Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

2 Acta Geophysica

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Characteristic of regional groundwater flow system: case modeling study in Longzici karst spring area, North China

100%

Qiao X. , Cheng Y. , Wang D.

Acta Geophysica

2024

tom Vol. 72, no. 1

323--339

Karst spring water dynamic characteristics and its response to atmospheric precipitation are of great significance for water resources utilization under the background of climate change. This paper selects Longzici spring area, North China, as the study area. Based on a long series of spring water flow and precipitation data, the dynamic characteristics of spring flow were analyzed and the numerical simulation of the groundwater flow model was established. The results show that the groundwater kept the sustained decline over the past decades which is in a negative equilibrium state, with a storage variable of - 2.26 million m3/year. The sensitivity of spring flow to precipitation under different precipitation scenarios shows that the water level changes in the recharge and drainage areas are similar about (3-5 cm) and slightly larger than that in the runoff area(1.5 cm) when minimum rainfall (287.24 mm) happens. When the precipitation is at its maximum (867.66 mm), the water level change in the runoff area can reach 95 cm which is much larger than those in the recharge and discharge areas. The results indicate that Longzici karst spring has a relatively good regulation water resource capacity and the runoff area is more sensitive which plays an important role in response to climate change.

Machine learning for predicting discharge fuctuation of a karst spring in North China

100%

Cheng S. , Qiao X. , Shi Y. , Wang D.

Acta Geophysica

2021

tom Vol. 69, no. 1

257--270

The quantitative analyses of karst spring discharge typically rely on physical-based models, which are inherently uncertain. To improve the understanding of the mechanism of spring discharge fuctuation and the relationship between precipitation and spring discharge, three machine learning methods were developed to reduce the predictive errors of physical-based groundwater models, simulate the discharge of Longzici spring’s karst area, and predict changes in the spring on the basis of long time series precipitation monitoring and spring water fow data from 1987 to 2018. The three machine learning methods included two artifcial neural networks (ANNs), namely multilayer perceptron (MLP) and long short-term memory–recurrent neural network (LSTM–RNN), and support vector regression (SVR). A normalization method was introduced for data preprocessing to make the three methods robust and computationally efcient. To compare and evaluate the capability of the three machine learning methods, the mean squared error (MSE), mean absolute error (MAE), and root-mean-square error (RMSE) were selected as the performance metrics for these methods. Simulations showed that MLP reduced MSE, MAE, and RMSE to 0.0010, 0.0254, and 0.0318, respectively. Meanwhile, LSTM–RNN reduced MSE to 0.0010, MAE to 0.0272, and RMSE to 0.0329. Moreover, the decrease in MSE, MAE, and RMSE was 0.0397, 0.1694, and 0.1991, respectively, for SVR. Results indicated that MLP performed slightly better than LSTM–RNN, and MLP and LSTM–RNN performed considerably better than SVR. Furthermore, ANNs were demonstrated to be prior machine learning methods for simulating and predicting karst spring discharge.