The research group explores the intersection of remote sensing and machine learning to develop data-driven methods that address critical environmental and societal challenges. We focus on advancing deep learning and computer vision techniques, particularly for applications in geophysical and satellite-based remote sensing.
Our work is motivated by the need for scalable, autonomous, and computationally efficient solutions for workflows that are traditionally labor-intensive and require domain-specific expertise. By bridging domain knowledge with modern machine learning methods, we aim to improve the efficiency, accuracy, and usability of tools that support climate resilience and sustainable resource management.
Our current activities span multiple interdisciplinary projects—ranging from groundwater management in Ethiopia using remote sensing and nature-based solutions, to soil moisture monitoring for sustainable agriculture, to automating airborne and ground-based transient electromagnetic data processing. These efforts are supported by national and international research grants and involve collaborations with academic and industrial partners.
