相关实验视频
Updated: Jul 15, 2026
08:47
Computer Vision-Based Biomass Estimation for Invasive Plants
Published on: February 9, 2024
基于多种深度学习方法在区域范围内预测标准化复合干旱和热量指数
Zongcan Lu1,2, Xiang Yu1, Xin Zheng1
1School of Computer Science and Technology, Qingdao University, Qingdao, 266071, China.
Environmental science and pollution research international
|March 12, 2026
概括
深度学习模型使用时空预测准确预测复合干旱和热情事件 (CDHEs). 斯温LSTM表现出卓越的性能,增强了气候弹性早期预警系统.
科学领域:
- 气候科学 气候科学
- 环境科学 环境科学
- 数据科学数据科学数据科学
背景情况:
- 复合干旱和热情事件 (CDHEs) 对水资源,农业和生态系统构成重大风险.
- 现有的预报方法与气象变量的复杂,非线性相互作用作斗争.
研究的目的:
- 开发和评估深度学习模型,用于预测标准化复合干旱和热量指数 (SCDHI) 的时空演变.
- 为了比较CNN-LSTM,ConvLSTM,SA-ConvLSTM和SwinLSTM用于CDHE预测的性能.
主要方法:
- 使用了四种深度学习模型:CNN-LSTM,ConvLSTM,SA-ConvLSTM和SwinLSTM,后两个具有注意力机制.
- 采用了气象变量的ERA5再分析数据.
- 预测了从2004年到2023年在长江三角洲 (YRD) 地区SCDHI的10天时空演变.
主要成果:
- 所有模型都显示出强大的预测性能.
- 斯温LSTM实现了最高的确定系数 (R2 = 0.892).
- 斯温LSTM的表现优于ConvLSTM,R2提高了3.24%,并减少了RMSE和MAE.
结论:
- 深度学习,特别是SwinLSTM,为短期的时空空间CDHE预测提供了有效的框架.
- 这些发现支持加强预警系统和区域气候弹性战略.
相关概念视频
02:41Responses to Drought and Flooding
12.3K
Water plays a significant role in the life cycle of plants. However, insufficient or excess of water can be detrimental and pose a serious threat to plants.
12.3K
01:17Precipitation and Co-precipitation
5.2K
Precipitation and coprecipitation methods can be used to separate a mixture of ions in a solution. In qualitative inorganic analysis, ions that form sparingly soluble precipitates with the same reagent are separated based on the differences in solubility products. For example, consider the separation of Cu(II) and Fe(II) ions by precipitation as insoluble sulfides. First, copper(II) sulfide is precipitated by the addition of acidic H2S, where the dissociation of H2S is suppressed. Adding H2S...
5.2K