PROJECT DETAILS
Innovative Moisture Measurement of Organic Litter Layers for Highly Granular Modeling of Regional Forest Fire Risks
Problem Statement
The forest fire risk of a wooded area is significantly influenced by the moisture content of the near-ground litter layer consisting of branches, sticks, and leaves. Conventional moisture measurement of litter layers is highly cost-intensive. As a result, moisture content of litter layers is only accounted for in forest fire risk modeling through estimations. However, this approach considerably reduces the reliability and spatial resolution of forest fire predictions.
Project Objective
The goal of the IFSW innovation project is to develop novel ultrasound and radar sensors, along with machine learning systems, capable of reliably and cost-effectively measuring the moisture content of litter layers within forests. By collecting scalable moisture data, stakeholders such as national meteorological services and other scientific institutions can model regional forest fire risks with significantly higher safety and spatial resolution.
Execution
Within the scope of the project, selected commercially available ultrasound and radar sensors will be taken up and further developed for project-specific purposes. These sensors are intended to operate entirely on solar energy, feature extremely energy-efficient machine learning systems, and communicate over long-range radio. The training of machine learning systems will be conducted using data from extensive controlled smoldering tests.