Research on Interval Probability Prediction and Optimization of Vegetation Productivity in Hetao Irrigation District Based on Improved TCLA Model DOI Creative Commons
Jie Ren,

Delong Tian,

Hexiang Zheng

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(6), P. 1279 - 1279

Published: May 23, 2025

Vegetation productivity, as an essential global carbon sink, directly influences the variety and stability of ecosystems. Precise vegetation productivity monitoring forecasting are crucial for cycle. Traditional machine learning algorithms frequently experience overfitting when processing high-dimensional time-series data or substantial numbers outliers, impeding accurate prediction various metrics. We propose a multimodal regression model utilizing TCLA framework—comprising Transient Trigonometric Harris Hawks Optimizer (TTHHO), Convolutional Neural Networks (CNN), Least Squares Support Vector Machine (LSSVM), Adaptive Bandwidth Kernel Density Estimation (ABKDE)—with Hetao Irrigation District, vast irrigation basin in China, serving study area. This employs TTHHO to effectively navigate search space adaptively optimize network node positions, integrates CNN-LSSVM feature extraction analysis, incorporates ABKDE probability density function estimation outlier detection, resulting interval enhanced resilience interference. Experimental indicate that improves accuracy by 10.57–26.47% compared conventional models (Long Short-Term Memory (LSTM), Transformer). In presence 5–15% fusion results drop RMSE (p < 0.05), with reduction 45.18–69.66%, yielding values between 0.079 0.137, thereby demonstrating model’s high robustness resistance interference predicting next three years. work introduces scientific approach precisely alterations regional using proposed model, significantly enhancing resource management ecological conservation techniques.

Language: Английский

Predicting the chemical equilibrium point of reacting components in gaseous mixtures through a novel Hierarchical Manta-Ray Foraging Optimization Algorithm DOI Creative Commons
Oğuz Emrah Turgut, Hadi Genceli, Mustafa Asker

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 1, 2025

Abstract This study proposes a Hierarchical Manta-Ray Foraging Optimization (HMRFO) algorithm for calculating the equilibrium points of chemical reactions. To improve solution diversity in trial population and enhance general optimization effectivity algorithm, an ordered hierarchy is integrated into original taking account efficient search strategies Elite-Opposition learning, Dynamic Opposition Learning, Quantum operator. Within this proposed concept, Manta-ray divided three main sub-populations: Elite Oppositional learning scheme manipulates top elite individuals, equations update average members, quantum-based process worst members. The improved MRFO applied to hundred 30D 500D benchmark functions, results have been compared those obtained from state-of-art metaheuristic optimizers. Then, optimizer solved twenty-eight test problems previously employed CEC-2013 competitions, corresponding were benchmarked against well-reputed metaheuristics. research also suggests novel mathematical model solving ideal gas mixtures. Four challenging case studies related performed by HMRFO varying conditions, it observed that can effectively cope with tedious nonlinearities complexities governing thermodynamic models associated gaseous reacting mixture components.

Language: Английский

Citations

0
Improved Manta Ray Foraging Optimization for PID Control Parameter Tuning in Artillery Stabilization Systems DOI Creative Commons
Xiuye Wang, Xiang Li, Qinqin Sun

et al.

Biomimetics, Journal Year: 2025, Volume and Issue: 10(5), P. 266 - 266

Published: April 26, 2025

In this paper, an Improved Manta Ray Foraging Optimization (IMRFO) algorithm is proposed to address the challenge of parameter tuning in traditional PID controllers for artillery stabilization systems. The introduces chaotic mapping optimize initial population, enhancing global search capability; additionally, a sigmoid function and Lévy flight-based dynamic adjustment strategy regulate selection factor step size, improving both convergence speed optimization accuracy. Comparative experiments using five benchmark test functions demonstrate that IMRFO outperforms commonly used heuristic algorithms four cases. validated through co-simulation physical platform experiments. Experimental results show approach significantly improves control accuracy response speed, offering effective solution optimizing complex nonlinear By introducing self-tuning system parameters, work provides new intelligence adaptability modern control.

Language: Английский

Citations

0
Machine Learning-Based Sweet Spot Prediction for Lacuscrine Shale Oil in the Weixinan Sag, Beibu Gulf Basin, China DOI

Ren-Yi Huang,

Yifan Li, Zhiqian Gao

et al.

Marine and Petroleum Geology, Journal Year: 2025, Volume and Issue: 179, P. 107436 - 107436

Published: April 29, 2025

Language: Английский

Citations

0
Optimization strategies for public health education based on ISSA and information system technology DOI Creative Commons

Zhanyu Ye,

Yifei Li, Yan Zhang

et al.

Frontiers in Public Health, Journal Year: 2025, Volume and Issue: 13

Published: May 8, 2025

Against the backdrop of rapid development information technology, public health education is facing challenges such as uneven resource allocation and lagging content. To propose an optimization strategy that can effectively improve level education, this study improves sparrow search algorithm by introducing theory best point sets to optimize resources. Combined with system a platform proposed education. The experiment findings denoted improved had significantly better average fitness value than other compared algorithms after 500 iterations, accuracy 92.4% area under PR curve 0.84. In practical application, model for resources increased balance 0.89, educational effectiveness 25.5%, user satisfaction 31.4%. At same time, constructed showed excellent performance in terms CPU usage time consumption, improving coverage content update frequency. above indicate raised provides scientific basis guidance which helps raise quality

Language: Английский

Citations

0
Research on Interval Probability Prediction and Optimization of Vegetation Productivity in Hetao Irrigation District Based on Improved TCLA Model DOI Creative Commons
Jie Ren,

Delong Tian,

Hexiang Zheng

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(6), P. 1279 - 1279

Published: May 23, 2025

Vegetation productivity, as an essential global carbon sink, directly influences the variety and stability of ecosystems. Precise vegetation productivity monitoring forecasting are crucial for cycle. Traditional machine learning algorithms frequently experience overfitting when processing high-dimensional time-series data or substantial numbers outliers, impeding accurate prediction various metrics. We propose a multimodal regression model utilizing TCLA framework—comprising Transient Trigonometric Harris Hawks Optimizer (TTHHO), Convolutional Neural Networks (CNN), Least Squares Support Vector Machine (LSSVM), Adaptive Bandwidth Kernel Density Estimation (ABKDE)—with Hetao Irrigation District, vast irrigation basin in China, serving study area. This employs TTHHO to effectively navigate search space adaptively optimize network node positions, integrates CNN-LSSVM feature extraction analysis, incorporates ABKDE probability density function estimation outlier detection, resulting interval enhanced resilience interference. Experimental indicate that improves accuracy by 10.57–26.47% compared conventional models (Long Short-Term Memory (LSTM), Transformer). In presence 5–15% fusion results drop RMSE (p < 0.05), with reduction 45.18–69.66%, yielding values between 0.079 0.137, thereby demonstrating model’s high robustness resistance interference predicting next three years. work introduces scientific approach precisely alterations regional using proposed model, significantly enhancing resource management ecological conservation techniques.

Language: Английский

Citations

0