首页> 外文期刊>Journal of Hydrology >Simulation and prediction of suprapermafrost groundwater level variation in response to climate change using a neural network model
【24h】

Simulation and prediction of suprapermafrost groundwater level variation in response to climate change using a neural network model

机译:基于神经网络模型的超霜冻地下水位响应气候变化的模拟和预测

获取原文
获取原文并翻译 | 示例
       

摘要

Suprapermafrost groundwater has an important role in the hydrologic cycle of the permafrost region. However, due to the notably harsh environmental conditions, there is little field monitoring data of groundwater systems, which has limited our understanding of permafrost groundwater dynamics. There is still no effective mathematical method and theory to be used for modeling and forecasting the variation in the permafrost groundwater. Two ANN models, one with three input variables (previous groundwater level, temperature and precipitation) and another with two input variables (temperature and precipitation only), were developed to simulate and predict the site-specific suprapermafrost groundwater level on the slope scale. The results indicate that the three input variable ANN model has superior real-time site-specific prediction capability and produces excellent accuracy performance in the simulation and forecasting of the variation in the suprapermafrost groundwater level. However, if there are no field observations of the suprapermafrost groundwater level, the ANN model developed using only the two input variables of the accessible climate data also has good accuracy and high validity in simulating and forecasting the suprapermafrost groundwater level variation to overcome the data limitations and parameter uncertainty. Under scenarios of the temperature increasing by 0.5 or 1.0 degrees C per 10 years, the suprapermafrost groundwater level is predicted to increase by 1.2-1.4% or 2.5-2.6% per year with precipitation increases of 10-20%, respectively. There were spatial variations in the responses of the suprapermafrost groundwater level to climate change on the slope scale. The variation ratio and the amplitude of the suprapermafrost groundwater level downslope are larger than those on the upper slope under climate warming. The obvious vulnerability and spatial variability of the suprapermafrost groundwater to climate change will impose intensive effects on the water cycle and alpine ecosystems in the permafrost region. (C) 2015 Elsevier B.V. All rights reserved.
机译:多年冻土区地下水在多年冻土区的水文循环中具有重要作用。但是,由于极端恶劣的环境条件,很少有地下水系统的现场监测数据,这限制了我们对多年冻土地下水动力学的理解。仍然没有有效的数学方法和理论可用于建模和预测多年冻土层地下水的变化。开发了两个ANN模型,一个具有三个输入变量(先前的地下水位,温度和降水),另一个具有两个输入变量(仅温度和降水),以在坡度规模上模拟和预测特定地点的超霜冻地下水位。结果表明,三输入变量神经网络模型具有卓越的实时现场特定预测能力,并且在超霜冻土地下水位变化的模拟和预测中具有出色的准确性。但是,如果没有现场观测到超霜冻土的地下水位,则仅使用可获取的气候数据的两个输入变量建立的ANN模型在模拟和预测超霜冻土的地下水位变化以克服数据限制方面也具有较高的准确性和较高的有效性。和参数不确定性。在温度每10年升高0.5或1.0摄氏度的情况下,预计超霜冻地下水位每年将增加1.2-1.4%或2.5-2.6%,而降水量分别增加10-20%。坡度上超霜冻地下水位对气候变化的响应存在空间变化。在气候变暖下,超霜冻地下水位下坡的变化率和幅度大于上坡。多年冻土区地下水对气候变化的明显脆弱性和空间变异性将对多年冻土区的水循环和高山生态系统造成强烈影响。 (C)2015 Elsevier B.V.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号