Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article we review explainable machine learning in view of applications in the natural sciences and discuss three core elements which we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas.
1 June 2020 in ISPRS Journal of Photogrammetry and Remote Sensing
In past years, we have witnessed the fields of geosciences and remote sensing and artificial intelligence (AI) become closer. Thanks to the massive availability of observational data, improved simulations, and algorithmic advances, these disciplines have found common objectives and challenges to help advance the modeling and understanding of the Earth system. Despite such great opportunities, we have also observed a worrisome tendency to remain in disciplinary comfort zones, applying recent advances from AI on well-resolved remote sensing problems. Here, we take a position on the research directions for which we think the interface between these fields will have the most significant impact and become potential game changers. In our declared agenda for AI in Earth sciences, we aim to inspire researchers, especially the younger generations, to tackle these challenges for a real advance of remote sensing and the geosciences.
1 January 2014 in Computers and Electronics in Agriculture
Global climate change plays an essential role in our daily life. Mesoscale ocean eddies have a significant impact on global warming, since they affect the ocean dynamics, the energy as well as the mass transports of ocean circulation. From satellite altimetry we can derive high-resolution, global maps containing ocean signals with dominating coherent eddy structures. The aim of this study is the development and evaluation of a deep-learning based approach for the analysis of eddies. In detail, we develop an eddy identification and tracking framework with two different approaches that are mainly based on feature learning with convolutional neural networks. Furthermore, state-of-the-art image processing tools and object tracking methods are used to support the eddy tracking. In contrast to previous methods, our framework is able to learn a representation of the data in which eddies can be detected and tracked in more objective and robust way. We show the detection and tracking results on sea level anomalies (SLA) data from the area of Australia and the East Australia current, and compare our two eddy detection and tracking approaches to identify the most robust and objective method.
In this paper, we present GrowliFlower, a georeferenced, image‐based unmanned aerial vehicle time‐series dataset of two monitored cauliflower fields (0.39 and 0.60 ha) acquired in 2 years, 2020 and 2021. The proposed dataset contains RGB and multispectral orthophotos with coordinates of approximately 14,000 individual cauliflower plants. The coordinates enable the extraction of complete and incomplete time‐series of image patches showing individual plants. The dataset contains the collected phenotypic traits of 740 plants, including the developmental stage and plant and cauliflower size. The harvestable product is completely covered by leaves, thus, plant IDs and coordinates are provided to extract image pairs of plants pre‐ and post‐defoliation. In addition, to facilitate classification, detection, segmentation, instance segmentation, and other similar computer vision tasks, the proposed dataset contains pixel‐accurate leaf and plant instance segmentations, as well as stem annotations. The proposed dataset was created to facilitate the development and evaluation of various machine‐learning approaches. It focuses on the analysis of growth and development of cauliflower and the derivation of phenotypic traits to advance automation in agriculture. Two baseline results of instance segmentation tasks at the plant and leaf level based on labeled instance segmentation data are presented. The complete GrowliFlower dataset is publicly available (http://rs.ipb.uni-bonn.de/data/growliflower/).