Short-Term Solar Irradiance Forecasting Based on a Hybrid Deep Learning Methodology

Water quality prediction (WQP) plays an essential role in water quality management for aquaculture to make aquaculture production profitable and sustainable. In this work, we propose hybrid deep learning (DL) models, convolutional neural network (CNN) with the long short-term memory (LSTM) and gated recurrent unit (GRU) for aquaculture WQP. CNN can effectively fetch the aquaculture water quality characteristics, whereas GRU and LSTM can learn long-term dependencies in the time series data. We conduct experiments using the two different water quality datasets and present an extensive study on the impact of hyperparameters on the performance of the proposed hybrid DL models. Furthermore, the performance of hybrid CNN-LSTM and CNN-GRU models are compared with different baseline LSTM, GRU and CNN DL models and also with attention-based LSTM and attention-based GRU DL models. The results show that the hybrid CNN-LSTM outperformed all other models in terms of prediction accuracy and computation time.

Parts of Speech (pos) tagging corresponds to techniques of tagging accurate pos tags of each word of a sentence. It is a pivotal and indispensable part of sentiment analysis, synthesizing text to speech, analyzing textual data and many more Natural Language Processing (NLP) tasks. Though there are many researches done in the field of languages like English, Chinese etc., it is still comparatively unexplored for Bangla. An excellent pos tagger in Bangla language can accelerate NLP of Bangla textual data. In this study, we have developed a novel hybrid Deep Learning (DL) model with two parallel input networks with Convolutional Neural Network (CNN), and Bidirectional Long Short Term Memory (BiLSTM), and an output network of CNN. CNN works well regarding the local dependencies of words in sentences, and BiLSTM works well with the global dependencies of words regarding the context in a sentence. No other work has been done with local features of textual data along with long term word dependencies in Bangla pos tagging studies. The model can work with any external Word Embeddings. In this study, it is implemented with both Embedding Layer and Word2Vec layer. In the evaluation process, Mathews Correlation Coefficient (MCC), Precision-Recall curve are used along with accuracy and F1-score due to the dataset's imbalanced characteristic. Our proposed model accompanied by Word2Vec layer has outperformed Vanilla Recurrent Neural Network (RNN), Gated Recurrent Units (GRU), Long Short Term Memory (LSTM), BiLSTM networks, and also one recent study using the same dataset with the highest accuracy of 0.974, F1-score of 0.883, and MCC value of 0.936.

Short-term solar radiation forecasting using hybrid deep residual learning and gated LSTM recurrent network with differential covariance matrix adaptation evolution strategy

Identify suitable artificial groundwater recharge zones using hybrid deep learning models

Small and Medium-sized Enterprises (SMEs) in Sri Lanka are increasingly turning to social media to gain insights into consumer preferences; however, they frequently lack sophisticated analytical tools to derive actionable insights. This research introduces a hybrid deep learning framework aimed at sentiment and emotion analysis specifically for the Sri Lankan cake sector. Customer reviews and social media comments were gathered and processed through various methods including text cleaning, emoji translation, stopword elimination, tokenization, and sequence padding. Several deep learning models— Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Units (GRU) were assessed, along with hybrid models that combined CNN and BiLSTM with GPT-2 embeddings. The CNN+GPT-2 model achieved the highest accuracy in sentiment classification at 96.14%, while BiLSTM performed best in emotion classification with an accuracy of 91.57%. In terms of trend forecasting, Long Short-Term Memory (LSTM) outshone both SARIMA and Prophet, yielding the lowest error metrics and the most reliable sentiment predictions. These results underscore the potential of hybrid deep learning and transformer-based models to effectively capture complex consumer sentiments and provide SMEs with practical, AI-driven insights. This study is among the first to implement such hybrid NLP models within a localized Sri Lankan context, presenting a scalable approach for business intelligence and informed decision-making.

Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capture more information from inputs. For modeling long-term dependencies in a dataset, the gating mechanism concept can help RNNs remember and forget previous information. Representing the hidden layers of an RNN with more expressive operations (i.e., tensor products) helps it learn a more complex relationship between the current input and the previous hidden layer information. These ideas can generally improve RNN performances. In this paper, we proposed a novel RNN architecture that combine the concepts of gating mechanism and the tensor product into a single model. By combining these two concepts into a single RNN, our proposed models learn long-term dependencies by modeling with gating units and obtain more expressive and direct interaction between input and hidden layers using a tensor product on 3-dimensional array (tensor) weight parameters. We use Long Short Term Memory (LSTM) RNN and Gated Recurrent Unit (GRU) RNN and combine them with a tensor product inside their formulations. Our proposed RNNs, which are called a Long-Short Term Memory Recurrent Neural Tensor Network (LSTMRNTN) and Gated Recurrent Unit Recurrent Neural Tensor Network (GRURNTN), are made by combining the LSTM and GRU RNN models with the tensor product. We conducted experiments with our proposed models on word-level and character-level language modeling tasks and revealed that our proposed models significantly improved their performance compared to our baseline models.

This paper presents a real-time, lightweight system for detecting Wi-Fi deauthentication (DA) attacks that uses the NodeMCU ESP8266 microcontroller for live packet sniffing and feature extraction. Tailored for low-power IoT environments, the system combines the sequential learning capabilities of Long short-term memory (LSTM), Gate recurrent unit (GRU), and Recurrent neural network (RNN) with the interpretability of logistic regression (LR). These hybrid models analyze Wi-Fi traffic in real time to detect anomalous behavior based on key metrics such as Received Signal Strength indicator (RSSI), DA, packet count, and Signal noise ratio (SNR), which are also displayed live on an OLED screen. The proposed framework uniquely integrates hybrid temporal deep learning with interpretable classification through (LR) in an ultra-low-cost embedded data acquisition setup through NodeMCU, addressing a gap in existing intrusion detection research that often focuses on either cloud-based processing or non-interpretable model. The system was trained and validated on a dataset of over 5,600 labeled samples collected under varied network conditions. Among the evaluated models, GRU_LR achieved the highest accuracy (96%) and demonstrated superior performance in identifying minority-class threats. By combining explainable AI with cost-effective embedded sensing, this work delivers a practical and transparent intrusion detection approach that can be readily adapted to diverse IoT and wireless security contexts.

Within the scope of this study, a range of advanced machine learning and deep learning models—including Singular Spectrum Analysis (SSA), Adaptive Neuro-Fuzzy Inference System (ANFIS), Categorical Boosting (CatBoost), Convolutional Neural Network (CNN), Deep Autoencoder, Deep Neural Network (DNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM)—were employed to estimate the Standardized Groundwater Index (SGI) in Erzincan Province. SSA was utilized as a preprocessing technique to decompose input variables such as precipitation, relative humidity, temperature, and past SGI values into distinct components including trend, seasonality, cyclicality, and noise. These decomposed components were then fed into the artificial intelligence models to construct hybrid forecasting frameworks. The performance of each hybrid model was evaluated using multiple statistical indicators and visual analyses. The findings demonstrated that incorporating all SSA-derived subcomponents as inputs generally improved the monthly SGI prediction accuracy. However, for 12-month SGI predictions, the results were more variable, with both improvements and deteriorations observed depending on the model configuration. Additionally, the elimination of noise components was found to enhance both model generalization capability and overall prediction performance. Among the models tested, ANFIS emerged as the most effective in capturing GWD dynamics. To further investigate variable importance, Sobol sensitivity analysis was applied to the ANFIS outputs. The analysis revealed that previous SGI-1 values (t − 1) and relative humidity were the most influential inputs in predicting current SGI-1 (t) values.

Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU)

Recently different Deep Learning (DL) models have been emerging to predict the disease amelioration. Generally deep learning is the state of art for learning the multiple representation of neuron. Discriminant DL model includes different architecture and initial architecture is Recurrent Neural Network (RNN) which learn the data labeled in the form of sequence and it has long term dependency and vanishing gradient problem. Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) is an improved version of RNN which deal with problems in RNN. Deep care LSTM is one of the model in LSTM developed by [Trang Pham et.al] for predicting diabetes disease and compared the results with markovian and support vector machine model. In deep LSTM model some problems are reported like short term trajectories, less accuracy. To overcome the problem Deep Care GRU has been proposed to identify the diabetes disease amelioration.

Very short-term forecasting of wind power generation using hybrid deep learning model

Abstract. Rainfall time series prediction is essential for monitoring urban hydrological systems, but it is challenging and complex due to the extreme variability of rainfall. A hybrid deep learning model (VMD-RNN) is used in order to improve prediction performance. In this study, variational mode decomposition (VMD) is first applied to decompose the original rainfall time series into several sub-sequences according to the frequency domain, where the number of decomposed sub-sequences is determined by power spectral density (PSD) analysis. To prevent the disclosure of forthcoming data, non-training time series are sequentially appended for generating the decomposed testing samples. Following that, different recurrent neural network (RNN) variant models are used to predict individual sub-sequences, and the final prediction is reconstructed by summing the prediction results of sub-sequences. These RNN variants are long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM) and bidirectional GRU (BiGRU), which are optimal for sequence prediction. In addition to three common evaluation criteria, mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE), the framework of universal multifractals (UMs) is also introduced to assess the performance of predictions, which enables the extreme variability of predicted rainfall time series to be characterized. The study employs two rainfall time series with daily and hourly resolutions, respectively. The results indicate that the hybrid VMD-RNN model provides a reliable one-step-ahead prediction, with better performance in predicting high and low values than the pure LSTM model without decomposition.

Production prediction plays an important role in decision making, development planning, and economic evaluation during the exploration and development period. However, applying traditional methods for production forecasting of newly developed wells in the conglomerate reservoir is restricted by limited historical data, complex fracture propagation, and frequent operational changes. This study proposed a Gated Recurrent Unit (GRU) neural network-based model to achieve batch production forecasting in M conglomerate reservoir of China, which tackles the limitations of traditional decline curve analysis and conventional time-series prediction methods. The model is trained by four features of production rate, tubing pressure (TP), choke size (CS), and shut-in period (SI) from 70 multistage hydraulic fractured horizontal wells. Firstly, a comprehensive data preprocessing is implemented, including excluding unfit wells, data screening, feature selection, partitioning data set, z-score normalization, and format conversion. Then, the four-feature model is compared with the model considering production only, and it is found that with frequent oilfield operations changes, the four-feature model could accurately capture the complex variance pattern of production rate. Further, Random Forest (RF) is employed to optimize the prediction results of GRU. For a fair evaluation, the performance of the proposed model is compared with that of simple Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) neural network. The results show that the proposed approach outperforms the others in prediction accuracy and generalization ability. It is worth mentioning that under the guidance of continuous learning, the GRU model can be updated as soon as more wells become available.

The climate crisis has sparked a global shift toward renewable energy sources, increasing the demand for models that provide accurate risk assessment and forecasting to support informed investment decisions. The novelty of this study is to analyze renewable energy investments through three methodological approaches: risk assessment, deep learning-based volatility forecasting, and renewable energy demand forecasting. First, risk profiles of two renewable energy stocks (NextEra Energy and Iberdrola) and two traditional energy stocks (ExxonMobil and Chevron) are evaluated for the time period 2020 to 2024. Second, deep learning (DL) models such as recurrent neural network (RNN), long short-term memory (LSTM), gated recurrent unit (GRU), bidirectional long short-term memory (BiLSTM), bidirectional gated recurrent unit (BiGRU) are employed, and it is shown that renewable energy stocks have more stable performance across all DL models, with BiLSTM revealed as the most robust architecture. Third, UK liquid biofuel consumption trends are analyzed using multiple forecasting methods, including Mean, Naïve, Seasonal Naïve, Drift, and machine learning models. It is shown that the neural network autoregressive (NNAR) model has the highest forecast accuracy, and among the combined forecast models, constrained least squares achieved the highest forecast accuracy. The results indicate that renewable energy produces lower risk exposure and more stable returns, and improves predictability despite short-term volatility.

Automatic identification of abnormal and irregular heart rhythms is necessary to reduce mortality. Tachyarrhythmia is a type of abnormally fast heartbeat that can be detected using electrocardiogram (ECG) signals. In the elderly, life-threatening tachyarrhythmia such as ventricular fibrillation (VFIB), atrial fibrillation (AFIB), and atrial flutter (AFL) can lead to sudden cardiac arrest. Here, we present a hybrid deep learning (HDL) model for automatic identification of tachyarrhythmia rhythms from heart rate variability (HRV) datasets based on a one-dimensional convolution neural network (1D CNN) and a long-term short-term memory (LSTM) model. In this study, we used the HRV database with five-second windows as input data for our HDL model. Four different statistical parameters have been used to determine the model efficiency: The average accuracy is 99.19%, the average precision is 91.75%, the recall is 93.63%, and the F1 score is 92.71%. The overall accuracy of the experiment was 98.4%. This model outperformed other state-of-the-art models. As a result, this method can be useful in clinical systems of cardiological care.KeywordsAFIBAFLVFIBHRVCNNLSTM