采用混合深度学习来近乎实时预测基于传感器的藻类参数在Microcystis开花占主导地位的湖泊
Lan Wang1, Kun Shan2, Yang Yi2
1School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China; Chongqing Key Laboratory of Big Data and Intelligent Computing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing 400714, China; School of Artificial Intelligence, Chongqing University of Education, Chongqing 400065, China.
The Science of the total environment
|February 25, 2024
概括
这项研究引入了一种混合深度学习框架,用于使用实时传感器数据预测有害的蓝藻细菌繁殖 (CyanoHABs). SSA-TCN模型显著提高了对甲和藻类细胞密度的预测准确性,提供了更好的水生生态系统管理.
科学领域:
- 环境科学 环境科学
- 数据科学数据科学数据科学
- 生态生态学 生态生态学
背景情况:
- 有害的蓝藻细菌繁殖 (CyanoHABs) 对水生生态系统构成全球威胁.
- 实时监控和深度学习为早期CyanoHAB警告提供了潜力.
- 高频传感器数据的变化挑战了传统的预测模型.
研究的目的:
- 开发和验证用于近实时CyanoHAB预测的混合框架.
- 评估Singular Spectrum Analysis (SSA) 在增强时间序列数据的深度学习模型中的有效性.
- 为了确定CyanoHAB预测的关键环境驱动因素.
主要方法:
- 开发了一个混合框架,将SSA与时间卷积网络 (TCN) 结合起来.
- 该模型经过训练和验证,使用每小时的叶绿素a (Chl a) 度和来自中国迪安基湖的藻类细胞密度.
- 分析了环境因素,以确定它们对预测准确性的影响.
主要成果:
- SSA-TCN模型显著提高了Chl a (R2 = 0.45-0.93) 和藻类细胞密度 (R2 = 0.63-0.89) 的预测准确度.
- 花强度预测达到98.56%的准确率,准确率为94.04%.
- 水温被确定为CyanoHAB预测中最有效的环境驱动因素 (R2 = 0.83 ± 0.01).
结论:
- 混合SSA-TCN框架显示了对藻类参数准确,基于传感器的预测具有很高的潜力.
- 这种方法为通过在线监测和人工智能来管理CyanoHAB提供了一种新的策略.
- 这些发现为保护水生生态系统免受有害藻类繁殖提供了宝贵的见解.
相关概念视频
01:18Deep Sea Microbial Ecology
53
The deep ocean and its underlying sediments represent vast, largely unexplored microbial habitats that extend far beyond the sunlit photic zone. The photic (euphotic) zone typically spans the upper ~100–200 meters of pelagic waters in the open ocean, but its depth varies geographically and seasonally, where sufficient light supports photosynthetic life. Below this lies the deep sea, spanning roughly 1000–6000 meters (bathypelagic to abyssal zones), with deeper hadal trenches...
53
01:24Freshwater Microbial Ecology
58
Freshwater systems such as streams, rivers, and lakes exhibit distinct physical and biological characteristics that influence their microbial communities. These environments are broadly categorized into lotic systems—those with flowing waters like streams and most rivers—and lentic systems, which include still or slow-moving waters such as lakes, ponds, and marshes.In lentic systems, phytoplankton drive primary production, generating autochthonous organic carbon. In contrast, lotic...
58
01:17Microbial Biosensors
88
Microbial biosensors are analytical devices that utilize living microbes to detect specific substances through measurable signals. These devices consist of two main components: biosensing organisms and signal-transducing elements. Biosensing organisms, such as Escherichia coli or Saccharomyces cerevisiae, are typically housed in multiwell plates connected to transducers, enabling rapid, real-time detection of target analytes.Signal Generation MechanismWhen a target analyte—such as...
88