Dynamic Forecasting of Solar Energy Microgrid Systems Using Feature Engineering

Introduction: Air quality forecasting, particularly predicting Particulate Matter (PM 2.5 ) concentrations, has gained significant attention due to itscritical implications for public health and environmental management.Accurately predicting PM2.5 , a harmful air pollutant associated with respiratory and cardiovascular diseases, is vital for effective air quality management in densely populated urban areas. Materials and methods: This study uses various meteorological and environmental data combinations in Tehran, Iran, this study investigates the efficacy of three predictive modeling techniques Auto Regressive Integrated Moving Average (ARIMA), Extreme Gradient Boosting (XGBoost), and Long Short-Term Memory (LSTM) in forecasting daily and monthly PM2.5levels. The models were evaluated based on performance metrics such as RootMean Square Error (RMSE), Mean Absolute Error (MAE), and R² scores. Results: Results indicate that XGBoost excelled in daily predictions when using solely meteorological data, achieving an R² score of 0.998674, while ARIMA demonstrated strong predictive capacity but struggled with added complexity. LSTM maintained reasonable performance amidst increased data input but faced challenges in both daily and monthly forecasts. Monthly predictions from all models proved less reliable, particularly with ARIMA yielding negative R² values, indicating suboptimal performance compared to simplistic models. Conclusion: The findings highlight the importance of model selection and feature engineering in accurately predicting PM2.5 levels. The study suggests a shift towards hybrid modeling approaches and incorporating diverse environmental data to enhance forecasting accuracy in air quality management, particularly for long-term predictions.

Solar energy produced by photovoltaic panels is a vital energy source that offers numerous benefits to both the environment and society. However, meteorological variables such as solar irradiation, weather patterns, precipitation and climate conditions present significant challenges to seamless energy integration into the power grid. Accurate forecasting is essential to maintain supply-demand balance, optimize energy storage and ensure grid stability. This study leverages machine learning (ML) techniques to predict solar power generation and address renewable energy integration challenges. Nine ML models were employed, including linear regression, autoregressive integrated moving average (ARIMA), artificial neural network (ANN), support vector machines (SVM), random forest (RF), decision tree, gradient boosting machine (GBM), light gradient boosting (LGBM) and extreme gradient boosting (XGBM). Inputs such as irradiance, humidity, minimum temperature, maximum temperature and surface pressure were used to train these models. The model performances were evaluated using metrics like root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The results highlighted ANN as the most effective model, achieving an RMSE of 274.84 kWh, MAE of 245.93 kWh and a MAPE of 5.26 %. This research contributes to the existing literature by addressing the relatively unexplored application of multiple machine learning models for predicting energy output from photovoltaic systems. A key novelty of this study is its ability to achieve accurate solar power forecasts using a limited dataset from a newly installed solar power plant, unlike many existing studies that rely on large volumes of data. Additionally, it explores the solar power production potential of Namakkal district in Tamil Nadu, India-a region with limited prior research.

Urban rail transit features much strength, such as large capacity, safety and environment-friendliness, and it becomes a preferred choice for most passengers. It also plays a prominent part in solving urban traffic problems. In order to improve the operation efficiency of the urban rail transit system and achieve the goal of smart operations, this paper applies machine learning algorithms and completes the feature engineering of urban rail transit passenger flow data in terms of time, space and external factors. Based on passenger flow characteristics as collected, we build the short-term passenger flow forecast models, which include light gradient boosting machine (LightGBM) model, long short-term memory (LSTM) model, and LightGBM-LSTM fusion model. Besides, we construct the autoregressive integrated moving average (ARIMA) model and extreme gradient boosting (XGBoost) model for experiment comparison. Finally, we conduct the passenger flow forecasting experiments on the Hangzhou subway dataset based on the five prediction-models mentioned above. Then, five types of subway stations are selected (residential type, occupation type, residential-occupation type, business type, and transportation hubs type) and three accuracy evaluation indicators are chosen (mean absolute error, root mean square error and mean absolute percentage error) to evaluate the prediction accuracy of the five prediction models. The experimental results show that, the multi-feature machine learning model can effectively forecast urban rail transit short-term passenger flow which is difficult for the traditional time series model. However, the single model has poor adaptability to different types of subway stations. Compared with a single model, LightGBM-LSTM model equipped with merits of multiple models, fulfills a better function in forecasting and a better adaptability to different types of urban rail transit stations.

BackgroundAccurate incidence prediction of sexually transmitted diseases (STDs) is critical for early prevention and better government strategic planning. In this paper, four different forecasting models were presented to predict the incidence of AIDS, gonorrhea, and syphilis.MethodsThe annual percentage changes in the incidence of AIDS, gonorrhea, and syphilis were estimated by using joinpoint regression. The performance of four methods, namely, the autoregressive integrated moving average (ARIMA) model, Elman neural network (ERNN) model, ARIMA-ERNN hybrid model and long short-term memory (LSTM) model, were assessed and compared. For 1-year prediction, the collected data from 2011 to 2020 were used for modeling to predict the incidence in 2021. For 5-year prediction, the collected data from 2011 to 2016 were used for modeling to predict the incidence from 2017 to 2021. The performance was evaluated based on four indices: mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).ResultsThe morbidities of AIDS and syphilis are on the rise, and the morbidity of gonorrhea has declined in recent years. The optimal ARIMA models were determined: ARIMA(2,1,2)(0,1,1)12, ARIMA(1,1,2)(0,1,2)12, and ARIMA(3,1,2)(1,1,2)12 for AIDS, gonorrhea, and syphilis 1-year prediction, respectively; ARIMA (2,1,2)(0,1,1)12, ARIMA(1,1,2)(0,1,2)12, and ARIMA(2,1,1)(0,1,0)12 for AIDS, gonorrhea and syphilis 5-year prediction, respectively. For 1-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS are 23.26, 20.24, 18.34, and 18.63, respectively; For gonorrhea, the MAPEs are 19.44, 18.03, 17.77, and 5.09, respectively; For syphilis, the MAPEs are 9.80, 9.55, 8.67, and 5.79, respectively. For 5-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS are 12.86, 23.54, 14.74, and 25.43, respectively; For gonorrhea, the MAPEs are 17.07, 17.95, 16.46, and 15.13, respectively; For syphilis, the MAPEs are 21.88, 24.00, 20.18 and 11.20, respectively. In general, the performance ranking of the four models from high to low is LSTM, ARIMA-ERNN, ERNN, and ARIMA.ConclusionThe time series predictive models show their powerful performance in forecasting STDs incidence and can be applied by relevant authorities in the prevention and control of STDs.

Crime and violation are the threat to justice and meant to be controlled. Accurate crime prediction and future forecasting trends can assist to enhance metropolitan safety computationally. The limited ability of humans to process complex information from big data hinders the early and accurate prediction and forecasting of crime. The accurate estimation of the crime rate, types and hot spots from past patterns creates many computational challenges and opportunities. Despite considerable research efforts, yet there is a need to have a better predictive algorithm, which direct police patrols toward criminal activities. Previous studies are lacking to achieve crime forecasting and prediction accuracy based on learning models. Therefore, this study applied different machine learning algorithms, namely, the logistic regression, support vector machine (SVM), Naïve Bayes, k-nearest neighbors (KNN), decision tree, multilayer perceptron (MLP), random forest, and eXtreme Gradient Boosting (XGBoost), and time series analysis by long-short term memory (LSTM) and autoregressive integrated moving average (ARIMA) model to better fit the crime data. The performance of LSTM for time series analysis was reasonably adequate in order of magnitude of root mean square error (RMSE) and mean absolute error (MAE), on both data sets. Exploratory data analysis predicts more than 35 crime types and suggests a yearly decline in Chicago crime rate, and a slight increase in Los Angeles crime rate; with fewer crimes occurred in February as compared to other months. The overall crime rate in Chicago will continue to increase moderately in the future, with a probable decline in future years. The Los Angeles crime rate and crimes sharply declined, as suggested by the ARIMA model. Moreover, crime forecasting results were further identified in the main regions for both cities. Overall, these results provide early identification of crime, hot spots with higher crime rate, and future trends with improved predictive accuracy than with other methods and are useful for directing police practice and strategies.

Abstract: This research is driven by the challenges faced by Universitas Lancang Kuning (UNILAK) in attracting applicants amidst intense competition, especially after the government's policy opened independent pathways to State Universities (PTN) from 2022-2023, which impacted private university applicant numbers. To address this and support strategic planning, this study aims to predict the trend of prospective students applying to all study programs at UNILAK for the period 2025-2027. Two time series models were employed: ARIMA (AutoRegressive Integrated Moving Average) and LSTM (Long Short-Term Memory). Applicant data from 2019 to 2024 was used to build the model. The Augmented Dickey-Fuller (ADF) test confirmed the data's stationarity with a p-value of 0.0. ACF and PACF analyses determined the ARIMA parameters as p=1, d=1, q=1. The LSTM model was trained to capture more complex data patterns. ARIMA predictions for 2025, 2026, and 2027 are 3298.66, 3362.33, and 3371.30, respectively. LSTM predictions for the same years are 3335.64, 3476.52, and 3518.42. Evaluation using Root Mean Squared Error (RMSE) showed ARIMA (RMSE=588.72) to be more accurate than LSTM (RMSE=653.96). Nevertheless, LSTM provided a more optimistic prediction. This study concludes that ARIMA is better suited for short-term planning, while LSTM can be used for more ambitious long-term strategies. Keywords: arima; LSTM; applicants; prediction; university Abstrak: Penelitian ini didorong oleh tantangan Universitas Lancang Kuning (UNILAK) dalam menarik pendaftar di tengah persaingan ketat, khususnya setelah kebijakan pemerintah membuka jalur mandiri ke Perguruan Tinggi Negeri (PTN) sejak 2022-2023, yang menyebabkan penurunan jumlah pendaftar di universitas swasta. Untuk mendukung perencanaan strategis, studi ini bertujuan memprediksi tren jumlah calon mahasiswa yang mendaftar ke seluruh program studi di UNILAK untuk periode 2025-2027.Dua model deret waktu digunakan: ARIMA (AutoRegressive Integrated Moving Average) dan LSTM (Long Short-Term Memory). Data jumlah pendaftar dari 2019 hingga 2024 digunakan untuk membangun model. Uji Augmented Dickey-Fuller (ADF) menunjukkan data stasioner dengan p-value 0,0. Analisis ACF dan PACF menentukan parameter ARIMA sebagai p=1, d=1, q=1. Model LSTM dilatih untuk menangkap pola data yang lebih kompleks.Prediksi ARIMA untuk 2025, 2026, dan 2027 adalah 3298.66, 3362.33, dan 3371.30. Prediksi LSTM untuk tahun yang sama adalah 3335.64, 3476.52, dan 3518.42. Evaluasi menggunakan Root Mean Squared Error (RMSE) menunjukkan ARIMA (RMSE=588.72) lebih akurat daripada LSTM (RMSE=653.96). Meskipun demikian, LSTM memberikan prediksi yang lebih optimis. Studi ini menyimpulkan ARIMA lebih cocok untuk perencanaan jangka pendek, sementara LSTM dapat digunakan untuk strategi jangka panjang yang ambisius. Kata kunci: arima; LSTM; pendaftar; prediksi; universitas

Accurate and efficient prediction of oilfield productivity is very important for the formulation of development and adjustment plans. Machine learning (ML) productivity prediction model can quickly obtain the productivity of oilfield development. In this paper, an oilfield development productivity prediction model based on five ML algorithms including multivariable linear regression (LR), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), back propagation (BP) neural network and long short term memory (LSTM) neural network is established. Through the evaluation of model performance indicators (include the root mean square error (RMSE), the coefficient of determination (R2), the mean absolute error (MAE) and mean absolute percentage error (MAPE)), the best performance prediction model is selected. The research results show that the prediction results of LR model are greatly affected by the data of high productivity oil wells, XGBoost model are easily affected by fitting, and BP neural network model is far less effective than other models. Through comprehensive comparison of prediction results, LightGBM model has better stability and generalization performance. The difference between the prediction results of each model is mainly caused by the characteristics of the algorithm and the size of the data sets. At the same time, LSTM can predict the future oil well production based on the oil well time series observation data. The research results of this paper have guiding significance for the selection of productivity prediction model for oilfield development based on data-driven.

Dengue hemorrhagic fever (DHF) is one of the most widespread and deadly diseases in several parts of Indonesia. An accurate forecast-based model is required to reduce the incidence rate of this disease. Time-series methods such as autoregressive integrated moving average (ARIMA) models are used in epidemiology as statistical tools to study and forecast DHF and other infectious diseases. The present study attempted to forecast the monthly confirmed DHF cases via a time-series approach. The ARIMA, seasonal ARIMA (SARIMA), and long short-term memory (LSTM) models were compared to select the most accurate forecasting method for the deadly disease. The data were obtained from the Surabaya Health Office covering January 2014 to December 2016. The data were partitioned into the training and testing sets. The best forecasting model was selected based on the lowest values of accuracy metrics such as the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The findings demonstrated that the SARIMA (2,1,1) (1,0,0) model was able to forecast the DHF outbreaks in Surabaya City compared to the ARIMA (2,1,1) and LSTM models. We further forecasted the DHF cases for 12 month horizons starting from January 2017 to December 2017 using the SARIMA (2,1,1) (1,0,0), ARIMA (2,1,1), and LSTM models. The results revealed that the SARIMA (2,1,1) (1,0,0) model outperformed the ARIMA (2,1,1) and LSTM models based on the goodness-of-fit measure. The results showed significant seasonal outbreaks of DHF, particularly from March to September. The highest cases observed in May suggested a significant seasonal correlation between DHF and air temperature. This research is the first attempt to analyze the time-series model for DHF cases in Surabaya City and forecast future outbreaks. The findings could help policymakers and public health specialists develop efficient public health strategies to detect and control the disease, especially in the early phases of outbreaks.

Examining nonlinear effects of socioecological drivers on urban solar energy development in China using machine learning and high-dimensional data

Comparing modern and traditional modeling methods for predicting soil moisture in IoT-based irrigation systems

Solar energy is one of the most promising renewable energy sources in Indonesia, particularly in Bali, which has relatively high solar irradiance throughout the year. However, daily variability in solar radiation caused by weather conditions and atmospheric factors leads to fluctuations in solar energy production, making accurate forecasting essential for effective energy planning. This study aims to evaluate the performance of the Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and hybrid ARIMA–LSTM models in forecasting daily solar energy at the Jembrana Climatological Station, Bali. The dataset consists of 10-minute solar radiation observations obtained from an Automatic Weather Station (AWS) for the period January 2023 to September 2025, which were aggregated into daily solar energy values expressed in kWh/m². Data preprocessing included missing value handling, outlier correction, normalization, and an 80:20 split between training and testing datasets. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results show that the hybrid ARIMA–LSTM model achieved the best performance, with an RMSE of 0.960 kWh/m², MAE of 0.771 kWh/m², and MAPE of 22.245%, outperforming both the ARIMA and LSTM models. These findings indicate that the hybrid approach is more effective in capturing both linear and nonlinear characteristics of daily solar energy time series.

ObjectivesHuman brucellosis is a public health problem endangering health and property in China. Predicting the trend and the seasonality of human brucellosis is of great significance for its prevention. In...

The forecasting of evapotranspiration (ET) in some water-stressed regions remains a major challenge due to the lack of reliable and sufficient historical datasets. For efficient water balance, ET remains the major component and its proper forecasting and quantifying is of the utmost importance. This study utilises the 18-year (2001 to 2018) MODIS ET obtained from a drought-affected irrigation scheme in the Eastern Cape Province of South Africa. This study conducts a teleconnection evaluation between the satellite-derived evapotranspiration (ET) time series and other related remotely sensed parameters such as the Normalised Difference Vegetation Index (NDVI), Normalised Difference Water Index (NDWI), Normalised Difference Drought Index (NDDI), and precipitation (P). This comparative analysis was performed by adopting the Mann–Kendall (MK) test, Sequential Mann–Kendall (SQ-MK) test, and Multiple Linear Regression methods. Additionally, the ET detailed time-series analysis with the Keiskamma River streamflow (SF) and monthly volumes of the Sandile Dam, which are water supply sources close to the study area, was performed using the Wavelet Analysis, Breaks for Additive Seasonal and Trend (BFAST), Theil–Sen statistic, and Correlation statistics. The MODIS-obtained ET was then forecasted using the Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANNs) for a period of 5 years and four modelling performance evaluations such as the Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and the Pearson Correlation Coefficient (R) were used to evaluate the model performances. The results of this study proved that ET could be forecasted using these two time-series modeling tools; however, the ARIMA modelling technique achieved lesser values according to the four statistical modelling techniques employed with the RMSE for the ARIMA = 37.58, over the ANN = 44.18; the MAE for the ARIMA = 32.37, over the ANN = 35.88; the MAPE for the ARIMA = 17.26, over the ANN = 24.26; and for the R ARIMA = 0.94 with the ANN = 0.86. These results are interesting as they give hope to water managers at the irrigation scheme and equally serve as a tool to effectively manage the irrigation scheme.

A digital currency known as a cryptocurrency uses blockchain technology to record transactions electronically, guaranteeing security and transparency. Cryptocurrencies, in contrast to conventional hard currency, are virtual or soft currencies; that do not exist in the actual world like coins or banknotes. Since all transactions occur digitally, cryptocurrencies are decentralized and frequently stand-alone from conventional financial institutions. Peer-to-peer transfers, increased anonymity, and often quicker transaction processing without middlemen are made possible by this. In this study, two machine learning models; autoregressive integrated moving average (ARIMA), extreme gradient boosting (XGBoost), and two deep learning models; long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM) were compared. By employing past Bitcoin data from 2012 to 2020, we evaluated the models' mean absolute error (MAE) and root mean squared error (RMSE). Compared to other models, the Bi-LSTM model yields minimal RMSE scores of 67.18 and MAE scores of 24.73. This aids in capturing all temporal correlations, which are important for forecasting the price of Bitcoin.

Accurate prediction of lower limb joint angles is essential for enabling natural human-exoskeleton interaction in rehabilitation robotics. This study proposes a novel framework for knee joint angle prediction using surface electromyography (sEMG) signals, integrating an XGBoost-driven feature selection algorithm and a multiattention hybrid-enhanced long short-term memory (LSTM) network. First, sEMG signals were acquired from healthy participants during dynamic lower limb movements. After preprocessing, temporal and spectral features were extracted, after which the eXtreme Gradient Boosting (XGBoost) algorithm was applied to eliminate redundant features, reducing input dimensionality while maintaining predictive accuracy. Finally, the reduced features were fed into the proposed model, which leverages hybrid attention mechanisms to enhance temporal dependencies and feature relevance. The experimental results validate that the XGBoost-driven feature selection framework significantly minimizes redundancy in sEMG feature extraction. When evaluating the performance of joint angle prediction, the mean absolute error (MAE), root mean square error (RMSE), adjusted <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${R}^{{2}}$ </tex-math></inline-formula>, and Pearson correlation coefficient (CC) of the proposed model were 2.47°, 3.55°, 0.95, and 0.98, outperforming traditional machine learning (ML) algorithms and the benchmarks CNN, LSTM, TCN, and CNN-BiLSTM. The framework’s superior computational efficiency and prediction accuracy highlight its potential for real-time implementation in exoskeleton systems, addressing critical limitations in existing control paradigms. This advancement paves the way for adaptive human-robot collaboration in clinical rehabilitation settings.