Search

Terrestrial water storage (TWS) is crucial for the worldwide hydrologic water cycle and sustainability of water. Gravimetric missions such as the Gravity Recovery and Climate Experiments (GRACE) & GRACE-Follow on (GRACE-FO) are essential for evaluating changes in TWS.This study introduces a new approach by combining remote sensing data in the form of mascon data with deep learning models (DL) such as the Long Short-Term Memory (LSTM) Model to reconstruct GRACE data in the Nile River basin (NRB) from 2002 to 2022 to study the changes in water storage with high accuracy. This research strategy depends on applying several convolutional neural network (CNN) models, including AlexNet, VGG Net, and GoogleNet, for extracting features from time series GRACE data. After that, use the optimization algorithm (DTOFGW) to get the best hyperparameters for LSTM. Finally, comparing many different optimization algorithms showed the proposed model’s superiority. Applying statistical analysis tests illustrated the significance of our proposed model, such as ANOVA and T-test. The results of the trial showed that the proposed model (DTOFGW-LSTM) outperformed the other models by an accuracy of 96.8%, sensitivity of 0.5, specificity of 99.5%, P value of 0.85, N value of 0.97, F-score of 0.63, and confidence value of 97%.

Vehicle-to-everything (V2X) communication is essential in 5G and upcoming networks as it enables seamless interaction between vehicles and infrastructure, ensuring the reliable transmission of critical and time-sensitive data. Challenges like unstable communication in highly mobile vehicular networks, limited channel state information, high transmission overhead, and significant communication costs hinder vehicle-to-vehicle (V2V) communication. To tackle these issues, a unified approach utilizing distributed deep reinforcement learning is proposed to enhance the overall network performance while meeting the quality of service (QoS), latency, and rate requirements. Recognizing the complexity of this NP-hard, non-convex problem, a machine learning framework based on the Markov decision process (MDP) is adopted for a robust strategy. This framework facilitates the formulation of a reward function and the selection of optimal actions with certainty. Furthermore, a spectrum-based allocation framework employing multi-agent deep reinforcement learning (MADRL) is confidently introduced. The deep deterministic policy gradient (DDPG) within this framework enables the exchange of historical data globally during the primary learning phase, effectively removing the need for signal interaction and manual intervention in optimizing system efficiency. The data transmission policy follows an augmented online policy scheme, known as the proximal online policy scheme (POPS), which confidently reduces the computational complexity during the learning process. The complexity is marginally adjusted using the clipping substitute technique with assurance in the learning phase. Simulation results validate that the proposed method outperforms existing decentralized systems in achieving a higher average data transmission rate and ensuring quality of service (QoS) satisfaction confidently.

In addressing sediment accumulation challenges in the water diversion canal and enhancing both water utilization and ecological conditions, this study introduces a fish mouth engineering design, akin to the sediment reduction strategies used at the Dujiangyan water conservancy hub. A specialized two-dimensional hydrodynamic and sediment transport model was developed, specifically tailored to the Qixing Canal section in Ningxia. Utilizing SMS software, an unstructured grid division of the study area was executed. The research employed simulations under two distinct scenarios: direct water diversion and fish mouth engineering at the canal head. These simulations were pivotal in analyzing the variations in sedimentation thickness and sediment concentration across different flow rates and irrigation cycles. It was observed that the use of the fish mouth engineering for water diversion significantly improved the sedimentation thickness, underscores the efficacy of the fish mouth model in altering the structural characteristics of water flow and achieving a redistribution of water flow and sediment within the canal. This approach to fish mouth diversion and sediment reduction substantially curtails sediment accumulation in the irrigation canal, presenting a viable strategy for canal head design in the self-flow irrigation areas of the Yellow River. This research result provides certain reference value for water conservancy engineering organizations.

This study examines the modified Sardar sub-equation method (MSSEM) for deriving the novel solutions of the (3+1)-dimensional p-type model. This framework is commonly employed to explain the behavior of optical solitons in nonlinear media. The applications of MSSEM allows us to acquire the precise analytical solutions, which incorporate a diverse array of optical soliton solutions. We discuss the dynamical structure of the solitons, bifurcation and chaos theory to develop the multiple soliton solutions, including rational, hyperbolic, exponential, and trigonometric functions and depending on the principle of balancing equation. Moreover, by using bifurcation and chaos theory, we examine the governing model with and without the perturbation term and provide the three-dimensional, two-dimensional, and density profiles to improve the clarity of obtained results. The different aspects of the solutions are evident in our visual representations. These solutions are applicable to a wide range of domains, including fluid physics, oceanography, physics, engineering, and nonlinear optics.

In this paper, we present a novel approach based on Bayesian Expectation Maximization-Maximization (BEMM) to address this challenge. Unlike traditional optimization methods, which may struggle with high-dimensional and nonlinear optimization problems, BEMM offers a robust framework that combines the benefits of Bayesian inference with the flexibility of expectation maximization and maximization techniques. By iteratively updating parameter estimates based on observed data and maximizing the likelihood of the model, BEMM effectively navigates the solution space to converge on accurate estimates of the unspecified variables in Proton Exchange Membrane Fuel Cells (PEMFCs)models. Through extensive experimentation and comparison with other metaheuristic techniques, including Arithmetic Optimization Algorithm (AOA), Gravitational Search Algorithm (GSA), Flower Pollination Algorithm (FPA), and Biogeography-Based Optimization (BBO), we demonstrate the superior performance of our BEMM approach. Our results show that BEMM outperforms these alternative methods in terms of precision, convergence speed, and stability across various scenarios involving different numbers of unspecified variables. The implications of our findings are significant for both researchers and practitioners in the field of PEMFC modeling and optimization. By providing a more efficient and reliable method for estimating model parameters, our approach can facilitate more accurate predictions of PEMFC performance, leading to better-informed decision-making in the design, operation, and optimization of PEMFC systems. Furthermore, the robustness and versatility of BEMM make it well-suited for a wide range of optimization problems beyond PEMFC modeling, highlighting its potential impact across various domains of engineering and scientific research. In the sensitivity analysis, as the population size increases from 10 to 40, there is a significant improvement in solution quality by approximately 100 %. However, beyond a population size of 40, the marginal gains diminish, with only marginal improvements of less than 1 % observed despite further increases in population size up to 200.

So far in the literature, numerous probabilistic models and families of probabilistic models have been suggested and put into practice. A large portion of these probabilistic models are developed and updated by introducing new parameters ranging up to five. There are only a few methods that are introduced without adding additional parameters. This paper also contributed to the development of a probabilistic model without adding additional parameters. The proposed model is introduced by incorporating the weighted distributional strategy and the weighted Ramos–Louzada distribution. Therefore, the generalized weighted Ramos–Louzada distribution is a suitable name for the newly proposed model. The derivation of the estimators based on the maximum likelihood for this novel model is presented. Certain distributional properties of the generalized weighted Ramos–Louzada distribution are derived. In order to validate the effectiveness and superiority of the generalized weighted Ramos–Louzada distribution, three applications are chosen as examples. The first two applications are considered from the physical sciences, while, the third application is taken from the musical area. We consider four statistical tests to show the validatity of the proposed model over some well-known established models. The findings from the statistical tests consistently indicate that the proposed model performs better than its rivals.

Cybersecurity is crucial for protecting the privacy of digital systems, maintaining economic stability, and ensuring national security. This study presents a comprehensive approach to cybersecurity knowledge discovery through topic modelling, using a multi-perspective analysis of academic and industry sources. The datasets include 15,751 articles from the Web of Science (WoS) database and 5,831 articles from Security Magazine, spanning from 2011 to 2023. We employed BERTopic for topic modelling, UMAP for dimensionality reduction, and HDBSCAN clustering algorithm for grouping and analysing distinct article clusters to uncover latent topics, enhancing the understanding of the evolving cybersecurity landscape. This study found 12 micro-clusters and three macro-clusters, namely technology, smart city and education, from the WoS database and 12 more micro-clusters and four macro-clusters, including organization, public security, governance, and education, from magazines. This study reveals key cybersecurity research and practice trends, such as the increasing focus on malware, ransomware, and cyber-attack mitigation. Additionally, temporal analysis indicates a significant rise in cybersecurity interest around 2020, followed by a diversification of topics. The results highlight the importance of integrating diverse data sources to capture a holistic view of cybersecurity developments. Future work will aim to refine the clustering algorithms to further improve topic extraction and analysis and expand the datasets to include more diverse sources and perspectives. This approach helps discover current cybersecurity trends and provides a foundation for more targeted and effective cybersecurity strategies.

There are currently many clinical issues plaguing digestive oncologists, including the impact of dietary habits on the occurrence of early gastrointestinal cancer, the association between irritable bowel syndrome, ulcerative colitis, and early gastrointestinal cancer, the expected changes in gastrointestinal cancer after IBS, IBD, and susceptibility gene mutations, and the mechanisms by which susceptibility gene mutations in gastrointestinal cancer lead to different diseases. Meanwhile, as a carcinogen, betel nut is also prone to cancer and emotional disorders, and there are also many doctor-patient conflicts in the current clinical treatment of digestive tract tumors. To address the aforementioned issues, the research team analyzed dietary habits data using SOM clustering algorithm and isolated forest algorithm. Based on bioinformatics, new therapies have been developed for the pathogenesis and immune pathways of various cancers in the digestive system. Using network pharmacology methods, explore the toxicological mechanism of betel nut and its mechanism in mediating emotional disorders. Molecular docking is used to elucidate drug prediction. Based on four AI algorithms, the occurrence of gastrointestinal cancer was predicted through dietary habits. Using computer vision technology to address the deficiencies in early clinical reporting of cancer. This article provides clinical doctors with new treatment tools.

In daily fitness activities, posture recognition and motion capture are extremely important. This study aims to explore skeleton-based action recognition technology and compare the effects of using only skeleton information and fused image features. We introduce an improved spatiotemporal pyramid graph convolutional network, which enhances the performance of the model by introducing edge importance scores and multi-level feature representation when dealing with specific action recognition tasks. The proposed model is tested on the UW-IOM and TUM kitchen datasets to verify its applicability in real-world scenarios, the mAP of UW-IOM reached 85.89, achieving the best result and proving the effectiveness of the model. Through experiments, we confirm that in certain cases, the accuracy of skeleton information is the key to improving action recognition performance, while in scenarios where image information is not rich or skeleton information is inaccurate, the fusion of image features can provide performance supplements. In addition, we demonstrate the advantages of our method by comparing with existing methods.

The Lomax distribution is widely recognized in distributional theory and thoroughly applied in many study fields, particularly in engineering and lifetime studies. Considering the importance of fitting the lifetime datasets, this article deals a weighted exponentiated Lomax model using a novel modification on Lomax distribution. The proposed modification is powerful tool in modeling numerous types of data sets notably skewed, complex, asymmetric and symmetric. Various distributional characterizations are provided. Additionally, the estimation of the model parameter is obtained via two numerous estimation techniques. Monte Carlo simulation based research is conducted to demonstrate the potential of proposed estimator’s using some measures, including the average estimate, average bias, and associated mean square error. Two real datasets drawn from lifetime area are illustrated to show the applicability of the suggested distribution. The results underscore the superior performance of the proposed model compared to its competitors, showcasing its effectiveness in accurately representing the analyzed datasets.

This paper proposes an Adaptive Grey Wolf Optimizer based on Transfer function Inertia Weight of Second-order High-pass Filter (SAGWO), aiming to overcome the limitations of Grey Wolf Optimizer (GWO) in terms of convergence speed and solution accuracy. SAGWO enhances the algorithm's dynamic adaptability and greatly speeds up convergence by incorporating the transfer function of the second-order high-pass filter into the modifications of inertia and leader wolves' weight. Furthermore, SAGWO incorporates an adaptive random search component, which significantly enhances the search range and the ability to explore globally. The performance of SAGWO is assessed and compared against three prominent Swarm Intelligence Algorithms (ALO, WOA, and EHO), along with GWO and GWO optimized by PSO. This evaluation is conducted through trials on the CEC2017 standard test set. The experimental results indicate that SAGWO outperforms in terms of both convergence speed and solution correctness. Moreover, SAGWO is utilized to address practical engineering problems such as pressure vessel design and robot gripper design, showcasing its remarkable effectiveness once more. This research enhances the theoretical development of Swarm Intelligence Algorithms and demonstrates the significant utility of SAGWO in practical applications, establishing it as a powerful instrument for scientific investigation and engineering optimization.

With the integration of dance art and computer technology, automatic dance score generation has become a new research direction in computer vision and machine learning, but generating the corresponding Laban symbols by capturing the skeletal key points of dance movements is a challenging task. In this study, we propose an automatic dance score generation model that utilizes local spatio-temporal features to address the inefficiency and creativity limitations of traditional choreography methods. Specifically, we propose the Multiscale Spatio-Temporal Convolution (MSConv) module to capture local spatio-temporal features in human skeletal motion sequences. In addition, the Compressed Pyramid Attention (CPA) mechanism is used to achieve effective fusion of global and local features. This mechanism facilitates the interaction between global and local spatio-temporal information and automatically generates dance sequences by analyzing motion data from dance videos to extract key features. We validate the proposed method on Laban 16 and Laban 48 dance score datasets, and the generated Laban sequences preserve the original style of the dance sequences with a combined accuracy of 94.2% and 93.7%, respectively.

Accurate and timely flow prediction is the most significant element for intelligent traffic management systems. However, developing a robust and potential prediction method is a challenge because of the nonlinear characteristics and inherent randomness of the traffic flow in smart cities. Deep learning can analyze historical traffic data and predict future traffic patterns in traffic flow prediction. This can be done by training deep neural networks on large datasets, such as traffic speed and volume data, to learn the underlying relationships between various factors influencing traffic flow. The resulting models can then be used to predict future traffic conditions, helping optimize traffic management, reduce congestion, and improve safety. This study introduces a Hunter Prey Optimization with Hybrid Deep Learning-Driven Traffic Flow in smart cities Prediction (HPOHDL-TFPM). The HPOHDL-TFPM approach's primary goal is to accurately and rapidly forecast traffic flow. The HPOHDL-TFPM technique uses Z-score normalization to normalize the traffic data to achieve this. In addition, the CBLSTM-AE model, which combines convolutional bidirectional long short-term memory and autoencoder, is utilized in the prediction of traffic flow in smart cities. Moreover, the HPO technique is applied as a hyperparameter optimizer to select the hyperparameter values properly. The experimental validation of the HPOHDL-TFPM approach is tested in several contexts. Numerous comparative studies demonstrated the improved performance of the HPOHDL-TFPM approach over other existing methods.

Smart actuators have shown great potential for a range of industries, including artificial muscles, sensors, and smart devices. However, traditional actuators often suffer from small deformation and complex materials and manufacturing processes. Graphene oxide (GO) has emerged as an ideal candidate for moisture-responsive actuators due to its excellent moisture sensitivity. In this study, we present the development of a moisture-responsive actuator using a simple and straightforward approach based on a monolayer graphene oxide (GO) paper. By utilizing the different affinity of its two sides for water, the graphene oxide actuator demonstrates excellent performance in response to humidity gradients, achieving a large bending amplitude with a curvature of 3 cm−1. Furthermore, the graphene oxide actuator was used as a humidity-sensitive switch to perform on and off switch movements, demonstrating its capability for autonomous detection for real-time humidity monitoring. This work provides a new avenue for the development of moisture-responsive materials and their potential applications in the design of intelligent control systems, actuators, soft robots, artificial muscles, and switches.

Over the past few years, the elimination of pharmaceuticals from polluted water has been a major challenge for many researchers. The presented project reports the photoelectrochemical (PEC) detection of ciprofloxacin (CIP) by using a BiVO4 thin layer prepared by a facile spin coat method on an Indium doped tin oxide (ITO) glass as photoanode. The mesoporous nanostructure of the fabricated photoanodes was characterized with UV–vis diffusion transmission spectra, Tauc plot, electrochemical impedance spectroscopy, Mott-Schottky diagram, and chronoamperometry analysis. After optimizing some of the key factors affecting current response of the photoanode, the PEC detection results showed that the BiVO4 thin-layer photoanode had high and stable photocurrent responses for CIP under UV-Vis light irradiation. Furthermore, the fabricated PEC sensor displayed two wide-spreading linear detection ranges from 0.05 to 100 nM and 100–5700 nM with very low detection limits (LOD) of 0.016 nM. Furthermore, the interferences evaluation demonstrated excellent selectivity of the PEC sensor toward CIP molecules in the presence of other interfering species in solution. Therefore, the marked performance of this photoelectrode in the PEC detection of CIP, extraordinary stability, and admirable reproducibility suggests its potential as a photoanode for the pharmaceutical pollutant oxidation including various antibiotics in wastewater.

Named Entity Recognition (NER) in Chinese Electronic Medical Records (EMRs) is crucial for enhancing healthcare quality and efficiency. However, the unique complexity of the Chinese language and the unstructured format of medical texts create significant challenges. To address these issues, we propose MSCNER, a unified Multi-Scale Embedding Network designed specifically for NER in Chinese EMRs. MSCNER navigates linguistic and contextual challenges by employing a character relation classification scheme. The model first extracts detailed contextual information through an information extraction module and a context modeler. It then incorporates multi-scale feature extraction to gather comprehensive features across characters, words, and positions. Additionally, a weight allocation module based on an attention mechanism optimizes the recognition of complex and discontinuous entities. Experimental results on three benchmark Chinese EMR datasets demonstrate that MSCNER achieves state-of-the-art performance. It significantly surpasses existing models in terms of accuracy and reliability. These findings underscore the potential of MSCNER to improve NER in medical applications, paving the way for more effective and scalable healthcare data systems and broader applications in other language processing tasks.

IoT enables the emergence and implementation of smart devices to address real-world problems and challenges. Today we are surrounded by various smart devices, such as smart phones, smart homes, smart cars, smart televisions, and smartwatches that assist us in making our lives easier and smoother. IoT is a conglomeration of multiple technologies at various layers to impart the best of ubiquitous and pervasive computing to deliver several benefits in a variety of application sectors such as medicine, agriculture, and industry. In an IoT setting, blockchain technology is used for addressing security challenges and eradicating third-party participation. Utilizing public networks for storing or transmitting health care images poses risks of eavesdropping, data breaches, and unauthorized access. Before uploading medical data to the decentralized network, encryption is required to prevent unauthorized access. The aim of this study is to integrate technologies to ensure transactions are conducted safely and securely. We proposed an IoT-Blockchain system based on chaos encryption scheme using Tinkerbell mapping to ensure medical data integrity and authenticity. The suggested approach is examined to assess performance parameters such as, key space analysis, key sensitivity analysis, Information Entropy (IE), histogram, correlation of adjacent pixels, Number of Pixel Change Rate (NPCR), Unified Average Changing Intensity (UACI), Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE) and Structural Similarity Index (SSIM). These findings demonstrated that the suggested method is extremely efficient in avoiding security breaches and guaranteeing information integrity.

Bolted connections for built-up cold-formed sections are studied using different section configurations, gusset plates, and bolt arrangements. This paper presents the study of a connection between beam and column in light-weight steel frames with spans ranging between 8.0 and 12.0 m and a maximum height of 6.0 m that are used in agricultural sheds. The cross section of the beam and column is a novel built-up cold-formed cross section. A total of eight connections were tested and studied. The purpose of the study is to determine the effect of serval factors on the moment capacity and failure modes of the connection. The experimental study considered the effects of different shapes of tie plates, numbers, and spacings of bolts, as well as the effect of strengthening angles with different numbers of bolts in the connections. The experimental results showed that the failure modes in all connection types were due to a local failure in the connecting parts. The experimental results revealed that the configuration type has a great influence on the moment capacity of the connection.

In investigations of domains under post-stratified random sampling, it is difficult to get an acceptable precision for domain-specific estimates due to low sample sizes. Small area estimate, a popular technique that has been widely used over the past few decades, involves indirect estimating using the auxiliary data from the entire population. In this article, we utilize a ranked set sampling (RSS) technique to achieve a greater level of precision in area-specific estimations under the assumption that ranking the smaller sets is simple, inexpensive, and flawless. RSS optimizes sample size for a fixed degree of precision or increases precision for a fixed sample size. We create direct estimators for population total under homogeneous, ratio, and regression models that are area specific. To evaluate the effectiveness and application of the suggested RSS technique, data from the Pakistan Demographic Health Survey (PDHS 2017–18) and Iris flower data are used. The effectiveness of the RSS mechanism is supported by both theoretical characteristics and Bootstrapped tests.

An electrochemical biosensor based on a polystyrene-gold nanocomposite was fabricated for the ultrasensitive sensing of clenbuterol. The PS-Au nanocomposite was synthesized by modifying polystyrene with triazine and aminothiazole groups, followed by the in-situ reduction of AuNPs. The PS-Au/SPCE exhibited a linear range (0.01–10 μM) with a limit of detection of 3.2 nM towards clenbuterol along with high selectivity and good stability. The sensor platform showcased its prowess by accurately quantifying clenbuterol in milk specimens fortified with known analyte concentrations, yielding recovery percentages within the range of 96.5–102.8 %, accompanied by relative standard deviations below 4.2 %. The superior performance of the PS-Au/SPCE is due to the synergistic effect of the high surface area and electrocatalytic activity of the AuNPs, the efficient adsorption of clenbuterol on the functionalized polystyrene matrix, and the enhanced electron transfer kinetics.

In anti-lock brake systems (ABS), the primary goal of the controller is to maximize vehicle deceleration by maintaining the slip ratio at an optimal level. This work presents a fresh approach that enhances ABS performance by integrating a sliding mode controller with a barrier function. This method combines integral sliding mode control with adaptive laws informed by barrier functions, effectively managing external disturbances and uncertainties in inertia. A significant benefit of this approach is that it does not require prior knowledge of the upper limits of these uncertainties and disturbances, thanks to the barrier function-based sliding mode control. The system state is initially aligned with the switching manifold, ensuring robust compensation for any uncertainties and disturbances right from the start of braking. During the sliding mode phase, dynamic properties are finely tuned to ensure that the system’s performance remains consistent. The effectiveness and reliability of the proposed controller have been demonstrated through numerical simulations conducted in MATLAB/Simulink, proving its capability across a range of road conditions.

This study explores the Petrov–Galerkin method’s application in solving a linear fourth-order ordinary beam equation of the form u″″+qu=fu^{\prime\prime} ^{\prime\prime} +qu=f. The equation entails two distinct boundary conditions: pinned–pinned conditions on uu and u′u^{\prime} , and clamped–clamped conditions on uu and u″{u}^{^{\prime\prime} }. To satisfy these boundary conditions, we have built two sets of basis functions. The explicit forms of all spectral matrices were reported. The nonhomogeneous boundary conditions were easily handled using perfect transformations, ensuring the numerical solution’s accuracy. Detailed analysis of the method’s convergence was studied. Some numerical examples were presented, accompanied by comparisons with other existing methods in the literature.

A practical examination of the traditional robotic arm (RA) in operation revealed a significant limitation in its ability to control the position of motion. This underscores the urgent need to enhance the current RA’s position control capabilities. Therefore, this study proposes the use of nonlinear differential equations (NDEs) to establish a mathematical model and the design of NDE-based RA motion control algorithms in conjunction with a central pattern generator neural network. A comparison of the control effects showed that the proposed method was highly fitted to the target trajectory. The joint node (JN) motion tracking trajectories of the three RAs were similar, up to 90–85% to the target trajectories of the JNs. In addition, the control of the motion position was similar up to 95–98% to the target motion position trajectories. The motion control algorithm based on NDEs was effective in improving the average execution time of the Pareto optimal frontier of the RA by 58.29%. The joint velocity and angle changes of the three types of RAs under the NDE control algorithm exhibited a high degree of similarity to the fluctuations observed in the expected and predicted curves. These observations contribute to an understanding of the effectiveness of the system observer in observing the joint angle changes. This indicates that the motion control based on NDEs can effectively enhance the tracking effectiveness of the JN positions of the RA, improve the control ability of the RA motion, and increase the joint stability of the RA.

This article presents the application of the Faedo–Galerkin compactness method to establish the local well-posedness of the Newell–Whitehead–Segel equation. By analyzing a finite-dimensional approximate problem, the existence and uniqueness of a local solution were demonstrated. A priori estimates were derived, enabling the transition to the limit and the recovery of the original problem’s local solution. The study further proves the uniqueness and continuous dependence of the solution on initial data. Additionally, under certain conditions, it is shown that the energy norm of the solution decays exponentially over time, and the L2{L}^{2}-norm of the time derivative of the solution approaches zero asymptotically.

Abstract The spatiotemporal resolution of diagnostic X-ray images is limited by the erosion and rupture of conventional stationary and rotating anodes of X-ray tubes from extreme density of input power and thermal cycling of the anode material. Conversely, detector technology has developed rapidly. Finer detector pixels demand improved output from brilliant keV-type X-ray sources with smaller X-ray focal spots than today and would be available to improve the efficacy of medical imaging. In addition, novel cancer therapy demands for greatly improved output from X-ray sources. However, since its advent in 1929, the technology of high-output compact X-ray tubes has relied upon focused electrons hitting a spinning rigid rotating anode; a technology that, despite of substantial investment in material technology, has become the primary bottleneck of further improvement. In the current study, an alternative target concept employing a stream of fast discrete metallic microparticles that intersect with the electron beam is explored by simulations that cover the most critical uncertainties. The concept is expected to have far-reaching impact in diagnostic imaging, radiation cancer therapy and non-destructive testing. We outline technical implementations that may become the basis of future X-ray source developments based on the suggested paradigm shift.

Abstract Various successful applications of deep artificial neural networks are effectively facilitated by the possibility to increase the number of layers and neurons in the network at the expense of the growing computational complexity. Increasing computational complexity to improve performance makes hardware implementation more difficult and directly affects both power consumption and the accumulation of signal processing latency, which are critical issues in many applications. Power consumption can be potentially reduced using analog neural networks, the performance of which, however, is limited by noise aggregation. Following the idea of physics-inspired machine learning, we propose here a type of neural network using stochastic resonances as a dynamic nonlinear node and demonstrate the possibility of considerably reducing the number of neurons required for a given prediction accuracy. We also observe that the performance of such neural networks is more robust against the impact of noise in the training data compared to conventional networks.

Abstract Accurate estimation of battery state of health is crucial for effective electric vehicle battery management. Here, we propose five health indicators that can be extracted online from real-world electric vehicle operation and develop a machine learning-based method to estimate the battery state of health. The proposed indicators provide physical insights into the energy and power fade of the battery and enable accurate capacity estimation even with partially missing data. Moreover, they can be computed for portions of the charging profile and real-world driving discharging conditions, facilitating real-time battery degradation estimation. The indicators are computed using experimental data from five cells aged under electric vehicle conditions, and a linear regression model is used to estimate the state of health. The results show that models trained with power autocorrelation and energy-based features achieve capacity estimation with maximum absolute percentage error within 1.5% to 2.5%.

Abstract Ventricular arrhythmias after myocardial infarction (MI) originate from discrete areas within the MI border zone (BZ), identified during functional electrophysiology tests. Accurate sampling of arrhythmogenic sites for ex-vivo study remains challenging, yet is critical to identify their tissue, cellular and molecular signature. In this study, we developed, validated, and applied a targeted sampling methodology based on individualized 3D prints of the human-sized pig heart. To this end, 3D anatomical models of the left ventricle were created from magnetic resonance imaging and fused with biplane fluoroscopy. Regions of interest for sampling were annotated on the anatomical models, from which we created a unique 3D printed cast with custom slits identifying the annotated regions for sampling. The methodology was validated by retrieving ablation lesions created at predefined locations on the anatomical model. We applied the methodology to sample arrhythmia-vulnerable regions after MI during adrenergic stimulation. A pipeline of imaging was developed to create a 3D high-resolution map of each sample, highlighting the complex interplay of cellular organization, and altered innervation in the BZ.

Abstract Understanding Pd effects on NOx storage and release is crucial for designing passive NOx adsorber (PNA) to control NOx emissions during diesel cold-starts. Herein, we report two oxidation states of Pd species on CexZr1-xO2 regulated by metal-support interaction. Pdδ+ (0

Abstract Condensation trail (contrail) formation in an airplane’s wake requires thermodynamics supersaturation and ice nucleation to form visible ice crystals. Here, using a thermodynamic analysis, we evaluate the potential for forming contrails in a carbon-free, ammonia-powered propulsion system compared to conventional planes powered by jet fuel. The analysis calculates the moisture released by fuel into the atmosphere for each one-degree increase in air temperature due to exhaust gas. It then determines if this moisture can saturate the initially undersaturated atmosphere, maintain saturation as temperature rises, and result in supersaturation with respect to ice while leaving enough moisture for a visible cloud to form. With ammonia increases the critical temperature required for supersaturation. Although ammonia does not generate soot particles in the exhaust gas, various aerosols exist in the atmosphere through other sources that can facilitate heterogeneous ice nucleation. Hence, while ammonia’s contrails might not be as dense, they can form at lower altitudes where the air is warmer and endure longer due to the increased water content, which preserves supersaturation for longer as fresh air dilutes the contrail.

Abstract Understanding biological activities in cells or deep tissues requires high-speed three-dimensional (3D) imaging. Substantial progress has been made with the emergence of 3D random-access microscopy. However, current solutions for fast 3D random-access imaging remain complex and costly. Herein we propose a simple, cost-effective, and fast 3D random-access confocal microscopy with remote focusing system. Our system shows isotropic response times across the x, y, and z axes, with a 34-fold improvement in axial response time over traditional piezo stages. We demonstrate its volumetric imaging performance with fluorescent particles and live cells. Furthermore, we validate the 3D random-access imaging capability of this system by continuously monitoring the signals in three different planes, showing a refresh rate of 500 Hz on two different positions in 3D. The simplicity, versatility, and affordability of our system promise widespread applications in research and industry.

Abstract It is not currently possible for an infrared camera to see through a hot window. The window’s own blinding thermal emission prevents objects on the other side from being imaged. Here, we demonstrate a path to overcoming this challenge by coating a hot window with an asymmetrically emitting infrared metasurface whose specially engineered imaginary index of refraction produces an asymmetric spatial distribution of absorption losses in its constituent nanoscale resonators. Operating at 873 K, this metasurface-coated window suppresses thermal emission towards the camera while being sufficiently transparent for thermal imaging, doubling the thermal imaging contrast when compared to a control window at the same temperature

Abstract Surface lattice resonances (SLR) have been demonstrated to enhance the sensitivity and reduce the full width at half maximum (FWHM) of the plasmonic resonances. However, their widespread application in immunoassays has been hindered by limitations of high structural defect sensitivity and fabrication costs. Here, we design a novel three-layer cylindrical SLR array that exhibits high tolerance against structural defects, which would facilitate straightforward fabrication. By integrating metal evaporation and nanoimprint lithography, we demonstrate the replication of the SLR array with exceptional quality. Theoretical simulations indicate that the resonance dips of these arrays exhibit are not sensitive to various structural defects. The experimental results reveal that the FWHM of these arrays can be as low as 5.1 nm while maintaining robust resonance characteristics. Furthermore, we demonstrated the high spectral sensitivity of the SLR array, which enabled the detection of immunoglobulin G (IgG) at concentrations as low as 609 pg/mL. These findings emphasize the potential of the defect-insensitive SLR array as a highly scalable immunoassay platform with exceptional performance.

Abstract Limited to the direct modulation on the surface acoustic wave (SAW) by the rotation, the conventional SAW gyroscopes incur weak Coriolis effects and gyroscopic effects. In this paper, we innovatively utilize a phononic metamaterial (PM) operated at whispering-gallery modes (WGMs) as the vehicle for the Coriolis effect rather than SAW itself. The gyroscopic effects of this PM are investigated, and a new SAW gyroscope is subsequently proposed based on the slow SAW in PM. We show, combining theoretical modeling and finite element method simulation, that the rate of rotation can linearly induce the splitting of WGMs and modulate the phase velocity of SAW down to 4600 m/s (initial phase velocity of 5355 m/s); the direction of rotation results in the chiral symmetry of the PM vibration and the asymmetric distribution of the transmissive SAW. Besides, the proposed SAW gyroscope measures the angular velocity by detecting the phase shift resulting from rotation-dependent slow SAW in PM, obtaining a sensitivity of 0.016 deg/Hz when 50-cell PM. Compared with the existing SAW gyroscopes based on phase velocity modulation, the gyroscopic gain factor in this paper is enhanced by 430–1600 times. This work jumps out of the framework of directly modulating SAW in gyroscopes and provides an innovative scheme of the indirect modulations from the rotation-dependent PM on SAW, showing excellent performance and potential for angular velocity measurement in extreme environments.

Abstract The emergence of cracks in cementitious composites and concrete, stemming from both autogenous processes and external stressors, poses a significant challenge to the long-term durability and safety of structures. In response to this challenge, researchers have developed an innovative method featuring inherent capabilities for autonomous crack repair, known as self-healing concrete, which offers promising benefits for enhancing structural longevity and reducing environmental impact. This method offers not only an autogenous healing mechanism but also the potential for autonomous repair, significantly reducing the need for maintenance while concurrently extending the lifespan of concrete structures. This paper comprehensively reviews the working principles, fabrication techniques, and self-healing capabilities, specifically in relation to crack recovery and mechanical performance, of concrete incorporated with chemical-based self-healing agents. These agents encompass a range of materials, such as sodium silicate, calcium nitrate, dicyclopentadiene, calcium hydroxide, calcium sulfoaluminate (CSA), silica, and superabsorbent polymers. In this review, both autogenous and autonomous self-healing were considered, and literature studies suggested cracks can effectively heal, and mechanical performances can be significantly restored. Healing performance and mechanical performance restoration can vary significantly with the type of healing agents and their concentrations. Many researchers have achieved more than 100% restoration of mechanical performance and fully healed crack depths. Superabsorbent polymers (SAP) are highly effective self-healing agents, particularly when combined with autogenous healing agents like calcium nitrate or CSA. This combination can lead to significant healing in cracks up to 750 μm. Chemical-based self-healing agents can be an efficient way to enhance the durability of concrete, ensuring safety and promoting their practical application.

Abstract The Himalayan region is one of the most seismically active areas in the world due to its tectonic setting. This vulnerability poses significant risks to buildings, resulting in substantial loss of life, property, and infrastructure. This study investigates the seismic performance of a reinforced concrete (RC) low-rise building using the seismic codes of countries situated along the Himalayan belt: China, India, Nepal, and Pakistan. These countries, despite sharing a common geological seismic threat, have developed a distinct code and standards for construction. This inconsistency concerns the effectiveness and suitability of seismic design practices in this region, hence prompting a comparative study. This study begins by reviewing the development of seismic codes in these countries. Subsequently, a prototype RC low-rise building was modeled and analyzed using finite element software, employing the linear static method of analysis according to each country's seismic codes. This study focused on key seismic responses, including the fundamental period, base shear, displacement, and story drift. The analysis revealed significant differences in seismic responses among the codes. Notably, the Chinese seismic code resulted in the highest values for the parameters studied, followed by the Nepalese, Pakistani, and Indian codes. The comparison revealed that the base shear from the Chinese code was the highest, being 3.10 times greater than the Indian code, 1.66 times greater than the Nepalese code, and 1.86 times greater than the Pakistani code. Similar ratios for displacements and story drifts were found in the study.

Abstract Double-deck cable-stayed bridges are appropriate when there is a high traffic volume and little space for the structure. They combine road and rail transit to maximize the utilization of bridge structures and tackle traffic issues. This study investigates the fluctuations in the modal properties caused by several factors that impact the modal characteristics of bridges. The aim is to ascertain the system’s inherent frequencies, associated natural periods, and mode shapes. The modal analysis inquiry was conducted utilizing a software model grounded in the finite element method. The bridge deck slab, cable, pier, and pylon are discretized utilizing SHELL 181, CABLE 280, and BEAM 188 elements in this finite element model. The model’s dependability was validated by mesh convergence analysis and comparison with findings from prior research investigations. The cumulative mass participation factor analysis reveals that the bridge induces vibrations in 90% of the mass associated with the first five modes in the research of cumulative modal vibration. The application of prestressing force has significantly increased the natural frequencies of the bridges, resulting in a large rise. An increase in the damping ratio leads to a reduction in the natural frequency. Several factors, such as the existence or absence of prestressing force and different damping ratios in the bridge system, will affect free vibration results. Additionally, it can provide the foundation for subsequent fatigue analysis related to different dynamic loads.

Abstract Transverse cracking in flexible pavements poses significant challenges to road infrastructure, impacting durability and increasing maintenance costs. This study addresses the lack of predictive models specifically for transverse cracking by employing machine learning techniques. Utilizing data from the long-term pavement performance (LTPP) program, we analyzed the influence of various factors including pavement structure, environmental conditions, and traffic loads. Descriptive statistical analysis revealed a positive skew in the frequency of transverse cracks, while a heatmap correlation matrix identified pavement age, effective asphalt content, and freeze indices as key contributors to cracking. Machine learning models were evaluated, with the Exponential Gaussian Process Regression (GPR) model demonstrating superior predictive accuracy, achieving an R-squared value of 0.70 and RMSE of 17.50, outperforming other models such as the Cubic SVM. Sensitivity analysis emphasized the linear relationship between pavement age and transverse cracking, highlighting the progressive impact of aging on pavement integrity. This research provides a comprehensive and innovative machine learning-based approach to predict transverse cracking, offering valuable insights for pavement management strategies that aim to optimize maintenance schedules and extend pavement service life, particularly in regions with varying environmental conditions.

Abstract Supply chain management has shown to be an aspect of construction that is neglected, yet with great impact on project delivery time frames and the overall cost of construction projects. This research seeks to identify, assess, and propose solutions for the challenges hindering the adoption of digital technologies in construction supply chain management, hence creating a sustainable foundation for practitioners and relevant agencies to leverage the benefits of digital technologies in the management of construction supply chain. The literature review identified challenges of digital technology adoption in construction supply chain management, guiding subsequent research. A structured questionnaire captured demographic data and insights, with 171 industry professionals surveyed. Data analysis, including Likert scale ratings and Relative Impact/Feasibility Index, informed an Impact-Feasibility Matrix. This matrix categorized challenges and strategies into quadrants, aiding prioritization. A conceptual framework emerged, offering actionable insights for addressing adoption challenges. The study identified 14 challenges to digital technology adoption in construction supply chain management, ranked by respondents. These challenges were categorized based on their impact and feasibility, with strategies mapped accordingly. The resulting framework prioritizes High Impact/High Feasibility challenges for action, while Low Impact/Low Feasibility challenges may require further exploration. This strategic approach aims to address key hurdles efficiently, enhancing the adoption of digital technologies in construction supply management. The findings from this study will inform construction practitioners and relevant agencies about the challenges hindering the seamless integration of digital technologies into construction supply chain management and propose feasible strategies for addressing these challenges.

Abstract This study investigates the effects of various fibers and their combinations on the mechanical properties of fiber-reinforced cementitious composites (FRCC). Sixteen distinct mix designs were prepared, each incorporating different types and proportions of fibers, Polyvinyl Alcohol (PVA), Polypropylene (PP), Basalt, and Banana fibers, while maintaining a consistent cement-to-sand ratio of 25% to 75%. The objective was to evaluate how these fibers influence the compressive, flexural, and tensile strengths of the FRCC. The results revealed significant variations in mechanical properties based on fiber type and content. Mixes containing PVA and Basalt fibers demonstrated superior compressive strength, flexural strength, and tensile strength compared to those with other fibers. Notably, hybrid fiber combinations, such as PVA and Basalt or PVA and PP, showed enhanced mechanical performance, indicating the synergistic benefits of combining different fiber types. In contrast, Banana fibers alone were less effective in improving mechanical properties but contributed positively when combined with synthetic fibers. The study highlights the potential of fiber hybridization in optimizing the performance of cementitious composites. The strategic use of PVA and Basalt fibers, both individually and in combination, provides a promising approach for developing high-strength for diverse construction applications. These findings offer valuable insights for future research and the development of advanced composite materials with tailored mechanical properties. Graphical Abstract

Abstract This research explores the advanced application of nano-silica (nS) in concrete, emphasizing its significant role in improving the mechanical strength and longevity of concrete structures. Unlike prior studies on nS in concrete, this work goes beyond evaluating typical performance metrics such as compressive strength, water absorption, air permeability, and drying shrinkage, by also examining the effect on production costs. The study involved detailed experimental procedures, where concrete mixtures were prepared with varying water-to-binder (w/b) ratios of 0.33, 0.45, and 0.55, and nS contents of 0, 1, 3, and 5 percent by binder weight. The results indicate that a 3% nS admixture significantly boosts compressive strength and reduces both water and gas permeability, although it also leads to an increase in drying shrinkage. Furthermore, the cost analysis shows that even a small 1% addition of nS can raise production costs, underscoring the importance of balancing cost-effectiveness with performance improvements when considering nS for concrete applications.

Abstract For its outstanding aerodynamic capabilities, the integrated design of the waverider and inlet is widely accepted in hypersonic aircraft. Three aspects of the integrated design of the waverider and inlet since 2020 are mainly described in this paper. Firstly, the advantages and shortcomings of the conventional integrated design are examined. Then, different layouts of integrated design are proposed, and the aerodynamic performance optimization methods of the waverider, inlet, and their coupling are introduced. Besides, a series of methods for increasing the calculating accuracy of the waverider and inlet are presented, and the focus of attention is to consider the lateral flow problem.

Solar Power Plants (PLTS) have become a very popular energy source and have great potential in reducing dependence on fossil energy sources. The Node MCU ESP8266 is one type of microcontroller that is highly popular in the development of IoT projects. In generating electrical energy, the Internet of Things (IoT) technology has rapidly developed and become one of the most popular technologies in the field of electrical energy. With a PLTS monitoring system using a website, users can monitor the performance of the PLTS in real-time. Solar panels or solar cells are equipment modules that can convert solar energy into electrical energy with DC current. Monitoring is the process of systematically and continuously collecting and analyzing information based on predetermined indicators of activities/programs, allowing corrective actions to be taken for the improvement of the program/activity. The researchers will also discuss the importance of monitoring PLTS, as well as the potential of IoT technology to improve the efficiency and quality of electrical energy production. The website is used to operate IoT principles designed for fast and easy real-time reading. Functional testing is divided into three parts: voltage sensor testing, ACS712 current sensor testing, and NodeMCU testing. The electrical parameters to be measured include output current and output voltage. The PLTS monitoring system device, also known as the Box Panel, has been designed, built, and tested. The testing phase is carried out by conducting functional tests on the system to determine the success rate and accuracy of the device. Once the box panel functions properly, it can be used to monitor the output of the PLTS, and the measurement results will be displayed on the website that has been created.

Load variations found in PT PLN Persero customers, such as resistive, inductive, or capacitive loads, can potentially affect the error rate in kWh meter readings. To determine the error rate of kWh meter readings, it is necessary to compare the reading data from each kWh meter with the measurement data from a 6-in-1 multimeter display. This involves comparing the prepaid digital kWh meter, the postpaid semi-digital kWh meter, and the postpaid analog kWh meter, all assembled in series. Based on the test results, the average reading error rate for resistive loads was found to be 0,11% for the prepaid digital kWh meter, 6,91% for the postpaid semi-digital kWh meter, and 0,36% for the postpaid analog kWh meter. For inductive loads, the average reading error rate was 0,36% for the prepaid digital kWh meter, 7,00% for the postpaid semi-digital kWh meter, and 0,27% for the postpaid analog kWh meter. For capacitive loads, the average reading error rate was 0,09% for the prepaid digital kWh meter, 7,52% for the postpaid semi-digital kWh meter, and 0,62% for the postpaid analog kWh meter. This research is important for the electricity supply industry because the accuracy of electrical energy measurement is a key factor in maintaining operational efficiency and improving tariff fairness for customers.

The reliability index of the distribution system is a measure of the system's ability to continuously supply electrical energy to loads over a specific period and under certain conditions. PT. PLN (Persero) Rayon Samalanga, as the electricity service provider in Bireun Regency, adheres to service standards in accordance with SPLN 59:1985 and the IEEE Reliability Index standard 1366-2003. This research analyzes the reliability level of PT. PLN (Persero) Rayon Samalanga's distribution network on six (6) feeders: feeder SL-1, feeder SL-2, feeder SL-3, feeder SL-4, feeder SL-5, and feeder SL-6. The reliability index calculation is based on the estimated failure rate (λ) and the estimated interruption duration (U) for each installed component. The calculation results show that the distribution lines of PT. PLN (Persero) Rayon Samalanga are categorized as reliable according to SPLN 59:1985 and the IEEE Reliability Index standard 1366-2003, with the highest reliability index on feeder SL-4 at SAIFI = 2.04 times/failure; the best SAIDI value is on feeder SL-3 with SAIDI = 2.06852 hours/year; the best CAIDI value is on feeder SL-3 with CAIDI = 0.21 times/failure; the best MAIFI value is on feeder SL-2 with MAIFI = 14.82 times/customer; the best ASAI value is on feeder SL-3 with ASAI = 0.99999684, and the best ASUI value is on feeder SL-2 with ASUI = 0.0000081

Distributed Generator (DG) is a small-capacity power plant located within the electrical distribution system and is usually placed on buses directly connected to the load. The placement of distributed generators is a technical effort to reduce voltage drops and power losses in the system. Additionally, Power flow analysis is conducted to plan and determine the power levels within an electrical power system. The results in terms of power losses after adding a DG were achieved in the fifth experiment on bus 149, where the system's total active power loss (P) decreased from 720.822 kW to 682.939 kW, and the total reactive power loss (Q) decreased from 530.02 kVar to 405.835 kVar. These results were obtained from power flow calculations using Electrical Transient Analyzer Program (ETAP) software.Therefore, it can be concluded that the electrical network system is operating efficiently. The results show that the more wind turbine generators are added to the buses, the more the voltage drop is reduced. After simulation, the overall voltage drops still meet the standards according to the text report in ETAP.

Electrical energy is essential for the growth and advancement of technological knowledge that continues to increase. Solar cells are devices that convert solar energy through photovoltaic devices. Solar cell public street lighting (PJUBS) uses unlimited and free solar energy, is a feasible and cheap alternative to providing electric lighting. The Islamic center mosque is one of the places of worship for the majority of Muslims in the city of Lhokseumawe using public street lighting to support public security and safety. Installation of lamps for lighting is installed at several points, namely right, left or in the middle of the road, as needed, including flyovers, underpasses, and bridges. Public street lighting that is efficient and environmentally friendly is in accordance with SNI 7391: 2008. In this study, the lamps used in this evaluation study are solar types with a power of 50 Watts. The calculation results show that the illumination produced at the end of the road when using a 50 Watt solar LED lamp is 0.29 lux so that this does not comply with the provisions of BSN SNI 7391: 2008. This condition is influenced by several factors, namely surface temperature, shadows, inclination angle, light intensity, irradiation, and the condition of the panel surface in order to maximize the conversion value of sunlight into electrical energy

Geospatial technology, including remote sensing, Geographic Information Systems (GIS), and Global Navigation Satellite Systems (GNSS), is identified as a key component in disaster management. It enables hazard, risk, and vulnerability mapping, aiding in the development of effective evacuation plans and resource allocation strategies. Moreover, it facilitates the evaluation of the Sustainable Development Goals (SDGs) and can contribute to improving accountability. While geospatial technology has seen rapid development primarily in developed countries, there's a growing need to expand its adoption globally, particularly in developing and vulnerable regions. Capacity building initiatives are highlighted as crucial in achieving this goal, emphasizing the importance of education, training, and infrastructure development. India is a leading example in the application of geospatial technology for disaster risk reduction, with significant integration into various phases of disaster management. The government's commitment and leadership, along with extensive training programs facilitated by institutions like Indian Space Research Organization, have been instrumental in promoting the widespread use of geospatial technology. Furthermore, India's efforts extend beyond its borders, with capacity building initiatives targeted towards the Asia-Pacific region through the Centre for Space Science and Technology Education in Asia and the Pacific (CSSTEAP). These initiatives aim to equip officials with the necessary skills to apply geospatial technology in disaster management within their respective countries. The paper underscores the importance of integrating geospatial technology into DRR strategies to build resilient communities and minimize the impact of disasters. It emphasizes the need for concerted efforts in capacity building to meet the growing demand for skilled professionals and promote evidence-based decision-making in disaster management.

Annually, a considerable quantity of forest is burned on a global scale. Therefore, it is essential to obtain precise and fast information regarding the size of burned regions in order to effectively monitor the adverse consequences of wildfires. The objective of this investigation is to indicate the effectiveness and usefulness of a deep learning (DL) architecture, such as Convolutional Neural Networks (CNNs), in the mapping of areas affected by fire, employing an eXplainable artificial intelligence (XAI) algorithm known as SHapley Additive exPlanations (SHAP) with accuracy evaluation criteria. Furthermore, this paper presents the evaluation of the Çanakkale-Kizilkeçili village wildfire. The research investigated the impacts of a variety of spectral indices, including the normalized burn index (NBR), differentiated normalized burn index (dNBR), Green-Red Vegetation Index (GRVI), simple ratio vegetation index (RVI), and normalized difference vegetation index (NDVI). At the end of the training process, the model achieved a training accuracy of approximately 0.99, with model loss values converging to approximately 0.1. The findings of the burned area identification analysis indicate that by incorporating spectral indices as supplementary information, the CNN model achieved a high level of accuracy, with an overall accuracy of 98.88% and a Kappa Coefficient of 0.98. Additionally, the SHAP technique was employed to gain insights into the output of the models. The feature importances of the spectral bands were determined through the SHAP analysis of the CNN model. Hence, the significance of the auxiliary data generated by the NBR, dNBR, and NDVI indices was identified as being the highest among the original bands and auxiliary data employed in this investigation.

Poplars (Populus sp.), a tree that grows rapidly species, are significant as industrial forest products. The delineation and monitoring of poplar cultivated areas are invaluable for decision-making processes. With the remote sensing technology, accurate detection of poplar planted areas could be determined much faster, more economically, and with minimum labor requirements. The objective of this research is to create a map of poplar plantations in the Sakarya region of Turkey utilizing Worldview-3 satellite imagery. Object-based image analysis (OBIA) through the application of the multi-resolution segmentation method (MRS) was employed to generate image segments, and then three prevailing machine learning algorithms, namely Support Vector Machine (SVM), Random Forest (RF) and Rotation Forest (RotFor) were implemented to produce LULC maps of the study area including 11 landscape features. The most effective and contributing object features that assure high separability between landscape features were determined using a filter-based Chi-square algorithm for the prediction models constructed with SVM, RF, and RotFor classifiers. Results revealed that the SVM classifier achieved the highest overall accuracy (91.73%) with 38 features out of 88 features, about 3% improvement compared to the other algorithms. According to the SHAP analysis, the IHS feature was the most effective one in the constructed RF model, followed by the CI (red edge), NDVI-1 and NDVI-2 vegetation indices.