Diffusive flux of CH4 and N2O from agricultural river networks: Regression tree and importance analysis

Abstract The field of metacommunity studies is growing rapidly, including recent applications to river networks. Most of these studies have targeted a single river network but whether their findings are relevant to other river systems is unknown. This study investigated the influence of environmental, spatial and temporal parameters on the community structure of nematodes in the river networks of the Elbe and Rhine. We asked whether the variance in community structure was better explained by spatial variables representing the watercourse than by overland distances. After determining the patterns in the Elbe river network, we tested whether they also explained the Rhine data. The Elbe data were evaluated using a boosted regression tree analysis. The predictive ability of the model was then assessed using the Rhine data. In addition to strong temporal dynamics, environmental factors were more important than spatial factors in structuring riverine nematode communities. Community structure was more strongly influenced by watercourse than by Euclidean distances. Application of the model’s predictions to the Rhine data correlated significantly with field observations. Our model shows that the consequences of changes in environmental factors or habitat connectivity for aquatic communities across different river networks are quantifiable.

Download Full-text

Recognizing Crucial Aquatic Factors Influencing Greenhouse Gas Emissions in the Eutrophication Zone of Taihu Lake, China

Sustainability ◽

10.3390/su11195160 ◽

2019 ◽

Vol 11 (19) ◽

pp. 5160

Author(s):

Yulin Wang ◽

Liang Wang ◽

Jilin Cheng ◽

Chengda He ◽

Haomiao Cheng

Keyword(s):

Greenhouse Gas ◽

Taihu Lake ◽

Eastern China ◽

Effective Means ◽

Ghg Emissions ◽

Regression Tree ◽

Key Factor ◽

Ch4 And N2o ◽

Meiliang Bay ◽

Positive Correlations

Greenhouse gas (GHG) emissions, which are closely related to climate change and serious ecological instability, have attracted global attention. The estimation of crucial aquatic factors for the flux of GHGs in lakes is a key step in controlling and reducing GHG emissions. The importance of 14 aquatic factors for GHG emissions was estimated in Meiliang Bay, which is an eutrophication shallow bay in Taihu Lake in eastern China. The random forest (RF) method, which is an improved version of the classified and regression tree (CART) model, was employed. No distribution assumption on variables was required in this method and it could include nonlinear actions and interactions among factors. The results show significant positive correlations among the fluxes of CO2, CH4, and N2O. The most crucial factor influencing CO2 emissions is the water temperature (WT) followed by sulfate (SO42−), alkalinity (Alk), dissolved oxygen (DO), and nitrate (NO3−–N). The important factors for CH4 emissions are WT, SO42−, DO, Alk, and NO2−–N. The outcome for N2O, in which the key factor is NO2−–N, was slightly different from those of CO2 and CH4. A comprehensive ranking index (CRI) for the fluxes of all three GHGs was also calculated and showed that WT, NO2−–N, SO42−, DO, and Alk are the most crucial aquatic factors. These results indicate that increasing DO might be the most effective means of controlling GHG emissions in eutrophication lake bays. The role of SO42− in GHG emissions, which has previously been ignored, is also worth paying attention to. This study provides a useful basis for controlling GHG emissions in eutrophication shallow lake bays.

Download Full-text

Predicting the Recurrence of Child Maltreatment: A Classification and Regression Tree Analysis

PsycEXTRA Dataset ◽

10.1037/e517322011-501 ◽

2007 ◽

Author(s):

Eve Sledjeski ◽

Lisa Dierker ◽

Rebecca Brigham ◽

Eileen Breslin

Keyword(s):

Child Maltreatment ◽

Regression Tree ◽

Classification And Regression Tree ◽

Tree Analysis ◽

Regression Tree Analysis ◽

Classification And Regression

Download Full-text

Using boosted regression tree models to predict the diets of juvenile bull sharks in a subtropical estuary

Marine Ecology Progress Series ◽

10.3354/meps13568 ◽

2020 ◽

Author(s):

E Cottrant ◽

P Matich ◽

MR Fisher

Keyword(s):

Regression Tree ◽

Boosted Regression Tree ◽

Tree Models ◽

Subtropical Estuary

Download Full-text

Drivers of diversity gradients of a highly mobile marine assemblage in a mesoscale seascape

Marine Ecology Progress Series ◽

10.3354/meps13264 ◽

2020 ◽

Vol 638 ◽

pp. 149-164

Author(s):

GM Svendsen ◽

M Ocampo Reinaldo ◽

MA Romero ◽

G Williams ◽

A Magurran ◽

...

Keyword(s):

Environmental Gradients ◽

Regression Tree ◽

Demersal Fish ◽

Open Ocean ◽

Shared Resources ◽

Thermal Front ◽

Boosted Regression Tree ◽

Diversity Gradients ◽

Α Diversity ◽

Bottom Depth

With the unprecedented rate of biodiversity change in the world today, understanding how diversity gradients are maintained at mesoscales is a key challenge. Drawing on information provided by 3 comprehensive fishery surveys (conducted in different years but in the same season and with the same sampling design), we used boosted regression tree (BRT) models in order to relate spatial patterns of α-diversity in a demersal fish assemblage to environmental variables in the San Matias Gulf (Patagonia, Argentina). We found that, over a 4 yr period, persistent diversity gradients of species richness and probability of an interspecific encounter (PIE) were shaped by 3 main environmental gradients: bottom depth, connectivity with the open ocean, and proximity to a thermal front. The 2 main patterns we observed were: a monotonic increase in PIE with proximity to fronts, which had a stronger effect at greater depths; and an increase in PIE when closer to the open ocean (a ‘bay effect’ pattern). The originality of this work resides on the identification of high-resolution gradients in local, demersal assemblages driven by static and dynamic environmental gradients in a mesoscale seascape. The maintenance of environmental gradients, specifically those associated with shared resources and connectivity with an open system, may be key to understanding community stability.

Download Full-text

A NEW SCHEME FOR THE DISCRETIZATION OF DIFFUSIVE FLUX ON EXTREMELY SKEWED UNSTRUCTURED MESHES

10.1615/tfec2018.cfd.022360 ◽

2018 ◽

Author(s):

Minghai Xu ◽

Huawen Shu ◽

Liang Gong ◽

Peng Ding ◽

Wenbo Liu

Keyword(s):

Unstructured Meshes ◽

Diffusive Flux

Download Full-text

River networks

Physics Subject Headings (PhySH) ◽

10.29172/d3d66936fc594c19a956d58d21db7d5e ◽

2018 ◽

Keyword(s):

River Networks

Download Full-text

In silico Prediction of Inhibitory Constant of Thrombin Inhibitors Using Machine Learning

Combinatorial Chemistry & High Throughput Screening ◽

10.2174/1386207322666181220130232 ◽

2019 ◽

Vol 21 (9) ◽

pp. 662-669 ◽

Cited By ~ 1

Author(s):

Junnan Zhao ◽

Lu Zhu ◽

Weineng Zhou ◽

Lingfeng Yin ◽

Yuchen Wang ◽

...

Keyword(s):

Machine Learning ◽

Prediction Models ◽

Regression Tree ◽

Large Data ◽

Thrombin Inhibitors ◽

Coagulation Cascade ◽

Gradient Boosting ◽

Support Vector ◽

Data Set ◽

Descriptor Selection

Background: Thrombin is the central protease of the vertebrate blood coagulation cascade, which is closely related to cardiovascular diseases. The inhibitory constant Ki is the most significant property of thrombin inhibitors. Method: This study was carried out to predict Ki values of thrombin inhibitors based on a large data set by using machine learning methods. Taking advantage of finding non-intuitive regularities on high-dimensional datasets, machine learning can be used to build effective predictive models. A total of 6554 descriptors for each compound were collected and an efficient descriptor selection method was chosen to find the appropriate descriptors. Four different methods including multiple linear regression (MLR), K Nearest Neighbors (KNN), Gradient Boosting Regression Tree (GBRT) and Support Vector Machine (SVM) were implemented to build prediction models with these selected descriptors. Results: The SVM model was the best one among these methods with R2=0.84, MSE=0.55 for the training set and R2=0.83, MSE=0.56 for the test set. Several validation methods such as yrandomization test and applicability domain evaluation, were adopted to assess the robustness and generalization ability of the model. The final model shows excellent stability and predictive ability and can be employed for rapid estimation of the inhibitory constant, which is full of help for designing novel thrombin inhibitors.

Download Full-text