Research

The progress of statistical machine learning methods has made AI increasingly successful. Deep learning exceeds human performance even in the medical domain. However, their full potential is limited by their difficulty to generate underlying explanatory structures, hence they lack an explicit declarative knowledge representation. A motivation for this project are rising legal and privacy issues – to understand and retrace machine decision processes. Transparent algorithms could appropriately enhance trust of medical professionals, thereby raising acceptance AI solutions generally. This project will provide important contributions to the international research community in the following ways: 1) evidence in various methods of explainability, patterns of explainability, and explainability measurements. Based on empirical studies (“How do humans explain ?”) we will develop a library of explanatory patterns and a novel grammar how these can be combined. Finally, we will define criteria/benchmarks for explainability and provide answers to the question “What is a good explanation?”. 2) Principles to measure effectiveness of explainability and explainability guidelines and 3) Mapping human understanding with machine explanations and deploying an open explanatory framework along with a set of benchmarks and open data to stimulate and inspire further research among the international AI/machine learning community. All outcomes of this project will be made openly available to the international research community.

The aim of this project is to develop a new water drainage system for forest roads based on the principle of retention. Instead of the densest possible surface layers, forest roads are to be constructed with infiltration-capable superstructures, which allows the water to infiltrate the adjoining forest in a delayed and damage-free manner by means of retention and storage. It is intended to reduce the concentrated run off from pipe culverts to such an extent that, if possible, the pipe culverts will no longer be the starting point for debris flows and pluvial floods in the settlement area in the future. Reduced water runoff on the surface of forest roads is also expected to decrease the erosion and reduce damage due to heavy rains. This, in addition to a reduction in required maintenance measures, will also ensure an extension in the life of the forest roads.

Due to climate change with its extreme weather conditions, the roundwood supply chain is increasingly exposed to damage events. Accompanying sales problems in the domestic and international forestry industry affect the management of these additional, unscheduled roundwood volumes. Already harvested timber must then be temporarily stored on site or/and treated to prevent or control bark beetle infestation. However, interim storage away from the customer requires appropriate precautions to ensure timber quality during storage, which can be degraded by insect infestation, fungal infection, and abiotic factors. Debarking is an effective and long-established measure against bark beetle infestation. In steep terrain, the respective assortments could be debarked at the forest roadside during the harvesting operation. Debarked assortments have the advantage that, from a phytosanitary point of view, the propagation of bark beetles in the forest can be prevented. At the same time, debarking in the larval and pupal stages has a decimating effect on the population density of the insects and thus has a controlling effect. With regard to the quality of the stored assortments, debarking also counteracts the possibility of breeding and development of longhorn beetles and thus prevents a technical reduction in quality. In addition, the possibility of blue stain fungi and other bark- and wood-breeding insects being introduced is reduced in debarked saw logs. Therefore, the aim of this research project is to build on the previous project "DEBARK" and to analyze and evaluate the potential of debarking also in steep terrain timber harvesting. The focus will be on the effects of debarking on timber harvesting, the propagation potential of bark beetles and longhorn beetles, and the blue stain of the assortments. As a result, the knowledge gained will be prepared for the responsible decision-makers in day-to-day business.