Estimation Algorithm Research Articles

Comparative study of LSTM and ANN models for power consumption prediction of variable refrigerant flow (VRF) systems in buildings

The optimized control of variable refrigerant flow (VRF) system requires an accurate time series forecast model for power consumption. Currently, physics-based and black-box models widely used for forecasting power consumption may not be able to capture the dynamic and non-linear behavior of such complex systems. This study presents a long-short-term memory (LSTM), deep learning-based model to accurately predict the power consumption of a VRF system with heat recovery units. The model training used one year of VRF system field test data. The feature selection through the Pearson correlation coefficient was implemented to improve the model's accuracy and computational efficiency. The sensitivity analysis of feature selection was performed by preparing three feature sets, including different levels of relationship with the predicted target. Additionally, the hyperparameters of the models were optimized by Bayesian optimization with the Tree-structured Parzen Estimator algorithm. The deep learning model, LSTM model, was compared to the baseline machine learning model, Artificial Neural Network (ANN) and decision tree. The results show that LSTM-30feat with input time step 4 has the best testing performance of Coefficient of the Variation of the Root Mean Square Error (CvRMSE) 23.3%. The best ANN model is ANN-10feat with input time step 8, which has a CvRMSE of 27.8% in testing and 13,569 trainable parameters. However, LSTM-10feat with input time step 4 has the CvRMSE of 24.8% in testing, and the trainable parameters are 1,809. A higher number of trainable parameters in models might result in increased memory usage on the computer and be computationally expensive.

Bolus tracking from pulsed x-ray projections: A feasibility study using a five-dimensional cardiac CT contrast dynamics model.

Cardiac computed tomography (CT) exams are some of the most complex CT exams due to the need to carefully time the scan when the heart chambers are near the peak contrast concentration. With current "bolus tracking" and "timing bolus" techniques, after contrast medium is injected, a target vessel or chamber is scanned periodically, and images are reconstructed to monitor the opacification. Both techniques have opportunities for improvement, such as reducing the contrast medium volume, the exam time, the number of manual steps, and improving the robustness of correctly timing the peak opacification. The objective of our study is to (1) develop a novel autonomous cardiac CT clinical workflow to track contrast bolus dynamics directly from pulsed x-ray projections, (2) develop a new five-dimensional virtual cardiac CT data generation tool with programmable cardiac profiles and bolus dynamics, and (3) demonstrate the feasibility of projection-domain prospective bolus tracking using a neural network trained and tested with the virtual data to find the contrast peak. In our proposed workflow, pulsed mode projections (PMPs) are acquired with a wide-open collimator under sparse view conditions (monitoring phase). Each time a new PMP is acquired, the neural network is used to estimate the contrast enhancement inside the target chambers. To train such a network, we introduce a new approach to generate clinically realistic virtual scan data based on a five-dimensional cardiac model, by synthesizing user-defined contrast bolus dynamics and patient electrocardiogram profiles. In this study, we investigated a scenario with one single PMP per rotation. To find the optimal PMP view angle, 20 angles were explored. For each angle, 300 virtual exams were generated from 115 human subject datasets and divided into training, validation, and testing groups. Twenty neural networks were trained and evaluated in total to find the optimal network. Finally, a simple bolus peak time estimation algorithm was developed and evaluated by comparing to the ground truth bolus peak time. To evaluate the accuracy of a bolus time-intensity curve estimated by the network, the cosine similarity between the estimation and the ground truth was computed. The cosine similarity was larger than 0.97 for all projection angles. A view angle corresponding to the x-ray tube at 30 degrees from vertical (left-anterior of subject) showed the lowest errors. The amplitude of the estimated bolus curves (in Hounsfield Units) was not always correctly predicted, but the shape was accurately predicted. This resulted in an RMSE of 1.23s for the left chambers and 0.78s for the right chambers in the contrast peak time estimation. In this study, we proposed an innovative real-time way to predict the contrast bolus peak in cardiac CT as well as an innovative approach to train a neural network using virtual but clinically realistic data. Our trained network successfully estimated the shape of the time-intensity curve for the target chambers, which led to accurate bolus peak time estimation. This technique could be used for autonomous diagnostic cardiac CT to trigger a diagnostic scan for optimal contrast enhancement.

Integrating clinical and genomic landscape analysis of perineural invasion identify ACTA1 as an oncogene for oral squamous cell carcinoma.

Perineural invasion (PNI) has been shown to be a key pathological feature of several types of cancer, including oral squamous epithelial carcinoma (OSCC). However, the overall clinical and genomic landscape of PNI+ OSCC are still unclear, and the molecular mechanism of PNI remains to be further investigated. 279 OSCC samples were extracted from the TCGA database and grouped according to PNI. The clinicopathological information, prognostic and survival analyses were performed. The Cibersort algorithm and ESTIMATE algorithm was used to estimate the impacts on proportion of immune cells, immune score and stromal score by PNI. Immunotherapy prediction analysis was also performed. 167 differentially expressed genes were screened for functional enrichment analysis. Actin α1 (ACTA1) protein, which was significantly upregulated in the PNI+ group, was selected for validation in our OSCC patient's cohort (n = 70). We next analyzed the ratio and absolute number of key immunocytes in peripheral blood of OSCC patients according to Actin α1 expression by flow cytometry. PNI was more likely to occur in patients with advanced tumors and worse prognosis. Immunomodulation analyses showed that T cells follicular helper and cells were significantly lower, but M2 macrophages and total stromal score was significantly higher in PNI+ OSCC. Immunotherapy prediction analyses showed that PNI+ OSCC may be more sensitive to CTLA4 inhibitor treatment. 167 differentially expressed genes were identified and enriched in muscle structure and cell movement-related pathway. Among them, Actin α1 (ACTA1) was significantly upregulated in PNI+ advanced OSCC with worse clinical outcome whose had relatively low ratio of CD3+CD8+ circulating cytotoxic T cells. PNI+ OSCC patients with upregulated of Actin α1 could benefit from cytotoxic T cell-mediated immunotherapy.

Investigation of laser phase noise tolerance in simplified coherent PON with subcarrier multiplexing

In this paper, we experimentally investigate the laser phase noise tolerance for a 100 Gb/s/λ coherent passive optical network (PON) with simplified optical network units (ONUs) transceivers when distributed feedback (DFB) laser is used as the local oscillator (LO). In the proposed scheme, the digitally subcarrier-multiplexed (DSCM) signals are generated in the coherent transmitter at the optical line terminal (OLT) side based on Alamouti encoding in two polarizations and received by a single-polarization heterodyne receiver at the ONU side. The experimental results show that the power budget can achieve 34.2 dB and 33.9 dB after a 25 km standard single-mode fiber (SSMF) link when external cavity laser (ECL) and DFB lasers are used as the LOs at the ONU side. Polarization and carrier phase tracking schemes for the DSCM systems based on frequency domain pilot tones were used in digital signal process (DSP). At the same time, the frequency offset estimation and phase noise compensation algorithms are conducted using residual carriers. By choosing an appropriate width for the low-pass filter, the optimal performance for the phase noise compensation can be achieved. The pre-equalization operation at the OLT side is also verified for the subcarrier-multiplexed signals to provide better and flatter performances.

Estimation of Lower Limb Joint Angles Using sEMG Signals and RGB-D Camera.

Estimating human joint angles is a crucial task in motion analysis, gesture recognition, and motion intention prediction. This paper presents a novel model-based approach for generating reliable and accurate human joint angle estimation using a dual-branch network. The proposed network leverages combined features derived from encoded sEMG signals and RGB-D image data. To ensure the accuracy and reliability of the estimation algorithm, the proposed network employs a convolutional autoencoder to generate a high-level compression of sEMG features aimed at motion prediction. Considering the variability in the distribution of sEMG signals, the proposed network introduces a vision-based joint regression network to maintain the stability of combined features. Taking into account latency, occlusion, and shading issues with vision data acquisition, the feature fusion network utilizes high-frequency sEMG features as weights for specific features extracted from image data. The proposed method achieves effective human body joint angle estimation for motion analysis and motion intention prediction by mitigating the effects of non-stationary sEMG signals.

Chromatic dispersion-aware Tx and LO laser phase noise independent estimation enabled by dual pilot tones in DSCM systems

In the backbone networks employing high modulation formats such as 64QAM and metropolitan area networks, data center interconnection networks using the distributed feedback (DFB) lasers with several megahertz laser linewidths dramatically degrades system performance in the equalization enhanced phase noise (EEPN). Even though digital subcarrier multiplexing (DSCM) systems are known for their tolerance to EEPN, they still cause performance degradation in this case. Therefore, the EEPN mitigation algorithm becomes an indispensable part of DSP algorithms in DSCM systems. A dual pilot tone-based chromatic dispersion-aware transmitter and local oscillator laser phase noise independent estimation algorithm is proposed in this paper to solve the above problem. Simulations/offline experiment results under 5 MHz laser linewidth and 1000/800 km transmission indicate that the proposed algorithm could bring about 1/0.6 dB improvement of the required SNR for the normalized generalized mutual information of 0.9 compared with the blind phase searching algorithm.

Carrier Phase-Based Underwater Source Localization for Ultrashort Baseline

In this paper, we propose a phase-based pseudorange estimation and source localization algorithm to improve the localization performances of ultrashort baseline (USBL) systems. The conventional USBL system estimates pseudorange through cross-correlation of received chirps. However, due to the limited sampling rate, precise pseudorange cannot be estimated, resulting in low localization performance. The proposed method calculates the number of wavelengths between the transducer and receiver and detects the initial phase to estimate the pseudorange more accurately than the conventional method. It also improves localization performance by estimating and compensating for phase variations by underwater channels. The source localization performances of the proposed method and the conventional methods were compared and analyzed through computer simulations and ocean experiments, and the proposed method had better localization performances than the conventional methods.

Distributed adaptive moving horizon estimation for multi-sensor networks subject to quantization effects

This paper investigates the distributed state estimation problem for multi-sensor networks with quantized measurements. Within the Bayesian framework, a distributed adaptive moving horizon estimation algorithm is developed. Unlike the existing methods regarding quantized errors roughly as bounded uncertainties, the posterior distributions of the errors are demanded to be derived. To overcome the difficulty of evaluating the posterior distributions for series of the states and quantized errors jointly, the variational Bayesian methodology is adopted to approximate the true distributions. Based on the fixed-point iteration method, the update rules are analytically derived, with the convergence criterion provided. Furthermore, by incorporating the average consensus algorithm into the prediction process, all sensors can achieve consensus on their estimates in a distributed manner. Finally, a numerical example of target tracking under logarithmic and uniform quantization effects is given to illustrate the validity of the proposed algorithm.

Holistic Sensitivity Analysis for Long-Term Energy Demand Prediction of Battery Electric Vehicles

AbstractAccurate and robust range estimation algorithms for battery electric vehicles have the potential to reduce range anxiety, increase the acceptance of lower-range vehicles, and improve the overall driving experience. However, developing such algorithms faces challenges due to the complexity of the driver-vehicle-environment system and the multitude of factors influencing a vehicle's energy demand. To address these challenges, this paper introduces a sensitivity analysis focused on driver- and environment-related factors, which are notably difficult to predict. Employing a global sensitivity analysis for factor prioritization, this study delineates and assesses the parameters and their value distributions using a validated vehicle simulation model. The co-simulation of a powertrain and an auxiliaries model enables the parameter-specific investigation of parameters related to the thermal system. The results are scenario-individual parameter rankings that show the importance of the considered factors in prediction algorithms and guide the strategy for the development of these algorithms. The acceleration behavior of the driver, often emphasized in literature, is shown to be of secondary importance to energy consumption. Moreover, factors such as air density and wind speed are identified as crucial in highway driving scenarios, whereas outside temperature and the probability of stopping at traffic lights are critical in urban settings. For validation purposes, the resulting rankings of the sensitivity study are validated by means of a convergence analysis.

An approach for coherent periodogram averaging of tilt-series data for improved CTF estimation.

Cryo-electron microscopy (cryo-EM) has become an indispensable technique for determining three-dimensional structures of biological macromolecules. A critical aspect of achieving high-resolution cryo-EM reconstructions is accurately determining and correcting for the microscope's contrast transfer function (CTF). The CTF introduces defocus-dependent distortions during imaging; if not properly accounted for, the CTF can distort features in and limit the resolution of 3D reconstructions. For tilt-series data used in cryo-electron tomography (cryo-ET), CTF estimation becomes even more challenging due to the tilt of the specimen, which introduces a defocus gradient across the field of view, as well as the low dose and signal in individual tilt images. Here, we describe a simple algorithm to improve the accuracy of CTF estimation of tilted images by leveraging the tilt-series alignment parameters determined for tomographic reconstruction to explicitly account for the tilted specimen geometry. In brief, each tilt image is divided into patches, each of which are then stretched according to their defocus shift. These are then summed to provide a coherent power spectra at the tilt axis, which can then be used in standard CTF estimation algorithms. This uses all the data in each image to enhance the visibility of Thon rings, thereby improving high-resolution CTF estimation and subsequent enhancements in the resolution of subtomogram averages.

In Operando Health Monitoring for Lithium-Ion Batteries in Electric Propulsion Using Deep Learning

Battery management systems (BMSs) play a vital role in understanding battery performance under extreme conditions such as high C-rate testing, where rapid charge or discharge is applied to batteries. This study presents a novel BMS tailored for continuous monitoring, transmission, and storage of essential parameters such as voltage, current, and temperature in an NCA 18650 4S lithium-ion battery (LIB) pack during high C-rate testing. By incorporating deep learning, our BMS monitors external battery parameters and predicts LIB’s health in terms of discharge capacity. Two experiments were conducted: a static experiment to validate the functionality of BMS, and an in operando experiment on an electrically propelled vehicle to assess real-world performance under high C-rate abuse testing with vibration. It was found that the external surface temperatures peaked at 55 °C during in operando flight, which was higher than that during static testing. During testing, the deep learning capacity estimation algorithm detected a mean capacity deviation of 0.04 Ah, showing an accurate state of health (SOH) by predicting the capacity of the battery. Our BMS demonstrated effective data collection and predictive capabilities, mirroring real-world conditions during abuse testing.

Association between Drug Use and Perception of Mental Health in Women Diagnosed with Fibromyalgia: An Observational Study.

Fibromyalgia (FM) is a chronic syndrome characterized by widespread musculoskeletal pain, fatigue, sleep disturbances, and mental health issues. It affects approximately 1.78% of the general population; an estimated 4:1 ratio between women and men is observed. It significantly impacts quality of life and carries both clinical and social stigma. This study aims to evaluate the relationship between drug use and mental health in female patients with fibromyalgia. This study is prospective, observational, and cross-sectional. A questionnaire was administered to 544 subjects, achieving a representative sample size from a population of 800,000 subjects by using an algorithm for proportion estimation with a known sampling frame. The selection was non-random, making the sampling non-probabilistic. Logistic regression models were applied to assess the effect of drug use on perception of mental health; presence of symptoms such as comprehension and memory problems, insomnia, depression, and anxiety; and severity of cognitive symptoms and non-restorative sleep. To quantify the impact, odds ratios and confidence intervals have been observed. The findings indicate the non-recommended use of medications and reveal the ineffectiveness and adverse effects of drug interactions on mental health. The use of benzodiazepines and sedative-hypnotics is significantly associated with a negative perception of mental health. Benzodiazepines do not improve symptoms or significantly reduce their severity. SSRI antidepressants do not enhance mental health perception; however, when used exclusively, they are effective in reducing the severity, but not the prevalence, of cognitive symptoms. The results highlight the complexity of pharmacological management in FM and raise concerns about the inappropriate use of ineffective or counterproductive drug interactions affecting patients' mental health. They underscore the need for multidisciplinary and personalized strategies that include close and careful monitoring, as well as the simultaneous use of non-pharmacological treatments that have demonstrated evidence in improving quality of life without negatively affecting mental health, such as patient education, psychological therapy, physiotherapy, and mindfulness.

Plasma metabolomics profiles and breast cancer risk

BackgroundBreast cancer (BC) is the most common cancer in women and incidence rates are increasing; metabolomics may be a promising approach for identifying the drivers of the increasing trends that cannot be explained by changes in known BC risk factors.MethodsWe conducted a nested case–control study (median followup 6.3 years) within the New York site of the Breast Cancer Family Registry (BCFR) (n = 40 cases and 70 age-matched controls). We conducted a metabolome-wide association study using untargeted metabolomics coupling hydrophilic interaction liquid chromatography (HILIC) and C18 chromatography with high-resolution mass spectrometry (LC-HRMS) to identify BC-related metabolic features.ResultsWe found eight metabolic features associated with BC risk. For the four metabolites negatively associated with risk, the adjusted odds ratios (ORs) ranged from 0.31 (95% confidence interval (CI): 0.14, 0.66) (L-Histidine) to 0.65 (95% CI: 0.43, 0.98) (N-Acetylgalactosamine), and for the four metabolites positively associated with risk, ORs ranged from 1.61 (95% CI: 1.04, 2.51, (m/z: 101.5813, RT: 90.4, 1,3-dibutyl-1-nitrosourea, a potential carcinogen)) to 2.20 (95% CI: 1.15, 4.23) (11-cis-Eicosenic acid). These results were no longer statistically significant after adjusting for multiple comparisons. Adding the BC-related metabolic features to a model, including age, the Breast and Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm (BOADICEA) risk score improved the accuracy of BC prediction from an area under the curve (AUC) of 66% to 83%.ConclusionsIf replicated in larger prospective cohorts, these findings offer promising new ways to identify exposures related to BC and improve BC risk prediction.

Gridless DOA Estimation Method for Arbitrary Array Geometries Based on Complex-Valued Deep Neural Networks

Gridless direction of arrival (DOA) estimation methods have garnered significant attention due to their ability to avoid grid mismatch errors, which can adversely affect the performance of high-resolution DOA estimation algorithms. However, most existing gridless methods are primarily restricted to applications involving uniform linear arrays or sparse linear arrays. In this paper, we derive the relationship between the element-domain covariance matrix and the angular-domain covariance matrix for arbitrary array geometries by expanding the steering vector using a Fourier series. Then, a deep neural network is designed to reconstruct the angular-domain covariance matrix from the sample covariance matrix and the gridless DOA estimation can be obtained by Root-MUSIC. Simulation results on arbitrary array geometries demonstrate that the proposed method outperforms existing methods like MUSIC, SPICE, and SBL in terms of resolution probability and DOA estimation accuracy, especially when the angular separation between targets is small. Additionally, the proposed method does not require any hyperparameter tuning, is robust to varying snapshot numbers, and has a lower computational complexity. Finally, real hydrophone data from the SWellEx-96 ocean experiment validates the effectiveness of the proposed method in practical underwater acoustic environments.

Eco-Friendly Route Planning Algorithms: Taxonomies, Literature Review and Future Directions

Eco-friendly navigation (a.k.a. eco-routing) finds a route from A to B in a road network that minimizes the greenhouse gas (GHG) emission or fuel/energy consumption of the traveling vehicle. As road transport is a major contributor to GHG emissions, eco-routing has received considerable research attention in the past decade, mainly on two research themes: (1) developing models to estimate emissions or fuel/energy consumption of vehicles; and (2) developing algorithms to find eco-friendly routes for a vehicle. There are some excellent literature reviews that cover the existing estimation models. However, there is no literature review on eco-friendly route-planning algorithms. This article fills this gap and provides a systematic literature review in this area. From mainstream online databases, we obtained 2,494 articles and shortlisted 76 articles using our exclusion criteria. Accordingly, we establish a holistic view of eco-routing systems and define five taxonomies of estimation models, eco-routing problems and algorithms, vehicle types, traffic, and road network characteristics. Concerning the taxonomies, we categorize and review the shortlisted articles. Finally, we highlight research challenges and outline future directions in this important area.

Innovation Adaptive UKF Train Location Method Based on Kinematic Constraints

To address the issue of reduced positioning accuracy caused by satellite signal interruptions when trains pass through long tunnels, a novel train positioning method based on an innovative adaptive unscented Kalman filter (UKF) under kinematic constraints is proposed. This method aims to improve the accuracy of the location of trains during operation. By considering the dynamic characteristics of the train, a dynamic kinematic-constrained inertial navigation system (INS)/odometer (ODO) combination positioning system is established. This system utilizes kinematic constraints to correct the accumulated errors of the INS. Additionally, the algorithm incorporates real-time estimation of the measurement noise covariance using innovation sequences. The updated adaptive estimation algorithm is applied within the UKF framework for nonlinear filtering, forming the innovative adaptive UKF algorithm. At each time step, the difference between the ODO sensor data and the INS output is used as the measurement input for the innovative adaptive UKF algorithm, enabling global estimation. This process ultimately yields the actual positioning result for the train. Simulation results demonstrate that the innovative adaptive UKF train positioning method, incorporating kinematic constraints, effectively mitigates the impact of satellite signal interruptions. Compared with the traditional INS/ODO positioning method, the innovative adaptive UKF method reduces position errors by 34.35% and speed errors by 36.33%. Overall, this method enhances navigation accuracy, minimizes train positioning errors, and meets the requirements of modern train positioning systems.

Time trends in anxiety disorders incidence across the BRICS: an age-period-cohort analysis for the GBD 2021.

Anxiety disorders are a significant global mental health concern, contributing to substantial disability-adjusted life years (DALYs) and imposing considerable social and economic burdens. Understanding the epidemiology of anxiety disorders within the BRICS nations (Brazil, Russian Federation, India, China, and South Africa) is essential due to their unique socio-economic landscapes and ongoing transformations. This study utilized data from the Global Burden of Disease (GBD) 2021 database to evaluate anxiety disorder incidence trends in BRICS countries from 1992 to 2021. The Age-Period-Cohort (APC) model with an intrinsic estimator (IE) algorithm was employed to disentangle the effects of age, period, and cohort on incidence rates. Data were categorized into 5-year age groups, and 95% uncertainty intervals (UIs) were calculated to account for data variability. From 1992 to 2021, the global number of anxiety disorders cases increased by 73.44%, with age-standardized incidence rates rising by 21.17%. Among BRICS nations, India experienced the largest increase in cases (113.30%), while China had the smallest increase (2.79%). Globally, young (15-49 years) and oldest (80-94 years) age groups showed predominantly positive local drift values, indicating rising incidence rates. Brazil and India mirrored this trend, while China and South Africa mostly exhibited negative local drift values. Russia Federation had mixed trends with younger groups showing negative and older groups positive local drift values. The incidence of anxiety disorders exhibited an "M-shaped" age pattern with peaks at 10-14 and 35-39 years. Period effects were stable globally but varied in BRICS countries, with Brazil showing a decline and India an increase. Cohort effects were stable globally but showed increasing trends in Brazil and India post-1955-1959 cohort. This study highlights a significant increase in anxiety disorders incidence globally and within BRICS nations over the past three decades, with marked variations across countries. The distinct trends observed in age, period, and cohort effects call for age-specific and gender-sensitive mental health policies. Continuous monitoring, research, and tailored public health strategies are essential to address the rising burden of anxiety disorders and improve mental health outcomes in these rapidly evolving regions.

MSAO-EDA: A Modified Snow Ablation Optimizer by Hybridizing with Estimation of Distribution Algorithm.

Metaheuristic algorithms provide reliable and effective methods for solving challenging optimization problems. The snow ablation algorithm (SAO) performs favorably as a physics-based metaheuristic algorithm. Nevertheless, SAO has some shortcomings. SAO is overpowered in its exploitation, has difficulty in balancing the proportion of global and local search, and is prone to encountering local optimum traps when confronted with complex problems. To improve the capability of SAO, this paper proposes a modified snow ablation algorithm hybrid distribution estimation algorithm named MSAO-EDA. In this work, a collaborative search framework is proposed where SAO and EDA can be organically integrated together to fully utilize the exploitation capability of SAO and the exploration capability of EDA. Secondly, an offset EDA approach that combines the optimal solution and the agent itself is used to replace SAO's exploration strategy for the purpose of enhancing SAO's exploration capability. Finally, the convergence of SAO is accelerated by selecting the next generation of agents through a greedy strategy. MSAO-EDA is tested on the CEC 2017 and CEC 2022 test suites and compared with EO, RIME, MRFO, CFOA, and four advanced algorithms, AFDBARO, CSOAOA, EOSMA, and JADE. The experimental results show that MSAO-EDA has excellent efficiency in numerical optimization problems and is a highly competitive SAO variant.

An explainable hybrid framework for estimating daily reference evapotranspiration: Combining extreme gradient boosting with Nelder-Mead method

Accurate estimation of reference evapotranspiration (ETo) is essential for effective water resources management, irrigation system design, and various hydrological and agricultural applications. This study employed extreme gradient boosting (XGBoost) model, signal decomposition techniques, and XGBoost coupled with Nelder–Mead (NM) method to enhance ETo prediction across two meteorological stations in Iran. This study proposed a novel framework which lies in its comprehensive integration of advanced techniques to create a model that is both interpretable and highly accurate for ETo estimation. For this aim, sixty meteorological variables were categorized into solar and cloud-based, temperature-based, wind and humidity-based, and pressure-based groups to analyze their effect on ETo estimation. Feature selection methods, including the Gradient Boosting Machine, Kendall’s Tau, and Relief Algorithm, were employed to identify the most influential predictors. Variables with normalized weights equal to or greater than 0.9 were selected for model input, resulting in the top 10% of variables being utilized. The XGBoost models were then developed using these selected inputs (level 1), a wavelet-based hybrid was developed according to the most effective features (level 2), and the XGBoost model was coupled by NM algorithm (level 3) for ETo estimation. Results of estimated ETo by levels 1 to 3 were compared with four common empirical approaches. The results indicated that Kendall’s Tau-based feature selection provided the most accurate predictions in Shiraz, achieving an RMSE of 0.721 (mm/day) for solar and cloud-based variables during the test phase. Additionally, the application of wavelet analysis further refined the model inputs, which enhanced ETo estimation in most variable groups. Integrating the NM algorithm with XGBoost demonstrated significant improvements in ETo estimation, where it could improve RMSE to 0.091 and 0.155 (mm/day) for testing section in Fasa and Shiraz, respectively.

Mitigating noise in digital and digital–analog quantum computation

Noisy Intermediate-Scale Quantum (NISQ) devices lack error correction, limiting scalability for quantum algorithms. In this context, digital-analog quantum computing (DAQC) offers a more resilient alternative quantum computing paradigm that outperforms digital quantum computation by combining the flexibility of single-qubit gates with the robustness of analog simulations. This work explores the impact of noise on both digital and DAQC paradigms and demonstrates DAQC’s effectiveness in error mitigation. We compare the quantum Fourier transform and quantum phase estimation algorithms under a wide range of single and two-qubit noise sources in superconducting processors. DAQC consistently surpasses digital approaches in fidelity, particularly as processor size increases. Moreover, zero-noise extrapolation further enhances DAQC by mitigating decoherence and intrinsic errors, achieving fidelities above 0.95 for 8 qubits, and reducing computation errors to the order of 10−3. These results establish DAQC as a viable alternative for quantum computing in the NISQ era.