Estimation Model Research Articles

Unveiling the transferability of PLSR models for leaf trait estimation: lessons from a comprehensive analysis with a novel global dataset.

Leaf traits are essential for understanding many physiological and ecological processes. Partial least squares regression (PLSR) models with leaf spectroscopy are widely applied for trait estimation, but their transferability across space, time, and plant functional types (PFTs) remains unclear. We compiled a novel dataset of paired leaf traits and spectra, with 47 393 records for > 700 species and eight PFTs at 101 globally distributed locations across multiple seasons. Using this dataset, we conducted an unprecedented comprehensive analysis to assess the transferability of PLSR models in estimating leaf traits. While PLSR models demonstrate commendable performance in predicting chlorophyll content, carotenoid, leaf water, and leaf mass per area prediction within their training data space, their efficacy diminishes when extrapolating to new contexts. Specifically, extrapolating to locations, seasons, and PFTs beyond the training data leads to reduced R2 (0.12-0.49, 0.15-0.42, and 0.25-0.56) and increased NRMSE (3.58-18.24%, 6.27-11.55%, and 7.0-33.12%) compared with nonspatial random cross-validation. The results underscore the importance of incorporating greater spectral diversity in model training to boost its transferability. These findings highlight potential errors in estimating leaf traits across large spatial domains, diverse PFTs, and time due to biased validation schemes, and provide guidance for future field sampling strategies and remote sensing applications.

Deep learning-based channel estimation with application to 5G and beyond networks

Channel state information (CSI) feedback estimation for a downlink medium in a massive multiple input multiple output (MIMO) system is an essential and critical task to improve channel capacity and performance yield, especially in a frequency division duplex (FDD) multiplexing system. However, spectral efficiency degradation is a massive issue due to high channel feedback overhead. This work proposes a deep learning-based channel estimation (DLCE) model to improve channel reconstruction efficiency and channel overhead reduction accuracy. The proposed deep learning (DL) mechanism consists of encoder and decoder network where encoder network is utilized to compress CSI matrices whereas decoder network is used to decompress obtained CSI matrices. Here, inverse discrete Fourier transform (IDFT) method is utilized to convert CSI matrices of frequency domain into CSI matrices of delay domain. Simulation results are evaluated between uplink and downlink medium in the massive MIMO system considering a co-operation in science and technology (COST) 2,100 model. Here, a significant improvement in correlation and normalized mean square error (NMSE) results is observed. The proposed DLCE model shows superior performance against varied channel estimation techniques in terms of NMSE and correlation efficiency.

A Simple Thermal Model for Junction and Hot Spot Temperature Estimation of 650 V GaN HEMT during Short Circuit

Temperature is a critical parameter for the GaN HEMT as it sharply impacts the electrical characteristics of the device more than for SiC or Si MOSFETs. Either when designing a power converter or testing a device for reliability and robustness characterizations, it is essential to estimate the junction temperature of the device. For this aim, manufacturers provide compact models to simulate the device in SPICE-based simulators. These models provide the junction temperature, which is considered uniform along the channel. We demonstrate through two-dimensional numerical simulations that this approach is not suitable when the device undergoes high electrothermal stress, such as during short circuit (SC), when the temperature distribution along the channel is strongly not uniform. Based on numerical simulations and experimental measurements on a 650 V/4 A GaN HEMT, we derived a thermal network suitable for SPICE simulations to correctly compute the junction temperature and the SC current, even if not providing information about the possible failure of the device due to the formation of a local hot spot. For this reason, we used a second thermal network to estimate the maximum temperature reached inside the device, whose results are in good agreement with the experimental observed failures.

Relationship between hukou conversion and psychological integration of rural older migrants: the mediating effect of accessibility to health resources

ObjectiveThis study investigates the relationship between hukou conversion and the psychological integration of rural older migrants, exploring the mediating role of accessibility to health resources.MethodsThe 3,963 valid samples of rural older migrants included in the study were sourced from the 2017 China Migrants Dynamic Survey (CMDS). The study established a multiple linear regression model for estimation and utilized inverse probability-weighted regression adjustment (IPWRA) method to correct for the selection bias of hukou conversion.ResultsCompared to older migrants with rural hukou, merit-based (β = 0.384, 95% CI: 0.265 to 0.504), family-based (β = 0.371, 95% CI: 0.178 to 0.565) and policy-based (β = 0.306, 95% CI: 0.124 to 0.487) converters have significantly higher psychological integration. These findings remain robust even after addressing the potential issue of endogenous selection bias using the IPWRA method. Bootstrap mediating effect tests indicate that hukou conversion can indirectly affect psychological integration through the mediator role of health resources accessibility.ConclusionAccessibility of health resources mediates the association between hukou conversion and psychological integration. Policymakers should enhance the implementation of hukou conversion, strengthen the health resource guarantee system, and achieve a deeper psychological integration among rural older migrants.

Development of machine learning models for estimation of daily evaporation and mean temperature: a case study in New Delhi, India

ABSTRACT Accurate prediction of pan evaporation and mean temperature is crucial for effective water resources management, influencing the hydrological cycle and impacting water availability. This study focused on New Delhi's semi-arid climate, data spanning 31 years (1990–2020) were used to predict these variables using advanced algorithms such as Bagging, Random Subspace (RSS), M5P, and REPTree. The models were rigorously evaluated using 10 performance metrics, including correlation coefficient, mean absolute error (MAE), and Nash–Sutcliffe Efficiency (NSE) model coefficient. The Bagging model emerged as the best model with performance indices values as r, MAE, RMSE, RAE, RRSE, MBE NSE, d, KGE, and MAPE as 0.86, 0.76, 1.43, 32.70, 49.44, 0.03, 0.85, 0.96, 0.90, and 22.0, respectively, during model testing phase for pan evaporation prediction. In predicting mean temperature, the Bagging model reported the best results with performance indices values as r, MAE, RMSE, RAE, RRSE, MBE NSE, d, KGE, and MAPE as 0.86, 0.76, 1.43, 32.70, 49.44, 0.03, 0.85, 0.96, 0.90 and 22.0, respectively, during the model testing phase. These findings offer valuable insights for enhancing relative humidity prediction models in diverse climatic conditions. The Bagging model's robust performance underscores its potential application in water resource management.

A Cognitive Approach for Modeling Customer Demand Dynamics for Optimal Product Release Strategies

Abstract As agile processes are increasingly adopted for product design, and as consumer preferences are rapidly evolving with increasing information available from digital media, there is a need for a demand model that can accommodate the dynamics of product development. However, existing models of demand estimation, such as the discrete-choice models, do not capture the dynamics of product development and decision-making processes and thus are unable to effectively capture the effect of product updates and the release of information. To address this gap, we present a dynamic demand model and demonstrate how it can be used to determine the optimal time to release product updates. The demand model is based on decision field theory (DFT), which enables the modeling of the dynamic behavior of human decision makers. The contributions of this article are as follows. First, we formulate a computational model for demand modeling built on DFT and demonstrate the viability of using the model to determine product release strategies. Second, we provide analytical approximations of the demand model and compare the accuracy of the approximated demand against the demand predicted by the dynamics model. Third, we show an example of a game played by competitors trying to optimize demand for their products by choosing the optimal update time relative to each other. Finally, we demonstrate the feasibility of parameter estimation using only the demand data.

A novel transformer-based neural network under model interpretability for improving wheat yield estimation using remotely sensed multi-variables

Timely and accurate yield prediction before wheat harvest is of great significance for food policy formulation and national economic development. Deep learning method gains importance on crop yield estimation and growth monitoring with the rapid development of deep learning models combined with remotely sensed data. However, the problems of nonlinear parameter optimization and long-term dependence in time series data have restricted the improvement of yield estimation accuracy. Transformer model completely abandons the traditional deep learning architecture and is gradually applied to time series tasks due to the advantage in modeling long-term dependence. This study introduced a novel transformer-based deep learning framework to estimate winter wheat yield in the Guanzhong Plain utilizing remotely sensed multi-variables, namely leaf area index (LAI), fraction of photosynthetically active radiation (FPAR) and vegetation temperature condition index (VTCI). The proposed model, called SSA-LSTM-transformer (SLTF), was developed for dealing with above problems under the automatic optimization capability of the sparrow search algorithm (SSA) and the long-term memory advantage of the long short-term memory (LSTM) structure. The findings demonstrated that the SLTF model achieved better estimation accuracy at the county level (R2 = 0.72, RMSE = 488.68 kg/ha) compared with the single transformer model (R2 = 0.61, RMSE = 573.99 kg/ha). The analysis on SLTF model’s performance at sampling sites over different disasters suggested that the model can effectively learn the effects of diseases, lodge and pests on crop yield estimation, which had good generalization ability at all sampling sites (R2 = 0.45, RMSE = 738.63 kg/ha). The Shapley Additive exPlanations (SHAP) approach was employed to evaluate the relative importance of remotely sensed multi-variables to yield and to understand how each input variable influences the estimated yield for global interpretability and local interpretability of the SLTF model. It was found that FPAR played the largest roles in yield estimation with the highest importance value, and FPAR and LAI from late April to late May and VTCI from late March to mid-April were regarded as important features for the estimated yield with high importance value. In conclusion, our findings indicated the potential of SLTF model for winter wheat yield estimation, which contributes to promoting further application of remotely sensed technology for agricultural production.

3D CT based age estimation from the pubic symphyseal surface in an Indian population using the Chen et al. method.

The pubic symphyseal surface is one of the reliable parameters used to estimate age, as it consistently shows degenerative observational variations throughout the lifespan, particularly from the 3rd decade onwards. These changes have been extensively studied to generate population-specific models for forensic age estimation. In the past, there have been many studies used to estimate age at death from the pubis symphysis using skeletal remains. However, due to dearth of contemporary skeletal repositories, and the resource intensive maceration process required for obtaining examination quality bones, studies on cadaver are difficult to conduct. Moreover, due to recent advancements in the science of medical imaging, newer radiological modalities like computed tomography (CT) can be used to visualize previously inaccessible areas such as the pubic symphysis in cadavers and the living alike, and subsequent age estimation is feasible. Recently, Chen et al. (2008, 2011) conducted a study on the cadaveric Chinese Han population in both males and females separately by using nine morphological changes and scoring them according to the changes that occurred. The present study aimed to estimate an individual's age using CT images of the pubic symphysis, by applying the scoring method for its morphological changes given by Chen et al. The present study was conducted on 263 randomly selected participants (Males = 154, Females = 109), who came for diagnostic purposes to the hospital. The CT images of these individuals were collected after obtaining ethical approval and proper consent from the study participants. Each of the morphological indicators was assessed, and appropriate scores were given according to criteria given by Chen et al. In the present study, both linear and multiple regression models to estimate age using the pubic symphyseal morphological changes were developed. From the results of the present study, it was concluded that the Chen et al. scoring method can be used to accurately estimate age from 3DCT images of the living, and the models derived in the present study could be applicable to individuals from the Indian subcontinent.

Improved estimation of gross primary productivity (GPP) using solar-induced chlorophyll fluorescence (SIF) from photosystem II

Solar-induced chlorophyll fluorescence (SIF) contains contributions from both photosystem I (PSI) and photosystem II (PSII). In theory, SIF emitted from PSII (SIFPSII) should be extracted from at-sensor SIF to quantify photosynthetic CO2 assimilation, as PSI fluorescence yield is nearly insensitive to changes in photochemical yield. In many SIF-related studies, the fraction of chlorophyll-absorbed energy allocated to PSII (β2), a key factor controlling the flux of excitation energy for SIFPSII, is simply assigned a fixed value. However, β2 is regulated in response to variations in environmental conditions to avoid an energy imbalance between PSI and PSII. By quantifying the regulating effect of the cytochrome b6f complex (Cyt b6f) on the electron transport from PSII to PSI, and its interaction with energy dissipation in both photosystems, we develop a framework to estimate β2 and PSII fluorescence yield (ΦF2), two key determinants for SIFPSII, from SIF emission, PAR, air temperature, the maximum carboxylase activity of Rubisco (Vcmax), and the maximum activity of Cyt b6f (JCB6F_max). The framework is equipped with a two-leaf scheme, enabling us to estimate SIFPSII for sunlit and shaded leaves from top-of-canopy SIF observations (SIFTOC). Our simulation results showed that β2 and ΦF2 tend to change in opposite directions with varying PAR, making the contribution of PSII to SIFTOC relatively constant. We compare gross primary productivity (GPP) mechanistically estimated from SIFPSII obtained with fixed (GPPSIF_Fβ) and dynamic β2 (GPPSIF_Dβ) against the eddy-tower-derived GPP (GPPEC) at a winter-wheat experiment site. At a half-hourly time scale, GPPSIF_Dβ is better than GPPSIF_Fβ, showing higher correlations with GPPEC (R2 = 0.74 versus R2 = 0.64 and RMSE = 6.61 μmol m−2 s−1 versus RMSE = 7.67 μmol m−2 s−1). The study provides a practical way to estimate the contribution of SIFPSII to SIFTOC, giving a better theoretical basis to SIF-based GPP estimation models.

Estimation of potato yield using a semi-mechanistic model developed by proximal remote sensing and environmental variables

Timely monitoring of potato yield status is crucial for guiding field management and ensuring the sustainability of food trade. In recent years, non-destructive remote sensing techniques have emerged as one of the most promising methods for crop yield monitoring. However, most existing potato yield estimation models have primarily been tested at specific growth stages within a single ecosystem, highlighting the urgent need for a model that can be applied across different ecological environments. In this study, we developed a semi-physical model based on hierarchical linear modeling (HLM) to automatically correct yield estimation based on remotely sensed vegetation indices using environmentally relevant variables such as net solar radiation at the surface (ssr), air temperature at 2 m above the surface (t2m), and soil water content in the root zone (swvl). The accuracy and transferability of the model were further evaluated by comparing it with aboveground destructive sampling methods, conventional empirical models, and machine learning approaches. The results demonstrated that site-specific relationships exist between aboveground agronomic traits parameters like biomass and leaf area index (LAI) with respect to yield estimation. Conventional linear statistical and machine learning methods faced challenges in transferring their constructed yield estimation models across regions and years. However, the HLM approach exhibited excellent generalization ability across all trial samples. In the middle and later stages of potato growth, the standardized LAI determining index proved to be the most effective vegetation for predicting yield, while ssr, sktmax, and shallow swvl were identified as key environmental variables affecting yield. By integrating these variables using HLM modeling techniques, we achieved optimal generalization performance (R2 = 0.57, RMSE = 7.65 t/ha, NRMSE = 25.02 % during tuber growth stage; R2 = 0.60, RMSE = 7.37 t/ha, NRMSE = 24.13 % during starch accumulation stage). This study underscores the importance of considering environmental factors when constructing a reliable model for estimating potato yield at different spatial and temporal scales using remote sensing technology.

Estimation of chronological age of Risso’s dolphin (Grampus griseus) based on DNA methylation frequency

Age of cetaceans is an important data set for their conservation and management. Although the chronological age of a toothed whale has traditionally estimated from the number of annual tooth growth layer groups (GLGs), this method has potential difficulties such as errors due to the subjectivity of the age-readers and time-consuming sample processing, in addition to lethal tooth sampling in many cases. To overcome these difficulties through a non-lethal approach, considerable amount of efforts has been made in recent years to construct chronological age estimation models based on the correlation between chronological and biological age expressed as the frequency of DNA methylation at CpG (cytosine-phosphate-guanine) sites. The present study, by using next-generation sequencing on DNA extracted from the skin tissues of 30 individuals (15 males and 15 females), performed methylation analysis on multiple CpG sites in the three genes previously reported as age-linked in cetaceans (GRIA2, TET2, and CDKN2A) to construct an age estimation model for Risso’s dolphins. Key aspects of this study are: (1) the chronological ages of Risso’s dolphins of wild origins used in this study had been determined by the GLGs of teeth prior to this study, and (2) as Risso’s dolphins are said to have a lifespan of 30 years, samples were collected from individuals aged 1–29 years, covering from young to old ages. Among the 11 CpG sites in GRIA2, 6 CpG sites in TET2, and 7 CpG sites in CDKN2A analyzed, the CpG sites in GRIA2 showed a statistically significant correlation with age, whereas those in TET2 and CDKN2A did not show such a strong correlation. Using multiple regression analysis on the CpG sites in the three genes, the best fitted model was expressed as follows: y=-0.7548 + 5.6164x(GRIA2_CpG3)+2.6187x(TET2_CpG6)-1.5907x(CDKN2A_CpG3) (R²=0.7062, residual mean=2.98, standard deviation=2.3). With the mean error of 2.98 years between the estimated and known chronological ages, the accuracy of this model was found to be comparable to or higher than that of previously reported age estimation models for cetaceans. This study demonstrated for the future that the age of wild Risso’s dolphins can be estimated by using their skin samples collected with minimal invasiveness.

Estimating built-up area carbon emissions through addressing regional development disparities with population and nighttime light data

Carbon emission inventories in urban built-up areas are critical for formulating effective emission reduction policies. Nighttime light data, reflecting socioeconomic activities, is routinely used as a proxy for estimating emissions. However, the reliability of this proxy is limited in areas with minimal or absent lighting and demonstrates variability according to the urban development. To address these limitations, a novel approach was developed. Firstly, it enhances the representation of human activities under different light values through integrating light values and population distributions into multidimensional proxy features. Secondly, cities with different socio-economic development were clustered to minimize the development disparities within the same cluster. Four clusters were detected including ‘Agriculture-dependent & Low-density’, ‘Agriculture-dependent & High-density’, ‘Industry-oriented’, and ‘Tertiary-oriented’. Then A multilayer perceptron regressor, refined with a moving average method, was employed to model the nonlinear relationships between emissions and these proxy features. The results show a significant increase in modeling accuracy when regional development disparities are incorporated through this clustering strategy. Additionally, the Shapley Additive Explanatory method was utilized to analyze the influence of regional development heterogeneity on the estimation model. It demonstrated that areas with high light intensity and population significantly influence emission estimates in all clusters, except for the ‘Industry-oriented cluster’. This finding underscores the varying effectiveness of proxy features across different regions, emphasizing the importance of considering regional development disparities. Finally, based on the estimated inventory obtained, spatio-temporal hot spot detection pinpointed eastern and central China as significant emission hot spots. This research not only enhances the data resources for managing carbon emissions but also underscores the need for inter-city cooperation strategies to achieve China's carbon reduction targets.

A Round Trip Time Weighting Model for One-way Delay Estimation

A Round Trip Time Weighting Model for One-way Delay Estimation

The effects of non-local observations on the adjoint estimation of local model parameters: An example of Manning’s n coefficient in a tidal model over the Bohai, Yellow, and East China Seas

Accurate parameter estimation is a key issue for enhancing the performance of hydrological models. With the rapid development of satellite technology, integrating satellite data and numerical modelling for parameter estimation has gained more prominence. The limited spatial coverage of altimeters necessitates areas without direct local observations to rely only on information from nearby non-local observations. However, the relation is far from clear between non-local observations and the estimation of local model parameters. In this study, a two-dimensional adjoint tidal model over the Bohai, Yellow, and East China Seas (BYECS) is developed, assimilating observations from TOPEX/Poseidon, Jason-1, and Jason-2 altimeters in conjunction with tide-gauge stations. In twin experiments, the feasibility and reliability of utilizing non-local observations are emphasized by varying synthetic observations. The experiments also reveal how the number and distance of non-local observations affect the ill-posedness of local parameter estimation. The estimation errors can be reduced by increasing observations within a ‘critical distance’, beyond which the accuracy does not improve further. Subsequently, the robustness of ‘critical distance’ is discussed under different prescribed parameter distributions, sizes of predefined optimized area, and random observational errors, indicating that the ‘critical distance’ is approximately 1.0°-2.0°. These results provide a positive reference for practical experiment. In BYECS, the order of Manning’s n coefficient ranges from 10-4 to 10-1, with an average value of 0.0246 in shallow waters. The spatial distribution reveals 9 high-value areas, primarily modulated by a concurrence of sandy sediment and weak tidal currents. This study offers valuable insights into refining the adjoint model for physical parameter estimation, particularly in anticipation of the expanded spatial coverage of SWOT. Compared to only assimilating T/P series altimeters, incorporating SWOT reduces discrepancies by over 38%. Additionally, the spatial Manning’s n coefficient provides guidance for enhancing tidal simulation in other models.

Deep Learning Model for Estimation of LV Ejection Fraction from Echocardiogram

Heart failure, a leading global cause of death, poses challenges for early prediction of cardiac dysfunction, especially ejection fraction (EF). This study employs Convolutional Neural Networks (CNNs), utilizing ResNet and MobileNet architectures, on the CAMUS dataset with 500 patient records (2CH and 4CH). The goal is to aid healthcare professionals in accurately measuring EF. The CAMUS dataset, comprising multi-modality cardiac imaging and segmentation data, serves as the foundation. The CNN, ResNet, and MobileNet models are fine-tuned through transfer learning and their performance is evaluated based on accuracy. This comparative analysis identifies the model with the best predictive capabilities for EF, showcasing their potential for earlier diagnosis and intervention. Deep learning techniques enhance cardiac healthcare by providing reliable, noninvasive means of predicting heart failure, reducing its impact on patients and healthcare systems.

Robust clustering-based hybrid technique enabling reliable reservoir water quality prediction with uncertainty quantification and spatial analysis

Machine learning methodology has recently been considered a smart and reliable way to monitor water quality parameters in aquatic environments like reservoirs and lakes. This study employs both individual and hybrid-based techniques to boost the accuracy of dissolved oxygen (DO) and chlorophyll-a (Chl-a) predictions in the Wadi Dayqah Dam located in Oman. At first, an AAQ-RINKO device (CTD+ sensor) was used to collect water quality parameters from different locations and varying depths in the reservoir. Second, the dataset is segmented into homogeneous clusters based on DO and Chl-a parameters by leveraging an optimized K-means algorithm, facilitating precise estimations. Third, ten sophisticated variational-individual data-driven models, namely generalized regression neural network (GRNN), random forest (RF), gaussian process regression (GPR), decision tree (DT), least-squares boosting (LSB), bayesian ridge (BR), support vector regression (SVR), K-nearest neighbors (KNN), multilayer perceptron (MLP), and group method of data handling (GMDH) are employed to estimate DO and Chl-a concentrations. Fourth, to improve prediction accuracy, bayesian model averaging (BMA), entropy weighted (EW), and a new enhanced clustering-based hybrid technique called Entropy-ORNESS are employed to combine model outputs. The Entropy-ORNESS method incorporates a Genetic Algorithm (GA) to determine optimal weights and then combine them with EW weights. Finally, the inclusion of bootstrapping techniques introduces a stochastic assessment of model uncertainty, resulting in a robust estimator model. In the validation phase, the Entropy-ORNESS technique outperforms the independent models among the three fusion-based methods, yielding R2 values of 0.92 and 0.89 for DO and Chl-a clusters, respectively. The proposed hybrid-based methodology demonstrates reduced uncertainty compared to single data-driven models and two combination frameworks, with uncertainty levels of 0.24% and 1.16% for cluster 1 of DO and cluster 2 of Chl-a parameters. As a highlight point, the spatial analysis of DO and Chl-a concentrations exhibit similar pattern variations across varying depths of the dam according to the comparison of field measurements with the best hybrid technique, in which DO concentration values notably decrease during warmer seasons. These findings collectively underscore the potential of the upgraded weighted-based hybrid approach to provide more accurate estimations of DO and Chl-a concentrations in dynamic aquatic environments.

Distributed State Estimation for Mixed Delays System Over Sensor Networks With Multichannel Random Attacks and Markov Switching Topology.

This article deals with the distributed state estimation for mixed delays system under unknown attacks. A new multichannel random attack model is established for the first time, where network attacks are considered to exist in three channels: the target-to-sensor channel, the senor-to-sensor channel, and the sensor-to-estimator channel. In the above model, transmitted packets are allowed to be attacked multiple times simultaneously, and when they are successfully attacked, the transmitted information is modified. Besides, the topology of the sensor network is considered to change dynamically according to the Markov chain. Based on the newly established distributed estimation model, the estimation error system is proven to be asymptotically mean-square stable under a given H∞ antidisturbance index by using a Lyapunov theory and a stochastic analysis technique; then, the estimator parameter matrices are solved utilizing a linearization method. Finally, several simulation examples are listed to testify the effectiveness of the designed algorithm.

Estimation of the shear strength of UHPC beams via interpretable deep learning models: Comparison of different optimization techniques

In this article, optimized deep learning (DL) models with different algorithms are adopted to estimate the shear strength of rectangular ultra-high performance concrete beams (UHPC-Bs) in order to overcome the challenges in traditional mechanics-based approaches. Long short-term memory (LSTM) and gated recurrent unit (GRU) are chosen as the DL models, whereas the recent popular optimization algorithms are phasor particle swarm optimization (PPSO), dwarf mongoose optimization (DMO), mountain gazelle optimizer (MGO), and atom search optimization (ASO). A thorough and reliable dataset of 244 UHPC-Bs test results with ten input features has been used to construct the hybrid DL models. The performance of the optimized hybrid LSTM and GRU models with different algorithms is extensively assessed and compared based on various statistical metrics, error, and score analyses. Then, the model with the best estimation performance is determined and compared with the mechanics-based formulas in the current international design codes. Additionally, Shapley additive explanations (SHAP) analysis is used to assist in the interpretability of DL models and to reveal the effects of input features that contribute to the model's estimation. According to the results of the present work, all DL models successfully estimate the shear strength of UHPC-Bs. Among these models, the MGO-LSTM model stands out compared to the other models in terms of several performance measures for both the training and testing phases, like a higher R2 value, lower RMSE, MAPE, and MAE values, as well as a smaller error ratio and a higher final score. The performance of the algorithms applied to optimize the hyper-parameters of the LSTM and GRU models can be ranked as follows: MGO > DMO > PPSO > ASO. Moreover, a graphical user interface (GUI) was constructed based on the best estimation model that was built so that the shear strength of UHPC-Bs could be estimated in real-world situations without the need for any extra software or tools. This enables more users to quickly and easily estimate the shear strength of UHPC-Bs, optimize design processes, and decrease experimental testing costs.

Exploring large language model for generic and robust state-of-charge estimation of Li-ion batteries: A mixed prompt learning method

State-of-charge (SOC) estimation is important to ensure safe functioning of Li-ion batteries (LIBs). However, distinct measurements, harsh temperatures, and dynamic operations pose challenges in estimating intricate SOC changes of multiple LIBs with one estimator. Hence, this paper proposes a novel mixed prompt learning method to explore a large-scale pretrained language model (PLM) for SOC estimation. A new hard prompt generator is proposed to translate LIB data into instruction and answer text, eliciting the inherent representational capability of PLM to jointly learn the sequential patterns and contextual semantics of measurements through language modeling for accurate SOC estimation. A new soft prompt adapter is proposed to encode task-specific information of different LIBs into a small set of independent vectors, ensuring PLM adaptation with minimal parameters while maintaining good generalization. By integrating soft prompt vectors along the forward propagation, the hidden states of PLM are dynamically regulated to characterize volatile and variable SOC for robust estimation. Extensive experiments show that by leveraging mixed hard-soft prompts, PLM can make accurate, generic, and robust estimates for multiple LIBs simultaneously in subzero temperature, charge-pause-discharge, and low-capacity discharge scenarios, with the average MAE, RMSE, and MAX of all tasks as low as 1.20 %, 1.51 %, and 5.29 %, respectively.

Ray-Tracing modeling for urban photovoltaic energy planning and management

The traditional Radiative Transfer Modelling solutions for Solar Energy monitoring and forecasting often provide outputs for a single point location or an area location. However, for high resolution representation of areas these solutions suffer due to low simulation speeds. This approach makes it difficult for decision-makers to accurately estimate the solar potential of the administrative area and plan installations accordingly. In this direction, the study introduces three-dimensional Ray-Tracing based radiative modeling which is a high-speed area-based solution for solar energy monitoring. The three-dimensional ray-tracing was simulated by using advanced graphic creation platforms and cloud computing in conjunction with satellite data of the clouds, aerosols, building shadows effects and three-dimensional representations of the city using Cesium 3D tiles and Unreal Engine ®. The entire system was developed in a hybrid model to be exploited by urban planners for solar PV installations and by electricity distribution system operators for energy management and efficient incorporation of the produced energy into the regular and smart grids. This study implements and analyses this Ray-Tracing model for solar photovoltaic energy potential estimation at a rooftop level for the city of Athens, Greece. The total rooftop exploitable area in Athens was found to be close to 34 km2, which is able to massively host distributed PVs followed by almost 4.3 TWh of annually produced energy, whilst Penteli (a Municipality in Athens) possessed a potential of 96.8 GWh with an exploitable area of just 0.8 km2. This amount of energy, in a hypothetical full coverage scenario, is able to provide for 48.7% of Athens’s total energy requirement. Similar year-long simulations were conducted using the EU’s largest rooftop solar installation at Stavros Niarchos Foundation Cultural Center and randomly selected rooftops having solar installations in different municipalities in Athens. With these estimated solar potential values, the gross savings in natural gas consumption and hence the CO2 equivalent emissions can be computed. With the current estimated solar potential of Athens, the analyzed savings accounted of nearly 2.43 billion euros and 18 MT CO2 equivalent emissions. These computed annual savings are capable of covering installation costs for nearly 100,000 new solar installations. The end-product of this study is the development of a solar cadastre web tool which will support the decision-makers in the energy transition policies and the solar PV penetration into the urban environment and eventually drive the effort into renewable energy transition across the globe.