor uptake of all constructs. PD-L1 in tumors was clearly visualized by SPECT/CT, as well as whole body fluorescence imaging. Immunohistochemistry staining of tumor sections demonstrated that PD-L1 co-localized with the fluorescent and autoradiographic signal. Intratumoral localization of the imaging agent could be determined with cellular resolution using fluorescent microscopy.ConclusionsA set of molecularly defined multimodal antibody-based PD-L1 imaging agents were synthesized and validated for multiscale monitoring of PD-L1 expression and localization. Our modular approach for site-specific functionalization could easily be adapted to other targets.Graphical