Research

This project involves the development of advanced machine learning (ML) frameworks based on transfer learning that integrate multi-sensor remote sensing data. These frameworks support detailed land cover mapping and the assessment of agricultural plant health. The approach leverages pre-trained ML models and adapts them systematically across different agro-ecological regions, management systems and sensor configurations. Specific consideration is given to high-spatial-and-temporal-resolution data from the Sentinel-2 and Planet constellations. The project aims to improve the robustness and generalisation capacity of ML models under varying environmental conditions by combining complementary spectral, spatial and temporal information. There is a particular focus on transferability across sites and seasons to reduce the need for extensive local training data while maintaining high classification and diagnostic accuracy. The resulting frameworks are designed to be scalable and operational, enabling the consistent monitoring of vegetation status, crop conditions and land cover dynamics. They will support decision-making in precision agriculture, ecosystem monitoring and sustainable land management.

Analysis of the development of groundwater recharge and available groundwater resources in the reference period 3rd to 4th NGP (National Water Management Plan) for near-surface groundwater bodies: Review and, if necessary, update of groundwater recharge and groundwater resources based on the BML study “Austria's Water Resources.” This is done by comparing relevant data from the time series 1998–2017 and 2004–2023. The findings obtained in the course of the analysis are to be incorporated into the draft for the 4th NGP. Furthermore, scenarios for groundwater recharge and available groundwater resources are being developed as part of adaptation strategies to climate change for Austrian water management. Translated with DeepL.com (free version)

IGNOS aims to evaluate the potential and limitations of GNSS-R as a scalable, all-weather complementary solution for Leaf Area Index (LAI) estimation. It is particularly important because of the urgent need for consistent observations in tropical areas where Copernicus Sentinel-2 optical satellites encounter significant challenges. By analyzing the relationship between GNSS-R data with Sentinel-2 imagery, IGNOS assesses the potential of the GNSS-R technique to become a complementary technique to Sentinel-2, enhancing vegetation monitoring in cloud-prone regions without additional sensor deployment, thus offering a cost-effective and environmentally friendly strategy. The outcome of this project therefore should evaluate the capabilities for a continuous LAI observation under cloudy conditions, leading to better-informed decisions in sustainable forestry, agriculture, and ecosystem management. The improved LAI data will primarily benefit Earth Observation users (e.g., remote sensing experts working in ecosystem yodelling) and agricultural communities (e.g., farmers and land managers) by enabling precision agriculture and biodiversity monitoring.