China Institute of Geological Environmental Monitoring

Key Points Regional groundwater model for North China Plain integrating most available data Most comprehensive analyses to date of groundwater storage depletion in the NCP Groundwater sustainability under complex hydrologic and socioeconomic conditions

Identifying floods and producing flood susceptibility maps are crucial steps for decision-makers to prevent and manage disasters. Plenty of studies have used machine learning models to produce reliable susceptibility maps. Nevertheless, most research ignores the importance of developing appropriate feature engineering methods. In this study, we propose a local spatial sequential long short-term memory neural network (LSS-LSTM) for flood susceptibility prediction in Shangyou County, China. The three main contributions of this study are summarized below. First of all, it is a new perspective to use the deep learning technique of LSTM for flood susceptibility prediction. Second, we integrate an appropriate feature engineering method with LSTM to predict flood susceptibility. Third, we implement two optimization techniques of data augmentation and batch normalization to further improve the performance of the proposed method. The LSS-LSTM method can not only capture the attribution information of flood conditioning factors and the local spatial information of flood data, but also has powerful sequential modelling capabilities to deal with the spatial relationship of floods. The experimental results demonstrate that the LSS-LSTM method achieves satisfactory prediction performance (93.75% and 0.965) in terms of accuracy and area under the receiver operating characteristic (ROC) curve.

This study introduces four heterogeneous ensemble-learning techniques, that is, stacking, blending, simple averaging, and weighted averaging, to predict landslide susceptibility in Yanshan County, China. These techniques combine several state-of-the-art classifiers of convolutional neural network, recurrent neural network, support vector machine, and logistic regression in specific ways to produce reliable results and avoid problems with the model selection. The study consists of three main steps. The first step establishes a spatial database consisting of 16 landslide conditioning factors and 380 historical landslide locations. The second step randomly selects training (70% of the total) and test (30%) datasets out of grid cells corresponding to landslide and non-slide locations in the study area. The final step constructs the proposed heterogeneous ensemble-learning methods for landslide susceptibility mapping. The proposed ensemble-learning methods show higher prediction accuracy than the individual classifiers mentioned above based on statistical measures. The blending ensemble-learning method achieves the highest overall accuracy of 80.70% compared to the other ensemble-learning methods.

Significant advances in regional groundwater flow modeling have been driven by the demand to predict regional impacts of human inferences on groundwater systems and associated environment. The wide availability of powerful computers, user friendly modeling systems and GIS stimulates an exponential growth of regional groundwater modeling. Large scale transient groundwater models have been built to analyze regional flow systems, to simulate water budget components changes, and to optimize groundwater development scenarios. This paper reviews the historical development of regional groundwater modeling. Examples of Death Valley and Great Artesian Basin transient groundwater models are introduced to show the application of large scale regional groundwater flow models. Specific methodologies for regional groundwater flow modeling are descried and special issues in regional groundwater flow modeling are discussed.

The North China Plain (NCP) has been suffering from groundwater storage (GWS) depletion and land subsidence for a long period. This paper collects data on GWS changes and land subsidence from in situ groundwater-level measurements, literature, and satellite observations to provide an overview of the evolution of the aquifer system during 1971–2015 with a focus on the sub-regional variations. It is found that the GWS showed a prolonged declining rate of −17.8 ± 0.1 mm/yr during 1971–2015, with a negative correlation to groundwater abstraction before year ~2000 and a positive correlation after ~2000. Statistical correlations between subsidence rate and the GWS anomaly (GWSA), groundwater abstraction, and annual precipitation show that the land subsidence in three sub-regions (Beijing, Tianjin, and Hebei) represents different temporal variations due to varying driver factors. Continuous drought caused intensive GWS depletion (−76.1 ± 6.5 mm/yr) and land subsidence in Beijing during 1999–2012. Negative correlations between total groundwater abstraction and land subsidence exhibited after the 1980s indicate that it may be questionable to infer subsidence from regional abstraction data. Instead, the GWSA generally provides a reliable correlation with subsidence. This study highlights the spatio-temporal variabilities of GWS depletion and land subsidence in the NCP under natural and anthropogenic impacts, and the importance of GWS changes for understanding land subsidence development.

-based, and bismuth-based semiconductor materials and their applications in the degradation of water pollutants are highlighted with recent illustrative examples. Furthermore, the future prospects of semiconductor photocatalysis for water treatment are critically analyzed.

The main goal of this study is to produce a landslide susceptibility map in the Wanzhou section of the Three Gorges reservoir area (China) with a weighted gradient boosting decision tree (weighted GBDT) model. According to the current research on landslide susceptibility mapping (LSM), the GBDT method is rarely used in LSM. Furthermore, previous studies have rarely considered the imbalance of landslide samples and simply regarded the LSM problem as a binary classification problem. In this paper, we considered LSM as an imbalanced learning problem and obtained a better predictive model using the weighted GBDT method. The innovations of the article mainly include the following two points: introducing the GBDT model into the evaluation of landslide susceptibility; using the weighted GBDT method to deal with the problem of landslide sample imbalance. The logistic regression (LR) model and gradient boosting decision tree (GBDT) model were also used in the study to compare with the weighted GBDT model. Five kinds of data from different data source were used in the study: geology, topography, hydrology, land cover, and triggered factors (rainfall, earthquake, land use, etc.). Twenty nine environmental parameters and 233 landslides were used as input data. The receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC) value, and the recall value were used to estimate the quality of the weighted GBDT model, the GBDT model, and the LR model. The results showed that the GBDT model and the weighted GBDT model had a higher AUC value (0.977, 0.976) than the LR model (0.845); the weighted GBDT model had a little higher AUC value (0.977) than the GBDT model (0.976); and the weighted GBDT model had a higher recall value (0.823) than the GBDT model (0.426) and the LR model (0.004). The weighted GBDT method could be considered to have the best performance considering the AUC value and the recall value in landslide susceptibility mapping dealing with imbalanced landslide data.

genus.

In this work, an effective framework for landslide susceptibility mapping (LSM) is presented by integrating information theory, K-means cluster analysis and statistical models. In general, landslides are triggered by many causative factors at a local scale, and the impact of these factors is closely related to geographic locations and spatial neighborhoods. Based on these facts, the main idea of this research is to group a study area into several clusters to ensure that landslides in each cluster are affected by the same set of selected causative factors. Based on this idea, the proposed predictive method is constructed for accurate LSM at a regional scale by applying a statistical model to each cluster of the study area. Specifically, each causative factor is first classified by the natural breaks method with the optimal number of classes, which is determined by adopting Shannon’s entropy index. Then, a certainty factor (CF) for each class of factors is estimated. The selection of the causative factors for each cluster is determined based on the CF values of each factor. Furthermore, the logistic regression model is used as an example of statistical models in each cluster using the selected causative factors for landslide prediction. Finally, a global landslide susceptibility map is obtained by combining the regional maps. Experimental results based on both qualitative and quantitative analysis indicated that the proposed framework can achieve more accurate landslide susceptibility maps when compared to some existing methods, e.g., the proposed framework can achieve an overall prediction accuracy of 91.76%, which is 7.63–11.5% higher than those existing methods. Therefore, the local scale LSM technique is very promising for further improvement of landslide prediction.

Abstract The Heihe River Basin (HRB) is an inland watershed in northwest China with a total area of approximately 130,000 km 2 , stretching from the Qilian Mountains in the south to the oases and agricultural fields in the middle and further to the Gobi desert in the north bordering Mongolia. As part of a major ecohydrological research initiative to provide a stronger scientific underpinning for sustainable water management in arid ecosystems, a regional‐scale integrated ecological and hydrological model is being developed, incorporating the knowledge based on the results of environmental isotope tracer analysis and the multiscale observation datasets. The first step in the model development effort is to construct and calibrate a groundwater flow model for the middle and lower HRB where the oases and vegetation along the Heihe river corridor are highly dependent on groundwater. In this study, the software tool ‘Arc Hydro Groundwater’ is used to build and visualize a hydrogeological data model for the HRB that links all relevant spatiotemporal hydrogeological data in a unified geodatabase within the ArcGIS environment. From the conceptual model, a regional‐scale groundwater flow model has been developed using MODFLOW‐2005. Critical considerations in developing the flow model include the representation of mountainous terrains and fluvial valleys by individual model layers, treatment of aquifer heterogeneities across multiple scales and selection of proper observation data and boundary conditions for model calibration. This paper discusses these issues in the context of the Heihe River Basin, but the results and insights from this study will have important implications for other large, regional groundwater modelling studies, especially in arid and semiarid inland river basins. Copyright © 2014 John Wiley & Sons, Ltd.

Monitoring of regional groundwater levels provides important information for quantifying groundwater depletion and assessing impacts on the environment. Historically, groundwater level monitoring wells in Beijing Plain, China, were installed for assessing groundwater resources and for monitoring the cone of depression. Monitoring wells are clustered around well fields and urban areas. There is urgent need to upgrade the existing monitoring wells to a regional groundwater level monitoring network to acquire information for integrated water resources management. A new method was proposed for designing a regional groundwater level monitoring network. The method is based on groundwater regime zone mapping. Groundwater regime zone map delineates distinct areas of possible different groundwater level variations and is useful for locating groundwater monitoring wells. This method was applied to Beijing Plain to upgrade a regional groundwater level monitoring network.

Hexavalent chromium (Cr(VI)) is known to occur naturally in shallow oxic groundwater, typically from aquifers associated with mafic and ultramafic formations, but information on the occurrence of Cr(VI) in deep groundwater from large sedimentary basins is limited. This study shows that groundwater from the Baiyangdian Lake Basin (BYB), home to the future second capital city of China, had high Cr concentration (>10 μg/L, up to 86 μg/L) in the deep aquifer (>150 m), while shallow groundwater had lower Cr concentration (<10 μg/L). Chromium occurred predominantly as Cr(VI) (>95%). Shallow groundwater was characterized by higher Mn and Fe concentrations relative to deep groundwater, likely indicating more reducing conditions. Sequential extraction experiments from aquifer sediments suggest that Cr(VI) may derive from silicate weathering and that Mn oxides in the aquifer play a major role in the formation of Cr(VI) in groundwater. Inverse correlations between Mn and Cr(VI) suggest that reductive dissolution of Mn oxides constrains Cr(VI) mobilization in the shallow groundwater, while oxic-suboxic conditions in the deep aquifer limit Mn solubility, which enhances oxidation of Cr(III) to Cr(VI) and promotes desorption of Cr(VI) under alkaline conditions. This study demonstrates the potential geogenic occurrence of high Cr(VI) concentration in deep groundwater from a nonmafic, large sedimentary basin containing Mn oxides in the aquifer sediments.

Abstract Human activities and climate change threaten water quality in China’s rivers. We simulated the monthly concentrations of riverine total nitrogen (TN), ammonia-nitrogen (NH 3 -N), total phosphorus (TP), and chemical oxygen demand (COD Mn ) in 613 sub-watersheds of the nation’s 10 major river basins during the 1980–2050 period based on a 16-year (2003–2018) monitoring dataset using the stacking machine-learning models. The results showed that water quality improved markedly, except for the TN concentration, which was probably due to the lack of a TN control target and assessment system. Quantitative analysis indicated that anthropogenic factors were the primary controls compared with climatic drivers and geographical drivers for TN, TP, and NH 3 -N concentrations. On the basis of all 17 sustainable development goals (SDGs) relevant to water quality in China, the water resources, water environment, aquatic ecology and water security should be considered collectively to achieve improvements in the ecological status of China’s rivers.

In arid and semi‐arid areas, salinization of soil and water resources is one of the major threats to irrigated agriculture. For management purposes, quantifying both the extent and distribution of salinization is important, but accurate data with sufficient spatial resolution are often not available. Commonly used techniques such as soil sampling and geophysical methods are time‐consuming and yield only point data. A method is described in which multispectral remote sensing images can be used to regionalize point data measured on the field. Field data consist of measurements of electrical conductivity and are obtained by the combination of geophysical methods and the analysis of field soil samples. Uncalibrated salinity maps were calculated with spectral correlation mapping using image‐based reference spectra of saline areas. As an alternative indicator for soil salinity, the NDVI was used. The method was verified in the Yanqi Basin, northwestern China. Correlations between field data and the uncalibrated salinity maps were found over non‐irrigated sites for all images. Good correlations (R 2 up to 0.85) resulted for images collected during the winter months. The high correlation coefficients allow the uncalibrated salinity maps to be scaled to electrical conductivity maps.

Three-dimensional ionospheric electron density is an important parameter for characterizing the ionosphere. Synthetic aperture radar (SAR), an advanced earth observation technology, has shown its potential for observing two-dimensional vertical total electron content (VTEC). However, retrieval of three-dimensional electron density is limited by the SAR imaging geometry. To solve this problem, a simple method is proposed to reconstruct the regional three-dimensional electron density by ingesting the SAR-derived VTEC into an international reference ionosphere (IRI) model. The ionospheric global (IG) index is updated by minimizing the difference between the SAR-derived and IRI-derived VTECs. Subsequently, the high-spatial-resolution electron density is reconstructed by exploiting the monotonic relationship between the electron density and the IG index. For assessing the performance of the proposed method, two full-polarimetric advanced land observing satellite (ALOS) images with descending and ascending orbits were acquired to reconstruct the three-dimensional electron density over the Alaska region. Incoherent scattering radar (ISR) electron density was collected from the Poker Flat Incoherent Scatter Radar (PFISR) system to validate the reconstructed electron density. The results show that the standard deviations of the electron density decreased by approximately 30% for the ascending orbit and 19% for the descending orbit when the proposed method was used, thereby illustrating its feasibility.

This study presents a new ensemble framework to predict landslide susceptibility by integrating decision trees (DTs) with the rotation forest (RF) ensemble technique. The proposed framework mainly includes four steps. First, training and validation sets are randomly selected according to historical landslide locations. Then, landslide conditioning factors are selected and screened by the gain ratio method. Next, several training subsets are produced from the training set and a series of trained DTs are obtained by using a DT as a base classifier couple with different training subsets. Finally, the resultant landslide susceptibility map is produced by combining all the DT classification results using the RF ensemble technique. Experimental results demonstrate that the performance of all the DTs can be effectively improved by integrating them with the RF ensemble technique. Specifically, the proposed ensemble methods achieved the predictive values of 0.012–0.121 higher than the DTs in terms of area under the curve (AUC). Furthermore, the proposed ensemble methods are better than the most popular ensemble methods with the predictive values of 0.005–0.083 in terms of AUC. Therefore, the proposed ensemble framework is effective to further improve the spatial prediction of landslides.

One of the most important parameters related to soil salinization is the direct evaporation from the groundwater (phreatic evaporation). If the groundwater table is sufficiently close to the surface, groundwater will evaporate through capillary rise. In recent years, several methods have been suggested to map evapotranspiration (ET) on the basis of remote sensing images. These maps represent the sum of both transpiration of vegetation and evaporation from the bare soil. However, identifying the amount of phreatic evaporation is important as it is the dominant flux in the salt balance of the soil. The interpretation of stable isotope profiles at nonirrigated areas in the unsaturated zone allows one to quantify phreatic evaporation independently of the transpiration of the vegetation. Such measurements were carried out at different locations with a different depth to groundwater. The benefit is twofold. (1) A relation between phreatic evaporation rates and the depth to groundwater can be established. (2) By subtracting the measured values of phreatic evaporation from remotely sensed values of ET, vadose ET consisting of transpiration and excess irrigation water in the unsaturated zone can be estimated at the sampling locations. A correlation between the normalized differential vegetation index and the calculated vadose ET rates could be established ( R 2 = 0.89). With this correlation the contribution of phreatic evaporation can be estimated. This approach has been tested for the Yanqi basin located in western China. Finally, the distribution of phreatic evaporation was compared to a soil salinity map of the project area on a qualitative basis.

Ensemble learning methods have been widely used due to their remarkable generalized performance, but their potential in landslide spatial prediction application is not fully studied. To take full advantage of ensemble learning techniques, the classification and regression tree classifier and four tree-based ensemble classifiers of random forest, extremely randomized tree, gradient boosting decision trees, and extreme gradient boosting decision trees are used in this study for landslide susceptibility assessment. Specifically, a stacking ensemble learning framework coupled with embedded feature selection is presented, consisting of multiple tree-based classifiers mentioned previously as base learners and logistic regression as a metalearner in a two-layer structure. In the study area of Yongxin, China, 364 historical landslide locations were first randomly partitioned into a ratio of 7/3 for training and testing the model. Then, a spatial database of 16 landslide causative factors was constructed for landslide prediction. Meanwhile, the relative importance of these factors were quantified by using the total number of feature splits and the average Gini index during the training process, and a novel embedded feature selection method was used in the base learner of the proposed framework to further improve the computational efficiency and predictive performance by allowing each base learner to obtain its own optimal subfeature space. Finally, different methods were assessed by using several evaluation criteria. Experimental results demonstrated that the proposed ensemble learning framework had the highest area under the curve value of 0.864, and it is more effective than the conventional tree-based classifiers and other ensemble learning methods.

Water scarcity has led to wide use of reclaimed water for irrigation worldwide, which may threaten groundwater quality. To understand the status of groundwater in the reclaimed water irrigation area in Beijing, 87 samples from both shallow and deep aquifers were collected to determine the factors affecting groundwater chemistry and to assess groundwater quality for drinking and irrigation purposes. The results show that groundwater in both shallow and deep aquifers in the study area is weakly alkaline freshwater with hydrogeochemical faces dominated by HCO3-Na·Mg·Ca, HCO3-Mg·Ca·Na, HCO3-Ca·Na, and HCO3-Na. The chemical composition of groundwater in both shallow and deep aquifers is dominantly controlled by the dissolution of halite, gypsum, anhydrite, and silicates weathering, as well as ion exchange. Geogenic processes (rock weathering and ion exchange) are the only mechanisms controlling groundwater chemistry in deep aquifers. Besides geogenic processes, evaporation and anthropogenic activities also affect the chemistry of shallow groundwater. Quality assessment reveals that both shallow and deep groundwater are generally suitable for drinking and irrigation purposes. The quality of deep groundwater is more excellent for drinking than shallow groundwater. However, long-term use of deep groundwater for irrigation exhibits higher potential risks to deteriorate soil property due to the relative higher permeability indexes (PI). Therefore, it is recommended that deep groundwater is preferentially used for drinking and domestic purpose, and shallow groundwater for agricultural irrigation.

Introduction Microbes play key roles in maintaining soil ecological functions. Petroleum hydrocarbon contamination is expected to affect microbial ecological characteristics and the ecological services they provide. In this study, the multifunctionalities of contaminated and uncontaminated soils in an aged petroleum hydrocarbon-contaminated field and their correlation with soil microbial characteristics were analyzed to explore the effect of petroleum hydrocarbons on soil microbes. Methods Soil physicochemical parameters were determined to calculate soil multifunctionalities. In addition, 16S high-throughput sequencing technology and bioinformation analysis were used to explore microbial characteristics. Results The results indicated that high concentrations of petroleum hydrocarbons (565–3,613 mg•kg −1 , high contamination) reduced soil multifunctionality, while low concentrations of petroleum hydrocarbons (13–408 mg•kg −1 , light contamination) might increase soil multifunctionality. In addition, light petroleum hydrocarbon contamination increased the richness and evenness of microbial community ( p &amp;lt; 0.01), enhanced the microbial interactions and widened the niche breadth of keystone genus, while high petroleum hydrocarbon contamination reduced the richness of the microbial community ( p &amp;lt; 0.05), simplified the microbial co-occurrence network, and increased the niche overlap of keystone genus. Conclusion Our study demonstrates that light petroleum hydrocarbon contamination has a certain improvement effect on soil multifunctionalities and microbial characteristics. While high contamination shows an inhibitory effect on soil multifunctionalities and microbial characteristics, which has significance for the protection and management of petroleum hydrocarbon-contaminated soil.