Daily flow discharge prediction using integrated methodology based on LSTM models: Case study in Brahmani-Baitarani basin

HydroResearch, Год журнала: 2024, Номер 7, С. 272 - 284

Опубликована: Янв. 1, 2024

For flood control, hydropower operation, and agricultural planning, among other applications, flow discharge prediction is a critical first step toward the strong dependable planning management of water resources. Floods are destructive natural calamities that destroy human lives infrastructure across world. Development effective forecasting models for minimising deaths mitigating damages. This study employs hybrid deep learning Long Short Term Memory (LSTM) algorithms like LSTM, Convolution LSTM (Conv-LSTM) Convolutional Neural Network (CNN-LSTM) to predict likelihood events using daily precipitation, temperature relative humidity from two flood-forecasting stations i.e., Champua (Baitarani River, Odisha) Jarikela (Brahmani over 20-year period. The results show CNN-LSTM performed best followed by Conv-LSTM in terms R2 = 0.98055, 0.96564, 0.93244, RMSE 19.137, 35.635, 49.347, MAE 18.372, 33.766, 47.058, NSE 0.971, 0.9517 0.9257 respectively. findings support claim machine algorithms, particular model, can be applied with high accuracy, thereby enhancing hazard management.

Язык: Английский

---

Support Vector Machines in Polymer Science: A Review

Polymers, Год журнала: 2025, Номер 17(4), С. 491 - 491

Опубликована: Фев. 13, 2025

Polymer science, a discipline focusing on the synthesis, characterization, and application of macromolecules, has increasingly benefited from adoption machine learning (ML) techniques. Among these, Support Vector Machines (SVMs) stand out for their ability to handle nonlinear relationships high-dimensional datasets, which are common in polymer research. This review explores diverse applications SVM science. Key examples include prediction mechanical thermal properties, optimization polymerization processes, modeling degradation mechanisms. The advantages contrasted with its challenges, including computational cost, data dependency, need hyperparameter tuning. Future opportunities, such as development polymer-specific kernels integration real-time manufacturing systems, also discussed.

Язык: Английский

---

Evidential-bio-inspired algorithms for modeling groundwater total hardness: A pioneering implementation of evidential neural network for feature selection in water resources management

Environmental Chemistry and Ecotoxicology, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

Язык: Английский

---

Sustainable Water Quality Evaluation Based on Cohesive Mamdani and Sugeno Fuzzy Inference System in Tivoli (Italy)

Sustainability, Год журнала: 2025, Номер 17(2), С. 579 - 579

Опубликована: Янв. 13, 2025

Clean water is vital for a sustainable environment, human wellness, and welfare, supporting life contributing to healthier environment. Fuzzy-logic-based techniques are quite effective at dealing with uncertainty about environmental issues. This study proposes two methodologies assessing quality based on Mamdani Sugeno fuzzy systems, focusing water’s physiochemical attributes, as these provide essential indicators of chemical composition potential health impacts. The goal evaluate using single numerical value which indicates total specific location time. utilizes data from the Acea Group employs inference system combined various defuzzification well weighted average technique. suggested model comprises three middle models along one ultimate model. Each has input variables 27 rules, dataset nine key factors rate drinking purposes. methodology suitable alternative tool water-management plans. Results show final score 85.4% (centroid defuzzification) 83.5% (weighted defuzzification), indicating excellent in Tivoli, Italy. Water evaluation sustainability, ensuring clean resources, protecting biodiversity, promoting long-term health. Intermediate evaluations approach centroid showed amounts 72.4%, 83.4%, 92.5% first, second, third models, respectively. For method, corresponding were 76.2%, 83.5%, 92.5%. These results precision both systems capturing nuanced variations. aims develop logic evaluating index, comprehensive scalable management.

Язык: Английский

---

Enhancing groundwater level prediction accuracy using interpolation techniques in deep learning models

Groundwater for Sustainable Development, Год журнала: 2024, Номер 26, С. 101213 - 101213

Опубликована: Июнь 6, 2024

Язык: Английский

---

Exploring AI approaches for predicting groundwater levels in coastal agro-climatic zones: a case study in Cuttack District, Odisha

Discover Geoscience, Год журнала: 2024, Номер 2(1)

Опубликована: Июнь 24, 2024

Abstract Groundwater level (GWL) prediction across various time scales is essential for efficient management and governance of water resources especially in regions characterized by arid semi-arid climates, it holds great significance. Within certain coastal regions, agro-climatic zones give rise to challenges like scarcity summer waterlogging during the rainy season, resulting reduced GWL periods saltwater intrusion that contaminates groundwater. This study emphasizes on application diverse AI methodologies, encompassing Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), Wavelet Transform-based ANN (W-ANN), ANFIS (W-ANFIS), SVR (W-SVR), LSTM (W-LSTM) models quantitative assessment groundwater Odisha's Cuttack District, aiming comprehend fluctuations region. The investigation leverages historical data from monitoring wells, incorporating monthly datasets rainfall, temperature, relative humidity, GWLs. Through comparative using statistical methods namely Pearson’s R (R), co-efficient determination (R 2 ), Root Mean Squared Error (RMSE), Sum (SSE), most precise robust approach estimation area identified. W-LSTM -0.78196, RMSE- 0.09254, R-0.88428 SSE-2.66357) W-ANFIS -0.74068, RMSE-0.08229, R-0.86063 SSE-2.10596) hybrid algorithms consistently achieved accurate predictions GWLs followed W-SVR, W-ANN all stations. Overall, this demonstrated promising outcomes, offering a dependable foundation planners guide future investigations into resources.

Язык: Английский

---

Modeling of irrigation water quality parameter (sodium adsorption ratio) using hybrid swarm intelligence-based neural networks in a semi-arid environment at SMBA dam, Algeria

Theoretical and Applied Climatology, Год журнала: 2024, Номер 155(8), С. 8299 - 8318

Опубликована: Авг. 1, 2024

Язык: Английский

---

Research on Sustainable Form Design of NEV Vehicle Based on Particle Swarm Algorithm Optimized Support Vector Regression

Sustainability, Год журнала: 2024, Номер 16(17), С. 7812 - 7812

Опубликована: Сен. 7, 2024

With the growing emphasis on eco-friendly and sustainable development concepts, new energy vehicles (NEVs) have emerged as a popular alternative to traditional fuel (FVs). Due absence of an internal combustion engine, electric (EVs) do not require front air intake grille, allowing for more minimalist flexible design. Consequently, aligning EV styling with users’ visual cognition emotional perception is critical objective automakers designers. In this study, we establish mapping relationship between NEV design based experimental data. We introduce Particle Swarm Optimization Support Vector Regression (PSO-SVR) into perceptual engineering (KE) research process predict user emotions using (SVR). To optimize three hyperparameters (penalty coefficient C, RBF kernel function parameter γ, insensitivity loss ε) SVR model, utilize (PSO) algorithm. The results indicate that proposed PSO-SVR model outperforms BPNN models in predicting emotions. This effectively captures nonlinear battery vehicle (BEV) morphological features cognition, providing novel method enhancing are expected drive innovation technological advancement industry, contributing achievement ambitious goal global eco-friendliness development.

Язык: Английский

---

ML4FF: A machine-learning framework for flash flood forecasting applied to a Brazilian watershed

Journal of Hydrology, Год журнала: 2025, Номер unknown, С. 132674 - 132674

Опубликована: Янв. 1, 2025

Язык: Английский

---

Evaporation forecasting using different machine learning models in Beni Haroun Dam, Algeria

Theoretical and Applied Climatology, Год журнала: 2025, Номер 156(2)

Опубликована: Янв. 18, 2025

Язык: Английский

---