Variability Model Research Articles

Variability of the Acoustic Emission Signals Generated by Partial Discharges in Mineral Oil

The main purpose of the presented research is to investigate the partial discharge (PD) phenomenon variability under long-term AC voltage with particular consideration of the selected physical quantities changes while measured and registered by acoustic emission method (AE). During the research a PD model source generating surface discharges is immersed in the brand new insulation mineral oil. Acoustic signals generated by the continuously occurred PDs within 168 hours are registered. Several qualitative and quantitative indicators are assigned to describe the PD variability in time. Furthermore some long-term characteristics of the applied PD model source in mineral oil, are also presented according to acoustic signals emitted by the PD. Finally various statistical tools are applied for the results analysis and presentation. Despite there are numerous contemporary research papers dealing with long-term PD analysis, such complementary and multiparametric approach has not been presented so far, regarding the presented research. According to the presented research from among all assigned indicators there are discriminated descriptors that could depend on PD long-term duration. On the grounds of the regression models analysis there are discovered trends that potentially allow to apply the results for modeling of the PD variability in time using acoustic emission method. Subsequently such an approach may potentially support the development and extend the abilities of the diagnostic tools and maintenance policy in electrical power industry.

Evaluation of Bayesian spatiotemporal infectious disease models for prospective surveillance analysis

BackgroundCOVID-19 brought enormous challenges to public health surveillance and underscored the importance of developing and maintaining robust systems for accurate surveillance. As public health data collection efforts expand, there is a critical need for infectious disease modeling researchers to continue to develop prospective surveillance metrics and statistical models to accommodate the modeling of large disease counts and variability. This paper evaluated different likelihoods for the disease count model and various spatiotemporal mean models for prospective surveillance.MethodsWe evaluated Bayesian spatiotemporal models, which are the foundation for model-based infectious disease surveillance metrics. Bayesian spatiotemporal mean models based on the Poisson and the negative binomial likelihoods were evaluated with the different lengths of past data usage. We compared their goodness of fit and short-term prediction performance with both simulated epidemic data and real data from the COVID-19 pandemic.ResultsThe simulation results show that the negative binomial likelihood-based models show better goodness of fit results than Poisson likelihood-based models as deemed by smaller deviance information criteria (DIC) values. However, Poisson models yield smaller mean square error (MSE) and mean absolute one-step prediction error (MAOSPE) results when we use a shorter length of the past data such as 7 and 3 time periods. Real COVID-19 data analysis of New Jersey and South Carolina shows similar results for the goodness of fit and short-term prediction results. Negative binomial-based mean models showed better performance when we used the past data of 52 time periods. Poisson-based mean models showed comparable goodness of fit performance and smaller MSE and MAOSPE results when we used the past data of 7 and 3 time periods.ConclusionWe evaluate these models and provide future infectious disease outbreak modeling guidelines for Bayesian spatiotemporal analysis. Our choice of the likelihood and spatiotemporal mean models was influenced by both historical data length and variability. With a longer length of past data usage and more over-dispersed data, the negative binomial likelihood shows a better model fit than the Poisson likelihood. However, as we use a shorter length of the past data for our surveillance analysis, the difference between the Poisson and the negative binomial models becomes smaller. In this case, the Poisson likelihood shows robust posterior mean estimate and short-term prediction results.

Probing bursty star formation by cross-correlating extragalactic background light and galaxy surveys

ABSTRACT Understanding the star formation rate (SFR) variability and how it depends on physical properties of galaxies is important for developing and testing the theory of galaxy formation. We investigate how statistical measurements of the extragalactic background light (EBL) can shed light on this topic and complement traditional methods based on observations of individual galaxies. Using semi-empirical models of galaxy evolution and SFR indicators sensitive to different star formation time-scales (e.g. H α and ultraviolet continuum luminosities), we show that the SFR variability, quantified by the joint probability distribution of the SFR indicators (i.e. the bivariate conditional luminosity function), can be characterized as a function of galaxy mass and redshift through the cross-correlation between deep, near-infrared maps of the EBL and galaxy distributions. As an example, we consider combining upcoming SPHEREx maps of the EBL with galaxy samples from Rubin Observatory Legacy Survey of Space and Time. We demonstrate that their cross-correlation over a sky fraction of fsky ∼ 0.5 can constrain the joint SFR indicator distribution at high significance up to z ∼ 2.5 for mass-complete samples of galaxies down to $M_{*}\sim 10^9\, {\rm M}_{\odot }$. These constraints not only allow models of different SFR variability to be distinguished, but also provide unique opportunities to investigate physical mechanisms that require large number statistics such as environmental effects. The cross-correlations investigated illustrate the power of combining cosmological surveys to extract information inaccessible from each data set alone, while the large galaxy populations probed capture ensemble-averaged properties beyond the reach of targeted observations towards individual galaxies.

Classification of waste wood categories according to the best reuse using FT-NIR spectroscopy and chemometrics

In Europe, the volume of waste wood is increasing. Waste wood can be reused, promoting circular economy and avoiding landfills. It can be used as a bioenergy feedstock reducing the use of fossil fuels, or be reused for producing new composite wood material. Only wood with hazardous substances needs to be disposed. To this aim waste wood samples were collected from a panel board company and several recycling centres in Italy and Denmark. The samples were assigned to waste wood categories and analysed by Near Infrared Spectroscopy. Principal Component Analysis was used to investigate sample variability and Soft Independent Modelling of Class Analogies (SIMCA) for classifying the samples according to the appropriate reuse: energy production, panel board production or landfill. The results are good, with a classification rate of 90% for virgin wood material and 86.7% for treated wood material. The classification of waste wood is key for turning it into a secondary resource.

MDTOMO method for continuous conformational variability analysis in cryo electron subtomograms based on molecular dynamics simulations

Cryo electron tomography (cryo-ET) allows observing macromolecular complexes in their native environment. The common routine of subtomogram averaging (STA) allows obtaining the three-dimensional (3D) structure of abundant macromolecular complexes, and can be coupled with discrete classification to reveal conformational heterogeneity of the sample. However, the number of complexes extracted from cryo-ET data is usually small, which restricts the discrete-classification results to a small number of enough populated states and, thus, results in a largely incomplete conformational landscape. Alternative approaches are currently being investigated to explore the continuity of the conformational landscapes that in situ cryo-ET studies could provide. In this article, we present MDTOMO, a method for analyzing continuous conformational variability in cryo-ET subtomograms based on Molecular Dynamics (MD) simulations. MDTOMO allows obtaining an atomic-scale model of conformational variability and the corresponding free-energy landscape, from a given set of cryo-ET subtomograms. The article presents the performance of MDTOMO on a synthetic ABC exporter dataset and an in situ SARS-CoV-2 spike dataset. MDTOMO allows analyzing dynamic properties of molecular complexes to understand their biological functions, which could also be useful for structure-based drug discovery.

Intellectual property coordinators' cohorts: A study into the imprints in university technology transfer

The primary aim of Technology Transfer Offices (TTOs) is to enhance technology transfers, resulting in the commercialization of science. Technology transfer has typically been analyzed at the individual level of the core research staff or with the focus on the TTO as a whole, overlooking the fact that the university technology transfer is administered by intellectual property (IP) coordinators. This paper focuses on exposing a potentially crucial factor in technology transfer; the effects of cohorts based on imprinting. The imprinting theory implies that imprints are persistent and manifest themselves in the core activities of the IP coordinators' cohorts in the long term. We bring to light the effects of IP coordinators' cohorts on patenting and licensing, and test a conceptual model of inter-cohort variability. We analyze the patenting and licensing data of 18,393 patent cases and 845 licensed cases, handled by 63 IP coordinators. In combination with human resource data, we show that in the technology transfer process, IP coordinators’' cohorts matter. Using discriminant analysis, we demonstrate that some aspects of technology transfer activities are more typical for one cohort than the others. Variations between cohorts suggest that they are influenced by the prevailing practices inside the TTO at the time of hiring. Cohort patterns are also distinct in the two key technology transfer activities (patenting and licensing). Regression analysis shows that cohort effects remain resistant to erosion even when faced with subsequent changes as captured by organizational and individual time-period effects.

Impact of alternative soil data sources on the uncertainties in simulated land-atmosphere interactions

Numerical weather- and climate prediction models rely on soil data to accurately model land surface processes. However, as soil data are produced using soil profiles and maps with multiple sources of uncertainty, wide discrepancies prevail in global soil datasets. Comparison of four commonly used soil datasets in Earth system climate models, i.e., Food and Agriculture Organization soil data, Harmonized World Soil Database, Global Soil Dataset for Earth System Model, and global gridded soil information system SoilGrids, yields widespread differences in southern Africa. This study investigates the simulated land-atmosphere interactions in southern Africa in the context of the uncertainties from applying different global soil datasets. We conducted ensemble simulations using the fully coupled Weather Research and Forecasting Hydrological Modeling system (WRF-Hydro) incorporated with each of the global soil datasets mentioned above. Model simulations were performed at 4-km convection-permitting scale from January 2015 to June 2016. By quantifying model's internal variability and comparing the modeling results, results show that the simulated temperature, soil moisture, and surface energy fluxes are largely impacted by soil texture differences. For instance, changes in soil texture and associated hydrophysical parameters result in large differences in air temperature up to 1.7°C and surface heat flux up to 25 W/m2, and disparities in averaged surface soil moisture differ up to 0.1 m3/m3 in austral summer months. Differences in soil texture characteristics also regulate local climatic conditions differently in the wet and dry seasons as well as in different climatic regions. Furthermore, the thermodynamic differences in surface energy fluxes caused by soil texture demonstrate physical feedback perspective on atmospheric processes, resulting in distinct changes in planetary boundary layer height. This study demonstrates the non-negligible impact of soil data on land surface-atmosphere coupled modeling and highlights the need for consistent consideration of modeling uncertainties from soil data in modeling applications.

Multiwavelength variability and broad-band SED modelling of BL Lac during a bright flaring period MJD 59000–59943

ABSTRACT We carried out a detailed temporal and spectral study of the BL Lacertae (BL Lac) by using the long-term Fermi-Large Area Telescope (LAT) and Swift-X-ray Telescope (XRT)/Ultraviolet Optical Telescope (UVOT) observations, during the period MJD 59000–59943. The daily-binned γ-ray light curve displays a maximum flux of $1.74\pm 0.09\times 10^{-5} \,\rm photons\, cm^{-2}\, s^{-1}$ on MJD 59868, which is the highest daily γ-ray flux observed from BL Lac. The γ-ray variability is characterized by power spectral density (PSD), rms–flux relation, and flux distribution study. We find that the power-law model fits the PSD with index ∼1, which suggests a long-memory process at work. The observed rms–flux relation exhibits a linear trend, which indicates that the γ-ray flux distribution follows a lognormal distribution. The skewness/Anderson–Darling test and histogram fit reject the normality of flux distribution, and instead suggest that the flux distribution is a lognormal distribution. The fractional variability amplitude shows that the source is more variable in the X-ray band than in optical/ultraviolet/γ-ray bands. In order to obtain an insight into the underlying physical process, we extracted broad-band spectra from different time periods of the light curve. The broad-band spectra are statistically fitted with the convolved one-zone leptonic model with different forms of the particle energy distribution. We found that spectral energy distribution during different flux states can be reproduced well with the synchrotron, synchrotron self-Compton, and external Compton emissions from a broken power-law electron distribution, ensuring equipartition condition. A comparison between the best-fitting physical parameters shows that the variation in different flux states is mostly related to an increase in the bulk Lorentz factor and spectral hardening of the particle distribution.

Mixed-effects location-scale model based on generalized hyperbolic distribution

Motivated by better modeling of intra-individual variability in longitudinal data, we propose a class of location-scale mixed-effects models, in which the data of each individual is modeled by a parameter-varying generalized hyperbolic distribution. We first study the local maximum-likelihood asymptotics and reveal the instability in the numerical optimization of the log-likelihood. Then, we construct an asymptotically efficient estimator based on the Newton–Raphson method based on the original log-likelihood function with the initial estimator being naive least-squares-type. Numerical experiments are conducted to show that the proposed one-step estimator is not only theoretically efficient but also numerically much more stable and much less time-consuming compared with the maximum-likelihood estimator.

Impact of Climate Change on Paddy Farming in the Village Tank Cascade Systems of Sri Lanka

Consequences of global climate change are predicted to increase risks to crop production in the future. However, the possible broader impact of climate change on social-ecological systems still needs to be evaluated. Therefore, the present study focuses on one such globally important agricultural social-ecological system referred to as the Village Tank Cascade System (VTCS) in the dry zone of Sri Lanka. The VTCS has considerable potential to withstand seasonal climate variability mainly through continuous supply of water by the village tank storage throughout the year. The current study aimed to investigate trends of climate variability and possible impacts on paddy production in the North and North-central VTCS zone. Observed and projected rainfall and temperature data were analysed to evaluate the past variability trends (1970 to 2020) and model future (up to 2100) scenarios of climate variability and trends. Long-term observed rainfall and temperature data (1946 to 2020) were analysed to identify possible anomalies. The Maximum Entropy (MaxEnt) model has been used to predict the situation of future paddy farming (2050 and 2070) under two climate scenarios (RCP4.5 and RCP8.5) of the Intergovernmental Panel on Climate Change (IPCC). Six variables that would affect paddy growth and yield quality were used alongside the average monthly rainfall and temperature of two Global Climate Models (MIROC5 and MPI-ESM-LR). Climate suitability for two paddy cultivation seasons (Yala and Maha) were predicted for current and future climate scenarios. The findings revealed that observed and projected climate changes show considerable deviation of expected rainfall and temperature trends across the VTCS zone. Temperature exhibits warming of approximately 1.0 °C during the declared Global Warming Period (1970 to 2020) in the study area. In addition, there is a trend of significant warming by 0.02 °C/year, RCP4.5 and 0.03 °C/year, RCP8.5 from 1950 to 2100. Rainfall (1970–2020) shows high interannual variability but trends were not significant and less discernible. However, long-term projected rainfall data (1950–2100) analysis detected a significant (p = 0) upward trend (2.0 mm/year, RCP4.5 and 2.9 mm/year, RCP8.5), which is expected to continue up to the end of this century. Further, the study revealed some shifts in temperature towards higher values and positive anomalies in rainfall affecting seasonality and the likelihood of more extreme occurrences in the future, especially during the Maha cultivation season. The MaxEnt model predicts the following under future climate scenarios: (i) spatio-temporal shifts (conversions) in climate suitability for paddy farming in the VTCS zone; (ii) substantial low and moderate suitability areas that are currently suitable will remain unchanged; (iii) up to 96% of highly suitable and 38% of moderately suitable paddy growing areas in the VTCS zone will be at risk due to a decline in future climate suitability; and (iv) expansion of lower suitability areas by approximately 22% to 37%, due to conversion from moderate suitability areas. The study provides evidence that the continuous warming trend with increasing variability in rainfall and shifting seasonality could increase the vulnerability of future paddy farming in the VTCS. Thus, findings of this study will help planners to make more targeted solutions to improve adaptive capacity and regain the resilience to adjust the paddy farming pattern to deal with predicted climate variability and change.

Synergisticeffect of elevated glucose levels with SARS-CoV-2 spike protein induced NOX-dependent ROS production in endothelial cells.

Diabetic patients infected with coronavirus disease 2019 (COVID-19) often have a higher probability of organ failure and mortality. The potential cellular mechanisms through which blood glucose exacerbates tissue damage due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection is still unclear. We cultured endothelial cells within differing glucose mediums with an increasing concentration gradient of SARS-CoV-2 Spike protein (S protein). S protein can cause the reduction of ACE2 and TMPRSS2, and activation of NOX2 and NOX4. A high glucose medium was shown to aggravate the decrease of ACE2 and activation of NOX2 and NOX4 in cultured cells, but had no effect on TMPRSS2. S protein mediated activation of the ACE2-NOX axis induced oxidative stress and apoptosis within endothelial cells, leading to cellular dysfunction via the reduction of NO and tight junction proteins which may collectively be exacerbated by elevated glucose. In addition, the glucose variability model demonstrated activation of the ACE2-NOX axis in a similar manner observed in the high glucose model in vitro. Our present study provides evidence for a mechanism through which hyperglycemia aggravates endothelial cell injury resulting from S protein mediated activation of the ACE2-NOX axis. Our research thus highlights the importance of strict monitoring and control of blood glucose levels within the context of COVID-19 treatment to potentially improve clinical outcomes.

Deep learning for predicting future lesion emergence in high-risk breast MRI screening: a feasibility study

BackgroundInternational societies have issued guidelines for high-risk breast cancer (BC) screening, recommending contrast-enhanced magnetic resonance imaging (CE-MRI) of the breast as a supplemental diagnostic tool. In our study, we tested the applicability of deep learning-based anomaly detection to identify anomalous changes in negative breast CE-MRI screens associated with future lesion emergence.MethodsIn this prospective study, we trained a generative adversarial network on dynamic CE-MRI of 33 high-risk women who participated in a screening program but did not develop BC. We defined an anomaly score as the deviation of an observed CE-MRI scan from the model of normal breast tissue variability. We evaluated the anomaly score’s association with future lesion emergence on the level of local image patches (104,531 normal patches, 455 patches of future lesion location) and entire CE-MRI exams (21 normal, 20 with future lesion). Associations were analyzed by receiver operating characteristic (ROC) curves on the patch level and logistic regression on the examination level.ResultsThe local anomaly score on image patches was a good predictor for future lesion emergence (area under the ROC curve 0.804). An exam-level summary score was significantly associated with the emergence of lesions at any location at a later time point (p = 0.045).ConclusionsBreast cancer lesions are associated with anomalous appearance changes in breast CE-MRI occurring before the lesion emerges in high-risk women. These early image signatures are detectable and may be a basis for adjusting individual BC risk and personalized screening.Relevance statementAnomalies in screening MRI preceding lesion emergence in women at high-risk of breast cancer may inform individualized screening and intervention strategies.Key points• Breast lesions are associated with preceding anomalies in CE-MRI of high-risk women.• Deep learning-based anomaly detection can help to adjust risk assessment for future lesions.• An appearance anomaly score may be used for adjusting screening interval times.Graphical

Software system architecture based on the concept of reflexive adaptation

The conducted research substantiates the relevance of the application and the need to develop adaptive software to solve the problems of using IT in the construction industry. The basic principles of reflexive adaptation, as well as the use of software product lines engineering (SPLE) technology to create adaptive software systems, are considered. A generalized architecture of an adaptive software system based on models of variability and levels of reflection is proposed. A formal description of the reflexive software system for the implementation of variants of the adaptive behavior of application programs has been carried out. The practical significance of the research is that giving the applied software system adaptive properties will enable it to modify its structure at a qualitatively new level, which in turn will increase its reliability, resistance to failures, flexibility, reduce the cost of maintenance and extend the life of the system. Such a system will be able to expand the class of solvable tasks throughout the entire life cycle, as well as perform operations that are currently considered part of the duties of certain specialists, for example, it will be able to perform self-administration functions.

NN‐MLT Model Prediction for Low‐Latitude Region Based on Artificial Neural Network and Long‐Term SABER Observations

AbstractThe low‐latitude mesosphere and lower thermosphere (MLT) regions are distinct and, highly turbulent transition zones in Earth's atmosphere. The scarcity of reliable measurements makes continuous monitoring of these areas challenging. Therefore, the necessity for studies focused on the MLT region cannot be overstated, as they are essential for developing effective models that meet the accuracy requirements of satellite‐based observations. The neural networks NN‐MLT model, developed using 15 years of Thermosphere, Ionosphere, and Mesosphere Energetics and Dynamics/satellite, equipped with Broadband Emission Radiometry (SABER) observed temperature data spanning from January 2006 to December 2020, employs neural network techniques. The data set was split, with 90% used for training and the remaining 10% allocated for prediction. The model's validation was tested with two other partitions (80(20) and 70(30)). The 90(10) partition, exhibiting a high correlation coefficient (R), low standard deviation (σ), and low root mean square error (RMSE), demonstrated the model's good performance. As clearly shown from statistical metrics (R, RMSE, mean, and σ) at three specific altitude levels (60, 75, and 90 km), the NN‐MLT model's performance aligns closely with the empirical model (NRLMSISE2‐0) and SABER observations. The NN‐MLT model displays a high R (0.74) and low RMSE (4.35 K) at 60 km, indicating its effective performance compared to the other two heights of 75 and 90 km. The NN‐MLT model's spatiotemporal variability in MLT temperature prediction agrees well with the SABER data at all altitudes, particularly at 60 km. While the NN‐MLT model accurately captures the seasonal variations of MLT temperature, the analysis leads to the conclusion that it consistently outperforms the empirical model and aligns closely with observations.

A new decomposition model of sea level variability for the sea level anomaly time series prediction

A new decomposition model of sea level variability for the sea level anomaly time series prediction

Integrated Stochastic Investigation of Singularly Perturbed Delay Differential Equations for the Neuronal Variability Model

The proposed research utilizes a computational approach to attain a numerical solution for the singularly perturbed delay differential equation (SPDDE) problem arising in the neuronal variability model through artificial neural networks (ANNs) with different solvers. The log-sigmoid function is used to construct the fitness function. The implementation of ANN on SPDDE problems is formulated for different solvers and trained with different weights. The optimization solvers such as the genetic algorithm (GA), sequential quadratic programming (SQP), and pattern search (PS) are hybridized with the active set technique (AST) and the interior-point technique (IPT) and is used to check the accuracy and rapid convergence of the numerical results of the SPDDE model. The numerical outcomes demonstrate that the system is easy to handle and efficient to solve with boundary conditions. Moreover, we used the mean residual error for one hundred runs for each solver to validate the accuracy of the proposed scheme.

An Analytical Gate Delay Variability Model for Low-Power Applications under the Process Variations Effects

Defining the timing characteristics behavior, such as the gate delay and the oscillation period, is an essential task in integrated circuits (ICs), especially for low-power CMOS-based technologies. The nanometric-sized devices designed to achieve low-power consumption have higher threshold voltages. Hence, these devices are operated at the near-threshold regime, or slightly above the threshold. In these regions, shifts in electrical parameters (expressed in terms of drain current or threshold voltage) may severely impact the circuit behavior. Consequently, the time-dependent sources of variability (e.g., the bias temperature instability) impose a crucial reliability problem that affects time delay variability and induces slope propagation effects along the signal path. In this context, an improved analytical model to properly account for both the gate delay and its variability is presented, taking into account the properties of low-power devices. Additionally, the applicability of the model is presented in a case study of a ring oscillator. The derived equations allows a suitable estimative for the parameters’ degradation. Supported by Monte Carlo simulations, the extracted results indicate that the proposed method provides a better estimate for the ring oscillator jitter when compared to the simplified propagation of uncertainty method.

Comparing the intensity of variability changes in software product line evolution

The evolution of a Software Product Line (SPL) typically affects multiple kinds of artifacts. The intensity (frequency and amount) in which developers change variability information in them was unknown, until we introduced a fine-grained approach for the variability-centric extraction and analysis of changes to code, build, and variability model artifacts. Its application to the commits of the Linux kernel revealed that changes to variability information occur infrequently and only affect small parts of the analyzed artifacts. Further, we outlined how these results may improve certain analysis and verification tasks during SPL evolution. However, the sole analysis of a single SPL did not allow for generic conclusions.In this paper, we extend our previous work to a comparative evolution analysis of four SPLs. We provide a detailed analysis of the individual intensities of variability changes by applying our updated approach to each SPL. A comparison of these results confirms our findings of infrequent and small changes to variability information in our previous study. However, differences in the details of these changes exist, which we cannot explain solely by the characteristics of the SPLs or their development processes. We discuss their implications on supporting SPL evolution and on our previous optimization proposals.

Reliability and validity of the variability model testing procedure for somatic dysfunction assessment: a comparison with gait analysis parameters in healthy subjects

Reliability and validity of the variability model testing procedure for somatic dysfunction assessment: a comparison with gait analysis parameters in healthy subjects

Neural-network modeling of solar radiation and temperature variability due to climate change in Ibadan Metropolis

his research focused on studying the variability of solar radiation and temperature under climate change in the Ibadan metropolis. In the study, spatial distribution, temporal variations, annual distribution, estimation and prediction of the solar radiation, minimum and maximum temperature data in the Ibadan Metropolis was collected. A Long Short-Term Memory Neural Network (LSTM-NN) model was developed for the prediction using the time-series data obtained. An ARIMA model was further developed to compare and validate the LSTM-NN model. The performance of the prediction models were determined using the root mean square error (RMSE) and the mean absolute percentage error (MAPE). The RMSE values for the minimum, maximum temperature and solar radiation predictions were 1.543, 1.290, 1.967, and 1.611, 1.309, 2.106 for the LSTM-NN and ARIMA models respectively, while the MAPE values for the minimum, maximum temperature and solar radiation predictions were 3.603, 4.351, 8.859, and 3.840, 4.480, 9.502 for the LSTM-NN and ARIMA models respectively. The LSTM-NN model had a better prediction performance in all categories with lower error when compared with ARIMA. From the prediction, it was observed that there will be a reduction in the maximum temperature, minimum temperature and solar radiation values when compared to obtained data. The observed minimum temperature ranged from 22.9032-23.2032(0C), while the predicted minimum temperature ranged from 19.9260- 19.977(0C) also the observed maximum temperature ranged from 32.87096-33.7064(0C), while the predicted maximum temperature ranged from 29.5159-29.5529(0C), the observed solar radiation ranged from 19.203-19.722 (W/m2 ), while the predicted solar radiation ranged from 14.123-14.115 (W/m2 ). The year with the highest solar radiation which constitutes the useful energy is 2024 with an average value of 14.1395 W/m2