Logo des Repositoriums

Auflistung nach Autor:in "Hasenauer, Hubert"

1 - 3 von 3
  • Konferenzbeitrag
    Concepts Within Forest Ecosystem Modelling and Their Application
    (The Information Society and Enlargement of the European Union, 2003) Hasenauer, Hubert
    Three major modeling concepts have been evolved and successfully applied within forest ecosystem modeling: (1) Management models, (2) Succession models and (3) Biogeochemical-mechanistic models (BGC-Models). In this paper the different concepts including the main components, their advantages and disadvantages in assessing specific enduser needs are discussed as well as typical application examples are presented.
  • Konferenzbeitrag
    Conceptual Framework of a Data Warehouse for the Nationalpark Hohe Tauern
    (Umweltinformatik ’99 - Umweltinformatik zwischen Theorie und Industrieanwendung, 1999) Hasenauer, Hubert; Haslik, Ingrid; Rosenthaler, Roman; Pernul, Günther; Stangl, Dietmar
    Die Arbeit stellt ein Data Warehouse Konzepte für die Datenorganisation in einem Nationalpark vor. Die darauf aufbauende Implementierung eines Prototypen mit Hilfe des Universal Server 9.12 von INFORMIX zeigt die Anbindung an das Internet und diskutiert die daraus entstehenden Vorteile.
  • Konferenzbeitrag
    Mortalitätsschätzungen in ungleichaltrigen Fichtenwäldern mit Hilfe Neuronaler Netze
    (Umweltinformatik ’99 - Umweltinformatik zwischen Theorie und Industrieanwendung, 1999) Hasenauer, Hubert; Merkl, Dieter
    Within forest growth modeling it is understood that individual tree mortality can be captured realistically by relating the average rate of mortality to a few reliable and measurable size or site characteristics using a LOGIT model. In this paper we describe the application of neuronal networks adhering to the unsupervised learning paradigm to predict individual tree mortality. Using the large and representative Norway spruce data sample from the Austrian National Forest Inventory, we train different types of neural network architectures, namely Multi-Layer Perceptron, Cascade Correlation, and Learning Vector Quantization. For training, we use the following learning rules: Error Backpropagation, Resilient Propagation, and Scaled Conjugate Gradient. With an independent data set we evaluate the neural network types to predict individual tree mortality.