Intermittent Streamflow Forecasting and Extreme Event Modelling using Wavelet based Artificial Neural Networks

Makwana, Jaydip J.; Tiwari, Mukesh

doi:10.1007/s11269-014-0781-1

Cited by 58 publications

(12 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although distributed water quality models such as the Soil & Water Assessment Tool (SWAT) have been used to assess conservation practice effectiveness at watershed scales [ Yeo et al ., ], these models require a large amount of spatial and temporal data and model parameters that are sometimes difficult to specify over large regions [ Makwana and Tiwari , ]. The performance of the SWAT model depends upon the quality of input data and model parameters.…”

Section: Introductionmentioning

confidence: 99%

Investigating water use over the Choptank River Watershed using a multisatellite data fusion approach

Sun

Anderson

Gao

et al. 2017

Water Resources Research

View full text Add to dashboard Cite

The health of the Chesapeake Bay ecosystem has been declining for several decades due to high levels of nutrients and sediments largely tied to agricultural production systems. Therefore, monitoring of agricultural water use and hydrologic connections between crop lands and Bay tributaries has received increasing attention. Remote sensing retrievals of actual evapotranspiration (ET) can provide valuable information in support of these hydrologic modeling efforts, spatially and temporally describing consumptive water use by crops and natural vegetation and quantifying response to expansion of irrigated area occurring with Bay watershed. In this study, a multisensor satellite data fusion methodology, combined with a multiscale ET retrieval algorithm, was applied over the Choptank River watershed located within the Lower Chesapeake Bay region on the Eastern Shore of Maryland, USA to produce daily 30 m resolution ET maps. ET estimates directly retrieved on Landsat satellite overpass dates have high accuracy with relative error (RE) of 9%, as evaluated using flux tower measurements. The fused daily ET time series have reasonable errors of 18% at the daily time step ‐ an improvement from 27% errors using standard Landsat‐only interpolation techniques. Annual water consumption by different land cover types was assessed, showing reasonable distributions of water use with cover class. Seasonal patterns in modeled crop transpiration and soil evaporation for dominant crop types were analyzed, and agree well with crop phenology at field scale. Additionally, effects of irrigation occurring during a period of rainfall shortage were captured by the fusion program. These results suggest that the ET fusion system will have utility for water management at field and regional scales over the Eastern Shore. Further efforts are underway to integrate these detailed water use data sets into watershed‐scale hydrologic models to improve assessments of water quality and inform best management practices to reduce nutrient and sediment loads to the Chesapeake Bay.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigating water use over the Choptank River Watershed using a multisatellite data fusion approach

Sun

Anderson

Gao

et al. 2017

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…The regression cell, in this topology, treats the zero and non-zero flows as a continuum and makes a prediction. Conventionally used models for streamflow forecasting only include the regression cell of the wide network (Cigizoglu, 2005;Kişi, 2009;Makwana and Tiwari, 2014;Rahmani-Rezaeieh et al, 2020). This configuration typically has a single input layer, a hidden layer and an output layer and is referred to as shallow topology (or shallow model) in this study.…”

Section: Wide Topology For Modeling Intermittent Streamflowsmentioning

confidence: 99%

Deep, Wide, or Shallow? Artificial Neural Network Topologies for Predicting Intermittent Flows

Forghanparast

Hernandez

Uddameri

2021

Preprint

View full text Add to dashboard Cite

Abstract. Intermittent Rivers and Ephemeral Streams (IRES) comprise 60 % of all streams in the US and about 50 % of the streams worldwide. Furthermore, climate-driven changes are expected to force a shift towards intermittency in currently perennial streams. Most modeling studies have treated intermittent streamflows as a continuum. However, it is better to envision flow data of IRES as a “mixture-type”, comprised of both flow and no-flow regimes. It is therefore hypothesized that data-driven models with both classification and regression cells can improve the streamflow forecasting abilities in these streams. Deep and wide Artificial Neural Networks (ANNs) comprising of classification and regression cells were developed here by stacking them in series and parallel configurations. These deep and wide network architectures were compared against the commonly used single hidden layer ANNs (shallow), as a baseline, for modeling IRES flow series under the continuum assumption. New metrics focused on no-flow persistence and transitions between flow and no-flow states were formulated using contingency tables and Markov chain analysis. Nine IRES across the state of Texas, US, were used as a wide range of testbeds with different hydro-climatic characteristics. Model overfitting and the curse-of-dimensionality were reduced using extreme learning machines (ELM), and balancing training data using the synthetic minority oversampling technique (SMOTE), greedy learning and Least Absolute Shrinkage and Selection Operator (LASSO). The addition of classifier cells greatly improved the ability to distinguish between no-flow and flow states, in turn, improving the ability to capture no-flow persistence (dryness) and transitions to and from flow states (dryness initiation and cessation). The wide network topology provided better results when the focus was on capturing low flows and the deep topology did well in capturing extreme flows (zero and > 75th percentile).

show abstract

“…Over the last decades, the hydrologists have popularly used the soft computing methods for streamflow modeling. Since Artificial Neural Network (ANN) has ability to model linear and non-linear systems even without making any assumption, the models of ANN were widely used in various water science subjects [2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning Method for Daily Streamflow Time-Series Prediction: A Case Study of the Kowmung River at Cedar Ford, Australia

Latif¹,

Ahmed²

2021

IJSDP

View full text Add to dashboard Cite

Sustainable management of water supplies faces a comprehensive challenge due to global climate change. Improving forecasts of streamflow based on erratic precipitation is a significant activity nowadays. In recent years, the techniques of data-driven have been widely used in the hydrological parameter’s prediction especially streamflow. In the current research, a deep learning model namely Long Short-Term Memory (LSTM), and two conventional machine learning models namely, Random Forest (RF), and Tree Boost (TB) were used to predict the streamflow of the Kowmung river at Cedar Ford in Australia. Different scenarios proposed to determine the optimal combination of input predictor variables, and the input predictor variables were selected based on the auto-correlation function (ACF). Model output was evaluated using indices of the root mean square error (RMSE), and the Nash and Sutcliffe coefficient (NSE). The findings showed that the LSTM model outperformed RF and TB in predicting the streamflow with RMSE and NSE equal to 102.411, and 0.911 respectively. for the LSTM model. The proposed model could adopt by hydrologists to solve the problems associated with forecasting daily streamflow with high precision. This study may not be generalized because of the geographical condition and the nature of the data for each location.

show abstract

Intermittent Streamflow Forecasting and Extreme Event Modelling using Wavelet based Artificial Neural Networks

Cited by 58 publications

References 47 publications

Investigating water use over the Choptank River Watershed using a multisatellite data fusion approach

Investigating water use over the Choptank River Watershed using a multisatellite data fusion approach

Deep, Wide, or Shallow? Artificial Neural Network Topologies for Predicting Intermittent Flows

Application of Deep Learning Method for Daily Streamflow Time-Series Prediction: A Case Study of the Kowmung River at Cedar Ford, Australia

Contact Info

Product

Resources

About