Hydrological models are developed to simulate river flows over a watershed for many practical applications in the field of water resource management. The present paper compares the performance of two recurrent neural ...Hydrological models are developed to simulate river flows over a watershed for many practical applications in the field of water resource management. The present paper compares the performance of two recurrent neural networks for rainfall-runoff modeling in the Zou River basin at Atchérigbé outlet. To this end, we used daily precipitation data over the period 1988-2010 as input of the models, such as the Long Short-Term Memory (LSTM) and Recurrent Gate Networks (GRU) to simulate river discharge in the study area. The investigated models give good results in calibration (R2 = 0.888, NSE = 0.886, and RMSE = 0.42 for LSTM;R2 = 0.9, NSE = 0.9 and RMSE = 0.397 for GRU) and in validation (R2 = 0.865, NSE = 0.851, and RMSE = 0.329 for LSTM;R2 = 0.9, NSE = 0.865 and RMSE = 0.301 for GRU). This good performance of LSTM and GRU models confirms the importance of models based on machine learning in modeling hydrological phenomena for better decision-making.展开更多
Pyrite is a ubiquitous authigenic mineral in modern anoxic sediments and occurs in ancient sedimentary rocks.Study of sedimentary pyrite morphology, which can provide useful information on deposition environments and ...Pyrite is a ubiquitous authigenic mineral in modern anoxic sediments and occurs in ancient sedimentary rocks.Study of sedimentary pyrite morphology, which can provide useful information on deposition environments and early diagenetic processes,has become an important aspect for reconstruction of palaeoenviroment.The Upper Cretaceous Qingshankou Formation Unit 1（K<sub>2</sub>qn<sup>1</sup>）lithology,which occured in the south well of the SLCORE I for Continental Cretaceous Scientific Drilling Project展开更多
Coalbed methane enrichment will be controlled by many good macro geological dynamical conditions; there is evident difference of enrichment grade in different area and different geological conditions.This paper has st...Coalbed methane enrichment will be controlled by many good macro geological dynamical conditions; there is evident difference of enrichment grade in different area and different geological conditions.This paper has studied tectonic dynamical conditions, thermal dynamical conditions and hydraulic conditions, which affect coalbed methane enrichment in Qinshui basin.Coalbed methane enrichment units have been divided based on tectonic dynamical conditions of Qinshui basin,combined with thermal dynamical conditions and hydraulic conditions.展开更多
水质指标具有多元相关性、时序性和非线性的特点,为有效预测河流水质变化,针对水质数据存在缺失和异常的问题,提出基于灰色关联分析-门控循环单元(Grey Relational Analysis-Gated Recurrent Unit, GRA-GRU)的水质预测模型。以淮河流域...水质指标具有多元相关性、时序性和非线性的特点,为有效预测河流水质变化,针对水质数据存在缺失和异常的问题,提出基于灰色关联分析-门控循环单元(Grey Relational Analysis-Gated Recurrent Unit, GRA-GRU)的水质预测模型。以淮河流域水质数据为样本,使用线性插值修补缺失数据和剔除的异常数据。使用灰色关联分析计算不同水质指标间的相关性,选择高相关性的水质指标以确定输入变量,并使用门控循环单元(Gated Recurrent Unit, GRU)预测不同的水质指标。将GRA-GRU的预测结果与反向传播神经网络(Back Propagation Neural Network, BPNN)、循环神经网络(Recurrent Neural Network, RNN)、长短期记忆神经网络(Long Short Term Memory, LSTM)、GRU及灰色关联分析-长短期记忆神经网络(Grey Relational Analysis-Long Short Term Memory, GRA-LSTM)进行对比分析,结果显示GRA-GRU在不同水质指标预测上具有较好的适应性,可以有效降低预测误差。其中,与其他模型相比,GRA-GRU预测的化学需氧量在均方根误差上分别降低了3.617%、0.681%、0.478%、1.505%和0.471%。展开更多
The distribution of the Jurassic coal measures in the northern Qaidam Basin is obviously controlled by the regional structures. Based on the existing data of coalfield exploration and combined with the analysis of coa...The distribution of the Jurassic coal measures in the northern Qaidam Basin is obviously controlled by the regional structures. Based on the existing data of coalfield exploration and combined with the analysis of coalfield basement structures, features of the main faults, and the distribution of coal measures, this paper brings forward a scheme of coalfield tectonic divisional units and the definition of the coal-controlling structural styles in the northern Qaidam Basin. The structure control of the distribution of coal measures is further discussed. Several stages of regional tectonic activities since the Indosinian has led to the distribution of coal measures into the characteristics of zonation from the north to south and block from east to west. The results indicate that the structural deformations are the most intense in the front of the three uplifted belts, which are characterized by the combination of thrusts. The coal measures are uplifted to the shallow formations, and are easy to be exploited, but the scale of mines is small because of serious damages by the coal distribution. On the contrary, the stress and strain are weak in the three depressions, with the coal-controlling structural styles being mainly the thrust-fold and thrust-monocline combinations. The distribution of coals in the depressions is relatively stable. The shallower part of the depression will become the key areas for exploration and development of coal resources in the northern Qaidam Basin.展开更多
文摘Hydrological models are developed to simulate river flows over a watershed for many practical applications in the field of water resource management. The present paper compares the performance of two recurrent neural networks for rainfall-runoff modeling in the Zou River basin at Atchérigbé outlet. To this end, we used daily precipitation data over the period 1988-2010 as input of the models, such as the Long Short-Term Memory (LSTM) and Recurrent Gate Networks (GRU) to simulate river discharge in the study area. The investigated models give good results in calibration (R2 = 0.888, NSE = 0.886, and RMSE = 0.42 for LSTM;R2 = 0.9, NSE = 0.9 and RMSE = 0.397 for GRU) and in validation (R2 = 0.865, NSE = 0.851, and RMSE = 0.329 for LSTM;R2 = 0.9, NSE = 0.865 and RMSE = 0.301 for GRU). This good performance of LSTM and GRU models confirms the importance of models based on machine learning in modeling hydrological phenomena for better decision-making.
文摘Pyrite is a ubiquitous authigenic mineral in modern anoxic sediments and occurs in ancient sedimentary rocks.Study of sedimentary pyrite morphology, which can provide useful information on deposition environments and early diagenetic processes,has become an important aspect for reconstruction of palaeoenviroment.The Upper Cretaceous Qingshankou Formation Unit 1（K<sub>2</sub>qn<sup>1</sup>）lithology,which occured in the south well of the SLCORE I for Continental Cretaceous Scientific Drilling Project
文摘Coalbed methane enrichment will be controlled by many good macro geological dynamical conditions; there is evident difference of enrichment grade in different area and different geological conditions.This paper has studied tectonic dynamical conditions, thermal dynamical conditions and hydraulic conditions, which affect coalbed methane enrichment in Qinshui basin.Coalbed methane enrichment units have been divided based on tectonic dynamical conditions of Qinshui basin,combined with thermal dynamical conditions and hydraulic conditions.
文摘水质指标具有多元相关性、时序性和非线性的特点,为有效预测河流水质变化,针对水质数据存在缺失和异常的问题,提出基于灰色关联分析-门控循环单元(Grey Relational Analysis-Gated Recurrent Unit, GRA-GRU)的水质预测模型。以淮河流域水质数据为样本,使用线性插值修补缺失数据和剔除的异常数据。使用灰色关联分析计算不同水质指标间的相关性,选择高相关性的水质指标以确定输入变量,并使用门控循环单元(Gated Recurrent Unit, GRU)预测不同的水质指标。将GRA-GRU的预测结果与反向传播神经网络(Back Propagation Neural Network, BPNN)、循环神经网络(Recurrent Neural Network, RNN)、长短期记忆神经网络(Long Short Term Memory, LSTM)、GRU及灰色关联分析-长短期记忆神经网络(Grey Relational Analysis-Long Short Term Memory, GRA-LSTM)进行对比分析,结果显示GRA-GRU在不同水质指标预测上具有较好的适应性,可以有效降低预测误差。其中,与其他模型相比,GRA-GRU预测的化学需氧量在均方根误差上分别降低了3.617%、0.681%、0.478%、1.505%和0.471%。
文摘The distribution of the Jurassic coal measures in the northern Qaidam Basin is obviously controlled by the regional structures. Based on the existing data of coalfield exploration and combined with the analysis of coalfield basement structures, features of the main faults, and the distribution of coal measures, this paper brings forward a scheme of coalfield tectonic divisional units and the definition of the coal-controlling structural styles in the northern Qaidam Basin. The structure control of the distribution of coal measures is further discussed. Several stages of regional tectonic activities since the Indosinian has led to the distribution of coal measures into the characteristics of zonation from the north to south and block from east to west. The results indicate that the structural deformations are the most intense in the front of the three uplifted belts, which are characterized by the combination of thrusts. The coal measures are uplifted to the shallow formations, and are easy to be exploited, but the scale of mines is small because of serious damages by the coal distribution. On the contrary, the stress and strain are weak in the three depressions, with the coal-controlling structural styles being mainly the thrust-fold and thrust-monocline combinations. The distribution of coals in the depressions is relatively stable. The shallower part of the depression will become the key areas for exploration and development of coal resources in the northern Qaidam Basin.
