Information about clouds is important for observing and predicting weather and climate as well as for generating and distributing solar power. Most existing approaches extract cloud information from satellite data by classifying individual pixels instead of using closely integrated spatial information, ignoring the fact that clouds are highly dynamic, spatially continuous entities. This paper proposes a novel cloud classification method based on deep learning. Relying on a Convolutional Neural Network (CNN) architecture for image segmentation, the presented Cloud Segmentation CNN (CS-CNN), classifies all pixels of a scene simultaneously rather than individually. We show that CS-CNN can successfully process multispectral satellite data to classify continuous phenomena such as highly dynamic clouds. The proposed approach produces excellent results on Meteosat Second Generation (MSG) satellite data in terms of quality, robustness, and runtime compared to other machine learning methods such as random forests. In particular, comparing CS-CNN with the CLAAS-2 cloud mask derived from MSG data shows high accuracy (0.94) and Heidke Skill Score (0.90) values. In contrast to a random forest, CS-CNN produces robust results and is insensitive to challenges created by coast lines and bright (sand) surface areas. Using GPU acceleration, CS-CNN requires only 25 ms of computation time for classification of images of Europe with $508\times 508$ pixels.

Ecosystem functions and services are severely threatened by unprecedented global loss in biodiversity. To counteract these trends, it is essential to develop systems to monitor changes in biodiversity for planning, evaluating, and implementing conservation and mitigation actions. However, the implementation of monitoring systems suffers from a trade‐off between grain (i.e., the level of detail), extent (i.e., the number of study sites), and temporal repetition. Here, we present an applied and realized networked sensor system for integrated biodiversity monitoring in the Nature 4.0 project as a solution to these challenges, which considers plants and animals not only as targets of investigation, but also as parts of the modular sensor network by carrying sensors. Our networked sensor system consists of three main closely interlinked components with a modular structure: sensors, data transmission, and data storage, which are integrated into pipelines for automated biodiversity monitoring. We present our own real‐world examples of applications, share our experiences in operating them, and provide our collected open data. Our flexible, low‐cost, and open‐source solutions can be applied for monitoring individual and multiple terrestrial plants and animals as well as their interactions. Ultimately, our system can also be applied to area‐wide ecosystem mapping tasks, thereby providing an exemplary cost‐efficient and powerful solution for biodiversity monitoring. Building upon our experiences in the Nature 4.0 project, we identified ten key challenges that need to be addressed to better understand and counteract the ongoing loss of biodiversity using networked sensor systems. To tackle these challenges, interdisciplinary collaboration, additional research, and practical solutions are necessary to enhance the capability and applicability of networked sensor systems for researchers and practitioners, ultimately further helping to ensure the sustainable management of ecosystems and the provision of ecosystem services.

Detection and segmentation of macrophage cells in fluorescence microscopy images is a challenging problem, mainly due to crowded cells, variation in shapes, and morphological complexity. We present a new deep learning approach for cell detection and segmentation that incorporates previously learned nucleus features. A novel fusion of feature pyramids for nucleus detection and segmentation with feature pyramids for cell detection and segmentation is used to improve performance on a microscopic image dataset created by us and provided for public use, containing both nucleus and cell signals. Our experimental results indicate that cell detection and segmentation performance significantly benefit from the fusion of previously learned nucleus features. The proposed feature pyramid fusion architecture clearly outperforms a state-of-the-art Mask R-CNN approach for cell detection and segmentation with relative mean average precision improvements of up to 23.88% and 23.17%, respectively. To analyze cell infection and changes in cell morphology in fluorescence microscopy images, proper cell detection and segmentation are required. In automated fluorescence microscopy image analysis, the separation of signals in close proximity is a challenging problem. High cell densities or cluster formations increase the probability of such situations on the cellular level. Another limitation is the detection of morphologically complex cells, such as macrophages or neurons. Their indefinite morphology causes identification issues when looking for slight variations of fixed shapes. Compared to merely segmenting cytoplasm, instance-based segmentation is a much harder task, since the assignment of a cell instance identity to every pixel of the image is required. We present a new deep learning approach for cell detection and segmentation that efficiently utilizes the nucleus channel for improving segmentation and detection performance of cells by incorporating previously learned nucleus features. This is achieved by a fusion of feature pyramids for nucleus detection and segmentation. The performance is evaluated on a microscopic image dataset, containing both nucleus and cell signals.