Use of genetic algorithms to select input variables in decision tree models for the prediction of benthic macroinvertebrates

Predicting freshwater organisms based on machine learning is becoming more and more reliable due to the availability of appropriate datasets, advanced modelling techniques and the continuously increasing capacity of computers. A database consisting of measurements collected at 360 sampling sites in non-navigable watercourses in Flanders was applied to predict the absence/presence of benthic macroinvertebrate taxa by means of decision trees. The measured variables were a combination of physical–chemical (temperature, pH, dissolved oxygen concentration, conductivity, total organic carbon, Kjeldahl nitrogen and total phosphorus), structural (granulometric analysis of the sediment, width, depth and flow velocity of the river) and two ecotoxicological variables. The predictive power of decision trees was assessed on the basis of the number of Correctly Classified Instances (CCI). A genetic algorithm was introduced to compare the predictive power of different sets of input variables for the decision trees. The number of input variables was reduced from 15 to 2–8 variables without affecting the predictive power of the decision trees significantly. Furthermore, reducing the number of input variables allowed to ease the identification of general data trends.     

Using GIS for siting artificial reefs—Data issues, problems and solutions: ‘Real World’ to ‘Real World’

As GIS becomes an increasingly more ‘user-friendly’ tool, and more people recognize the benefits of the technology in their work environment, inevitably greater use will be made of it for a wide range of applications. The ease with which a GIS can now be used often overshadows the complexity underlying this technology and the potential difficulties that can (and do) arise when this is not fully understood. In practice, there are two routes open to the application of GIS technology for environmental studies. The first is to commission new data for the research. The second is to make use of existing data sets. Data are at the heart of any GIS application. A detailed knowledge about the data sources, the method of collection, capture, scale and sampling strategy, especially if the data are to be used in any analysis, modelling or simulation studies, is fundamental to any application. Unfortunately, information about data (metadata) is seldom available, especially for archival or legacy data sets. Furthermore, although it is now relatively easy to acquire digital data, to input, store, manipulate and display this data, and to output the results of any GIS analysis in the practical sense, little consideration is given to the problems associated with data quality and how this will ultimately affect present and future analyses and use of the output for planning and decision-making. The need to raise awareness about data quality for applications is set in the context of the development of an environmental database for the Moray Firth. Northeast Scotland, and more specifically the use of selected data sets from the database to aid in the proposed siting of an artificial reef. Using this example, this contribution explores the problems associated with the use of both existing analog and digital data sets as the basis for environmental applications, the problems of data acquisition, data quality, data standards, error and how these can affect the operational use of the data in GIS analyses. The solution to such problems appears to lie with improved error assessment and reporting. The outcome of this contribution is an attempt to offer guidance and solutions to researchers and applications specialists undertaking similar studies, by suggesting to what extent studies, such as the artificial reef siting, can safely make use of existing data sets without risking the problems associated with judgements based on inadequate information, and generated or inherent error.     

多准则离散型决策模型在NEQDSS中的开发应用

介绍了动态式多准则离散型决策模型原理、求解方法以及在国家环境质量决策支持系统(简称NEQDSS)中的应用开发。结果证明,该模型及其软件在NEQDSS中的应用是极其成功的。     

Development of an Earthen Dam Break Database

Earthen embankment dams comprise 85% of all major operational dams in the United States. Assessment of peak flow rates for these earthen dams and the impacts on dam failure are of high interest to engineers and planners. Regression analysis is a frequently used risk assessment approach for earthen dams. In this paper, we present a decision support tool for assessing the applicability of nine regression equations commonly used by practitioners. Using data from 108 case studies, six parameters were observed to be significant factors predicting for peak flow as a metric for risk analysis. We present our work on an expanded earthen dam break database that relates the regression equations and underlying data. A web application, regression selection tool, is also presented to assess the appropriateness of a given model for a given test point. This graphical display allows users to visualize how their data point compares with the data used for the regression equation. These contributions improve estimates and better inform decision makers regarding operational and safety decisions.     

Identifying the Institutional Decision Process to Introduce Decentralized Sanitation in the City of Kunming (China)

We conducted a study of the institutional barriers to introducing urine source separation in the urban area of Kunming, China. On the basis of a stakeholder analysis, we constructed stakeholder diagrams showing the relative importance of decision-making power and (positive) interest in the topic. A hypothetical decision-making process for the urban case was derived based on a successful pilot project in a periurban area. All our results were evaluated by the stakeholders. We concluded that although a number of primary stakeholders have a large interest in testing urine source separation also in an urban context, most of the key stakeholders would be reluctant to this idea. However, the success in the periurban area showed that even a single, well-received pilot project can trigger the process of broad dissemination of new technologies. Whereas the institutional setting for such a pilot project is favorable in Kunming, a major challenge will be to adapt the technology to the demands of an urban population. Methodologically, we developed an approach to corroborate a stakeholder analysis with the perception of the stakeholders themselves. This is important not only in order to validate the analysis but also to bridge the theoretical gap between stakeholder analysis and stakeholder involvement. We also show that in disagreement with the assumption of most policy theories, local stakeholders consider informal decision pathways to be of great importance in actual policy-making.     

Ecological Feasibility Studies in Restoration Decision Making

The restoration of degraded systems is essential for maintaining the provision of valuable ecosystem services, including the maintenance of aesthetic values. However, restoration projects often fail to reach desired goals for a variety of ecologic, financial, and social reasons. Feasibility studies that evaluate whether a restoration effort should even be attempted can enhance restoration success by highlighting potential pitfalls and gaps in knowledge before the design phase of a restoration. Feasibility studies also can bring stakeholders together before a restoration project is designed to discuss potential disagreements. For these reasons, a feasibility study was conducted to evaluate the efficacy of restoring a tidal freshwater marsh in the Potomac River near Alexandria, Virginia. The study focused on science rather than engineering questions, and thus differed in approach from other feasibility studies that are mostly engineering driven. The authors report the framework they used to conduct a feasibility study to inform other potential restoration projects with similar goals. The seven steps of the framework encompass (1) initiation of a feasibility study, (2) compilation of existing data, (3) collection of current site information, (4) examination of case studies, (5) synthesis of information in a handbook, (6) meeting with selected stakeholders, and (7) evaluation of meeting outcomes. By conducting a feasibility study using the seven-step framework, the authors set the stage for conducting future compliance studies and enhancing the chance of a successful restoration.     

A novel system for environmental monitoring through a cooperative/synergistic scheme between bioindicators and biosensors

This paper addresses environmental monitoring through a robust dynamic integration between biomonitor and biosensor systems, a strategy that has not been attempted before. The two systems are conceptually interrelated and methodologically correlated to a cooperative/synergistic scheme (CSS) with a view to minimise uncertainty and monitoring costs and increase reliability of pollution control and abatement. The structures and operations of the biosensor component (in terms of sensitivity, device and method versatility, nature-mimicking physicochemical mechanisms, prospects and technological input) are such that they reinforce or promote the structures and operations of the natural component (in terms of bio-surveillance, impact assessment, environmental quality indexing, stress responses, metabolic pathways, etc.) and vice versa. The bioindicator ontology presented herein, including concepts, relations and controlled vocabulary aiming at establishing an integrated methodology for mapping/assessing negative environmental externalities, provides a useful tool for the design/development/implementation of an environmental network for the monitoring of a variety of pollutants over time and space and the assessment of environmental quality; the collection of the available information and its classification into taxonomic and partonomic relations allows the construction of a database that links pollutants with organisms' response, at a phenomenological and in-depth level, considering ecological parameters, relations and geomorphologic characteristics. As a result, a computer program has been designed/developed as a decision support system and has been successfully tested on a representative population of species indigenous to southern Greece. Significantly, a novel system in the form of a rational framework at the conceptual design level has been developed, that actually contributes towards achieving a cost-effective long-term monitoring program, with the flexibility to counter on-course any (anticipated or not) variations/modifications of the surveillance environment. This novel and pioneering approach will further offer a dynamic system utilised in (a) environmental impact studies and risk assessment (positive/analytic approach), (b) decision-making in the short-run (normative/tactic approach), and (c) policy-making in the long-run (normative/strategic approach). The proposed CSS, based on the integration of multiple data sources, can establish a local area network, incorporated into/expanding to a wide area network, thus offering the potential of better predictive ability and greater lead-time warning at alarm conditions than that provided by separate, stand-alone surveillance modalities.     

A multi-criteria evaluation of organic amendments used to transform an unproductive shrubland into a Mediterranean dehesa

Environmental and health problems associated with the use of digested sewage sludge hinder its application and encourage the introduction of additional treatments such as composting and thermal drying. The aim of this paper is to assess the possibility of using three different types of sewage sludge (digested, composted and thermally dried) to improve soil fertility and enhance the transformation of an unproductive shrub land into a Mediterranean dehesa for grazing purposes and also to reduce wildfire risk. In total, 10t ha(-1) of dry matter of three types of sewage sludge were spread on the soil surface of 4x5m field plots, and then seeded with a mixture of grasses. Effects on soil fertility and plant growth were monitored over 2 years. The results show that all three types of sludge application had a significant effect on vegetation cover, herbaceous biomass (2767.7+/-716.1 and 1735.0+/-299.7kgha(-1) for digested sludge amended and control plots, respectively) and tree growth (0.41+/-0.108cmyear(-1) on amended trees, 14.6% more than control trees). This study proposes the use of multi-criteria analysis to identify the most suitable fertilization alternatives and to assist in the decision-making process of sludge recycling. Because of the high degree of uncertainty and conflicting objectives associated with these decisions, multi-criteria evaluation tools make a valuable contribution to decision-making processes concerning sewage sludge applications. According to multi-criteria results, the composted sludge alternative is the most suitable. This is because all the objectives are achieved: an improvement in the properties and functions of the soil with a positive vegetation response as well as minimal economic cost and risk of toxicity.