Marko Debeljak

Habitat suitability modelling for red deer (Cervus elaphus L.) in South-central Slovenia with classification trees

We study and assess the potential habitats of a population of red deer in South-central Slovenia. Using existing data on the deer population spatial distribution and size, as well as data on the landscape and ecological properties (GIS) of the area inhabited by this population, we develop a habitat suitability model by automated data analysis using machine learning of classification trees. We assume that the recorded observations of deer approximate the actual spatial distribution of the deer population reasonably well. The habitat suitability models for individual animals have the form of classification trees. The induced trees are interpreted by domain experts and a generic model is proposed. The generic habitat suitability models can help determine potential unoccupied habitats for the red deer population and develop guidelines for managing the development of the red deer population and its influence on the environment.

Data mining and visualization for decision support and modeling of public health-care resources

This paper proposes an innovative use of data mining and visualization techniques for decision support in planning and regional-level management of Slovenian public health-care. Data mining and statistical techniques were used to analyze databases collected by a regional Public Heath Institute. We also studied organizational aspects of public health resources in the selected Celje region with the objective to identify the areas that are atypical in terms of availability and accessibility of public health services for the population. The most important step was the detection of outliers and the analysis of availability and accessibility deviations. The results are applicable to health-care planning and support in decision making by local and regional health-care authorities. In addition to the practical results, which are directly useful for decision making in planning of the regional health-care system, the main methodological contribution of the paper are the developed visualization methods that can be used to facilitate knowledge management and decision making processes.

Modeling the brown bear population in Slovenia: A tool in the conservation management of a threatened species

In this paper, we address three aspects of the brown bear population in Slovenia: its size (and its evolution over time), its spatial expansion out of the core area, and its potential habitat based on natural habitat suitability. Data collected through measurement/observation of the bear population and from the literature are used. A model is developed for each aspect. The results are estimates of population size, a picture of the spatial expansion of the population and maps of its optimal and maximal potential habitat (based on natural suitability). Overall, the brown bear population has been increasing since the establishment of a core protective area and has been expanding outside this area. The habitat suitability maps show that there is room for further expansion. Based on habitat suitability and bear population density, as well as human activity and current damage reports, we recommend that the Alps should be temporarily kept free of the bears, until the necessary mitigation measures regarding human–bear conflicts are carried out. On the other hand it is of crucial importance to adapt human activities and improve bear management in the optimal habitat, with which the goals of successful conservation of the species might be achieved.

Modelling the population dynamics of red deer (Cervus elaphus L.) with regard to forest development

Abstract Recent advances in artificial intelligence in general, and in machine learning in particular, enable scientists to apply new machine learning technics to their specific areas. In our work we apply such a machine learning technique to the modelling of population dynamics of red deer for the 40 000 hectares co-natural manage forest area on high Karst of Notranjska in Slovenia. We used the RETIS program, a machine learning tool developed by A. Karalie at the Institute Jožef Stefan in Ljubljana. This program induces regression trees from data, and has already been applied to several ecological problems. RETIS was applied on data, collected in the period 1976–1994, which included several meteorological parameters, parameters about the state of the forest, and parameters about the population of the red deer. Given these data about the observed system, the system RETIS automatically induces a model which has the form of a regression tree. We evaluate our induced models qualitatively and quantitatively. For the qualitative evaluation, we present an expert interpretation of the models. We show that quantitatively, using the models (we use a relative prediction error) and given the meteorological parameters during winter and summer and an estimate of the number of red deer in the area, it is possible to predict the state of the forest in the near future. This is very important for maintaining the balance between red deer population and other parameters of the forest, which will allow sustainable development of the complex forest ecosystem.

Decision Trees in Ecological Modelling

Decision tree learning is among the most popular machine learning techniques used for ecological modelling. Decision trees can be used to predict the value of one or several target (dependent) variables. They are hierarchical structures, where each internal node contains a test on an attribute, each branch corresponding to an outcome of the test, and each leaf node giving a prediction for the value of the class variable. Depending on whether we are dealing with a classification (discrete target) or a regression problem (continuous target), the decision tree is called a classification or a regression tree, respectively. The common way to induce decision trees is the so-called Top-Down Induction of Decision Tress (TDIDT). In this chapter, we introduce different types of decision trees, present basic algorithms to learn them, and give an overview of their applications in ecological modelling. The applications include modelling population dynamics and habitat suitability for different organisms (e.g. soil fauna, red deer, brown bears, bark beetles) in different ecosystems (e.g. aquatic, arable and forest ecosystems) exposed to different environmental pressures (e.g. agriculture, forestry, pollution, global warming).

Modeling water outflow from tile-drained agricultural fields.

The estimation of the pollution risk of surface and ground water with plant protection products applied on fields depends highly on the reliable prediction of the water outflows over (surface runoff) and through (discharge through sub-surface drainage systems) the soil. In previous studies, water movement through the soil has been simulated mainly using physically-based models. The most frequently used models for predicting soil water movement are MACRO, HYDRUS-1D/2D and Root Zone Water Quality Model. However, these models are difficult to apply to a small portion of land due to the information required about the soil and climate, which are difficult to obtain for each plot separately. In this paper, we focus on improving the performance and applicability of water outflow modeling by using a modeling approach based on machine learning techniques. It allows us to overcome the major drawbacks of physically-based models e.g., the complexity and difficulty of obtaining the information necessary for the calibration and the validation, by learning models from data collected from experimental fields that are representative for a wider area (region). We evaluate the proposed approach on data obtained from the La Jaillière experimental site, located in Western France. This experimental site represents one of the ten scenarios contained in the MACRO system. Our study focuses on two types of water outflows: discharge through sub-surface drainage systems and surface runoff. The results show that the proposed modeling approach successfully extracts knowledge from the collected data, avoiding the need to provide the information for calibration and validation of physically-based models. In addition, we compare the overall performance of the learned models with the performance of existing models MACRO and RZWQM. The comparison shows overall improvement in the prediction of discharge through sub-surface drainage systems, and partial improvement in the prediction of the surface runoff, in years with intensive rainfall.

Complex Adaptive Hierarchical Systems

Publisher Summary This chapter focuses on an emerging coherent theory of CAHSystems. They have both intrinsic and instrumental values. The orientation of First-World societies is pragmatic, which must be tempered by the awareness of the critical importance of a new-knowledge generation, which cannot be judged practically. Old knowledge can be applied with inevitable results when human adaptability becomes increasingly impoverished. The area of CAHSystems represents new ground in science as 21st Century begins to unfold. Pragmatically, a turn to CAHSystems is motivated by the needs to integrate and make sense of the information overload to grapple with complexly interwoven environmental, political, economic, social, and ethical issues that span huge scales of space and time. The development and focus of this theory is still in its infancy and must be nurtured, but the pressing need to discover and integrate complex systems knowledge argues for its continuing promotion and coordination. Few tools are available to grapple with systems, and one of these is interdisciplinary modeling, which represents a potentially powerful means for integrating observation, theory, and practice. Development of CAHSystems Theory and modeling are essential if humanity is realized as a balanced and sustainable condition within the frames of healthy, diverse, and viable ecosystems across the globe.

Using data mining to predict soil quality after application of biosolids in agriculture.

The amount of biosolids recycled in agriculture has steadily increased during the last decades. However, few models are available to predict the accompanying risks, mainly due to the presence of trace element and organic contaminants, and benefits for soil fertility of their application. This paper deals with using data mining to assess the benefits and risks of biosolids application in agriculture. The analyzed data come from a 10-yr field experiment in northeast France focusing on the effects of biosolid application and mineral fertilization on soil fertility and contamination. Biosolids were applied at agriculturally recommended rates. Biosolids had a significant effect on soil fertility, causing in particular a persistent increase in plant-available phosphorus (P) relative to plots receiving mineral fertilizer. However, soil fertility at seeding and crop management method had greater effects than biosolid application on soil fertility at harvest, especially soil nitrogen (N) content. Levels of trace elements and organic contaminants in soils remained below legal threshold values. Levels of extractable metals correlated more strongly than total metal levels with other factors. Levels of organic contaminants, particularly polycyclic aromatic hydrocarbons, were linked to total metal levels in biosolids and treated soil. This study confirmed that biosolid application at rates recommended for agriculture is a safe option for increasing soil fertility. However, the quality of the biosolids selected has to be taken into account. The results also indicate the power of data mining in examining links between parameters in complex data sets.

Interactions among the red deer (Cervus elaphus, L.) population, meteorological parameters and new growth of the natural regenerated forest in Snežnik, Slovenia

Abstract Following a preliminary study (Stankovski et al., Ecol. Modelling, 108, 1998), we use machine learning techniques to conduct a more detailed analysis of the interactions among the red deer population, meteorological parameters and new forest growth. We use the machine learning program M5 (Quinlan, Proc. 10th Int. Conf. Machine Learning, Morgan Kaufmann, San Mateo CA, 1993) that learns regression trees to automate the modelling of dynamic interactions. An area of 40 000 hectares of naturally regenerated forest on the high Dinaric Karst of Notranjska, Slovenia, is studied. The analysis uses data collected during the period 1976–1993, which include several meteorological parameters, the degrees of browsing intensity of new growth of woody plants (beech and maple), and parameters about the population of red deer. Models of the degree of beech browsing and calf weight were studied earlier; here, we automatically induce models of the red deer population size, the degree of beech and maple browsing, calf weight for 1- and 2-year-olds, and hind weight. The induced models are evaluated in terms of predictive accuracy and interpreted for their explanatory power. The models show that the meteorological parameters, the parameters of the red deer population and the rates of the browsing intensity of the new growth form a complex system with closely related parameters. While these interactions can be mainly explained by our current knowledge, we still gain some new knowledge from the automatically induced models. The results emphasise the importance of a pluralistic approach and a holistic perception of the system formed by meteorological conditions, the red deer population and the new growth in a forest ecosystem.

Data mining for decision support: an application in public health care

We propose a selection of knowledge technologies to support decisions of the management of public health care in Slovenia, and present a specific application in one region (Celje). First, we exploit data mining and statistical techniques to analyse databases that are regularly collected for the national Institute of Public Health. Next, we study organizational aspects of public health resources in the Celje region with the objective to identify the areas that are atypical in terms of availability and accessibility of the public health services for the population. The most important step is the detection of outliers and the analysis of the causes for availability and accessibility deviations. The results can be used for high-level health-care planning and decision-making.