Land use is rapidly changing and is significantly affecting ecosystem service delivery all around the world. The socio-economic context and political choices largely determine land use change. This ...land use change, driven by socio-economic pressures, will impact diverse elements of the environment including, for example, air quality, soil properties, water infiltration and food and wood production, impacts that can be linked to the provisioning of ecosystem services. To gain more insight into the effects of alternative socio-economic developments on ecosystem service delivery, land use change models are being coupled to ecosystem service delivery models to perform scenario analyses. Although the uncertainty of the results of these kind of scenario analyses are generally far from negligible, studies rarely take them into account. In this study, a cellular automaton land use change model is coupled to Bayesian belief network ecosystem service delivery models to facilitate the study of error propagation in scenario analysis. The proposed approach is applied to model the impact of alternative socio-economic developments on ecosystem service delivery in Flanders, Belgium and to assess the impact of land use allocation uncertainty on the uncertainty associated to future ecosystem service delivery. Results suggest that taking into account uncertainties may have an effect on policy recommendations that come out of the scenario analysis. However, in this study, uncertainties in the applied ecosystem service models were dominant, reducing the importance of accounting for land use allocation uncertainty.
Display omitted
•Uncertainties are rarely addressed in ecosystem service assessments•This paper assesses future ecosystem service delivery and associated uncertainties•Our approach combines a cellular automaton with Bayesian belief networks•In our case study, the influence of land use allocation uncertainty was low•The use of more complex ecosystem service models might increase its influence
•The development of species distribution models relies on machine learning algorithms.•Evolutionary algorithms (EAs) bring new insights in ecological model development.•Feature selection and ...parameter-rich model calibration are key EA training subjects.•Many learning methods used in ecology can be combined with EAs.•Adaptable and flexible frameworks for machine learning in ecology are needed.
Scientists and decision-makers need tools that can assess which specific pressures lead to ecosystem deterioration, and which measures could reduce these pressures and/or limit their effects. In this context, species distribution models are tools that can be used to help asses these pressures. Evolutionary algorithms represent a collection of promising techniques, inspired by concepts observed in natural evolution, to support the development of species distribution models. They are suited to solve non-trivial tasks, such as the calibration of parameter-rich models, the reduction of model complexity by feature selection and/or the optimization of hyperparameters of other machine learning algorithms. Although widely used in other scientific domains, the full potential of evolutionary algorithms has yet to be explored for applied ecological research. In this synthesis, we study the role of evolutionary algorithms as a machine learning technique to develop the next generation of species distribution models. To do so, we review available methods for species distribution modelling and synthesize literature using evolutionary algorithms. In addition, we discuss specific advantages and weaknesses of evolutionary algorithms and present a guideline for their application. We find that evolutionary algorithms are increasingly used to solve specific and challenging problems. Their flexibility, adaptability and transferability in addition to their capacity to find adequate solutions to complex, non-linear problems are considered as main strengths, especially for species distribution models with a large degree of complexity. The need for programming and modelling skills can be considered as a drawback for novice modellers. In addition, setting values for hyperparameters is a challenge. Future ecological research should focus on exploring the potential of evolutionary algorithms that combine multiple tasks in one learning cycle. In addition, studies should focus on the use of novel machine learning schemes (e.g. automated hyperparameter optimization) to apply evolutionary algorithms, preferably in the context of open science. This way, ecologists and model developers can achieve an adaptable and flexible framework for developing tools useful for decision management.
Species distribution models have often been developed based on ecological data. To develop reliable data-driven models, however, a sound model training and evaluation procedures are needed. A crucial ...step in these procedures is the assessment of the model performance, with as key component the applied performance criterion. Therefore, we reviewed seven performance criteria commonly applied in presence–absence modelling (the correctly classified instances, Kappa, sensitivity, specificity, the normalised mutual information statistic, the true skill statistic and the odds ratio) and analysed their application in both the model training and evaluation process. Although estimates of predictive performance have been used widely to assess final model quality, a systematic overview was missing because most analyses of performance criteria have been empirical and only focused on specific aspects of the performance criteria. This paper provides such an overview showing that different performance criteria evaluate a model differently and that this difference may be explained by the dependency of these criteria on the prevalence of the validation set. We showed theoretically that these prevalence effects only occur if the data are inseparable by an
n-dimensional hyperplane,
n being the number of input variables. Given this inseparability, different performance criteria focus on different aspects of model performance during model training, such as sensitivity, specificity or predictive accuracy. These findings have important consequences for ecological modelling because ecological data are mostly inseparable due to data noise and the complexity of the studied system. Consequently, it should be very clear which aspect of the model performance is evaluated, and models should be evaluated consistently, that is, independent of, or taking into account, species prevalence. The practical implications of these findings are clear. They provide further insight into the evaluation of ecological presence/absence models and attempt to assist modellers in their choice of suitable performance criteria.
Knowledge of the distribution and habitat preference of freshwater snail intermediate hosts can provide information to initiate and set-up effective snail control programmes. However, there is ...limited research conducted on the factors driving the occurrence and abundance of freshwater snail intermediate hosts in the Ethiopian Rift Valley. Hence, in this study, we investigated how environmental and biotic factors influence the occurrence and abundance of the snail intermediate hosts in Ethiopian Rift Valley region.
Data on freshwater snails, physico-chemical water quality parameters, physical characteristics of habitat, predators and competitors, and anthropogenic activity variables were collected from 174 sampling sites during the wet season of 2017 and 2018. Generalized linear models were used to identify the main environmental and biotic factors affecting the occurrence and abundance of the snail species.
It was found that Bulinus globosus (31.7%) was the most abundant snail species followed by Lymnaea natalensis (21.6%), Lymnaea truncatula (15.1%) and Biomphalaria pfeifferi (14.6%). Generalized linear models indicated that physico-chemical parameters (water temperature, turbidity, chlorophyll-a, dissolved oxygen, chemical oxygen demand, alkalinity, calcium, magnesium, nitrate and ammonia), physical habitat characteristics (water depth, canopy cover, macrophyte cover and substrate type) and biotic factors (abundance of predators and competitors) were found to be the main variables determining the occurrence and abundance of snail species in the Ethiopian Rift Valley region. In terms of anthropogenic activities, human settlement, farming, bathing and swimming, clothes washing, grazing, drainage of land, car washing, boating, fishing and silviculture were also important variables determining the occurrence and abundance of snail species in the region.
The findings reported herein suggest that integrated snail control strategies should be considered to control snails via protection of water bodies from disturbance by anthropogenic activities. In this way, it is possible to reduce the concentration of organic matter and dissolved ions in aquatic ecosystems which are conducive for the presence of snails.
Data sets plagued with missing data and performance-affecting model parameters represent recurrent issues within the field of data mining. Via random forests, the influence of data reduction, outlier ...and correlated variable removal and missing data imputation technique on the performance of habitat suitability models for three macrophytes (Lemna minor, Spirodela polyrhiza and Nuphar lutea) was assessed. Higher performances (Cohen's kappa values around 0.2-0.3) were obtained for a high degree of data reduction, without outlier or correlated variable removal and with imputation of the median value. Moreover, the influence of model parameter settings on the performance of random forest trained on this data set was investigated along a range of individual trees (ntree), while the number of variables to be considered (mtry), was fixed at two. Altering the number of individual trees did not have a uniform effect on model performance, but clearly changed the required computation time. Combining both criteria provided an ntree value of 100, with the overall effect of ntree on performance being relatively limited. Temperature, pH and conductivity remained as variables and showed to affect the likelihood of L. minor, S. polyrhiza and N. lutea being present. Generally, high likelihood values were obtained when temperature is high (>20 °C), conductivity is intermediately low (50-200 mS m
) or pH is intermediate (6.9-8), thereby also highlighting that a multivariate management approach for supporting macrophyte presence remains recommended. Yet, as our conclusions are only based on a single freshwater data set, they should be further tested for other data sets.
Environmental and measure implementation costs are two key factors to be considered by river managers in decision making. To balance effects and costs of an action, practitioners can rely on ...diagnostic analysis of presence/absence freshwater species distribution models (SDMs) trained to over- or underestimating species presence. Prevalence-adjusted model training aims to balance under- and overestimation depending on study objectives and training data characteristics. The objective of minimising under- and overestimation is a typical example of multi-objective optimisation (MOO). The aim of this paper is to address, for the first time, the practice of MOO-based prevalence-adjusted SDM training for freshwater decision management. In a numerical experiment, the use of Pareto-based MOO, specifically the non-dominated sorting genetic algorithm II (NSGA-II), is compared to commonly-used single-objective optimisation. SDMs for 11 pollution-sensitive freshwater macroinvertebrate species are trained with a subset of the Limnodata, a large data set holding records in the Netherlands over 30 years at 20,000 locations. An increase of two to four times is observed for the ability to identify a large range distribution of the solutions in the Pareto space, when using NSGA-II counter to repeated single-objective optimisation, this by increasing the average runtime with only four percent for a single run. In addition, the use of NSGA-II is found to be effective to identify reliable SDMs useful for diagnostic analysis. By applying and comparing a broad range of MOO methodologies for prevalence-adjusted model training, we believe a closer collaboration between model developers and freshwater managers can be facilitated and environmental standard limits can be set on a more objective basis. In conclusion, the use of MOO for prevalence-adjusted model training is assessed as a valuable tool to support river - and potentially all environmental - decision making.
Display omitted
•Balancing correct estimation of species presence/absence is vital in model training.•Multi-objective optimisation is a valuable tool for prevalence-adjusted training.•Identifying objective trade-offs is effective for river management.•Diagnostics of species distribution models can support environmental limit setting.
Aquatic ecosystems are one of the most threatened ecosystems in the world resulting in the decline of aquatic biodiversity. Monitoring and the assessment of aquatic ecosystems are necessary to ...protect and conserve these ecosystems as monitoring provides insights into the changes in the aquatic ecosystem over a long period of time and assessment indicates the status of these ecosystems. This paper presents an overview of different methods for the hydromorphological, physical–chemical and the biological monitoring and assessment of surface waters. Furthermore, recently developed monitoring and assessment methods are discussed to support sustainable water management and contribute to the implementation of the Sustainable Development Goals 6 (SDG6 related to clean water and sanitation) and 15 (SDG15 related to terrestrial and freshwater systems) of the United Nations. However, many other SDGs are dependent on freshwater, such as food (e.g., SDG2) and climate-related SDGs. We presented an innovative concept for integrated monitoring and assessment. The main new elements are the monitoring of all communities and the use of integrated socio-environmental models to link these communities to ecosystem interactions and functions as a basis for determining their relation to the SDGs. Models can also allow to determine the effects of changes in SDGs on the different elements of the concept, and serve in this manner as tools for the selection of an optimal balance between the SDGs in the context of sustainable development.
Freshwater ponds deliver a broad range of ecosystem services (ESS). Taking into account this broad range of services to attain cost-effective ESS delivery is an important challenge facing integrated ...pond management.
To assess the strengths and weaknesses of an ESS approach to support decisions in integrated pond management, we applied it on a small case study in Flanders, Belgium.
A Bayesian belief network model was developed to assess ESS delivery under three alternative pond management scenarios: intensive fish farming (IFF), extensive fish farming (EFF) and nature conservation management (NCM). A probabilistic cost-benefit analysis was performed that includes both costs associated with pond management practices and benefits associated with ESS delivery.
Whether or not a particular ESS is included in the analysis affects the identification of the most preferable management scenario by the model. Assessing the delivery of a more complete set of ecosystem services tends to shift the results away from intensive management to more biodiversity-oriented management scenarios.
The proposed methodology illustrates the potential of Bayesian belief networks. BBNs facilitate knowledge integration and their modular nature encourages future model expansion to more encompassing sets of services. Yet, we also illustrate the key weaknesses of such exercises, being that the choice whether or not to include a particular ecosystem service may determine the suggested optimal management practice.
•Determining optimal pond management practices is a complex task.•CBAs that take into account ESS delivery can facilitate this task considerably.•ESS delivery of ponds can be modeled with Bayesian belief networks.•Including uncertainties in CBAs can provide valuable information for managers.•Modeling an incomplete set of ESS can result in biased recommendations.
Display omitted
•Plastic remediation technologies include clean-up and prevention systems.•Lack of knowledge on the environmental impact of plastic remediation technologies.•Most plastic remediation ...technologies target inland waterways.•Plastic remediation technologies minimize the amount of plastic in the environment.•Plastic clean-up technologies offer crucial opportunities such as data collection.
The global presence of plastic litter and its accumulation in the environment has become an issue of concern to the public and policymakers. This concern has triggered innovators in past decades to design and develop a multitude of remediation technologies to prevent plastic from entering the environment, or to clean up legacy litter. This study aims to (i) systematically review the current scientific literature on plastic remediation technologies, (ii) create a ‘plastic clean-up and prevention overview’ illustrating 124 remediation technologies and 29 characteristics, (iii) qualitatively analyse their key characteristics (e.g., fields of application, targeted plastic), and (iv) investigate challenges and opportunities of clean-up technologies for inland waterways (e.g., canals, rivers) and ports. We identified 61 scientific publications on plastic remediation technologies, until June 2022. Thirty-four of these studies were published within the last three years, demonstrating a growing interest. The presented overview indicates that inland waterways are, so far, the preferred field of application, with 22 technologies specifically designed for cleaning up plastics from inland waterways, and 52 additional ones with the potential to be installed in these locations. Given the importance of clean-up technologies in inland waterways, we highlighted their strengths, weaknesses, opportunities, and threats (SWOT). Our results indicate that, despite the challenges, these technologies provide essential prospects, from improving the environmental quality to raising awareness. Our study is instrumental as it illustrates an up-to-date overview and provides a comprehensive analysis of current in design phase, testing, and in use plastic remediation technologies.
Flow control flushing water from reservoirs has been imposed in South Korea for mitigating harmful cyanobacterial blooms (CyanoHABs) in rivers. This measure, however, can cause water shortage in ...reservoirs, as the measure adopting this flow control may require an additional amount of water which exceeds the water demand allocated to the reservoirs. In terms of sustainability, a trade-off between improving water quality and alleviating water shortage needs to be considered. This study aimed at establishing a practical framework for a decision support system for optimal joint operation of the upstream reservoirs (Andong and Imha) to reduce the frequency of CyanoHABs in the Nakdong River, South Korea. Methodologically, three models were introduced: (1) a machine learning model (accuracy 88%) based on the k-NN (k-Nearest Neighbor) algorithm to predict the occurrence of CyanoHABs at a selected downstream location (the Chilgok Weir located approximately 140 km downstream from the Andong Dam), (2) a multiobjective optimization model employing NSGA-II (Nondominated Sorting Genetic Algorithm II) to determine both the quantity and quality of water released from the reservoirs, and (3) a river water quality model (R2 0.79) using HEC-RAS to simulate the water quality parameter at Chilgok Weir according to given upstream boundary conditions. The applicability of the framework was demonstrated by simulation results using observational data from 2015 to 2019. The simulation results based on the framework confirmed that the frequency of CyanoHABs would be decreased compared with the number of days when CyanoHABs were observed at Chilgok Weir. This framework, with a combination of several models, is a novelty in terms of efficiency, and it can be a part of a solution to the problem of CyanoHABs without using an additional amount of water from a reservoir.