Low Error Values Research Articles

A high-throughput phenotyping method for sugarcane rind penetrometer resistance and breaking force characterization by near-infrared spectroscopy

BackgroundSugarcane (Saccharum spp.) is the core crop for sugar and bioethanol production over the world. A major problem in sugarcane production is stalk lodging due to weak mechanical strength. Rind penetrometer resistance (RPR) and breaking force are two kinds of regular parameters for mechanical strength characterization. However, due to the lack of efficient methods for determining RPR and breaking force in sugarcane, genetic approaches for improving these traits are generally limited. This study was designed to use near-infrared spectroscopy (NIRS) calibration assay to accurately assess mechanical strength on a high-throughput basis for the first time.ResultsBased on well-established laboratory measurements of sugarcane stalk internodes collected in the years 2019 and 2020, considerable variations in RPR and breaking force were observed in the stalk internodes. Following a standard NIRS calibration process, two online models were obtained with a high coefficient of determination (R2) and the ratio of prediction to deviation (RPD) values during calibration, internal cross-validation, and external validation. Remarkably, the equation for RPR exhibited R2 and RPD values as high as 0.997 and 17.70, as well as showing relatively low root mean square error values at 0.44 N mm−2 during global modeling, demonstrating excellent predictive performance.ConclusionsThis study delivered a successful attempt for rapid and precise prediction of rind penetrometer resistance and breaking force in sugarcane stalk by NIRS assay. These established models can be used to improve phenotyping jobs for sugarcane germplasm on a large scale.

Accelerated screening of sensitive and selective MoO3-based gas sensing materials by combining first-principles and machine learning approach

A large amount of hybrid metal oxides can be proposed for detecting various gases from rapidly developing of 2D materials and elemental doping technologies, and the key issue is how to search the large parameter space in an efficient way. First-principles approach can calculate molecular-scale electronic properties and provide a guide of material design for experiments, however, it is too time-consuming to explore all the possible metal oxides doped with different elements. Herein, we develop a novel framework via combining first-principles and machine learning, with the aim of enabling more efficient and practical screening of MoO3-based gas sensors than by experiments or first-principles alone. Owing to the high accuracy of first-principles calculations verified by experimental results, we demonstrate the reliability of the proposed methods for evaluating gas sensing performance. By proposing a set of new descriptors including d-band center and average bond length with demanding low-cost calculations, we significantly reduce the amount of required training data. In particular, the gradient boosting regression algorithm exhibits highR-square value of 0.96 and low mean absolute error value of 0.22, indicating superior reliability of the model. This work opens an avenue for quickly screening of novel metal oxides and other nano-materials with superior sensitivity and selectivity for gas detection.

Short-Term Forecasting of Ozone Concentration in Metropolitan Lima Using Hybrid Combinations of Time Series Models

In the modern era, air pollution is one of the most harmful environmental issues on the local, regional, and global stages. Its negative impacts go far beyond ecosystems and the economy, harming human health and environmental sustainability. Given these facts, efficient and accurate modeling and forecasting for the concentration of ozone are vital. Thus, this study explores an in-depth analysis of forecasting the concentration of ozone by comparing many hybrid combinations of time series models. To this end, in the first phase, the hourly ozone time series is decomposed into three new sub-series, including the long-term trend, the seasonal trend, and the stochastic series, by applying the seasonal trend decomposition method. In the second phase, we forecast every sub-series with three popular time series models and all their combinations In the final phase, the results of each sub-series forecast are combined to achieve the results of the final forecast. The proposed hybrid time series forecasting models were applied to four Metropolitan Lima monitoring stations—ATE, Campo de Marte, San Borja, and Santa Anita—for the years 2017, 2018, and 2019 in the winter season. Thus, the combinations of the considered time series models generated 27 combinations for each sampling station. They demonstrated significant forecasts of the sample based on highly accurate and efficient descriptive, statistical, and graphic analysis tests, as a lower mean error occurred in the optimized forecast models compared to baseline models. The most effective hybrid models for the ATE, Campo de Marte, San Borja, and Santa Anita stations were identified based on their superior out-of-sample forecast results, as measured by RMSE (4.611, 3.637, 1.495, and 1.969), RMSPE (4.464, 11.846, 1.864, and 15.924), MAE (1.711, 2.356, 1.078, and 1.462), and MAPE (14.862, 20.441, 7.668, and 76.261) errors. These models significantly outperformed other models due to their lower error values. In addition, the best models are statistically significant (p < 0.05) and superior to the rest of the combination models. Furthermore, the final proposed models show significant performance with the least mean error, which is comparatively better than the considered baseline models. Finally, the authors also recommend using the proposed hybrid time series combination forecasting models to predict ozone concentrations in other districts of Lima and other parts of Peru.

Exploring the Gradient Boosting and LSTM for Power Distribution-based Time Series Analysis

Electrical energy production is an important function in a country that has abundant demand for society. Therefore, power supply forecasting is very significant to keep the balance of power consumption and production and should not be in short supply at any cost. Thus, Forecasting and modelling time series analysis of power production becomes important in prediction. We explore the synergy between Gradient Boosting and Long Short-Term Memory (LSTM) networks in the context of time series analysis. Specifically, we investigate how XGBoost and LightGBM, well-known gradient boosting frameworks, complement LSTM, a recurrent neural network architecture. By combining these methods, we aim to uncover deeper insights and elevate predictive potential for time series forecasting. In this paper, we examine the machine learning methods of forecasting the power generation of 33-year time series data. In the conclusion, we put forward a comparative study between the outcomes attained from the use of LSTM and Gradient-boosting tree-based algorithms XGBoost and LightGBM. The results show that the XGBoost model outclasses the other models with a low error value in forecasting power generation.

AsCDPR: a novel framework for ratings and personalized preference hotel recommendation using cross-domain and aspect-based features

PurposeThe explosion of data due to the sophistication of information and communication technology makes it simple for prospective tourists to learn about previous hotel guests' experiences. They prioritize the rating score when selecting a hotel. However, rating scores are less reliable for suggesting a personalized preference for each aspect, especially when they are in a limited number. This study aims to recommend ratings and personalized preference hotels using cross-domain and aspect-based features.Design/methodology/approachWe propose an aspect-based cross-domain personalized recommendation (AsCDPR), a novel framework for rating prediction and personalized customer preference recommendations. We incorporate a cross-domain personalized approach and aspect-based features of items from the review text. We extracted aspect-based feature vectors from two domains using bidirectional long short-term memory and then mapped them by a multilayer perceptron (MLP). The cross-domain recommendation module trains MLP to analyze sentiment and predict item ratings and the polarities of the aspect based on user preferences.FindingsExpanded by its synonyms, aspect-based features significantly improve the performance of sentiment analysis on accuracy and the F1-score matrix. With relatively low mean absolute error and root mean square error values, AsCDPR outperforms matrix factorization, collaborative matrix factorization, EMCDPR and Personalized transfer of user preferences for cross-domain recommendation. These values are 1.3657 and 1.6682, respectively.Research limitation/implicationsThis study assists users in recommending hotels based on their priority preferences. Users do not need to read other people's reviews to capture the key aspects of items. This model could enhance system reliability in the hospitality industry by providing personalized recommendations.Originality/valueThis study introduces a new approach that embeds aspect-based features of items in a cross-domain personalized recommendation. AsCDPR predicts ratings and provides recommendations based on priority aspects of each user's preferences.

Forecasting the strength characteristics of concrete incorporating waste foundry sand using advance machine algorithms including deep learning

The incorporation of waste foundry sand (WFS) into concrete has been recognized as a sustainable approach to improve the strength properties of waste foundry sand concrete (WFSC). However, machine learning (ML) techniques are still necessary to forecast the characteristics of WFSC and evaluate the dominant input features for the suitable mix design. For this purpose, the present work selected five ML-based techniques based on gene expression programming (GEP), deep neural network (DNN), and optimizable Gaussian process regressor (OGPR) to predict the mechanical characteristics of WFSC. To build up the predictive models, a database containing 397 values of compressive strength (CS) and 169 values of flexural strength (FS) is collected from published literature. The models' performance was evaluated via various statistical metrics and additionally, external validation criteria were employed to validate the developed models. Furthermore, the Shapley additive explanation (SHAP) was carried out to interpret the model's prediction. The DNN2 model exhibited superior performance, with R-values of 0.996 (training), 0.999 (testing), and 0.997 (validation) for the compressive strength estimation. In contrast, the GEP2 model showed poor accuracy in estimating the CS compared to other developed models, with R-values of 0.851, 0.901, and 0.844 for the training, testing, and validation sets, respectively. Similarly, for the flexural strength estimation, the DNN2 model provided R-values of 0.999 for training, 0.996 for testing, and 0.999 for validation sets, indicating its robust performance. The SHAP analysis revealed that the age, water-cement ratio, and coarse aggregate-to-cement ratio have the prime influence in determining flexural and compressive strength, respectively. The comparison of the models provided that the DNN2 model accurately estimated the output with high accuracy and lower error values and might be utilized in practical fields to reduce labor and cost by optimizing the mix combinations. Finally, for future studies, it is recommended to utilize ensemble and hybrid algorithms, as well as post-hoc explanatory techniques, to forecast the characteristics of WFSC accurately.

Evolutionary conditional GANs for supervised data augmentation: The case of assessing berry number per cluster in grapevine

In viticulture, training a deep learning model to assess the number of berries in a cluster image requires labeling by manually counting the berries on each grape cluster. This repeating, demanding task directly opposes the need for large amounts of data of deep learning methods. The objective of this work is the development of evolutionary conditional generative adversarial networks (GANs) for supervised data augmentation in the task of assessing berry number per cluster in grapevine. Ninety-seven grape cluster images were collected and labeled by manually counting the berries, making up the original dataset, and it was used for the training of a conditional GAN using evolutionary schemes involving a population of generators competing within a common and dynamic environment: the discriminator. After generative networks training, the best performing generator was used for supervised data augmentation: generation of labeled images conditioned to a berry number, making up the augmented dataset. Two models were trained with one dataset each, original and augmented, both having approximately the same number of samples, around 400. The original dataset was enriched with traditional image transforms, while the augmented dataset had incorporated images from the trained GAN generator. The two models were trained using the same convolutional regression network architecture, and then tested on an external image dataset, with more than 1300 images not used in any training, to compare the performance of GAN data augmentation. Results showed that the model augmented with GANs yielded lower error values, with a validation error of 43 berries, than those from the original model, with a validation error of 65 berries. In the test dataset, the augmented model obtained an error of 39 berries (R2 = 0.75), surpassing again the original model, that obtained an error of 57 berries (R2 = 0.65). These results evidence that evolutionary conditional GANs generate synthetic labeled images that lead to higher performance deep learning regression models for assessing berry number from cluster images.

The Intraday High-Frequency Trading with Different Data Ranges: A Comparative Study with Artificial Neural Network and Vector Autoregressive Models

With the High-Frequency Trading process, which is a subclass of algorithmic trading transactions, intraday information has increasing importance. Traditional statistical methods often fall short in capturing the intricate patterns and volatility inherent in such high-frequency data. In contrast, ANN models demonstrate remarkable capability in handling these challenges, and VAR models provide insights into short-term relationships among variables. This study highlights the importance of using both ANN and VAR models for processing these short time intervals. BIST100 index which is the main index of Borsa Istanbul is predicted with two different models in different data ranges with artificial neural network models and vector auto regression models. Both generated ANN models successfully complete the training stages, with extremely high precision, and exhibit exceptionally low error values in their predictions. Although both models are effective, the evidence favors the model evaluated using 5-minute data for both the training and prediction phases of artificial neural network models. However, the relative importance of 15-minute data in explaining the variation of BIST100 is higher. Moreover, the VAR model results indicate that the short-term relationship between variables can be influenced by the range of data and the 15-minute interval data of the variables play a more significant role in explaining the BIST100 index over the longer term.

Quantification of Dry Matter Content in Hass Avocado by Near-Infrared Spectroscopy (NIRS) Scanning Different Fruit Zones.

Accurate dry matter determination (DM) in Hass avocados is vital for optimal harvesting and ensuring fruit quality. Predictive models based on NIRS need to capture fruit DM gradient. This work aimed to determine the DM content in Hass avocado whole by NIRS scanning different fruit zones. Spectra were recorded for each zone of the fruit: peduncle (P), equator (E), and base (B). The calibration and validation included fruit from different orchards in two harvest cycles. The results show a DM gradient within the fruit: 24.47% (E), 24.68% (B), and 24.79% (P). The DM gradient was observed within the spectra using the RMSi (root mean square) criterion and PCA. The results show that at least one spectrum per fruit zone was needed to represent the variability within the fruit. The performances of the calibration using the whole set of data were R2: 0.74 and standard error of cross-validation (SECV) = 1.18%. In the validation stage using independent validation sets, the models showed similar performance (R2: 0.75, SECV 1.15%) with low values of the standard error of prediction (SEP): 1.62%. These results demonstrate the potential of near-infrared spectroscopy for high-throughput sorting of avocados based on their commercial quality.

Application of Müntz Orthogonal Functions on the Solution of the Fractional Bagley–Torvik Equation Using Collocation Method with Error Stimate

This paper uses Müntz orthogonal functions to numerically solve the fractional Bagley–Torvik equation with initial and boundary conditions. Müntz orthogonal functions are defined on the interval 0 , 1 and have simple and distinct real roots on this interval. For the function f ∈ L 2 0 , 1 , we obtain the best unique approximation using Müntz orthogonal functions. We obtain the Riemann–Liouville fractional integral operator for Müntz orthogonal functions so that we can reduce the complexity of calculations and increase the speed of solving the problem, which can be seen in the process of running the Maple program. To solve the fractional Bagley–Torvik equation with initial and boundary conditions, we use Müntz orthogonal functions and consider simple and distinct real roots of Müntz orthogonal functions as collocation points. By using the Riemann–Liouville fractional integral operator that we define for the Müntz orthogonal functions, the process of numerically solving the fractional Bagley–Torvik equation that is solved using Müntz orthogonal functions is reduced, and finally, we reach a system of algebraic equations. By solving algebraic equations and obtaining the vector of unknowns, the fractional Bagley–Torvik equation is solved using Müntz orthogonal functions, and the error value of the method can be calculated. The low error value of this numerical solution method shows the high accuracy of this method. With the help of the Müntz functions, we obtain the error bound for the approximation of the function. We have obtained the error bounds for the numerical method using which we solved the fractional Bagley–Torvik equation with initial and boundary conditions. Finally, we have given a numerical example to show the accuracy of the solution of the method presented in this paper. The results of solving this example using Müntz orthogonal functions and comparing the results with other methods that have been used the solve this example show the higher accuracy of the method proposed in this paper.

Analysis of Time Series Water Level Data Prediction Using Deep Learning Method at the Water Gate of DKI Jakarta Water Resources Office

Indonesia has 2 seasons, namely the dry season and the rainy season. During the rainy season, many points in the DKI Jakarta area experience flooding or inundation. The reason why Jakarta often experiences flooding is caused by several factors, including local rain floods, shipment floods and tidal floods. The DKI Jakarta Water Resources Agency currently does not have a system that can predict future water levels by referring to past and present water level data. Through this background, the author tries to conduct research in one of the floodgates in the northern area of DKI Jakarta in predicting water levels using deep learning methods , namely Recurrent Neural Network (RNN) and Long Short Term Memory (LSTM). The purpose of this research is to analyze the best deep learning models and predict water level time series data. From the results of the analysis carried out, the best deep learning model is Long Short Term Memory (LSTM) using several tests such as n-input, split data with a composition of 90.33% train data and 9.67% test data , as well as testing of different parameters including epoch, batch size, learning rate, dropout , so the results obtained are the lowest error values with RMSE (17.65), MAPE (0.29), MAE (3.37) and the time needed in the process (runtime) is 39 minutes

High-Resolution Ratoon Rice Monitoring under Cloudy Conditions with Fused Time-Series Optical Dataset and Threshold Model

Ratoon rice, an effective rice cultivation system, allows paddy rice to be harvested twice from the same stubble, playing an important role in ensuring food security and adapting to climate change with its unique growth characteristics. However, there is an absence of research related to remote-sensing monitoring of ratoon rice, and the presence of other rice cropping systems (e.g., double-season rice) with similar characteristics poses a hindrance to the accurate identification of ratoon rice. Furthermore, cloudy and rainy regions have limited available remote-sensing images, meaning that remote-sensing monitoring is limited. To address this issue, taking Yongchuan District, a typical cloud-prone region in Chongqing, China, as an example, this study proposed the construction of a time-series optical dataset using the Modified Neighborhood Similar Pixel Interpolator (MNSPI) method for cloud-removal interpolation and the Flexible Spatiotemporal DAta Fusion (FSDAF) model for fusing multi-source optical remote-sensing data, in combination with vegetation index features and phenological information to build a threshold model to map ratoon rice at high-resolution (10 m). The mapping performance of ratoon rice was evaluated using independent field samples to obtain the overall accuracy and kappa coefficient. The findings indicate that the combination of the MNSPI method and FSDAF model had a stable and effective performance, characterized by high correlation coefficient (r) values and low root mean square error (RMSE) values between the restored/predicted images and the true images. Notably, it was possible to effectively capture the distinct characteristics of ratoon rice in cloudy and rainy regions using the proposed threshold model. Specifically, the identified area of ratoon rice in the study region was 194.17 km2, which was close to the official data (158–180 km2), and the overall accuracy and kappa coefficient of ratoon rice identification result were 90.73% and 0.81, respectively. These results demonstrate that our proposed threshold model can effectively distinguish ratoon rice during vital phenological stages from other crop types, enrich the technical system of rice remote-sensing monitoring, and provide a reference for agricultural remote-sensing applications in cloudy and rainy regions.

Reduction and Adsorption of Hexavalent Chromium by Iron Sulfide Loaded Biochar: Isotherms, Kinetics and Thermodynamics

AbstractThe removal of noxious Cr(VI) from water has gained worldwide attention. In this study, biochar derived from macadamia nut shells (MHP) was embedded with iron sulfide (FeS) nanoparticles produced through a solid‐phase reduction of pyrite. The MHP‐FeS composite was evaluated for the adsorption of Cr(VI) and its subsequent reduction to Cr(III). The scanning electron microscope images revealed that the particles were of irregular shape, while the energy dispersive spectroscopy results showed the existence of Fe, S, O, and C atoms. X‐ray diffraction peaks at 2=29.8°, 33.7°, 43.7°, and 53.1° were characteristic of the formation of FeS nanoparticles. A maximum Cr(VI) adsorption capacity of 4.95 mg/g was obtained at pH 3, 60 min, and 25 °C. The higher correlation coefficient (R2>0.873) and lower residual standard error (RSE=1.43) values pointed to the adsorption process favoring Langmuir and pseudo‐second‐order models. As per thermodynamic reaction calculations, the remediation process was spontaneous and endothermic. With further optimization, this material could be a potential adsorbent and reductant for Cr(VI) in water.

Artificial neural networks for insights into adsorption capacity of industrial dyes using carbon-based materials

Organic waste-derived carbon-based materials (CBMs) are commonly applied in sustainable wastewater treatment and waste management. CBMs can remove toxic, non-biodegradable and carcinogenic pollutants such as dyes which include indigo, triphenylmethyl, azo, anthraquinone and phthalocyanine derivatives. Nonetheless, their diverse composition, surface properties, presence of numerous surface functional groups and the altering adsorption experimental conditions to which they are applied against the elimination of organic dyes make it challenging to completely understand the removal mechanism. Herein, a dataset of 1514 data points was compiled from various published peer-reviewed journals along with additional adsorption experiments conducted in this study. Artificial neural networks (ANN) based machine learning (ML) model was compared with other ML and a deep learning model named Tab-Transformer and the findings proposed ANN showed superior prediction performance for adsorption capacity as a function of adsorbent synthesis conditions, adsorbent physical characteristics and adsorption experimental conditions. The hyperparameters of ANN model was optimized using Bayesian optimizer and the batch size, activation and units were proven to be more important than the number of hidden layers and learning rate. The ANN model exhibits a higher coefficient of determination (R2 = 0.98) and lower root mean square error (RMSE = 46.95 mg/g) values for test dataset. Feature importance using SHapley Additive exPlanations (SHAP) analysis suggested that the adsorption characteristics with 51.4% was the most important in the ANN prediction followed by the adsorption experimental condition (31.2%) and adsorbent synthesis condition (17.4%). Moreover, the impact of six most important features were individually analyzed. Finally, a detailed discussion on the environmental impact of the presented ANN model is also included.

PREDIKSI CURAH HUJAN DI KABUPATEN BADUNG, BALI MENGGUNAKAN METODE LONG SHORT-TERM MEMORY

Rainfall is the height of rainwater that falls on a flat area, assuming it doesn't evaporate, doesn't seep, and doesn't flow. Rain levels are measured in mm (millimeters). The target of the research being conducted is in Badung Regency, Bali because Bali is a tourist area that is often visited by tourists and from Indonesian itself, so predictions of meteorology, such as rainfall will greatly impact tourism. In this test, predictions use the Long Short Term Memory (LSTM) method, using daily weather data from the BMKG from 2010 to 2020 as training data and daily weather data for 2021 as prediction data. Based on the test results above, the results show that the two LSTM tests with LSTM Model 128.64 and LSTM Model 64.32 have low MAE and MAPE error values. From First Scenario, the Mean Absolute Error (MAE) value is 8.97246598930908 and Mean Absolute Percentage Error (MAPE) value is 1.7657206683278308%. From Second Scenario, the Mean Absolute Error is 9.706669940783014 and Mean Absolute Percentage Error is 1.9028466692362323%. From the MAE and MAPE values obtained in these two scenarios, it can be proven that from the evaluation results of Rainfall predictions in Badung Regency, Bali, the predictions can be said to be very accurate because they have an error value of less than 10.

An Exploratory Sequential Mixed Methods Design to Identify Criteria for Continuous Performance Evaluation

An alternative to the ubiquitous annual performance evaluation is continuous performance evaluation that is posed to give more objective, frequent and constructive feedbacks. Despite researchers recommending following a continuous performance evaluation for employees, there are hardly any progress in this regard. One of the hindrances is in identifying the evaluation criteria. Identifying the relevant criteria – both from employers and employee’s perspective – is important for the success of a continuous performance evaluation process. Given its novelty, it calls for an exploration to understand a holistic set of criteria. For this purpose, an exploratory sequential mixed method was adopted in the Information Technology Industry in India. In the first phase, an unstructured interview was conducted among 11 software engineers (employees). Based on the responses, a semi-structured interview was conducted among 52 software engineers. A qualitative content analysis of the interview transcripts resulted in 33 criteria. Criteria that were similar, synonymous and complementary were combined. An acceptable interrater reliability was obtained in the content coding and categorization process (Krippendorff’s α = 0.822). This was followed by a focus group discussion among employers (represented by 15 project managers) and 11 criteria were eliminated and seven were added. In the second phase, the importance of 28 criteria were sought using a questionnaire based survey. A simple random sampling was adopted and 498 responses were received. (Cronbach’s α = 0.786). After elimination for incompleteness and erratic information, responses from 443 participants were considered for quantitative analysis. An exploratory factor analysis was conducted on the responses with 28 criteria subjected to exploratory factor analysis. Two criteria were not included for analysis due to a low mean sampling error value. The 26 most relevant criteria were categorized into six factors based on their factor loading. The main criteria factors were titled: Diagnostic, Dynamic, Proactive, Prompt, Resourceful and Responsible. These factors and the criteria within these factors can be used for continuously evaluating the performance of employees.

Validation of Satellite Rainfall Product (GPM-IMERG) an Bali and Nusa Tenggara: A Comparison of Normal Seasons, El Nino and La Nina Events

Bali and Nusa Tenggara are regions where monsoonal wind changes and strange interactions between the ocean and atmosphere influence rainfall. The purpose of this research is to evaluate Integrated Multi-Satellite Retrievals for GPM (IMERG) rainfall data using in-situ observations from Bali and Nusa Tenggara, Indonesia, while considering seasonal variations and the El Nino-Southern Oscillation (ENSO) phenomenon. The study combines rainfall data from synoptic stations with rain gauge measurements over ten years, from January 2012 to December 2021, to obtain more accurate verification results. The study's findings indicate that, apart from the transitional seasons, IMERG data provides substantial estimates of monthly rainfall accumulation with low error values for both light and heavy rainfall. The study also reveals that the islands' complexity and topography can impact each province's validation values. The verification results show excellent accuracy in flat terrain areas and moderate elevations, while performance decreases in regions with high altitudes. These findings are significant because IMERG data can estimate rainfall for regions lacking monitoring stations during specific seasons and active ENSO conditions. Thus, this information can serve as a valuable tool to address the issue of data unavailability in hard-to-access areas and contribute to optimizing water resource management and weather-related disaster mitigation. Keywords: Validation, Rainfall, IMERG, ENSO

Improved Reptile Search Algorithm for Optimal Design of Solar Photovoltaic Module

This study focuses on the vital role of parameter extraction in optimizing and evaluating solar photovoltaic (PV) systems, as it directly influences their efficiency in converting solar energy to electricity. Researchers have extensively explored the application of various metaheuristic algorithms to accurately estimate solar PV parameters due to their crucial significance, leading to an extensive body of literature on the subject. However, the search for a robust and user-friendly optimizer with high convergence ability remains a challenging task that demands further research. To address this challenge, the study conducts a comprehensive comparative analysis of the RSALF optimizer, an innovative metaheuristic algorithm combining the reptile search algorithm (RSA) with Lévy flight (LF), for parameter extraction of PV model parameters using the Photowatt-PWP201 PV module as a case study. The experimental results demonstrate the RSALF optimizer's remarkable accuracy in parameter estimation, consistently yielding lower root mean square error values and closely aligning with experimental data. Moreover, comparative analysis with other recent optimization approaches highlights the RSALF optimizer's superiority, making it a promising tool for advancing the optimization of PV models and facilitating more efficient and sustainable solar energy utilization.

Comparison of intracranial pressure prediction in hydrocephalus patients among linear, non-linear, and machine learning regression models in Thailand.

Hydrocephalus (HCP) is one of the most significant concerns in neurosurgical patients because it can cause increased intracranial pressure (ICP), resulting in mortality and morbidity. To date, machine learning (ML) has been helpful in predicting continuous outcomes. The primary objective of the present study was to identify the factors correlated with ICP, while the secondary objective was to compare the predictive performances among linear, non-linear, and ML regression models for ICP prediction. A total of 412 patients with various types of HCP who had undergone ventriculostomy was retrospectively included in the present study, and intraoperative ICP was recorded following ventricular catheter insertion. Several clinical factors and imaging parameters were analyzed for the relationship with ICP by linear correlation. The predictive performance of ICP was compared among linear, non-linear, and ML regression models. Optic nerve sheath diameter (ONSD) had a moderately positive correlation with ICP (r=0.530, P<0.001), while several ventricular indexes were not statistically significant in correlation with ICP. For prediction of ICP, random forest (RF) and extreme gradient boosting (XGBoost) algorithms had low mean absolute error and root mean square error values and high R2 values compared to linear and non-linear regression when the predictive model included ONSD and ventricular indexes. The XGBoost and RF algorithms are advantageous for predicting preoperative ICP and establishing prognoses for HCP patients. Furthermore, ML-based prediction could be used as a non-invasive method.

Long-term validation of Aeolus L2B wind products at Punta Arenas, Chile, and Leipzig, Germany

Abstract. Ground-based observations of horizontal winds have been performed at Leipzig (51.35∘ N, 12.43∘ E), Germany, and at Punta Arenas (53.15∘ S, 70.91∘ W), Chile, in the framework of the German initiative EVAA (Experimental Validation and Assimilation of Aeolus observations) with respect to the validation of the Mie and Rayleigh wind products of Aeolus (L2B data). In Leipzig, at the Leibniz Institute for Tropospheric Research (TROPOS), radiosondes have been launched for the Aeolus overpasses on each Friday (ascending orbit) since the middle of May 2019. In Punta Arenas, scanning Doppler cloud radar observations have been performed in the framework of the DACAPO-PESO campaign (dacapo.tropos.de) for more than 3 years from the end of 2018 until the end of 2021 and could be used to validate Aeolus measurements on its ascending and descending orbits. We present two case studies and long‐term statistics of the horizontal winds derived with the ground-based reference instruments compared to Aeolus horizontal line-of-sight (HLOS) winds. The wind products of Aeolus considered are the Mie cloudy and Rayleigh clear products. It was found that the deviation of the Aeolus HLOS winds from the ground reference is usually of Gaussian shape, which allowed the use of the median bias and the scaled median absolute deviation (MAD) for the determination of the systematic and random errors of Aeolus wind products, respectively. The case study from August 2020 with impressive atmospheric conditions at Punta Arenas shows that Aeolus is able to capture strong wind speeds of up to more than 100 m s−1. The long-term validation was performed in Punta Arenas covering the period from December 2018 to November 2021 and in Leipzig from May 2019 until September 2022. This analysis showed that the systematic error of the Aeolus wind products could be significantly lowered during the mission lifetime with the changes introduced into the processing chain (different versions are called baselines). While in the early mission phase, systematic errors of more than 2 m s−1 (absolute values) were observed for both wind types (Mie and Rayleigh), these biases could be reduced with the algorithm improvements, such as the introduction of the correction for temperature fluctuations at the main telescope of Aeolus (M1 temperature correction) with Baseline 09. Hence, since Baseline 10, a significant improvement in the Aeolus data was found, leading to a low systematic error (close to 0 m s−1) and similar values for the midlatitudinal sites in both hemispheres. The random errors for both wind products were first decreasing with an increasing baseline but later increasing again due to performance losses of the Aeolus lidar instrument. Nevertheless, no significant increase in the systematic error in the Aeolus wind products was found. Thus, one can conclude that the uncertainty introduced by the reduced atmospheric return signal received by Aeolus mostly affects the random error. Even when considering all the challenges during the mission, we can confirm the general validity of Aeolus observations during its lifetime. Therefore, this space explorer mission could demonstrate that it is possible to perform active wind observations from space with the applied technique.