Recognizing protected and anthropogenic patterns in landscapes using interpretable machine learning and satellite imagery

TT Stomberg, J Leonhardt, I Weber… - Frontiers in Artificial …, 2023 - frontiersin.org
The accurate and comprehensive mapping of land cover has become a central task in
modern environmental research, with increasing emphasis on machine learning …

Leveraging activation maximization and generative adversarial training to recognize and explain patterns in natural areas in satellite imagery

A Emam, TT Stomberg… - IEEE Geoscience and …, 2023 - ieeexplore.ieee.org
Natural protected areas are vital for biodiversity, climate change mitigation, and supporting
ecological processes. Despite their significance, comprehensive mapping is hindered by a …

MapInWild: A remote sensing dataset to address the question of what makes nature wild [Software and Data Sets]

B Ekim, TT Stomberg, R Roscher… - IEEE Geoscience and …, 2023 - ieeexplore.ieee.org
The advancement in deep learning (DL) techniques has led to a notable increase in the
number and size of annotated datasets in a variety of domains, with remote sensing (RS) …

Confident Naturalness Explanation (CNE): A Framework to Explain and Assess Patterns Forming Naturalness

A Emam, M Farag, R Roscher - IEEE Geoscience and Remote …, 2024 - ieeexplore.ieee.org
Protected natural areas characterized by minimal modern human footprint are often
challenging to assess. Machine-learning (ML) models, particularly explainable methods …

MapInWild: A Remote Sensing Dataset to Address the Question What Makes Nature Wild

B Ekim, TT Stomberg, R Roscher, M Schmitt - arXiv preprint arXiv …, 2022 - arxiv.org
Antrophonegic pressure (ie human influence) on the environment is one of the largest
causes of the loss of biological diversity. Wilderness areas, in contrast, are home to …

A regression-based Convolutional Neural Network for yield estimation of soybean

A Venugopal - 2023 - essay.utwente.nl
Crop yield estimation is essential for decision-making and ensuring food security. This MSc
thesis explores the explainability of a regression-based Convolutional Neural Network …

Transformer-Based Reliable Explainability (T-ReX): A Framework to Reliably Interpret Naturalness using Foundation Models

A Emam, M Farag, M Rußwurm, R Roscher - researchgate.net
T-ReX Poster Page 1 Transformer-Based Reliable Explainability (T-ReX): A Framework to
Reliably Interpret Naturalness using Foundation Models Motivation Method We propose the …