Towards Generalized Hydrological Forecasting using Transformer Models for 120-Hour Streamflow Prediction

2024-06-11 · Bekir Z. Demiray, Ibrahim Demir

This study explores the efficacy of a Transformer model for 120-hour streamflow prediction across 125 diverse locations in Iowa, US. Utilizing data from the preceding 72 hours, including precipitation, evapotranspiration, and discharge values, we developed a generalized model to predict future streamflow. Our approach contrasts with traditional methods that typically rely on location-specific models. We benchmarked the Transformer model's performance against three deep learning models (LSTM, GRU, and Seq2Seq) and the Persistence approach, employing Nash-Sutcliffe Efficiency (NSE), Kling-Gupta Efficiency (KGE), Pearson's r, and Normalized Root Mean Square Error (NRMSE) as metrics. The study reveals the Transformer model's superior performance, maintaining higher median NSE and KGE scores and exhibiting the lowest NRMSE values. This indicates its capability to accurately simulate and predict streamflow, adapting effectively to varying hydrological conditions and geographical variances. Our findings underscore the Transformer model's potential as an advanced tool in hydrological modeling, offering significant improvements over traditional and contemporary approaches.

📄 PDF Abstract BibTeX arXiv:2406.07484

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Adam 설명 없음

Attention-based Domain Adaptation Forecasting of Streamflow in Data-Sparse Regions

2023-02-10 · Roland Oruche, Fearghal O'Donncha

Streamflow forecasts are critical to guide water resource management, mitigate drought and flood effects, and develop climate-smart infrastructure and governance. Many global regions, however, have limited streamflow obs…

Domain Adaptation Management

Short-term Streamflow and Flood Forecasting based on Graph Convolutional Recurrent Neural Network and Residual Error Learning

2024-12-06 · Xiyu Pan, Neda Mohammadi, John E. Taylor

Accurate short-term streamflow and flood forecasting are critical for mitigating river flood impacts, especially given the increasing climate variability. Machine learning-based streamflow forecasting relies on large str…

AIFL: A Global Daily Streamflow Forecasting Model Using a Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS

2026-02-18 · Maria Luisa Taccari, Kenza Tazi, Oisín M. Morrison, Andreas Grafberger 외 arxiv

Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer from a performance gap when transitioning from historical reanalysis to operat…

A Parsimonious Setup for Streamflow Forecasting using CNN-LSTM

2024-04-11 · Sudan Pokharel, Tirthankar Roy

Significant strides have been made in advancing streamflow predictions, notably with the introduction of cutting-edge machine-learning models. Predominantly, Long Short-Term Memories (LSTMs) and Convolution Neural Networ…

Time Series

A novel stochastic model based on echo state networks for hydrological time series forecasting

2021-10-16 · NeurIPS Workshop LatinX_in_AI 2021 12 · edson luque mamani

The Stochastic Streamflow Models (SSMS) are time series models for precise prediction of hydrological data useful in hydrologic risk management. Nowadays, deep learning networks get many considerations in time series for…

Management Network Embedding Time Series Time Series Analysis+1