Minimum Root Mean Research Articles

Lithium-Ion Battery Degradation and Capacity Prediction Model Considering Causal Feature

Accurate life prediction of lithium-ion batteries is essential for the safety and reliability of smart electronic devices, and data-driven methods are one of the mainstream methods nowadays. However, existing prediction methods suffer from the problems such as lack of practical meaning of features and insufficient interpretability. To address this problem, this article proposes a battery degradation and capacity prediction model based on the Granger causality (GC) test and the long short-term memory network. First, initial health indicators are set from the monitoring data of the battery. Second, the vector autoregressive model and the GC test are used to select causal features that are associated with capacity degradation. Then, the impulse response analysis approach is proposed for the first time to analyze the exact influence of the features on capacity degradation and combine the battery aging mechanism, further clarifying the interpretability of the selected features. Finally, using the causal features as model input, a prediction model based on the long short-term memory network is constructed. The experimental results of the two datasets show that the minimum root mean square error is 0.0093 Ah and 0.9635 mAh with the mean relative errors of 0.25% and 0.13%, which verifies the validity and accuracy of the proposed method.

Predicting Patient Wait Times by Using Highly Deidentified Data in Mental Health Care: Enhanced Machine Learning Approach.

BackgroundWait times impact patient satisfaction, treatment effectiveness, and the efficiency of care that the patients receive. Wait time prediction in mental health is a complex task and is affected by the difficulty in predicting the required number of treatment sessions for outpatients, high no-show rates, and the possibility of using group treatment sessions. The task of wait time analysis becomes even more challenging if the input data has low utility, which happens when the data is highly deidentified by removing both direct and quasi identifiers.ObjectiveThe first aim of this study was to develop machine learning models to predict the wait time from referral to the first appointment for psychiatric outpatients by using real-time data. The second aim was to enhance the performance of these predictive models by utilizing the system’s knowledge while the input data were highly deidentified. The third aim was to identify the factors that drove long wait times, and the fourth aim was to build these models such that they were practical and easy-to-implement (and therefore, attractive to care providers).MethodsWe analyzed retrospective highly deidentified administrative data from 8 outpatient clinics at Ontario Shores Centre for Mental Health Sciences in Canada by using 6 machine learning methods to predict the first appointment wait time for new outpatients. We used the system’s knowledge to mitigate the low utility of our data. The data included 4187 patients who received care through 30,342 appointments.ResultsThe average wait time varied widely between different types of mental health clinics. For more than half of the clinics, the average wait time was longer than 3 months. The number of scheduled appointments and the rate of no-shows varied widely among clinics. Despite these variations, the random forest method provided the minimum root mean square error values for 4 of the 8 clinics, and the second minimum root mean square error for the other 4 clinics. Utilizing the system’s knowledge increased the utility of our highly deidentified data and improved the predictive power of the models.ConclusionsThe random forest method, enhanced with the system’s knowledge, provided reliable wait time predictions for new outpatients, regardless of low utility of the highly deidentified input data and the high variation in wait times across different clinics and patient types. The priority system was identified as a factor that contributed to long wait times, and a fast-track system was suggested as a potential solution.

Adjustment Method of “FAST” Active Reflector Based on Optimal Fitting Strategy

The adjustment method of the fast active reflector of “Chinese heavenly eye” is studied. Firstly, this paper studies the offset characteristics of fast main cable node position, combined with the position of the celestial body to be measured, the follow-up coordinate system is established, and the optimal fitting model of active reflector adjustment based on discrete main cable node is established by using the idea of optimal fitting of the ideal surface. Secondly, the genetic algorithm is used to solve the minimum root mean square error (RMSE). The offset of the triangular reflector is driven by the offset of the main cable node, so that the working area is closer to the ideal paraboloid, and the maximum electromagnetic wave signal receiving ratio is achieved. Finally, rotate the coordinate data of each main cable node according to the known celestial body angle and use the Lagrange operator method to obtain the shortest distance from the actual offset point to the ideal paraboloid as the objective function, with the radial expansion range of the actuator and the variation range of the distance between adjacent points as constraints, and the size of the electromagnetic wave contact area is the basis for judging the amount of information, and a reflector adjustment model for the optimal displacement strategy of discrete main cable nodes is established. Through the test, concluded that the optimal fitting strategy is ideal, the model can accurately obtain the fast active reflector adjustment method under the constraint conditions. Through the test, the conclusion that the optimal fitting strategy is ideal is obtained, and the fast active reflector adjustment method that the model can accurately obtain under the constraints is verified.

Application of Suggested Three Parameters Collective Rotational Model to Superdeformed Thallium Odd-Mass Nuclei

The superdeformed rotational bands (SDRB’s) of axial symmetric Tl odd-A nuclei are described within the framework of the suggested model as an extended version of Bohr-Moltelson (BM) model. The suggested model has three parameters rather than the BM model’s two parameters. The model is employed to calculated the transition energies and therefore the unknown level spins within the three pairs of signature partners 191Tl (SD1, SD2), 193Tl (SD1, SD2) and 195Tl (SD1, SD2). The optimized model parameters and therefore the unknown spins for every band are adjusted by employing a computer simulated search program to induce a minimum root mean square deviation between the calculated theoretical and experimental transition energies Eγ (I). The most effective adopted model parameters and spins are wont to calculate the kinematic J (1) and dynamic J (2) moments of inertia, and rotational frequency ħω,. The calculated results agree excellently with the experimental ones. The behaviour of J (1) and J (2) with ħω is examined and discussed. Also, the calculated transition energies and spins are accustomed investigate and exhibit the ΔI = 1 staggering effects in transition energies between each pair of the signature partners. This can be done by considering three staggering indices looking on the dipole γ-transitions between the 2 bands of the signature partners and therefore the quadrupole γ-transitions within each band. All the studied three signature partner pairs showed an oversized amplitude staggering pattern. The ΔI = 1 energy staggering also appears within the transition energies after subtracting a rigid rotor reference when plotted versus spin. The phenomenon of identical bands (IB’s) is additionally investigated within the two pairs [193Tl (SD1), 195Tl (SD1)] and [193Tl (SD2), 195Tl (SD2)] by using the concept of incremental alignment.

A new hybrid method to estimate the single-diode model parameters of solar photovoltaic panel

Today, photovoltaic (PV) panels represent a large part of total power generation. Photovoltaic cells and modules parameter estimation is a relevant field of research that plays a critical role in PV system modeling and simulation. This paper presents a new simple and accurate hybrid method to estimate the five parameters of the single-diode model. The proposed method aims to build a set of equations as functions of the five unknown parameters based on the three remarkable points and the PV datasheet's information. These equations will be used to derive a closed form expression for I0, Iph, Rsh, and Rs. This paper also presents a new simple iterative approach to better estimate the fifth parameter, the ideality factor (n), using only datasheet information. The novelty of this study is to use a new effective simple hybrid method that combines the analytical and the iterative approaches based on the increment of the ideality factor by step of 0.01Vt to achieve the minimum Root Mean Square Error possible. The results reveal that the proposed method outperforms a large number of analytical, numerical, and even the most powerful meta-heuristic algorithms in terms of accuracy, simplicity and reliability.

New Generalized Regression Estimators Using a Ratio Method and Its Variance Estimation for Unequal Probability Sampling without Replacement in the Presence of Nonresponse

One of the most important problems for planning in economics is that reliable data can be difficult to obtain either because it has not been recorded or because of nonresponse in surveys. This paper is aimed at proposing new generalized regression estimators using the ratio method of estimation for estimating population mean and population total and also variance estimators of the proposed generalized regression estimators in the presence of uniform nonresponse of a study variable. We show in theory that the proposed estimators are almost unbiased under unequal probability sampling without replacement when nonresponse occurs in the study. In the simulation studies, the performances of the proposed estimators were better when compared to the existing ones in terms of minimum relative bias and relative root mean square error. In an application to Thai maize in Thailand with 2019 data, we can see that the proposed estimators gave smaller variance estimates when compared to the existing estimators

A novel method of curvature demodulation for Mach-Zehnder interferometer optical fiber curvature sensors

This paper constructs a novel curvature demodulation method for Mach-Zehnder interferometer (MZI) optical fiber sensors. The method is composed of two parts: spectral curve decomposition and support vector machine regression (SVR) of curvature. The authors fabricated the MZI fiber optic curvature sensor and carried out curvature loading experiments. The curvature demodulation method proposed in this paper includes the following steps: spectral data acquisition, data normalization, coefficient vectors calculation, and curvature calculation. The minimum root mean square errors (RMSE) of the curvature demodulation method is 0.02133 m−1. This method has two characteristics: wide curvature demodulation range and unitive curvature regression expression. The curvature demodulation method is not only limited to the MZI sensor curvature demodulation but also applicable to the demodulation of other physical quantities with the spectral data as input. This paper provides a new idea for solving similar demodulation problems.

Building a model for choosing a strategy for reducing air pollution based on data predictive analysis

This paper formalizes the model of choosing a strategy for reducing air pollution in an urban environment. The model involves determining the optimal location of biotechnological systems – biotechnological filter systems or smart air purification devices based on solving the problem of discrete optimization, taking into consideration the forecast of the air quality index. Two subtasks have been formalized, which make it possible to form a strategy for reducing air pollution. To solve one of the subtasks, a combined selective model for predicting the time series of the Air Quality Index (CSM) was built. The combined model software suite consists of the EMD-ESM hybrid model (Empirical Mode Decomposition-Exponential Smoothing Model), the HWM additive model (Holt-Winters Model), and the adaptive TLM (Trigg-Lich Model). To verify the proposed combined selective model, the time series of air quality indices (AQI) for the city of Nur-Sultan (data from 2010‒2021, period 6 hours) were selected. As a result of verification, it was established that in the case of short-term forecasting of the air quality index time series, the EMD-ESM model has an advantage according to the criterion of a minimum root mean square error (RMSE), δ=0.11. For the case of medium-term forecasting of 3<τ≤5, the combined selective model (CSM) has the advantage. The results reported here are input data for the task of choosing strategies for reducing the volume of air pollution in the urban environment. The study’s results make it possible to increase the flexibility of the formation of strategies for reducing air pollution since they avoid restrictions on the location of cleaners in specific urban areas. The consequence is the improvement of the environmental situation in the city and the development of the region in general

Neural network estimations of annealed and non-annealed Schottky diode characteristics at wide temperatures range

In this study, Artificial Neural Network (ANN) model has been proposed to characterize the annealed and the non-annealed Schottky diode from experimental data. The experimental current values of Ni/n-type 6H–SiC Schottky diode for the voltages applied to the diode terminal starting from 80 K with 20 K steps up to 500 K temperature were measured for both non-annealed and annealed Schottky diodes. The applied voltage has been varied starting from -2 V with 10 mV steps up to +2 V for each temperature value. The modeling performance has been assessed according to the varying number of neurons in the hidden layer, starting from 5 to 50 neurons, thereafter the optimum number of neurons has been obtained for both annealed and non-annealed ANN models. The minimum Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) indices values for both annealed and non-annealed diodes have been obtained with 40 neurons for both the training and test phase.

Optimum parametrization of the soil conservation service (SCS) method for simulating the hydrological response in arid basins

The use of the soil conservation service (SCS) curve number (CN) model for estimation of the rainfall excess and the SCS-unit hydrograph (UH) model are common tools for flood studies in arid regions. In this research, we are investigating the capability of these models to simulate flood events in the arid region under the common parametrization provided by the SCS model (SCS-CN, the initial abstraction ratio, λ, and UH theory) and the optimum parameterization for best simulating the hydrologic response. A case study is performed in Al-Lith basin in the west of Saudi Arabia (SA). The study simulates measured rainfall-runoff events in the area using seven scenarios (various SCS-CN estimation methods: least-squares method (CNLSM), asymptotic fitting method (CN∞), SCS-CN tables (CNdesign), and antecedent moisture content CN (CNI, CNII, and CNIII), λ = 0.2 and 0.01, and SCS-UH and UH derived from streamflow data) and a comparison is made between the observations and model results under the common parameterization of the SCS model and parameterization estimated from the Saudi arid environment. The comparison between simulated and observed peak flow and runoff volume of the studied events shows high scatter which is a common feature in arid regions due to the inherent uncertainties in the hydrological processes which are not yet resolved due to the lack of detailed measurements of the rainfall-runoff processes. Statistical analysis showed that λ = 0.01 provides a minimum root mean square error (RMSE) in the peak flow (24.8 m3/s) and the runoff volume (0.31 million m3) with CNLSM obtained by LSM. CN∞ is bad to simulate the hydrologic response. The SCS-CN Tables cannot be used for hydrological simulation. They can rather be used for the design purposes of mitigation structures.

Model Selection Using K-Means Clustering Algorithm for the Symmetrical Segmentation of Remote Sensing Datasets

The importance of unsupervised clustering methods is well established in the statistics and machine learning literature. Many sophisticated unsupervised classification techniques have been made available to deal with a growing number of datasets. Due to its simplicity and efficiency in clustering a large dataset, the k-means clustering algorithm is still popular and widely used in the machine learning community. However, as with other clustering methods, it requires one to choose the balanced number of clusters in advance. This paper’s primary emphasis is to develop a novel method for finding the optimum number of clusters, k, using a data-driven approach. Taking into account the cluster symmetry property, the k-means algorithm is applied multiple times to a range of k values within which the balanced optimum k value is expected. This is based on the uniqueness and symmetrical nature among the centroid values for the clusters produced, and we chose the final k value as the one for which symmetry is observed. We evaluated the proposed algorithm’s performance on different simulated datasets with controlled parameters and also on real datasets taken from the UCI machine learning repository. We also evaluated the performance of the proposed method with the aim of remote sensing, such as in deforestation and urbanization, using satellite images of the Islamabad region in Pakistan, taken from the Sentinel-2B satellite of the United States Geological Survey. From the experimental results and real data analysis, it is concluded that the proposed algorithm has better accuracy and minimum root mean square error than the existing methods.

Mayfly Optimization Algorithm–Based PV Cell Triple-Diode Model Parameter Identification

The maximum power output and control optimization analysis of photovoltaic (PV) systems are based on accurate and reliable PV cell parameter identification. However, its difficult problems such as high nonlinearity and multimodality have become obstacles to the traditional optimization methods to obtain accurate and efficient results. This study uses a new intelligent optimization algorithm called the mayfly algorithm (MA) to efficiently identify the triple-diode model (TDM) of PV cells and uses the minimum root mean square error (RMSE) as the evaluation index to verify the effectiveness of the algorithm. Moreover, by continuously adjusting the parameters, population number, and iteration times of the MA to better balance the relationship between global development and local optimization, we can obtain more efficient and better optimization results. The research case shows that the MA is superior to other meta-heuristic algorithms in the accuracy and stability of PV cell parameter identification. For example, the minimum standard deviation (SD) of the RMSE obtained by the MA is 1,305 times smaller than another algorithm.

A Comparative Analysis of Infiltration Models for Groundwater Recharge from Ephemeral Stream Beds: A Case Study in Al Madinah Al Munawarah Province, Saudi Arabia

Groundwater recharge is strongly influenced by the infiltration process. In this research, the Philip, Horton, Kostiakov, and Green–Ampt infiltration models were tested for the ability to describe the infiltration process in the ephemeral stream beds located in Al Madinah Al Munawarah Province in Saudi Arabia. Infiltration data were obtained from double-ring infiltrometer tests in 14 locations distributed over the province. The method of least squares through an objective function optimization formalism is utilized to estimate the parameters of each model. The results show high variability in the parameters of each model over the tests. Individual tests showed that some models were better for representing specific tests than other models. On average, the Kostiakov empirical model was the best at describing the 14 infiltration tests with only 2 empirical parameters, since it had the minimum root mean square error (RMSE) for the cumulative infiltration depth F (1.13 cm), and it also had the same RMSE for the infiltration rates f (0.1 cm/min), similar to other models. Moreover, the Kostiakov model had an acceptable correlation coefficient R = 0.61 for f, and R = 0.99 for F. The results imply significant variability in the groundwater recharge rates from flash floods in the region.

Metaheuristic Extreme Learning Machine for Improving Performance of Electric Energy Demand Forecasting

Electric energy demand forecasting is very important for electric utilities to procure and supply electric energy for consumers sufficiently, safely, reliably, and continuously. Consequently, the processing time and accuracy of the forecast system are essential to consider when applying in real power system operations. Nowadays, the Extreme Learning Machine (ELM) is significant for forecasting as it provides an acceptable value of forecasting and consumes less computation time when compared with the state-of-the-art forecasting models. However, the result of electric energy demand forecasting from the ELM was unstable and its accuracy was increased by reducing overfitting of the ELM model. In this research, metaheuristic optimization combined with the ELM is proposed to increase accuracy and reduce the cause of overfitting of three forecasting models, composed of the Jellyfish Search Extreme Learning Machine (JS-ELM), the Harris Hawk Extreme Learning Machine (HH-ELM), and the Flower Pollination Extreme Learning Machine (FP-ELM). The actual electric energy demand datasets in Thailand were collected from 2018 to 2020 and used to test and compare the performance of the proposed and state-of-the-art forecasting models. The overall results show that the JS-ELM provides the best minimum root mean square error compared with the state-of-the-art forecasting models. Moreover, the JS-ELM consumes the appropriate processing time in this experiment.

Proper orthogonal decomposition and physical field reconstruction with artificial neural networks (ANN) for supercritical flow problems

The development of mathematical models, and the associated numerical simulations, are challenging in higher-dimensional systems featuring flows of supercritical fluids in various applications. In this paper, a data-driven methodology is presented to achieve system order reduction, and to identify important physical information within the principal flow features. Firstly, a new hybrid neural network based on radial basis function (RBF) and multi-layer perceptron (MLP) methods, namely RBF-MLP, is tested to achieve a highly nonlinear approximation. When provided with 1000 nonlinear test samples, this model provides an excellent prediction accuracy with a maximum regression coefficient (R) of 0.99 and a minimum root mean square error (RMSE) below 1%. Furthermore, the model is also proven to be flexible enough to capture accurately the turbulent fluctuation characteristics, even at significant nonlinear buoyancy conditions. Secondly, the high-dimensional buoyancy data is collected and integrated into a matrix database. Subsequently, a proper orthogonal decomposition (POD) approach is employed to reduce the high-dimensional database, and to obtain a set of low-dimensional POD basis-spanned space, which defines a reduced-order system with low-dimensional basis vectors. The results reveal that the first five order modes contain dominant flow features, accounting for 93% of the total mode energy, which can be selected to reconstruct the physical flow field. Thirdly, a new data-driven POD-ANN model is established to construct the nonlinear mapping between the full-field buoyancy data and decomposed basis vectors. It is also demonstrated that the POD-ANN model reconstructs the principal flow features accurately and reliably. This POD-ANN model can be used to provide new insights for reduced-order modelling and for reconstructing physical fields of higher-dimensional nonlinear flow cases.

Detecting winter canola (Brassica napus) phenological stages using an improved shape-model method based on time-series UAV spectral data

Accurate information about phenological stages is essential for canola field management practices such as irrigation, fertilization, and harvesting. Previous studies in canola phenology monitoring focused mainly on the flowering stage, using its apparent structure features and colors. Additional phenological stages have been largely overlooked. The objective of this study was to improve a shape-model method (SMM) for extracting winter canola phenological stages from time-series top-of-canopy reflectance images collected by an unmanned aerial vehicle (UAV). The transformation equation of the SMM was refined to account for the multi-peak features of the temporal dynamics of three vegetation indices (VIs) (NDVI, EVI, and CIred-edge). An experiment with various seeding scenarios was conducted, including four different seeding dates and three seeding densities. Three mathematical functions: asymmetric Gaussian function (AGF), Fourier function, and double logistic function, were employed to fit time-series vegetation indices to extract information about phenological stages. The refined SMM effectively estimated the phenological stages of canola, with a minimum root mean square error (RMSE) of 3.7 days for all phenological stages. The AGF function provided the best fitting performance, as it captured multiple peaks in the growth dynamics characteristics for all seeding date scenarios using four scaling parameters. For the three selected VIs, CIred-edge achieved the greatest accuracy in estimating the phenological stage dates. This study demonstrates the high potential of the refined SMM for estimating winter canola phenology.

Parameter identification of photovoltaic models using a sine cosine differential gradient based optimizer

In this paper, an efficient sine cosine differential gradient-based optimization method is proposed for identifying unknown parameters of photovoltaic models. In the simulation, parameter identification is formulated as an objective function to be minimized based on the error between the estimated and experimental data. Based on the original gradient-based optimization method, the proposed method combines the sine cosine method and the mutation crossover of the differential evolution algorithm. Specifically, the crossover operator enables the algorithm to avoid local optima; and meanwhile, the sine cosine strategy encourages the new individual to calculate the worst position. The simulation results demonstrate that the new optimization method can achieve the minimal root mean square error and obtain better optima relative to other algorithms in different photovoltaic cells. Therefore, the proposed optimization method has great potential to be used for estimating photovoltaic model parameters.

Evaluation of decomposition parameters for high-density surface electromyogram using fast independent component analysis algorithm

The surface electromyogram (sEMG) signal reveals the electrical neuromuscular activities and offers theoretical and clinical information. Recently, exploring motoneuron discharge events at the microscopic level through decomposition has been proposed as a promising analysis approach, which can surpass traditional global sEMG-based analysis method in some aspects. However, computational efficiency is an essential issue when discharge events of individual motor unit are decomposed using blind source separation algorithms. Therefore, choosing proper parameters of decomposition algorithms for different research purposes is important. Accordingly, we have systematically investigated the influences between computation time and decomposition performance for fast independent component analysis (FastICA)-based sEMG decomposition algorithm under different value selections of five decomposition parameters, namely the percentage of eliminated channels, extension factor, the number of decomposition iteration loops, the number of maximum inner loops in each iteration and sampling frequency. We employed high-density sEMG signals from 14 intact subjects during muscle contractions of four-digit extension and flexion at different force levels (20% and 50% maximum voluntary contraction) and a public dataset for sEMG decomposition. According to obtained results, we offer four preference suggestions (less computation time, more motor units, higher accuracy and trade-off). Results show that the trade-off values with consideration of decomposition performance and computation time are recommended as 25% of channels with minimal root mean square, extension factor of 4, 200 iteration loop numbers of decomposition, 20 maximum inner loop numbers and 2048 sampling frequency. Overall, this paper provides a guide for researchers to determine proper decomposition parameters for sEMG decomposition-related works.

Updates and improvements to the satellite drag coefficient Response Surface Modeling toolkit

For satellites in the Low Earth Orbit (LEO) region, the drag coefficient is a primary source of uncertainty for orbit determination and prediction. Researchers at the Los Alamos National Laboratory (LANL) have created the so-called Response Surface Modeling (RSM) toolkit to provide the community with a resource for simulating and modeling satellite drag coefficients for satellites with complex geometries (modeled using triangulated facets) in the free molecular flow (FMF) regime. The toolkit fits an interpolation surface using non-parametric Gaussian Process Regression (GPR) over drag coefficient data computed using the numerical Test Particle Monte Carlo (TPMC) method. The fitted response surface provides a substantial computational benefit over numerical approaches for calculating drag coefficients. In this work, the RSM toolkit is further developed into a versatile software with extended capabilities. The capabilities are specifically expanded to include uncertainty quantification and adaptation for automatic development of regression models for satellites with non-stationary components (e.g. rotating solar panels). Furthermore, the toolkit uses Python 3.x and C programming languages to provide an open source software package with a OSI approved GPL license. To assist the end user, the new RSM toolkit has been developed to have a user-friendly installation process and is provided with extensive documentation. The analysis of two different conceptual satellites is performed during this work: a simple cube and a CubeSat consisting of a simple cube body with 2 rotating solar panels. During the creation of the regression model for each satellite for different atmospheric species, it is found that the cube’s minimum Root Mean Squared Error (RMSE) is 0.00211 and the maximum RMSE is 0.00350. The CubeSat has a minimum RMSE of 0.00304 and the maximum is 0.00498. These results are overall conducive of a well performing regression model.

An Artificial Neural Network-Based Approach for Predicting the COVID-19 Daily Effective Reproduction Number Rt in Italy

Since December 2019, the novel coronavirus disease (COVID-19) has had a considerable impact on the health and socio-economic fabric of Italy. The effective reproduction number Rt is one of the most representative indicators of the contagion status as it reports the number of new infections caused by an infected subject in a partially immunized population. The task of predicting Rt values forward in time is challenging and, historically, it has been addressed by exploiting compartmental models or statistical frameworks. The present study proposes an Artificial Neural Networks-based approach to predict the Rt temporal trend at a daily resolution. For each Italian region and autonomous province, 21 daily COVID-19 indicators were exploited for the 7-day ahead prediction of the Rt trend by means of different neural network architectures, i.e., Feed Forward, Mono-Dimensional Convolutional, and Long Short-Term Memory. Focusing on Lombardy, which is one of the most affected regions, the predictions proved to be very accurate, with a minimum Root Mean Squared Error (RMSE) ranging from 0.035 at day t + 1 to 0.106 at day t + 7. Overall, the results show that it is possible to obtain accurate forecasts in Italy at a daily temporal resolution instead of the weekly resolution characterizing the official Rt data.