Inicio  /  Water  /  Vol: 16 Par: 5 (2024)  /  Artículo
ARTÍCULO
TITULO

Assessing Objective Functions in Streamflow Prediction Model Training Based on the Naïve Method

Yongen Lin    
Dagang Wang    
Tao Jiang and Aiqing Kang    

Resumen

Reliable streamflow forecasting is a determining factor for water resource planning and flood control. To better understand the strengths and weaknesses of newly proposed methods in streamflow forecasting and facilitate comparisons of different research results, we test a simple, universal, and efficient benchmark method, namely, the naïve method, for short-term streamflow prediction. Using the naïve method, we assess the streamflow forecasting performance of the long short-term memory models trained with different objective functions, including mean squared error (MSE), root mean squared error (RMSE), Nash?Sutcliffe efficiency (NSE), Kling?Gupta efficiency (KGE), and mean absolute error (MAE). The experiments over 273 watersheds show that the naïve method attains good forecasting performance (NSE > 0.5) in 88%, 65%, and 52% of watersheds at lead times of 1 day, 2 days, and 3 days, respectively. Through benchmarking by the naïve method, we find that the LSTM models trained with squared-error-based objective functions, i.e., MSE, RMSE, NSE, and KGE, perform poorly in low flow forecasting. This is because they are more influenced by training samples with high flows than by those with low flows during the model training process. For comprehensive short-term streamflow modeling without special demand orientation, we recommend the application of MAE instead of a squared-error-based metric as the objective function. In addition, it is also feasible to perform logarithmic transformation on the streamflow data. This work underscores the critical importance of appropriately selecting the objective functions for model training/calibration, shedding light on how to effectively evaluate the performance of streamflow forecast models.

 Artículos similares

       
 
Manos Garefalakis, Zacharias Kamarianakis and Spyros Panagiotakis    
As it concerns remote laboratories (RLs) for teaching microcontroller programming, the related literature reveals several common characteristics and a common architecture. Our search of the literature was constrained to papers published in the period of ... ver más
Revista: Information

 
Xueyan Yang and Jie Shen    
Historic districts may be damaged during urban renewal. Landscape sensitivity can be used as a method to judge the ability of a landscape to resist change. This study proposes an improved method for assessing landscape sensitivity based on a geographic i... ver más

 
Christos Bormpotsis, Mohamed Sedky and Asma Patel    
In the realm of foreign exchange (Forex) market predictions, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been commonly employed. However, these models often exhibit instability due to vulnerability to data perturbations... ver más

 
Jeff Grasberger and Dominic Forbush    
Aquaculture systems require careful consideration of location, which determines water conditions, pollution impacts, and hazardous conditions. Mobility may be able to address these factors while also supporting the targeting of renewable energy sources s... ver más

 
Rahul Vardhan Bhatnagar and Sewa Ram    
The accessibility of railway stations plays a crucial role in assessing service quality, predicting travel patterns, and developing infrastructure in the surrounding areas. This paper proposes a railway station accessibility index (RsAI) (external) that ... ver más
Revista: Urban Science