一个智能混合深度学习机器学习模型,用于每月的地下水位预测
Fatemeh Barzegari Banadkooki1, Elham Ghanbari-Adivi2, Fatemeh Sayyahi3
1Department of Agriculture, Faculty of Engineering, Payame Noor University, Tehran, Iran.
Scientific reports
|January 7, 2026
概括
一个新的混合人工智能模型,PSO-COO-GRU-ANFIS (PCGA),准确地预测了每月的地下水位 (GWL). 这种先进的模型显著改进了现有的环境保护和水资源管理方法.
科学领域:
- 环境科学 环境科学
- 人工智能的人工智能
- 水资源管理 水资源管理
背景情况:
- 准确地预测地下水位 (GWL) 对有效的环境保护和可持续的水资源管理至关重要.
- 传统的方法经常与水文系统固有的复杂,非线性动力学作斗争.
- 需要先进的预测模型是由于环境压力和水资源短缺问题日益增加而造成的.
研究的目的:
- 开发和评估一种新的混合人工智能模型,用于准确的每月地下水位预测.
- 将优化算法与深度学习和模糊推理系统集成在一起,以提高预测准确度.
- 通过使用严格的评估指标,对拟议模型的性能与已建立的基准方法进行评估.
主要方法:
- 一种称为PSO-COO-GRU-ANFIS (PCGA) 的混合模型被开发出来,它结合了粒子群优化 (PSO),科蒂优化 (COO),门式循环单元 (GRU) 和自适应神经模糊推理系统 (ANFIS).
- 使用PSO-COO算法优化了GRU和ANFIS组件的参数.
- GRU被用来提取时间依赖性,而ANFIS则根据这些提取的模式处理最终的预测生成.
主要成果:
- PCGA模型的准确性很高,实现了1.90的平均绝对误差 (MAE) 和0.90的纳什-萨特克利夫效率 (NSE) 在阿尔达比尔平原每月GWL预测.
- PCGA的表现优于基准模型,MAE的改善率为14-77%,NSE的改善率为1-20%.
- 该研究证实了PSO-COO优化的有效性和GRU在捕获长期数据依赖性的能力,减少参数调整期间的错误波动.
结论:
- PCGA模型是预测月度地下水位的强大而优秀的工具,性能优于传统和独立模型.
- 混合方法有效地捕捉了GWL数据中的复杂,非线性关系.
- 这项研究在水文预测方面取得了重大进展,支持更好的环境和水资源管理战略.
相关概念视频
01:29Application of Linearization and Approximation
36
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
36
01:25Indefinite Integrals
14
The water inflow rate into a storage tank is not constant but increases over time. Initially, the pump delivers water at a rate of 5 L/min. However, the inflow rate increases by 2 L/min for each additional minute due to rising pressure or system adjustments. This scenario can be described mathematically by a linear function:It is necessary to integrate the inflow rate function to measure the total volume of water added to the tank over time. The total water volume V(t) is obtained by performing...
14
01:21Design Example: Creating a Hydraulic Model of a Dam Spillway
664
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
664
01:03Precipitation Gravimetry
13.8K
Precipitation gravimetry is based on converting an analyte into a sparingly soluble precipitate, which is separated by filtration and weighed. An ideal precipitate should be pure, insoluble, of known composition, and easily filtered from the reaction mixture.
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
13.8K