Continuous Monitoring System Research Articles

PMUT-Based System for Continuous Monitoring of Bolted Joints Preload.

In this paper, we present a bolt preload monitoring system, including the system architecture and algorithms. We show how Finite Element Method (FEM) simulations aided the design and how we processed signals to achieve experimental validation. The preload is measured using a Piezoelectric Micromachined Ultrasonic Transducer (PMUT) in pulse-echo mode, by detecting the Change in Time-of-Flight (CTOF) of the acoustic wave generated by the PMUT, between no-load and load conditions. We performed FEM simulations to analyze the wave propagation inside the bolt and understand the effect of different configurations and parameters, such as transducer bandwidth, transducer position (head/tip), presence or absence of threads, as well as the frequency of the acoustic waves. In order to couple the PMUT to the bolt, a novel assembly process involving the deposition of an elastomeric acoustic impedance matching layer was developed. We achieved, for the first time with PMUTs, an experimental measure of bolt preload from the CTOF, with a good signal-to-noise ratio. Due to its low cost and small size, this system has great potential for use in the field for continuous monitoring throughout the operative life of the bolt.

Technical note: An open-source, low-cost system for continuous monitoring of low nitrate concentrations in soil and open water

Abstract. Nitrate (NO3-), mainly leaching with soil porewater, is the primary nonpoint source pollutant of groundwater worldwide. Obtaining real-time information on nitrate levels in soils would allow for gaining a better understanding of the sources and transport dynamics of nitrate through the unsaturated zone. However, conventional nitrate detection techniques (e.g., soil sample analysis) necessitate costly, laboratory-grade equipment for analysis, along with human resources, resulting in a laborious and time-intensive procedure. These drawbacks raise the need to develop cost-effective and automated systems for in situ nitrate measurements in field conditions. This study presents the development of a low-cost, portable, automated system for field measurements of nitrate in soil porewater and open water bodies. The system is based on the spectrophotometric determination of nitrate using a single reagent. The system design and processing software are openly accessible, including a building guide, to allow duplicating or changing the system according to user-specific needs. Three field tests, conducted over 5 weeks, validated the system's measurement capabilities within the range of 0–10 ppm NO3-–N with a low RMSE of <0.2 ppm NO3-–N when comparing the results to standard laboratory nitrate analysis. Data derived from such a system allow for tracking of the temporal variation in soil nitrate, thus opening new possibilities for diverse soil and nutrient management studies.

Proficient Calibration Methodologies for Fixed Photogrammetric Monitoring Systems

This work focuses on investigating the accuracy of 3D reconstructions from fixed stereo-photogrammetric monitoring systems through different camera calibration procedures. New reliable and effective calibration methodologies that require minimal effort and resources are presented. A full-format camera equipped with fixed 50 and 85 mm focal length optics is considered, but the methodologies are general and can be applied to other systems. Four different calibration strategies are considered: (i) full-field calibration (FF); (ii) multi-image on-the-job calibration (MI); (iii) point cloud-based calibration (PC); and (iv) self (on-the-job) calibration (SC). To evaluate the calibration strategies and assess their actual performance and practicality, two test sites are used. The full-field calibration, while very reliable, demands significant effort if it needs to be repeated. The multi-image strategy emerges as a favourable compromise, offering good results with minimal effort for its realisation. The point cloud-based method stands out as the optimal choice, balancing ease of implementation with quality results; however, it requires a reference 3D point cloud model. On-the-job calibration with monitoring images is the simplest but least reliable option, prone to uncertainty and potential inaccuracies, and should hence be avoided. Ultimately, prioritising result reliability over absolute accuracy is paramount in continuous monitoring systems.

The method for calculating phase angle between exciter force of vibration exciter and roller displacement

Introduction. In the process of soil compaction it is important to have information about the current density of the layer, as it enables to quickly adjust the load on the compacted material. The field methods of compaction quality assessment do not cope with this task, as they make point estimation within the pavement area. Therefore, continuous compaction monitoring systems installed on vibratory road rollers are becoming increasingly common. The systems developed by BOMAG and AMMANN require, among other things, the phase angle between the exciter force and the roller movement to calculate the compaction quality index. The phase angle is determined by the unbalance position sensor, which is very labor-intensive. In addition, continuous compaction monitoring systems include an accelerometer. The purpose of this paper is to develop an indirect method for calculating the phase angle from accelerometer readings.The method of research. In order to achieve the purpose of the work, a roller-soil single-mass model in a typical mode for vibratory rollers (periodic loss of contact) has been studied. As a result of modeling it has been found that the reaction of the compacted material has the main influence on the vertical component of a roller acceleration and practically does not affect the horizontal component. This is confirmed by the experimental data.Results. The phase angle can be determined by mutual correlation of the horizontal and vertical acceleration signals of the roller obtained with the accelerometer.Conclusion. The study proposes a new method of calculating the phase angle between the exciter force and the roller displacement, which eliminates the direct measurement of this angle. The calculation of the angle is based on the readings of a two-axis accelerometer installed on the road roller. The proposed method enables to simplify the system of continuous compaction control and reduce the labor intensity of phase angle measurement.

Alarm Management in Intensive Care: Qualitative Triangulation Study.

The high number of unnecessary alarms in intensive care settings leads to alarm fatigue among staff and threatens patient safety. To develop and implement effective and sustainable solutions for alarm management in intensive care units (ICUs), an understanding of staff interactions with the patient monitoring system and alarm management practices is essential. This study investigated the interaction of nurses and physicians with the patient monitoring system, their perceptions of alarm management, and smart alarm management solutions. This explorative qualitative study with an ethnographic, multimethods approach was conducted in an ICU of a German university hospital. Using triangulation in data collection, 102 hours of field observations, 12 semistructured interviews with ICU staff members, and the results of a participatory task were analyzed. The data analysis followed an inductive, grounded theory approach. Nurses and physicians reported interacting with the continuous vital sign monitoring system for most of their work time and tasks. There were no established standards for alarm management; instead, nurses and physicians stated that alarms were addressed through ad hoc reactions, a practice they viewed as problematic. Staff members' perceptions of intelligent alarm management varied, but they highlighted the importance of understandable and traceable suggestions to increase trust and cognitive ease. Staff members' interactions with the omnipresent patient monitoring system and its alarms are essential parts of ICU workflows and clinical decision-making. Alarm management standards and workflows have been shown to be deficient. Our observations, as well as staff feedback, suggest that changes are warranted. Solutions for alarm management should be designed and implemented with users, workflows, and real-world data at the core.

A national surveillance system for continuous monitoring of blood transfusion safety: German haemovigilance data.

Haemovigilance (HV) systems aim to improve transfusion outcomes in patients and donor safety. An important question for blood regulators is how to ensure an effective HV system. We retrospectively analysed the HV reports submitted to Paul-Ehrlich-Institut over the last two decades. Between 2011 and 2020, 50.86 million units of blood components were used, and 8931 suspected serious donor and recipient adverse reactions (SARs), 874 serious adverse events (SAEs) and 12,073 donor look-backs were reported. Following implementation of specific risk-minimization measures (RMMs) between 2000 and 2010, SAR reporting rates decreased for transfusion-transmitted viral infections (TTVIs), transfusion-related acute lung injury (TRALI) and transfusion-transmitted bacterial infections (TTBIs), while increasing for other serious adverse transfusion reactions. Within this decade, the overall blood component use decreased. Long-term data collection forms the basis to establish trends and changes in reporting and to evaluate the effect of RMM. Standardized criteria for reaction types, seriousness and imputability assessments and availability of a denominator are important elements. Central data collection and independent assessment allow for monitoring HV data in a nationwide context over time. Stakeholder involvement and transparent feedback on the benefit of RMM will help to achieve the objectives of HV.

Efficiency, Research, and Healthcare Economics: (Vital Threat Detection System) A Systematic Review

Monitoring vital signs and detecting diseases like diabetes and cancer at an early stage are incredibly important for safeguarding patients' lives and ensuring a healthy environment. In this study, we present a comprehensive systematic review focusing on vital monitoring systems in diverse fields. We reviewed 85 articles spanning from 2019 to 2024. From the selected articles, our aim is to explore the frameworks and algorithms of vital signs monitoring, the latest techniques used in remote vital signs monitoring such as radar and smart watch, as well as the measurement of vital signs for heart rate and respiratory diseases. Also, we discuss the threats that may affect healthcare systems and how to secure against these threats. The findings emphasize the critical importance of acquiring continuous vital monitoring systems, which have immense potential for improving healthcare. These systems are crucial for early diagnosis and prediction of conditions that may negatively impact the patient's health. Additionally, it could be beneficial for doctors and healthcare staff by saving time and costs.

Designing a low-cost wireless sensor network for particulate matter monitoring: Implementation, calibration, and field-test

Poor air quality can provoke severe impacts on health, necessitating environmental monitoring of atmospheric particulate matter (PM) to assess potential threats to human well-being. However, traditional continuous air quality monitoring systems are often costly and time-consuming in data treatment. Lately, there is a growing trend towards the use of low-cost wireless PM sensors, providing more detailed information than standard systems. This paper presents a system designed to measure air quality, specifically, a wireless sensor network composed of a distributed sensor network linked to a cloud system. The proposed system can efficiently measure air quality as it is cost-effective, small-sized, and consumes little power. Sensor nodes based on low-power long range (LoRa) motes transmit field measurement data to the cloud via a gateway, and a cloud computing system is implemented to store, monitor, process, and visualise the data. Advanced techniques were included in our cloud for data processing and analysis to optimise the detection of PM. Laboratory and field tests in the historic Riotinto mine validate the system's viability, offering real-time air quality information for nearby populations. Once calibrated, sensors demonstrate high accuracy, presenting mean error of −0.3% and low deviation (R2 = 0.96) when compared to regulatory systems for both low (<10 μgPM10/m3) and hazardous concentrations (300 μgPM10/m3), which makes them perfect as early warning systems for atmospheric pollution in mining.

Detection of Electromagnetic Seismic Precursors from Swarm Data by Enhanced Martingale Analytics.

The detection of seismic activity precursors as part of an alarm system will provide opportunities for minimization of the social and economic impact caused by earthquakes. It has long been envisaged, and a growing body of empirical evidence suggests that the Earth's electromagnetic field could contain precursors to seismic events. The ability to capture and monitor electromagnetic field activity has increased in the past years as more sensors and methodologies emerge. Missions such as Swarm have enabled researchers to access near-continuous observations of electromagnetic activity at second intervals, allowing for more detailed studies on weather and earthquakes. In this paper, we present an approach designed to detect anomalies in electromagnetic field data from Swarm satellites. This works towards developing a continuous and effective monitoring system of seismic activities based on SWARM measurements. We develop an enhanced form of a probabilistic model based on the Martingale theories that allow for testing the null hypothesis to indicate abnormal changes in electromagnetic field activity. We evaluate this enhanced approach in two experiments. Firstly, we perform a quantitative comparison on well-understood and popular benchmark datasets alongside the conventional approach. We find that the enhanced version produces more accurate anomaly detection overall. Secondly, we use three case studies of seismic activity (namely, earthquakes in Mexico, Greece, and Croatia) to assess our approach and the results show that our method can detect anomalous phenomena in the electromagnetic data.

Working Smart versus Working Hard: Wireless UT Sensors for Asset Integrity Monitoring

In the 21st century of NDE technology and deployment, monitoring technologies and strategies are completely different than inspection technologies and strategies. Monitoring is no longer sending a technician to a location to take repeated manual data – this is still inspection, just more frequently. Monitoring takes place after a manual/automated inspection has located an anomaly and instrumentation (a sensor in this case), is installed to take recurring readings at that precise location to gather a large sample size of data to be analyzed. These two strategies, when employed in concert, even only on the most critical (10%) circuits/tanks/units, are optimizing asset health, reducing unplanned downtime, and eliminating the need to have people in potentially unsafe situations to the tune of tens of millions of dollars per year. This article will provide real life examples of the ~20% of the best run refineries, chemical, paper, and power plants which have cracked the code and are successfully using an inspect to monitor strategy to change the game of how they implement asset integrity in the 21st century. As you read this article, ask yourself the question, is my facility a part of this ~20%? If not, what can I start doing, and what incremental step changes can I make to my legacy inspection &amp; asset integrity strategy, to use technology to spend my precious budget and resources to be a part of this ~20% in 2024 and beyond? Many asset owners struggle to identify the root cause of fluctuating corrosion rates due to unreliable, infrequent, or sheer lacks of quantity (and quality) of inspection data to make informed decisions on asset health. Facilities worldwide are tasked with monitoring thousands of Condition Monitoring Locations (CMLs) with established NDE techniques such as manual ultrasonic testing and radiography. While these techniques can provide valuable “snapshots” of the condition of particular locations, limitations and inherent errors can compound leading to ill-advised decision making. Manually taken thickness data can vary greatly and result in unwarranted complacency or excessive and costly inspections. Utilizing long range wireless continuous monitoring systems have drastically improved operators understanding of how process changes influence corrosion rates. Installed UT sensors provide near real-time data with a 0.001” accuracy. This influx of data provides a trend line whereas with manually taken data, sometimes only taken a few times a year, only provides a few points scattered across a graph. Asset owners have realized they can use this wealth of new information to validate and discover the effects of operational changes on corrosion rates and make more informed decisions to impact asset extension, retirement, and increasing the efficiency of assets during its useful life.

Vital signs Measurement: A Critical Review of Methods and Quality Improvement Strategies

Accurate measurement of vital signs is crucial for effective patient care and clinical decision-making. This critical review aims to evaluate current methods of vital signs measurement and identify strategies for quality improvement. Traditional methods, such as manual blood pressure cuffs and mercury thermometers, are compared with modern technological advancements, including digital thermometers, automated blood pressure monitors, and wearable devices. The review highlights challenges associated with measurement accuracy, including human factors, technological limitations, and environmental influences. Quality improvement strategies are discussed, emphasizing the importance of training and education, standardization of protocols, technological innovations, and continuous monitoring and feedback systems. Case studies of successful implementations demonstrate the benefits of adopting best practices and advanced technologies. The review concludes with a discussion on the implications for clinical practice and future research directions, underscoring the need for ongoing efforts to enhance the accuracy and reliability of vital signs measurement. Ensuring high-quality vital signs measurement is essential for improving patient outcomes and optimizing healthcare delivery.

Circadian Rhythms Fluctuate the Treatment Effects of Intravesical Treatments on Rat Urinary Frequency Models.

It is still not clear how the intravesical instillation of drugs affects rat urinary frequency. This study aimed to examine the dynamics of intravesical treatments' treatment effect on rat urinary frequency models by real-time and extended monitoring using a novel continuous urination monitoring system. Nine eleven-week-old female Wistar rats were divided into three groups to receive intravesical instillation of 0.1% acetic acid (AA), 1.0% AA, or phosphate-buffered saline (PBS). Thirty minutes later, these drugs were voided, and rats were moved to a continuous urination monitoring system, UM-100. UM-100 monitored rat urination quantitatively and continuously for 24 hours. Rats were then euthanized, and histopathologic examinations using a damage score validated the severity of bladder inflammation. We used nine additional rats to determine the treatment effect of various drugs against the urinary frequency. These rats were also treated with 1.0% AA in the same way and divided into three groups (n = 3 each) to receive intravesical instillation of lidocaine, silver nitrate (AgNO3), or dimethyl sulfoxide (DMSO), respectively. Thirty minutes later, rats were catheterized again and moved to the UM-100, and their voiding was monitored for 24 hours. Intravesical instillation of AA increased the urinary frequency and decreased the mean voided volume (VV) in a concentration-dependent manner, with statistical significance at a concentration of 1.0% (urinary frequency; p=0.0007, mean VV; p=0.0032, respectively) compared with PBS. Histopathological analysis of these models demonstrated a significantly higher damage score of bladder mucosa in both 0.1% AA and 1.0% AA compared with PBS, with the severity in concordance with the clinical severity of urinary frequency (0.1% AA: p < 0.0001, 1.0% AA: p < 0.0001). Moreover, intravesical instillation of lidocaine, AgNO3, and DMSO decreased the urinary frequency. Continuous monitoring with UM-100 also demonstrated that the treatment effect of these intravesically instilled drugs occurred only at night. The extended monitoring of rat urination by UM-100 revealed a significant fluctuation in the treatment effect of intravesically instilled drugs between day and night. These findings may help establish novel therapies for urinary frequency.

Coagulase-negative Staphylococci – A True Pathogen in Bloodstream Infections and their Resistance Patterns in a Tertiary Care Hospital

Coagulase-negative staphylococci (CoNS) are primary skin commensals that have long been considered contaminants even when grown in blood cultures. This group of organisms has been recently recognized as a potential causative pathogen of septicemia. This increase has been attributed to the increased use of intravascular and prosthetic devices. Hence, we aimed to estimate the prevalence of CoNS as a true pathogen in adult and pediatric blood cultures along with their antibiotic susceptibility patterns. A total of 1076 adult and 611 pediatric blood cultures were subjected to an automated BacT/ALERT continuous monitoring system. Isolated CoNS were considered true pathogens if they met the diagnostic, clinical, and laboratory criteria. Antimicrobial susceptibility testing for pathogenic CoNS was carried out using the Kirby-Bauer disk diffusion method and interpreted as per CLSI 2021. CoNS were considered true pathogens in 23 (42.5%) of 54 adults and 12 (41.3%) of 29 pediatric CoNS isolated from blood cultures. Methicillin-resistant CoNS was detected in 66% and 70% of adult and pediatric cultures, respectively. All the CoNS isolates were sensitive to vancomycin and linezolid. Coagulase-negative staphylococci (CoNS) can either be a contaminant or a true pathogen, whose discrimination based on clinical and laboratory indices plays a pivotal role in the management of patients with sepsis.

Instant Detection of Cerebral Blood Flow Changes in Infants with Congenital Heart Disease during Transcatheter Interventions.

Background: Transcatheter interventions are increasingly used in children with congenital heart disease. However, these interventions can affect cardiac output and cerebral circulation. In this pilot study, we aimed to investigate the use of NeoDoppler, a continuous transfontanellar cerebral Doppler monitoring system, to evaluate the impact of transcatheter interventions on cerebral circulation. Methods: Nineteen participants under one year of age (mean age 3.5 months) undergoing transcatheter cardiac interventions were prospectively included. Transfontanellar cerebral Doppler monitoring with the NeoDoppler system was initiated after intubation and continued until the end of the procedure. Results: Instant detection of changes in cerebral blood flow were observed across a spectrum of transcatheter interventions. Balloon aortic valvuloplasty demonstrated temporary cessation of cerebral blood flow during balloon inflation. Increase in cerebral diastolic blood flow velocity and decreased pulsatility were observed during patent ductus arteriosus occlusion. Changes in cerebral blood flow patterns were detected in two patients who encountered complications during their transcatheter interventions. There was no significant change in Doppler parameters before and after the interventions for the entire patient group. High quality recordings were achieved in 87.3% of the monitoring period. Conclusions: Continuous transfontanellar cerebral Doppler is feasible in monitoring cerebral hemodynamic trends and shows instantaneous changes associated with interventions and complications. It could become a useful monitoring tool during transcatheter interventions in infants.

The importance of reinforcing advanced ceramics in space projects

This article addresses the role of advanced ceramics in space exploration, highlighting their importance in tackling the unique challenges of the extraterrestrial environment. Starting with an analysis of the Space Shuttle Columbia disaster in 2003, lessons learned and safety measures implemented in the aftermath of the incident are discussed. The properties of advanced ceramics, including resistance to extreme temperatures, chemical stability, and thermal insulation capability, are explored, along with their applicability in space missions, such as radiation protection, resistance to debris, and propulsion. Strategies for maximizing the resilience of ceramics in space environments are examined, including advanced manufacturing techniques and continuous monitoring systems. Finally, specific applications of ceramics in space components, such as rocket nozzles, propulsion systems, and heat-to-electricity conversion, are discussed, emphasizing the ongoing need for innovation to ensure the success of future space missions.

Source contribution of black carbon aerosol during 2020–2022 at an urban site in Indo-Gangetic Plain

The extensive emissions of black carbon (BC) from the Indo-Gangetic Plain (IGP) region of India have been well recognized. Particularly, biomass emissions from month-specific crop-residue burning (April, May, October, November) and heating activities (December–February) are considered substantial contributors to BC emissions in the IGP. However, their precise contribution to ambient BC aerosol has not been quantified yet and remains an issue of debate. Therefore, this study aims to fill this gap by quantifying the contribution of these month-specific biomass emissions to ambient BC at an urban site in IGP. This study presents the analysis of BC mass concentrations (MBC) measured for 3 years (2020−2022) in Delhi using an optical photometer i.e., continuous soot monitoring system (COSMOS). A statistical analysis of monthly mean MBC and factors affecting the MBC (ventilation coefficients, air mass back trajectories, fire counts) is performed to derive month-wise contribution due to background concentration, conventional emission, regional transport, crop-residue burning, and heating activities. The yearly mean MBC (5.3 ± 4.7, 5.6 ± 5.0, and 5.3 ± 3.5 μg m−3 during 2020, 2021, and 2022, respectively) remained relatively consistent with repetitive monthly patterns in each year. The peak concentrations were observed from November to January and low concentrations from June to September. Anthropogenic activities contributed significantly to MBC over Delhi with background concentration contributing only 30 % of observed MBC. The percentage contribution of emissions from crop-residue burning varied from 15 % (May) to 37 % (November), while the contribution from heating activities ranged from 25 % (December) to 39 % (January). This source quantification study highlights the significant impact of month-specific biomass emissions in the IGP and can play a vital role in better management and control of these emissions in the region.

Mitochonic Acid 5 Improves Mitochondrial Respiration Following Alcohol-Induced Mitochondrial Dysfunction

Chronic alcohol exposure can lead to the development of Alcohol Induced Cardiomyopathy (ACM). The pathological changes in ACM have been suggested to be largely caused by mitochondrial damage, reduction of ATP, oxidative stress, and apoptosis of the cardiomyocytes. Cardiomyocytes, as cells with high energy demand, rely greatly on mitochondrial homeostasis and ATP production. Thus, therapeutic intervention to specifically target the mitochondria and ATP production can potentially alleviate ACM. Mitochonic acid 5 (MA-5) has been recently identified as a potential therapeutic compound that increases cellular ATP and improves mitochondrial function in several cardiac disorders. Given the potential role of MA-5 in improving mitochondrial function, I speculate that MA-5 could be an effective treatment for alcohol-induced cardiotoxicity. In the present study, I test the hypothesis that MA-5 can mitigate mitochondrial energetics in cultured cardiomyocytes exposed to alcohol. To investigate this, neonatal mouse cardiomyocytes (NMCMs) were isolated from mice at day 1-2 of age and cultured for 6 days with alcohol (50mM). The cells were treated with MA-5 (1μM, 5μM, or 10μM) for 4 hours with serum starvation and then cellular energetic changes were measured using the Mito Stress assay with the Seahorse Bioanalyzer (XF96pro, Agilent). To investigate the impacts of chronic alcohol exposure, rat embryonic myoblasts, H9C2 cells, were treated with 50mM alcohol for 3 weeks. Subsequently, cells were treated with MA-5 (1μM, 5μM, or 10μM) for 24 hours and then attached to the Resipher system (Lucid Lab) for continuous oxygen consumption monitoring and recording. NMCMs treated with 50mM alcohol showed a substantial reduction in basal respiration, maximal respiration, and spare respiratory capacity compared to controls. NMCMs treated with 10μM MA-5 showed a significant improvement in these parameters. Chronically exposed H9C2 cells showed a prolonged decline in OCR. MA-5 treatment improved and maintained oxygen consumption in these cells. In summary, these results demonstrated that alcohol exposed cardiomyocytes experience a decline in cellular energetics that could be corrected by MA-5 treatment. Future in vivo studies on preclinical ACM animal models are warranted to yield further insights into a potential novel therapy for ACM in patients. This research was supported by grant #T32AA007577 from the NIAAA at the National Institutes of Health. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

추진 축거동 상시 모니터링 시스템 구축에 관한 연구

추진 축거동 상시 모니터링 시스템 구축에 관한 연구

Data-Driven Modeling for the Prediction of Stack Gas Concentration in a Coal-Fired Power Plant in Türkiye

In this research, deep learning and machine learning methods were employed to forecast the levels of stack gas concentrations in a coal-fired power plant situated in Türkiye. Real-time data collected from continuous emission monitoring systems (CEMS) serves as the basis for the predictions. The dataset includes measurements of carbon monoxide (CO), sulfur dioxide (SO2), nitrogen oxides (NOx), oxygen (O2), and dust levels, along with temperatures recorded. For this analysis, deep learning methods such as multi-layer perceptron network (MLP) and long short-term memory (LSTM) models were used, while machine learning techniques included light gradient boosted machine (LightGBM) and stochastic gradient descent (SGD) models were applied. The accuracy of the models was determined by analysing their performance using mean absolute error (MAE), root means square error (RMSE), and R-squared values. Based on the results, LightGBM achieved the highest R-squared (0.85) for O2 predictions, highlighting its variance-capturing ability. LSTM excelled in NOx (R-squared 0.87) and SO2 (R-squared 0.85) prediction, while showing the top R-squared (0.67) for CO. Both LSTM and LGBM achieved R-squared values of 0.78 for dust levels, indicating strong variance explanation. Conclusively, our findings highlight LSTM as the most effective approach for stack gas concentration forecasting, closely followed by the good performance of LightGBM. The importance of these results lies in their potential to effectively manage emissions in coal-fired power plants, thereby improving both environmental and operational aspects.Graphical

Monitoring Forest Dynamics and Conducting Restoration Assessment Using Multi-Source Earth Observation Data in Northern Andes, Colombia

Examining the efficacy of current assessment methodologies for forest conservation and restoration initiatives to align with global and national agendas to combat deforestation and facilitate restoration efforts is necessary to identify efficient and robust approaches. The objective of this study is to understand forest dynamics (1996–2021) and assess restoration implementations at the Urra’s supplying basin hydroelectric reservoir in Colombia. The processing approach integrates optical and radar Earth Observation (EO) data from Sentinel-2 and Landsat for forest mapping and multi-temporal forest change assessment (1996–2021), and a Sentinel-1 backscatter time-series analysis is conducted to assess the state of forest restoration implementations. The processing chain was scaled in a cloud-based environment using the Nebari and SEPPO software and the Python language. The results demonstrate an overall substantial decrease in forested areas in the 1996–2000 period (37,763 ha). An accuracy assessment of multi-temporal forest change maps showed a high precision in detecting deforestation events, while improvements are necessary for accurately representing non-forested areas. The forest restoration assessment suggests that the majority of the 270 evaluated plots are in the intermediate growth state (82.96%) compared to the reference data. This study underscores the need for robust and continuous monitoring systems that integrate ground truth data with EO techniques for enhanced accuracy and effectiveness in forest restoration and conservation endeavors.