Research on a Multi-Dimensional Indicator Assessment Model for Evaluating Landslide Risk near Large Alpine Reservoirs DOI Creative Commons

Hanyin Hu,

Ke Hu, Xinyao Zhang

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(12), P. 5201 - 5201

Published: June 14, 2024

Geological disasters in large alpine reservoirs primarily take the form of landslide occurrences and are predominantly induced by slope instability. Presently, risk monitoring assessment strategies tend to prioritize sudden alerts overlooking progressive trajectories from onset creeping deformations within its critical state preceding landslides. Hence, analyzing safety risks over time demonstrates a significant degree hysteresis, highlighting necessity for comprehensive approach that encompasses both gradual precursors events. This study analyzes factors affecting stability establishes evaluation indicator system includes terrain morphology, meteorological conditions, ecological environment, soil human activity, external manifestation. It proposes quantitative model based on fuzzy broad learning system, aiming accurately assess slopes with different levels. The overall accuracy rate reaches 92.08%. multi-dimensional provides long-term conditions scientific guidance management disaster prevention mitigation long scale risky reservoir areas.

Language: Английский

Multi-step prediction of dissolved oxygen in fish pond aquaculture using feature reconstruction-based deep neural network DOI
Yilun Jiang, Lintong Zhang,

C.-K. Chris Wang

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 232, P. 109997 - 109997

Published: Feb. 6, 2025

Language: Английский

Citations

1
Prediction of landfill gases concentration based on Grey Wolf Optimization – Support Vector Regression during landfill excavation process DOI
Zhimin Liu,

Zehua Zhang,

Qingwen Zhang

et al.

Waste Management, Journal Year: 2025, Volume and Issue: 198, P. 128 - 136

Published: March 4, 2025

Language: Английский

Citations

0
Enhanced Landslide Risk Evaluation in Hydroelectric Reservoir Zones Utilizing an Improved Random Forest Approach DOI Open Access

Aimin Wei,

Ke Hu,

Shuni He

et al.

Water, Journal Year: 2025, Volume and Issue: 17(7), P. 946 - 946

Published: March 25, 2025

Landslides on reservoir slopes are one of the key geologic hazards that threaten safe operation hydropower plants. The aim our study was to reduce limitations existing methods landslide risk assessment when dealing with complex nonlinear relationships and difficulty quantifying uncertainty predictions. We established a multidimensional system covers geological settings, meteorological conditions, ecological environment, we proposed model integrates Bayesian theory random forest algorithm. In addition, quantifies through probability distributions provides confidence intervals for prediction results, thus significantly improving usefulness reliability assessment. this study, adopted Gini index SHAP (SHapley Additive exPlanations) value, an analytical methodology, reveal factors affecting slope stability their interaction. empirical results obtained show effectively identifies also accurate risk, enhancing scientific targeted decision making. This offers strong support managing providing more solid guarantee station sites.

Language: Английский

Citations

0
Energy Efficiency and Mathematical Modeling of Shrimp Pond Oxygenation: A Multiple Regression Experimental Study DOI Creative Commons
Yoisdel Castillo Álvarez, Yorlan González González, Reinier Jiménez Borges

et al.

Eng—Advances in Engineering, Journal Year: 2024, Volume and Issue: 5(4), P. 2862 - 2885

Published: Nov. 4, 2024

Aquaculture is one of the key economic activities to reduce food shortages worldwide. Water recirculation systems using pumps are crucial maintain oxygenation and water quality, consuming about 35% total energy in this activity. This research proposes a multiple linear regression mathematical model optimize intensive shrimp aquaculture by reducing consumption minimizing changes ponds. The proposed optimizing operation pumping systems, allowing us significantly turnover without compromising dissolved oxygen levels as function variables such volume, biomass, solar radiation (0–1200 W/m2), temperature (20 °C–32 °C), phytoplankton (0–1,000,000 cells/ml), zooplankton (0–500,000 wind speed (0–15 m/s). These integrated into model, managing explain 94.02% variation oxygen, with an R2 92.9%, which adjusts system conditions real time, impact environmental fluctuations on quality. leads estimated annual savings 106,397.5 kWh, 663.8 MWh. contributes development approach that not only improves prediction, but also minimizes use resources, improving sustainability profitability farming robust tool maximizes operational efficiency aquaculture, particularly where management critical.

Language: Английский

Citations

2
A Variational Mode Decomposition–Grey Wolf Optimizer–Gated Recurrent Unit Model for Forecasting Water Quality Parameters DOI Creative Commons
Binglin Li,

Fengyu Sun,

Yufeng Lian

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(14), P. 6111 - 6111

Published: July 13, 2024

Water is a critical resource globally, covering approximately 71% of the Earth’s surface. Employing analytical models to forecast water quality parameters based on historical data key strategy in field monitoring and treatment. By using forecasting model, potential changes can be understood over time. In this study, gated recurrent unit (GRU) neural network was utilized dissolved oxygen levels following variational mode decomposition (VMD). The GRU network’s were optimized grey wolf optimizer (GWO), leading development VMD–GWO–GRU model for parameters. results indicate that outperforms both standalone GWO–GRU capturing information related Additionally, it shows improved accuracy medium long-term changes, resulting reduced root mean square error (RMSE) absolute percentage (MAPE). demonstrates significant improvement lag parameters, ultimately boosting accuracy. This approach applied effectively serving as solid foundation future treatment strategies.

Language: Английский

Citations

1
Research on a Multi-Dimensional Indicator Assessment Model for Evaluating Landslide Risk near Large Alpine Reservoirs DOI Creative Commons

Hanyin Hu,

Ke Hu, Xinyao Zhang

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(12), P. 5201 - 5201

Published: June 14, 2024

Geological disasters in large alpine reservoirs primarily take the form of landslide occurrences and are predominantly induced by slope instability. Presently, risk monitoring assessment strategies tend to prioritize sudden alerts overlooking progressive trajectories from onset creeping deformations within its critical state preceding landslides. Hence, analyzing safety risks over time demonstrates a significant degree hysteresis, highlighting necessity for comprehensive approach that encompasses both gradual precursors events. This study analyzes factors affecting stability establishes evaluation indicator system includes terrain morphology, meteorological conditions, ecological environment, soil human activity, external manifestation. It proposes quantitative model based on fuzzy broad learning system, aiming accurately assess slopes with different levels. The overall accuracy rate reaches 92.08%. multi-dimensional provides long-term conditions scientific guidance management disaster prevention mitigation long scale risky reservoir areas.

Language: Английский

Citations

0