SMGformer: integrating STL and multi-head self-attention in deep learning model for multi-step runoff forecasting

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 9, 2024

Accurate runoff forecasting is of great significance for water resource allocation flood control and disaster reduction. However, due to the inherent strong randomness sequences, this task faces significant challenges. To address challenge, study proposes a new SMGformer forecast model. The model integrates Seasonal Trend decomposition using Loess (STL), Informer's Encoder layer, Bidirectional Gated Recurrent Unit (BiGRU), Multi-head self-attention (MHSA). Firstly, in response nonlinear non-stationary characteristics sequence, STL used extract sequence's trend, period, residual terms, multi-feature set based on 'sequence-sequence' constructed as input model, providing foundation subsequent models capture evolution runoff. key features are then captured layer. Next, BiGRU layer learn temporal information these features. further optimize output MHSA mechanism introduced emphasize impact important information. Finally, accurate achieved by transforming through Fully connected verify effectiveness proposed monthly data from two hydrological stations China selected, eight compare performance results show that compared with Informer 1th step MAE decreases 42.2% 36.6%, respectively; RMSE 37.9% 43.6% NSE increases 0.936 0.975 0.487 0.837, respectively. In addition, KGE at 3th 0.960 0.805, both which can maintain above 0.8. Therefore, accurately sequence extend effective period

Язык: Английский

---

Active packaging coating based on Lepidium sativum seed mucilage and propolis extract: Preparation, characterization, application and modeling the preservation of buffalo meat

PLoS ONE, Год журнала: 2024, Номер 19(10), С. e0311802 - e0311802

Опубликована: Окт. 9, 2024

Buffalo meat is naturally perishable, making it susceptible to spoilage due its high moisture content and vulnerability microbial contamination. Edible coatings have attracted attention as a packaging method that can prolong the shelf life of meat. The study aimed examine impact combination Lepidium sativum mucilage (LS) coating propolis extract (PE) on prolonging buffalo chemical characteristics (chemical compounds, total phenol (TPC), flavonoid (TFC), antioxidant activity, cytotoxicity) antimicrobial activity PE (disk diffusion agar, well minimum inhibitory concentration, bactericidal concentration) were investigated. effect cell wall pathogenic bacteria was examined using scanning electron microscope. Biological properties LS (TPC, TFC, (pour plate method)) Different concentrations (0, 0.5, 1.5, 2.5%) added mixture containing LS, their effects extending samples stored at 4°C for 9 days assessed. included gallic acid, benzoic syringic 4-3 dimethoxy cinnamic p-coumaric myricetin, caffeic luteolin, chlorogenic apigenin. determined TPC 36.67 ± 0.57 mg GAE/g TFC 48.02 0.65 QE/g. extract's radical scavenging ranged from 0 76.22% DPPH radicals 50.31% ABTS radicals. viability C115 HeLa observed be 94.14 μg/mL. exhibited strong against bacteria. 15.23 0.43 11.51± 0.61 429.65 1.28 μg/mL 403.59 1.46 microbiological analysis revealed LS+2.5%PE treatment most effective in inhibiting growth viable count (6.23 vs. 8.00 log CFU/g), psychrotrophic (3.71 4.73 coliforms (2.78 3.70 fungi (2.39 3.93 CFU/g) compared control sample. addition edible also demonstrated concentration-dependent preserving moisture, pH, color, hardness Sensory evaluation results suggested incorporating into extended by three days. In second stage this paper, investigation employed two distinct forecasting methodologies: Radial Basis Function (RBF) Support Vector Machine (SVM), predict range quality indicators coated products. Upon comparison, RBF model higher level accuracy, showcasing exceptional capacity closely match experimental outcomes. Therefore, type food coating, renowned properties, has potential effectively package preserve perishable delicate items, such

Язык: Английский

---

A state-of-the-art review of long short-term memory models with applications in hydrology and water resources

Applied Soft Computing, Год журнала: 2024, Номер unknown, С. 112352 - 112352

Опубликована: Окт. 1, 2024

Язык: Английский

---

Biochar energy prediction from different biomass feedstocks for clean energy generation

Environmental Technology & Innovation, Год журнала: 2025, Номер unknown, С. 104012 - 104012

Опубликована: Янв. 1, 2025

Язык: Английский

---

Life cycle assessment and comparison of the conventional and third generation of photovoltaic panels

Journal of the Brazilian Society of Mechanical Sciences and Engineering, Год журнала: 2025, Номер 47(2)

Опубликована: Янв. 9, 2025

Язык: Английский

---