River algal blooms are well predicted by antecedent environmental conditions

Xia, Rui; Wang, Gangsheng; Zhang, Yuan; Yang, Peng; Yang, Zhongwen; Ding, Sen; Jia, Xin; Yang, Chen; Liu, Chengjian; Ma, Shuqin; Jiang, Lin; Wang, Xiao; Hou, Xueling; Zhang, Kai; Gao, Xin; Duan, Pingzhou; Chang, Qian

doi:10.1016/j.watres.2020.116221

Cited by 79 publications

(34 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final GBM model is a stage-wise additive model of previous individual trees. The GBM has been proven successful across many domains, including classification problems (Lawrence, 2004;Xia et al, 2020) and regression problems (Liao et al, 2020;Xenochristou et al, 2020;Yan et al, 2019), which is the case for this study.…”

Section: Parameter Regionalization Strategymentioning

confidence: 96%

“…We further estimated the relative importance of each explanatory variable based on the GBM model, which was determined by averaging the improvement (decrease) in the squared error at each split over all the trees made by each variable, with a range from 0 (least important) and 100 (most important;Natekin and Knoll, 2013;Xia et al, 2020). Fig-…”

Section: Identification Of Important Factors For Model Parametersmentioning

confidence: 99%

“…Here we attempted to estimate parameters as a function of watershed features in ungauged areas using a machine learning method, i.e., the gradient boosting machine (GBM; Friedman, 2001). GBMs are a family of powerful machine learning techniques that have achieved considerable success across many domains, such as image classification (Lawrence, 2004), text classification (Natekin and Knoll, 2013), pattern recognition (Schütz et al, 2019), motion detection (Bouwman et al, 2020), and ecological and environmental issues (Fan et al, 2021;Liao et al, 2020;Wei et al, 2019;Xia et al, 2020). The principal idea behind the GBM is to consecutively construct the new base learners, which optimally improves prediction in combination with the already existing ensemble, leading to a more accurate estimate of the response variable (Natekin and Knoll, 2013;Schütz et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Regionalization of hydrological model parameters using gradient boosting machine

Song

Xia

Wang

et al. 2022

Hydrol. Earth Syst. Sci.

Self Cite

View full text Add to dashboard Cite

Abstract. The regionalization of hydrological model parameters is key to hydrological predictions in ungauged basins. The commonly used multiple linear regression (MLR) method may not be applicable in complex and nonlinear relationships between model parameters and watershed properties. Moreover, most regionalization methods assume lumped parameters for each catchment without considering within-catchment heterogeneity. Here we incorporated the Penman–Monteith–Leuning (PML) equation into the Distributed Time Variant Gain Model (DTVGM) to improve the mechanistic representation of the evapotranspiration (ET) process. We calibrated six key model parameters, grid by grid across China, using a multivariable calibration strategy which incorporates spatiotemporal runoff and ET datasets (0.25∘; monthly) as reference. In addition, we used the gradient boosting machine (GBM), a machine learning technique, to portray the dependence of model parameters on soil and terrain attributes in four distinct climatic zones across China. We show that the modified DTVGM could reasonably estimate the runoff and ET over China using the calibrated parameters but performed better in humid rather than arid regions for the validation period. The regionalized parameters by the GBM method exhibited better spatial coherence relative to the calibrated grid-by-grid parameters. In addition, GBM outperformed the stepwise MLR method in both parameter regionalization and gridded runoff simulations at a national scale, though the improvement pertaining to watershed streamflow validation is not significant due to most of the watersheds being located in humid regions. We also revealed that the slope, saturated soil moisture content, and elevation are the most important explanatory variables to inform model parameters based on the GBM approach. The machine-learning-based regionalization approach provides an effective alternative to deriving hydrological model parameters from watershed properties, particularly in ungauged regions.

show abstract

Section: Parameter Regionalization Strategymentioning

confidence: 96%

Section: Identification Of Important Factors For Model Parametersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Regionalization of hydrological model parameters using gradient boosting machine

Song

Xia

Wang

et al. 2022

Hydrol. Earth Syst. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many hydro‐ecologists have conducted a large number of studies on the causes of spring diatom blooms in the Han River (Chen et al, 2002; Lu et al, 2000; Xia et al, 2020; Yin et al, 2012). The results of these studies can be summarized in the following three points.…”

Section: Study Areamentioning

confidence: 99%

Hydrological management strategies for the control of algal blooms in regulated lowland rivers

Yin

Jia

et al. 2021

Hydrological Processes

View full text Add to dashboard Cite

Reservoirs of lowland floodplain rivers with eutrophic backgrounds cause variations in the hydrological and hydraulic conditions of estuaries and low‐dam reservoir areas, which can promote planktonic algae to proliferate and algal bloom outbreaks. Understanding the ecological effects of variations in hydrological and hydraulic processes in lowland rivers is important for algal bloom control. In this study, the middle and lower reaches of the Han River, China, a typical regulated lowland river with a eutrophic background, are selected. Based on the effect of hydrological and hydraulic variability on algal blooms, a hydrological management strategy for river algal bloom control is proposed. The results showed that (a) differences in river morphology and background nutrient levels cause significant differences in the critical threshold flow velocities for algal bloom outbreaks between natural river and low‐dam reservoir sections; there is no uniform threshold flow velocity for algal bloom control. (b) There are significant differences in the river hydrological/hydraulic conditions between years with and without algal blooms. The average river flow, water level and velocity in years with algal blooms are significantly lower than those in years without algal blooms. (c) For different river sections where algal blooms occur and to meet the threshold flow velocities, the joint operation of cascade reservoirs and diversion projects is an effective method to prevent and control algal blooms in regulated lowland rivers. This study is expected to deepen our understanding of the ecological significance of special hydrological processes and guide algal bloom management in regulated lowland rivers.

show abstract

“…For example, hydrologic alteration or impairment has been shown to strongly influence aquatic benthic invertebrate communities (Poff et al, 2007;Rehn, 2009), and benthic invertebrates have been used to link metrics of hydrologic variability to biological community response (Poff and Zimmerman, 2010;Steel et al, 2018). Studies of the direct relationships between algae and flow are limited (Kirkwood et al, 2009;Miller et al, 2009;Schneider et al, 2016), with some exceptions involving algal blooms in large rivers (Cheng et al, 2019;Xia et al, 2020) and directly following a flood (Schneider et al, 2016). However, impacts of flow alteration on water quality (Nilsson and Renöfält, 2008) can also indirectly influence the composition of algal communities (Allan, 2004;Lange et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Identifying Functional Flow Linkages Between Stream Alteration and Biological Stream Condition Indices Across California

Peek

Irving

Yarnell

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Large state or regional environmental flow programs, such as the one based on the California Environmental Flows Framework, rely on broadly applicable relationships between flow and ecology to inform management decisions. California, despite having high flow and bioassessment data density, has not established relationships between specific elements of the annual hydrograph and biological stream condition. To address this, we spatially and temporally linked USGS gage stations and biological assessment sites in California to identify suitable paired sites for comparisons of streamflow alteration with biological condition at a statewide scale. Flows were assessed using a set of functional flow metrics that provide a comprehensive way to compare alteration and seasonal variation in streamflow across different locations. Biological response was evaluated using the California Stream Condition Index (CSCI) and Algal Stream Condition Index (ASCI), which quantify biological conditions by translating benthic invertebrate or algal resources and watershed-scale environmental data into an overall measure of stream health. These indices provide a consistent statewide standard for interpreting bioassessment data, and thus, a means of quantitatively comparing stream conditions throughout the state. The results indicate that indices of biological stream condition were most closely associated with flow alteration in seasonality and timing metrics, such as fall pulse timing, dry-season timing, and wet season timing. Magnitude metrics such as dry-season baseflow, wet season baseflow, and the fall pulse magnitude were also important in influencing biological stream conditions. Development of ecological flow needs in large-scale environmental programs should consider that alteration to any of the seasonal flow components (e.g., dry-season baseflow, fall pulse flow, wet-season baseflow, spring recession flow) may be important in restructuring biological communities.

show abstract

River algal blooms are well predicted by antecedent environmental conditions

Cited by 79 publications

References 56 publications

Regionalization of hydrological model parameters using gradient boosting machine

Regionalization of hydrological model parameters using gradient boosting machine

Hydrological management strategies for the control of algal blooms in regulated lowland rivers

Identifying Functional Flow Linkages Between Stream Alteration and Biological Stream Condition Indices Across California

Contact Info

Product

Resources

About