آمار
| تعداد نشریات | 20 |
| تعداد شمارهها | 444 |
| تعداد مقالات | 3,511 |
| تعداد مشاهده مقاله | 3,812,425 |
| تعداد دریافت فایل اصل مقاله | 2,508,346 |
A comparative study of deep learning and benchmark models for monthly urban water demand forecasting | ||
| Journal of Applied Research in Water and Wastewater | ||
| مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 20 خرداد 1405 | ||
| نوع مقاله: Research Paper | ||
| شناسه دیجیتال (DOI): 10.22126/arww.2026.13557.1476 | ||
| نویسندگان | ||
| Zahra Ghafari Moghadam* 1؛ Ali Sardar Shahraki2؛ Abdulhaseeb Azizi3؛ Somayyeh Mirshekari4 | ||
| 1Assistant Professor, Agricultural Research Institute, Zabol University | ||
| 2professor of agriculture economics, University of Sistan and Baluchestan | ||
| 3Center for Development Research (ZEF), University of Bonn, Germany | ||
| 4Agriculture Institute, Research Institute of zabol, Zabol, Iran. | ||
| چکیده | ||
| Accurate forecasting of urban water demand is essential for effective water resources management, especially in arid and water-stressed regions. This study evaluates the performance of Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models for forecasting monthly urban potable water demand in the Sistan region of Iran using data from April 2006 to March 2021. Two forecasting approaches are examined: a univariate approach based only on past water demand and a multivariate approach incorporating selected climatic and socioeconomic variables. A one-step-ahead monthly forecasting strategy is applied, with the dataset divided chronologically into training and testing subsets. The deep learning models are compared with two benchmark methods, Naïve and Seasonal Naïve, using MAE, RMSE, MAPE, and Pearson’s correlation coefficient. The results show that LSTM provides more stable predictions and higher correlation with observed demand than RNN. However, the simple benchmark models produce lower forecast errors overall, with the Naïve model achieving the best performance. Adding climatic and socioeconomic variables slightly improves correlation in some cases but does not consistently reduce errors. Overall, the findings suggest that urban water demand in the study area is strongly persistent and seasonal, indicating that simple forecasting methods can outperform more complex deep learning models under data-limited conditions. | ||
| کلیدواژهها | ||
| Water demand forecasting؛ Deep learning؛ LSTM neural network؛ RNN neural network؛ Climate variability | ||
|
آمار تعداد مشاهده مقاله: 5 |
||