Next Article in Journal
Response of Grain Yield to Extreme Precipitation in Major Grain-Producing Areas of China Against the Background of Climate Change—A Case Study of Henan Province
Previous Article in Journal
Spatiotemporal Variations and Drivers of the Ecological Footprint of Water Resources in the Yangtze River Delta
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Streamflow Forecasting: A Comparative Analysis of ARIMAX, Rolling Forecasting LSTM Neural Network and Physically Based Models in a Pristine Catchment

1
Department of Cardiac, Thoracic, Vascular Sciences and Public Health, University of Padua Via Giustiniani 2, 35128 Padova, Italy
2
I4 Consulting S.R.L., Galleria Milano, 1, 35139 Padova, Italy
3
School of Computer Science and Digital Technologies, London South Bank University (LSBU), 103 Borough Rd, London SE1 0AA, UK
*
Author to whom correspondence should be addressed.
Water 2025, 17(15), 2341; https://doi.org/10.3390/w17152341
Submission received: 1 July 2025 / Revised: 29 July 2025 / Accepted: 2 August 2025 / Published: 6 August 2025

Abstract

Accurate streamflow forecasting at fine temporal and spatial scales is essential to manage the diverse hydrological behaviors of individual catchments, particularly in rapidly responding mountainous regions. This study compares three forecasting models ARIMAX, LSTM, and HEC-HMS applied to the Posina River basin in northern Italy, using 13 years of hourly hydrological data. While recent literature promotes multi-basin LSTM training for generalization, we show that a well-configured single-basin LSTM, combined with a rolling forecast strategy, can achieve comparable accuracy under high-frequency, data-constrained conditions. The physically based HEC-HMS model, calibrated for continuous simulation, provides robust peak flow prediction but requires extensive parameter tuning. ARIMAX captures baseflows but underestimates sharp hydrological events. Evaluation through NSE, KGE, and MAE shows that both LSTM and HEC-HMS outperform ARIMAX, with LSTM offering a compelling balance between accuracy and ease of implementation. This study enhances our understanding of streamflow model behavior in small basins and demonstrates that LSTM networks, despite their simplified configuration, can be reliable tools for flood forecasting in localized Alpine catchments, where physical modeling is resource-intensive and regional data for multi-basin training are often unavailable.
Keywords: streamflow forecasting; ARIMAX; LSTM; deep learning; autoregressive model; time series forecasting streamflow forecasting; ARIMAX; LSTM; deep learning; autoregressive model; time series forecasting

Share and Cite

MDPI and ACS Style

Perazzolo, D.; Lazzaro, G.; Fiume, A.; Fanton, P.; Grisan, E. Streamflow Forecasting: A Comparative Analysis of ARIMAX, Rolling Forecasting LSTM Neural Network and Physically Based Models in a Pristine Catchment. Water 2025, 17, 2341. https://doi.org/10.3390/w17152341

AMA Style

Perazzolo D, Lazzaro G, Fiume A, Fanton P, Grisan E. Streamflow Forecasting: A Comparative Analysis of ARIMAX, Rolling Forecasting LSTM Neural Network and Physically Based Models in a Pristine Catchment. Water. 2025; 17(15):2341. https://doi.org/10.3390/w17152341

Chicago/Turabian Style

Perazzolo, Diego, Gianluca Lazzaro, Alvise Fiume, Pietro Fanton, and Enrico Grisan. 2025. "Streamflow Forecasting: A Comparative Analysis of ARIMAX, Rolling Forecasting LSTM Neural Network and Physically Based Models in a Pristine Catchment" Water 17, no. 15: 2341. https://doi.org/10.3390/w17152341

APA Style

Perazzolo, D., Lazzaro, G., Fiume, A., Fanton, P., & Grisan, E. (2025). Streamflow Forecasting: A Comparative Analysis of ARIMAX, Rolling Forecasting LSTM Neural Network and Physically Based Models in a Pristine Catchment. Water, 17(15), 2341. https://doi.org/10.3390/w17152341

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop