Showing papers in "Ecological Modelling in 2019"

TL;DR: It is confirmed that spatial cross-validation is essential in preventing overoptimistic model performance and that in addition to spatial validation, a spatial variable selection must be considered in spatial predictions of ecological data to produce reliable predictions.

TL;DR: In this article, the effects of spatial autocorrelation on hyperparameter tuning and performance estimation by comparing several widely used machine-learning algorithms such as boosted regression trees (BRT), k-nearest neighbor (KNN), random forest (RF) and support vector machine (SVM) with traditional parametric algorithms, such as logistic regression (GLM) and semi-parametric ones like generalized additive models (GAM) in terms of predictive performance.

TL;DR: In this paper, the authors analyzed the effect of vegetation cover and tree diversity on the provision of regulating ecosystem services (ES) in the Municipality of Rome, Italy, characterized by a complex territory and by a Mediterranean climate.

TL;DR: This review paper considers species occurrence datasets, climatic and soil predictor variables, modelling algorithms, evaluation methods and widely used software for SDM studies to conclude that SDM techniques provide a valuable asset for forest managers but it is essential to consider uncertainties behind the use of future climate change scenarios.

TL;DR: In this paper, the authors developed ecosystem services accounts at the European Union level, using nature-based recreation as a case study and following the current international accounting framework: System of Environmental-Economic Accounting - Experimental Ecosystem Accounting (SEEA EEA).

TL;DR: This synthesis paper discusses how to strengthen the role of ecological modeling in supporting environmental management decisions with a focus on methodological aspects, and identifies six requirements that are important to increase the usefulness of ecological models for management support.

TL;DR: The role of evolutionary algorithms as a machine learning technique to develop the next generation of species distribution models is studied and their flexibility, adaptability and transferability in addition to their capacity to find adequate solutions to complex, non-linear problems are considered as main strengths.

TL;DR: It is recommended to expand the combination of trait-based approaches with individual-based modelling to simplify the parameterization of models, to capture plant-plant interactions at the individual level, and to explain community dynamics under global change.

TL;DR: In this article, a comprehensive review on urban water-energy nexus from the perspective of urban metabolism is presented, with the objective of less independence and impact on eco-environment, making an inventory of alternative sources and associated optimized utilization pathways within urban water system context from resource management provision.

TL;DR: In this article, the authors present a systematic review of published literature on the application of eco-models to eutrophication from 1968-2018, using CiteSpace software, bibliometric methods, and documents combing methods to determine the hotspots, frontiers, and development trends.

TL;DR: The 3-PG model was originally designed for relatively homogenous forests, but with the recent development, the 3PGmix model has extended its use to mixed species forests as mentioned in this paper.

TL;DR: Results suggest that further efforts may be required to educate biologists on the construction of MPMs, perhaps in concert with the development of new software tools, and the conclusions of many studies that are based on MPMs may need to be re-examined.

TL;DR: In this paper, the authors compared several types of bootstrap experiments and their outputs (95% confidence intervals and confidence contour plots) provided a first glimpse into the accuracy of modern ELEFAN-based curve fitting methods.

TL;DR: The lake ecosystem model PCLake is a process-based model that was developed to simulate water quality based on ecological interactions in shallow, nonstratifying lakes in the temperate climate zone.

TL;DR: In this paper, the authors used both species distribution and spatial food-web models to predict the distribution of European hake, anglerfishes, and red mullets in an exploited marine ecosystem of the Northwestern Mediterranean Sea.

TL;DR: The sensitivity of eight widely used SDM algorithms to variation in configuration options settings is comprehensively tested, indicating that all of the algorithms tested showed sensitivity to alternative (non-default) values for some of their configuration settings and that often this sensitivity is species-dependent.

TL;DR: Wang et al. as discussed by the authors set the national economy of China as a whole system, and applied supply chains analysis based on the input-output structures, to identify the food-water linkage, food-energy linkage, and the energy-water link in the system.

TL;DR: This work addresses the problem of how to estimate a hypothetical fundamental niche from presence data by postulating a simple shape for the physiologically defined niche (Hutchinson’s fundamental niche), and providing prior information for the estimation of the parameters that define the shape of the niche.

TL;DR: In this paper, an approach using long-term observational data (from 1990 to 2013) and the Support vector machine (LS-SVM) for simulating algal blooms was applied.

TL;DR: In this paper, an individual tree-based vegetation model, the University of Virginia Forest Model Enhanced (UVAFME), was used to estimate current and future forest conditions across sites within interior Alaska.

TL;DR: Based on a laterally averaged two-dimensional hydrodynamic and water quality model (CE-QUAL-W2) of Xiangxi Bay (XXB), the authors analyzed the temporal and spatial variations in flow, water temperature, chlorophyll-a (Chl-a) during the impounding process.

TL;DR: In this article, the authors used thermodynamic goal functions (GFs) named emergy and eco-exergy to account for the natural capital value of two Mediterranean Marine Protected Areas (MPAs) located in Southern Italy.

TL;DR: Wang et al. as mentioned in this paper investigated the sustainability nexus using composite ecological efficiency (eco-efficiency) indicators from quantitative and computational modeling perspectives, and developed three data envelopment analysis (DEA) models incorporating metafrontier and undesirable outputs into a slacks-based measure (SBM), an epsilon based measure (EBM), and minimum distance to weak efficient frontier (MinDW), respectively.

TL;DR: In this article, the authors presented a new scheme for aDGVM2, a dynamic vegetation model for tropical ecosystems, that distinguishes annual and perennial grasses based on trait trade-offs to improve the representation of rangeland communities.

TL;DR: In this paper, the authors model changes in river flow and water temperature under changing climate scenarios through the integration of a physically-based semi-distributed hydrological model and a 1D stream water temperature model forced by climate change scenarios.

TL;DR: This analysis highlights LR limitations when data are imbalanced and supports using RF to develop post-fire tree mortality models and suggests how RF can be incorporated into future tree mortality studies, as well as possible implementation in future decision-support tools.

TL;DR: In this paper, the effects of biodiversity protection initiatives (i.e., declaration of Protected Areas -PAs) and related spatio-temporal land use/land cover (LULC) changes on ecosystem services (ESs) in the Nature Reserve of Paul do Boquilobo -NRPB (Central Portugal).

TL;DR: The authors developed a new fire model (Social-Climate Related Pyrogenic Processes and their Landscape Effects: SCRPPLE) that emphasizes the social dimensions of fire and enables simulation of fuel-treatment effects, fire suppression, and prescribed fires.

TL;DR: A model that estimates the conditions where an abnormal growth of algae in reservoirs and lakes takes place is built, combining artificial bee colony and support vector machines algorithms to predict the eutrophication taking into account physical-chemical and biological data sampled in the Englishmen Lake and posterior analysis in a laboratory.

TL;DR: Wang et al. as discussed by the authors developed an expansive river health assessment method based on ecological flow hydrology method in this study that estimates the ecological flow of a river by using a probability density curve combined with six levels of river flow in different states of river ecosystem.