Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Comparative Analysis on Snowmelt-Driven Streamflow Forecasting Using Machine Learning Techniques

Ukesh Thapa, Bipun Man Pati, Samit Thapa, Dhiraj Pyakurel, Anup Shrestha

TL;DR

The findings of this study demonstrate the effectiveness of the proposed deep learning model as compared to traditional machine learning approaches for snowmelt-driven streamflow forecasting and highlights its potential as a promising deep learning model for similar hydrological applications.

Abstract

The rapid advancement of machine learning techniques has led to their widespread application in various domains including water resources. However, snowmelt modeling remains an area that has not been extensively explored. In this study, we propose a state-of-the-art (SOTA) deep learning sequential model, leveraging the Temporal Convolutional Network (TCN), for snowmelt-driven discharge modeling in the Himalayan basin of the Hindu Kush Himalayan Region. To evaluate the performance of our proposed model, we conducted a comparative analysis with other popular models including Support Vector Regression (SVR), Long Short Term Memory (LSTM), and Transformer. Furthermore, Nested cross-validation (CV) is used with five outer folds and three inner folds, and hyper-parameter tuning is performed on the inner folds. To evaluate the performance of the model mean absolute error (MAE), root mean square error (RMSE), R square ($R^{2}$), Kling-Gupta Efficiency (KGE), and Nash-Sutcliffe Efficiency (NSE) are computed for each outer fold. The average metrics revealed that TCN outperformed the other models, with an average MAE of 0.011, RMSE of 0.023, $R^{2}$ of 0.991, KGE of 0.992, and NSE of 0.991. The findings of this study demonstrate the effectiveness of the deep learning model as compared to traditional machine learning approaches for snowmelt-driven streamflow forecasting. Moreover, the superior performance of TCN highlights its potential as a promising deep learning model for similar hydrological applications.

Comparative Analysis on Snowmelt-Driven Streamflow Forecasting Using Machine Learning Techniques

TL;DR

The findings of this study demonstrate the effectiveness of the proposed deep learning model as compared to traditional machine learning approaches for snowmelt-driven streamflow forecasting and highlights its potential as a promising deep learning model for similar hydrological applications.

Abstract

The rapid advancement of machine learning techniques has led to their widespread application in various domains including water resources. However, snowmelt modeling remains an area that has not been extensively explored. In this study, we propose a state-of-the-art (SOTA) deep learning sequential model, leveraging the Temporal Convolutional Network (TCN), for snowmelt-driven discharge modeling in the Himalayan basin of the Hindu Kush Himalayan Region. To evaluate the performance of our proposed model, we conducted a comparative analysis with other popular models including Support Vector Regression (SVR), Long Short Term Memory (LSTM), and Transformer. Furthermore, Nested cross-validation (CV) is used with five outer folds and three inner folds, and hyper-parameter tuning is performed on the inner folds. To evaluate the performance of the model mean absolute error (MAE), root mean square error (RMSE), R square (), Kling-Gupta Efficiency (KGE), and Nash-Sutcliffe Efficiency (NSE) are computed for each outer fold. The average metrics revealed that TCN outperformed the other models, with an average MAE of 0.011, RMSE of 0.023, of 0.991, KGE of 0.992, and NSE of 0.991. The findings of this study demonstrate the effectiveness of the deep learning model as compared to traditional machine learning approaches for snowmelt-driven streamflow forecasting. Moreover, the superior performance of TCN highlights its potential as a promising deep learning model for similar hydrological applications.
Paper Structure (21 sections, 2 equations, 6 figures, 5 tables)

This paper contains 21 sections, 2 equations, 6 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Hindu Kush Himalayan Region
  3. Snowmelt Forecasting Using Machine Learning
  4. Materials and Methods
  5. Study Area
  6. Hydrometeorological Data
  7. Snow Cover
  8. Dataset Preparation
  9. Experimental setup
  10. Methodology
  11. SVR
  12. LSTM
  13. Transformer
  14. TCN
  15. Results
  16. ...and 6 more sections

Figures (6)

  • Figure 1: Map of Langtang basin area
  • Figure 2: Methodological framework for assessment of performance of ML techniques for snowmelt forecasting
  • Figure 3: A classic LSTM cell, where sigmoid denotes sigmoidal function, tanh denotes a hyperbolic tangent function, C denotes cell state, h denotes hidden state, o denote output gate, i denote input vectors at time step t
  • Figure 4: The detail model architecture of the Transformer. [vaswani2017attention]
  • Figure 6: Scatter plot of predicted flow with observed flow (a) SVR model (b) LSTM model (c) Transformer model (d) TCN model. The solid line is the 1:1 line.
  • ...and 1 more figures