Abstract
The occurrence of toxic metals in the aquatic environment is as caused by a variety of contaminations which makes difficulty in the concentration prediction. In this study, conventional ...methods of back-propagation neural network (BPNN) and nonlinear autoregressive network with exogenous inputs (NARX) were applied as benchmark models. Explanatory variables of Fe, pH, electrical conductivity, water temperature, river flow, nitrate nitrogen, and dissolved oxygen were used as different input combinations to forecast the long-term concentrations of As, Pb, and Zn. The wavelet transformation was applied to decompose the time series data, and then was integrated with conventional methods (as WNN and WNARX). The modelling performances of the hybrid models of WNN and WNARX were compared with the conventional models. All the given models were trained, validated, and tested by an 18-year data set and demonstrated based on the simulation results of a 2-year data set. Results revealed that the given models showed general good performances for the long-term prediction of the toxic metals of As, Pb, and Zn. The wavelet transform could enhance the long-term concentration predictions. However, it is not necessarily useful for each metal prediction. Therefore, different models with different inputs should be used for different metals predictions to achieve the best predictions.
•An ecosystem services-based framework is established and integrated into water resource management.•We develop a participatory Bayesian network model to perform the framework under public ...participation.•The participatory Bayesian network effectively provides the support of transdisciplinary water management.
There is an increasing consensus on the importance of coupling ecosystem services (ES) into integrated water resource management (IWRM), due to a wide range of benefits to human from the ES. This paper proposes an ES–based IWRM framework within which a participatory Bayesian network (BN) model is developed to assist with the coupling between ES and IWRM. The framework includes three steps: identifying water-related services of ecosystems; analysis of the tradeoff and synergy among users of water; and ES-based IWRM implementation using the participatory BN model. We present the development, evaluation and application of the participatory BN model with the involvement of four participant groups (stakeholders, water manager, water management experts, and research team) in Qira oasis area, Northwest China. As a typical catchment-scale region, the Qira oasis area is facing severe water competition between the demands of human activities and natural ecosystems. Results demonstrate that the BN model developed provides effective integration of ES into a quantitative IWMR framework via public negotiation and feedback. The network results, sensitivity evaluation, and management scenarios are broadly accepted by the participant groups. The intervention scenarios from the model conclude that any water management measure remains unable to sustain the ecosystem health in water-related ES. Greater cooperation among the stakeholders is highly necessary for dealing with such water conflicts. In particular, a proportion of the agricultural water saved through improving water-use efficiency should be transferred to natural ecosystems via water trade. The BN model developed is appropriate for areas throughout the world in which there is intense competition for water between human activities and ecosystems.
Oasification is a complex oasis expansion and ecological processes caused by climate changes and human activities under available water supply in arid and semiarid regions. The process can ...effectively improve soil productivity, vegetation cover, and biomass production in fighting against land degradation, such as desertification and soil erosion. However, the significance of oasification has not yet reached the general cognition compared to desertification, which is regarded as one of the most severe global eco-environmental issues. This paper identifies desertification and oasification processes and their perspectives in cognition. The implication of oasification in combating desertification and controlling land degradation is emphasized by the justification between desertification and oasification processes. As opposite process of desertification, the oasification is an unable evasive process that can provide positive environmental effects in the control of desertification, ecological restoration, and land rehabilitation. According to the interaction of climatic variations and human activities, the oasification processes is classified into six main forms: natural oasis evolution process, engineering forest construction, conversion of natural landforms into farmlands, urban encroachment, constructed environments, and coupled ecosystems. These processes gradually modify the productive capacity of soils, increase vegetation cover for restoring degraded lands, and improve the living environment for human settlement and sustainability of an oasis ecosystem. Moreover, an overview of oasification research is detailed, and Northwest China as an example is used to illustrate the progress of the oasification research in recent decades. Currently, the oasification process and its mechanistic research still remain less concern in the arid and semiarid regions. A new science framework of the oasification research is proposed to effectively deal with ecological and environmental issues in the arid and semiarid regions.
•Desertification and oasification and their perspectives are identified.•Implication of oasification is emphasized in comparison with desertification.•Oasification processes are classified into six main forms.•Overview of oasification research is detailed and illustrated in Northwest China.•A new science framework of the oasification research is proposed.
Evapotranspiration (ET) is one of the most important components of global hydrologic cycle and has significant impacts on energy exchange and climate change. Numerous models have been developed to ...estimate ET so far; however, great uncertainties in models still require considerations. The aim of this study is to reduce model errors and uncertainties among multi-models to improve daily ET estimate. The Bayesian model averaging (BMA) method is used to assemble eight ET models to produce ET with Landsat 8 satellite data, including four surface energy balance models (i.e., SEBS, SEBAL, SEBI, and SSEB) and four machine learning algorithms (i.e., polymars, random forest, ridge regression, and support vector machine). Performances of each model and BMA method were validated through in situ measurements of semi-arid region. Results indicated that the BMA method outperformed all eight single models. The four most important models obtained by the BMA method were ranked by random forest, SVM, SEBS, and SEBAL. The BMA method coupled with machine learning can significantly improve the accuracy of daily ET estimate, reducing uncertainties among models, and taking different intrinsic benefits of empirically and physically based models to obtain a more reliable ET estimate.
Oases support 90% of the province’s inhabitants and produce more than 95% of the social wealth in Xinjiang Province of China. Oases’ dependency on water availability from mountainous regions plays a ...critical factor in the sustainability of agricultural practices and oasis expansion. In this study, we have chosen the Cele Oasis located in the south rim of the Taklimakan Desert, typical of oases in the region, as a case study to examine water availability. With over 97% of Cele’s economy tied to agriculture, unfettered expansion of the oasis into the desert has raised concern on water availability. A spatial and temporal analysis of water availability is performed using newly available data to determine whether agricultural production within the Cele Oasis has overexploited available water resources or if feasible expansion of agricultural production is feasible beyond its current boundary. Transferability of the methodology for assessing water availability spatially and temporally will be beneficial to other oases in the arid region that face similar concerns.
•A sparse grid method is developed to build a surrogate model of the RZWQM2.•The global optimization algorithm QPSO is used for parameter estimation.•Calibrating the surrogate gives comparable ...results as the calibration of the RZWQM2.•The surrogate global optimization greatly improves computational efficiency.
Robust calibration of an agricultural-hydrological model is critical for simulating crop yield and water quality and making reasonable agricultural management. However, calibration of the agricultural-hydrological system models is challenging because of model complexity, the existence of strong parameter correlation, and significant computational requirements. Therefore, only a limited number of simulations can be allowed in any attempt to find a near-optimal solution within an affordable time, which greatly restricts the successful application of the model. The goal of this study is to locate the optimal solution of the Root Zone Water Quality Model (RZWQM2) given a limited simulation time, so as to improve the model simulation and help make rational and effective agricultural-hydrological decisions. To this end, we propose a computationally efficient global optimization procedure using sparse-grid based surrogates. We first used advanced sparse grid (SG) interpolation to construct a surrogate system of the actual RZWQM2, and then we calibrate the surrogate model using the global optimization algorithm, Quantum-behaved Particle Swarm Optimization (QPSO). As the surrogate model is a polynomial with fast evaluation, it can be efficiently evaluated with a sufficiently large number of times during the optimization, which facilitates the global search. We calibrate seven model parameters against five years of yield, drain flow, and NO3-N loss data from a subsurface-drained corn-soybean field in Iowa. Results indicate that an accurate surrogate model can be created for the RZWQM2 with a relatively small number of SG points (i.e., RZWQM2 runs). Compared to the conventional QPSO algorithm, our surrogate-based optimization method can achieve a smaller objective function value and better calibration performance using a fewer number of expensive RZWQM2 executions, which greatly improves computational efficiency.
Combating desertification is vital for arresting land degradation and ensuring sustainable development of the global ecological environment. This study has analyzed the current desertification status ...and determined its control needs based on the difference between potential normalized difference vegetation index (PNDVI) and actual normalized difference vegetation index (ANDVI) in the Hotan desertoasis. The MaxEnt model, combined with the distribution point data of natural vegetation with long-term stable normalized difference vegetation index (NDVI) and 24 environmental factors was used to predict the PNDVI spatial distribution of different vegetation coverage grades and compared it with ANDVI. Excluding the areas of intense human activity such as arable land, the simulation results show that PNDVI with high, medium, and low vegetation cover was mainly distributed in the southwest and southeast of Hotan Oasis, in the midstream and downstream of Kalakash River and Yulong Kashi River, and the desert or Gobi area outside the oasis, respectively. The distribution of PNDVI with high, medium, and low vegetation cover accounted for 6.80%, 7.26%, and 9.17% of Hotan oasis, respectively. The comparison between ANDVI and PNDVI shows that 18.04% (ANDVI < PNDVI, about 3900 km
) of the study area is still suffering from desertification, which is mainly distributed in the desert-oasis ecotone in Hotan. The findings of this study implied that PNDVI could be used to assess the desertification status and endorsement of desertification control measures in vulnerable ecosystems. Hence, PNDVI can strengthen the desertification combating efforts at regional and global scales and may serve as a reference point for the policymakers and scientific community towards sustainable land development.
Abstract
Identifying suitable habitats for endangered species is critical in order to promote their recovery. However, conventional species distribution models (SDMs) need large amounts of labeled ...sample data to learn the relationship between species and environmental conditions, and are difficult to fully detangle the role of the environment in the distribution of the endangered species, which are very sparsely distributed and have environmental heterogeneity. This study’s first innovation used the semi-supervised model to accurately simulate the suitable habitats for endangered species with a small sample size. The model performance was compared with three conventional SDMs, namely Maxent, the generalized linear model, and a support vector machine. Applying the model to the endangered species
Populus euphratica (P. euphratica)
in the lower Tarim River basin (TRB), Northwest China. The results showed that the semi-supervised model exhibited better performance than conventional SDMs with an accuracy of 85% when only using 443
P. euphratica
samples. All models developed using smaller sample sizes exhibit worse performance in the prediction of habitat suitability areas for endangered species while the semi-supervised model is still excellent. The results showed that the suitable habitat for
P. euphratica
is mainly near the river channel of the lower TRB, accounting for 13.49% of the study area. The lower Tarim River still has enormous land potential for the restoration of endangered
P. euphratica
. The model developed here can be used to evaluate a suitable habitat for endangered species with only a small sample size, and provide a basis for the conservation of endangered species.
Soil environment and water quality face large pressure due to the rapid expansion of greenhouse cultivation in China. However, studies rarely provide the linkage between farmers’ practices and soil ...degradation in greenhouse cultivation field. In this study, a field survey and sampling of greenhouse cultivation soil were conducted in five regions of China to investigate the accumulation and variation characteristics of soil ion compositions in the field. First, the pH, ion compositions, and electrical conductivity (EC) of 132 composite soil samples were analyzed. Second, farmers’ practices with regard to fertilizer, crop yield, and soil degradation processes were surveyed. Lastly, soil nutrient status was evaluated by different grades, and the principal component analysis method was used to analyze the main sources of soil ion compositions. Results of the study reveal the following: (1) Enrichment of greenhouse soil nutrient was mainly caused by excessive fertilization, which introduced the secondary salinization phenomenon for 3–5 years in plastic greenhouse and 1–3 years in multispan greenhouse. (2) Significant changes between the EC and salt ion composition of open soil and greenhouse cultivated soil were observed. The contents of nitrate nitrogen and ammonium nitrogen in the greenhouse soil were high. (3) After a certain period of cultivation in the greenhouse, salt accumulation, pH decline, and varying degrees of acidification were observed in the soil profile. The relationship between soil pH and EC values indicated that the balance of soil compositions was broken. The recommended methods for sustaining greenhouse cultivation include balanced fertilization, rotation practices, and reasonable water utilization in the field.
Interest in the use of enhanced-efficiency nitrogen (N) fertilizers (EENFs) has increased in recent years due to their potential to increase crop yield and reduce environmental N loss. ...Drip-fertigation is widely used for crop production in arid regions to improve water and nutrient use efficiency whereas the effectiveness of EENFs with drip irrigation remains unclear. A field experiment was conducted in 2015 and 2016 to examine the effects of EENFs on yield, N use and quality of cotton (Gossypium hirsutum) grown under drip-fertigation in arid NW China. Treatments included an unfertilized control and application of 240 kg N ha
by polymer-coated urea (ESN), urea alone, or urea plus urease (NBPT) and nitrification (DCD) inhibitors. ESN was all banded in the plant row at planting, whereas urea was applied with 20% N banded at planting and 80% N by six fertigation events over the growing season. Results showed there was generally no treatment effect on seed and lint yield, N concentration or allocations, N recovery efficiency and fiber quality index of cotton. A lack of treatment effect could be due to N supplied with drip-fertigation better synthesized with crop N needs and the relatively high soil native NO
availability, which hindered the effect of polymer-coated urea and double inhibitors. These results highlight the challenge of the employment of EENFs products for drip-fertigation system in arid area. Further research is required to define the field conditions under which the agronomic efficiency of EENFs products may be achieved in accordance with weather conditions.