基于MTPI自动传输学习的深度网络自动训练方法和强化学习算法,用于在干燥的热谷环境中检测植被
Yayong Chen1,2, Beibei Zhou1,2, Chen Xiaopeng1,2
1State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, China.
Frontiers in plant science
|February 28, 2025
概括
本研究引入了一种用于水文监测的深度学习的新型自动训练方法,它结合了转移学习和强化学习,以显著减少复杂环境中的数据需求和手工劳动.
科学领域:
- 环境科学 环境科学
- 计算机科学 计算机科学
- 水文学的水文学
背景情况:
- 无人机成像和深度学习对于水文监测至关重要,但在干燥的热谷等复杂环境中面临手动培训成本和有限的自动培训实用性挑战.
- 现有的自动训练方法与非结构化数据集和复杂的网络架构作斗争,阻碍它们在现实世界中应用.
研究的目的:
- 开发一个自动化的深度学习培训框架,尽量减少水文应用的人类经验和试错成本.
- 通过转移学习和强化学习的结合,增强数据集和网络自动训练过程.
主要方法:
- 使用改进的最大转移潜力指数 (MTPI) 方法来确定最佳代条件,减少数据集和时间消耗.
- 多普森采样算法 (MTSA) 强化学习在MTPI条件下 (MTSA-MTPI) 得到了增强,用于自动增强数据集.
- 结合的MTPI-MTSA框架被应用于自动训练四个深度学习网络 (FCN,Seg-Net,U-Net,Seg-Res-Net 50).
主要成果:
- 该MTPI方法确定了最佳条件,使得后续代只能使用2.30%的数据集和6.31%的时间.
- MTSA-MTPI提高了准确率16.0%,并减少了标准误差20.9%,显著降低了试错成本.
- 使用MTPI-MTSA进行训练的Seg-Res-Net 50实现了95.2%的准确性 (WPA) 和90.9%的交叉超过联盟 (WIoU).
结论:
- 这项研究提出了一种有效的自动化培训方法,用于使用深度学习收集复杂的植被信息.
- 在环境监测的深度学习应用中,MTPI-MTSA方法为减少手动干预提供了有价值的参考.
相关概念视频
Light Acquisition
8.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.4K
Survival Tree
50
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
50


