پیوندهای مفید
آمار
| تعداد نشریات | 31 |
| تعداد شماره‌ها | 484 |
| تعداد مقالات | 4,712 |
| تعداد مشاهده مقاله | 7,347,308 |
| تعداد دریافت فایل اصل مقاله | 5,492,679 |
Estimating Groundwater Levels in Tehran Province Using Ensemble Learning Algorithms | ||
| Contributions of Science and Technology for Engineering | ||
| دوره 2، شماره 1، خرداد 2025، صفحه 51-63 اصل مقاله (646.67 K) | ||
| نوع مقاله: Original Article | ||
| شناسه دیجیتال (DOI): 10.22080/cste.2025.29082.1036 | ||
| نویسندگان | ||
| Seyed Mojtaba Mousavimehr* ؛ Mohammad Reza Kavianpour | ||
| Faculty of Civil Engineering, K.N. Toosi University of Technology, Tehran, Iran | ||
| تاریخ دریافت: 14 فروردین 1404، تاریخ بازنگری: 11 اردیبهشت 1404، تاریخ پذیرش: 14 اردیبهشت 1404 | ||
| چکیده | ||
| The study of groundwater levels is of paramount importance due to its critical role in water resource management, agriculture, and ecosystem sustainability. This study focuses on predicting groundwater levels in observation wells across Tehran using machine learning algorithms. A range of input parameters, including satellite-derived data from GRACE, GLDAS, and ERA5, were employed to train models for estimating groundwater level fluctuations. The primary aim was to evaluate and compare the performance of 12 different machine learning models, including Random Forest, AdaBoost, Support Vector Machine, and Artificial Neural Networks, among others, in terms of their prediction accuracy. The results indicated that ensemble-based models generally outperformed individual algorithms, achieving the highest coefficients of determination (R²) and the lowest error metrics. Spatial analysis of the errors revealed that the northern part of the study area experienced higher prediction errors than the southern region, likely due to more significant groundwater level fluctuations, influenced by regional climatic conditions and topography. Furthermore, the study demonstrated that combining various input parameters, such as terrestrial water storage, total soil moisture, and precipitation, improved the accuracy of the groundwater level predictions. The models were evaluated using standard error metrics, including Mean Error (ME), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Pearson Correlation Coefficient (R), with results showing strong agreement between predicted and observed data. The findings suggest that machine learning models, especially those leveraging high-resolution satellite and reanalysis data, can be highly effective for groundwater level prediction and management in regions with limited in-situ measurement data. | ||
| کلیدواژه‌ها | ||
| Groundwater Level Estimation؛ Machine Learning؛ Ensemble Models؛ Remote Sensing Data؛ Water Resource Management | ||
|
آمار تعداد مشاهده مقاله: 33 تعداد دریافت فایل اصل مقاله: 30 |
||