.png){kind=icon}
返回
Data reformation - A novel data processing technique enhancing machine learning applicability for predicting streamflow extremes
.png){kind=icon}
OA
AI
DOI：10.1016/j.advwatres.2023.104569.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Hydrologists have been actively exploring the utility of machine learning (ML) models for predicting streamflow. While ML methods have proven to be as accurate as conventional modeling techniques for streamflows well represented in the training set, they continue to lack satisfactory skills for extreme events. In this study, a novel 'data reformation' technique is proposed based on the Relative Strength Index (RSI) - a measure of speed and direction of changes in the time series. RSI homogenizes all observations to a constrained 0-100 range, and all 'out-of-sample' data in the testing set fall within the space of the training set. Long Short-Term Memory network with an attention mechanism is used to train three ML models using 55,055 events from the CAMELS dataset (670 basins, 1980-2014). Predictions are made for 12,424 events, of which 3,810 are significantly higher than streamflows in the training set. The ML model based on RSI-reformed data exhibits superior performance, as compared to other advanced ML models without data reformation. Peaks up to 15 times larger than those in the training events are accurately predicted, leading to an outperforming model skill for 433 out of 670 catchments. These findings indicate that incorporating a new data reformation technique into the data pre-processing step in ML modeling can enhance the utility of ML models for extreme events. This research encourages further exploration to identify better data reformation methods to enable confident ML predictions.
Keyword:
Machine learning
Extrapolation
Data reformation
Relative strength index
Streamflow predictions
Extreme events
Out-of-samples
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.2
论文数:
4.6K
被引数:
1.5W
机构
引用论文
分享收藏Continuous limit, higher-order rational solutions and relevant dynamical analysis for Belov–Chaltikian lattice equation with 3$$\times $$3 Lax pair.png)
Pramana
PramanaIF0
PREAI
分享收藏Long lead-time daily and monthly streamflow forecasting using machine learning methods使用机器学习方法进行长时间的每日和每月流量预测JOURNAL OF HYDROLOGY
JOURNAL OF HYDROLOGYIF6.3
PREAI
分享收藏Increased human and economic losses from river flooding with anthropogenic warmingNATURE CLIMATE CHANGE
NATURE CLIMATE CHANGEIF27.1
PREAI
分享收藏分享收藏A novel attention-based LSTM cell post-processor coupled with bayesian optimization for streamflow predictionJOURNAL OF HYDROLOGY
JOURNAL OF HYDROLOGYIF6.3
PREAI
分享收藏
查看更多内容