Search

Crop phenology determines crop growth stages and is valuable information for decision makers to plant and adapt agricultural management strategies to enhance food security. In the era of big Earth observation data ubiquity, attempts have been made to accurately predict crop phenology based on Remote Sensing (RS) data. However, most studies either focused on large scale interpretations of phenology or developed methods which are not adequate to help crop modeler communities on leveraging the value of RS data evaluated using more accurate and confident methods. Here, we estimate phenological developments for eight major crops and 13 phenological stages across Germany at 30m scale using a novel framework which fuses Landsat and Sentinel 2 (Harmonized Landsat and Sentinel data base; HLS) and radar of Sentinel 1 with a Machine Learning (ML) model. We proposed a thorough feature fusion analysis to find the best combinations of RS data on detecting phenological developments based on the national phenology network of Germany (German Meteorological Service; DWD) between 2017 and 2021. The nation-wide predicted crop phenology at 30 m resolution showed a very high precision of R2 > 0.9 and a very low Mean Absolute Error (MAE) < 2 (days). These results indicate that our fusing strategy of optical and radar datasets is highly performant with an accuracy highly relevant for practical applications, too. The subsequent uncertainty analysis indicated that fusing optical and radar data increases the reliability of the RS predicted crop growth stages. These improvements are expected to be useful for crop model calibrations and evaluations, facilitate informed agricultural decisions, and contribute to sustainable food production to address the increasing global food demand.

Modeling dynamical systems, e.g. in climate and engineering sciences, often necessitates solving partial differential equations. Neural operators are deep neural networks designed to learn nontrivial solution operators of such differential equations from data. As for all statistical models, the predictions of these models are imperfect and exhibit errors. Such errors are particularly difficult to spot in the complex nonlinear behaviour of dynamical systems. We introduce a new framework for approximate Bayesian uncertainty quantification in neural operators using function-valued Gaussian processes. Our approach can be interpreted as a probabilistic analogue of the concept of currying from functional programming and provides a practical yet theoretically sound way to apply the linearized Laplace approximation to neural operators. In a case study on Fourier neural operators, we show that, even for a discretized input, our method yields a Gaussian closure--a structured Gaussian process posterior capturing the uncertainty in the output function of the neural operator, which can be evaluated at an arbitrary set of points. The method adds minimal prediction overhead, can be applied post-hoc without retraining the neural operator, and scales to large models and datasets. We showcase the efficacy of our approach through applications to different types of partial differential equations.

The complexity of black-box algorithms can lead to various challenges, including the introduction of biases. These biases present immediate risks in the algorithms' application. It was, for instance, shown that neural networks can deduce racial information solely from a patient's X-ray scan, a task beyond the capability of medical experts. If this fact is not known to the medical expert, automatic decision-making based on this algorithm could lead to prescribing a treatment (purely) based on racial information. While current methodologies allow for the "orthogonalization" or "normalization" of neural networks with respect to such information, existing approaches are grounded in linear models. Our paper advances the discourse by introducing corrections for non-linearities such as ReLU activations. Our approach also encompasses scalar and tensor-valued predictions, facilitating its integration into neural network architectures. Through extensive experiments, we validate our method's effectiveness in safeguarding sensitive data in generalized linear models, normalizing convolutional neural networks for metadata, and rectifying pre-existing embeddings for undesired attributes.

Here we report on an elastic and inelastic neutron scattering study addressing the effect of electric fields on quantum paraelectric SrTiO3. Our elastic scattering results find small changes as a function of field in a superlattice reflection that sample the octahedral rotations, which is indicative of only weak coupling of octahedral rotation and electric polarization. By collecting not only the change in gap, but also of the dispersion, we can better quantify the changes in the lattice dynamics. The findings are put in context to recent field DFT calculations predicting the E-field effect on the atomic motions of the lowest lying transverse optical (soft) mode. We find hints of non-linear coupling to the acoustic mode and to the phonon with polarization perpendicular to the E-field, which shows the non-linearity in the chemical potential that is also relevant when strongly driving SrTiO3 with E-field (THz) pulses.

We address the computational barrier of deploying advanced deep learning segmentation models in clinical settings by studying the efficacy of network compression through tensor decomposition. We propose a post-training Tucker factorization that enables the decomposition of pre-existing models to reduce computational requirements without impeding segmentation accuracy. We applied Tucker decomposition to the convolutional kernels of the TotalSegmentator (TS) model, an nnU-Net model trained on a comprehensive dataset for automatic segmentation of 117 anatomical structures. Our approach reduced the floating-point operations (FLOPs) and memory required during inference, offering an adjustable trade-off between computational efficiency and segmentation quality. This study utilized the publicly available TS dataset, employing various downsampling factors to explore the relationship between model size, inference speed, and segmentation performance. The application of Tucker decomposition to the TS model substantially reduced the model parameters and FLOPs across various compression rates, with limited loss in segmentation accuracy. We removed up to 88% of the model's parameters with no significant performance changes in the majority of classes after fine-tuning. Practical benefits varied across different graphics processing unit (GPU) architectures, with more distinct speed-ups on less powerful hardware. Post-hoc network compression via Tucker decomposition presents a viable strategy for reducing the computational demand of medical image segmentation models without substantially sacrificing accuracy. This approach enables the broader adoption of advanced deep learning technologies in clinical practice, offering a way to navigate the constraints of hardware capabilities.

Purpose: To analyze and remove protected feature effects in chest radiograph embeddings of deep learning models. Methods: An orthogonalization is utilized to remove the influence of protected features (e.g., age, sex, race) in CXR embeddings, ensuring feature-independent results. To validate the efficacy of the approach, we retrospectively study the MIMIC and CheXpert datasets using three pre-trained models, namely a supervised contrastive, a self-supervised contrastive, and a baseline classifier model. Our statistical analysis involves comparing the original versus the orthogonalized embeddings by estimating protected feature influences and evaluating the ability to predict race, age, or sex using the two types of embeddings. Results: Our experiments reveal a significant influence of protected features on predictions of pathologies. Applying orthogonalization removes these feature effects. Apart from removing any influence on pathology classification, while maintaining competitive predictive performance, orthogonalized embeddings further make it infeasible to directly predict protected attributes and mitigate subgroup disparities. Conclusion: The presented work demonstrates the successful application and evaluation of the orthogonalization technique in the domain of chest X-ray image classification.

Anomaly detection in imbalanced datasets is a frequent and crucial problem, especially in the medical domain where retrieving and labeling irregularities is often expensive. By combining the generative stability of a $\beta$-variational autoencoder (VAE) with the discriminative strengths of generative adversarial networks (GANs), we propose a novel model, $\beta$-VAEGAN. We investigate methods for composing anomaly scores based on the discriminative and reconstructive capabilities of our model. Existing work focuses on linear combinations of these components to determine if data is anomalous. We advance existing work by training a kernelized support vector machine (SVM) on the respective error components to also consider nonlinear relationships. This improves anomaly detection performance, while allowing faster optimization. Lastly, we use the deviations from the Gaussian prior of $\beta$-VAEGAN to form a novel anomaly score component. In comparison to state-of-the-art work, we improve the $F_1$ score during anomaly detection from 0.85 to 0.92 on the widely used MITBIH Arrhythmia Database., Comment: accepted at AI4TS @ ICDMW 2023

Undersampling is a common method in Magnetic Resonance Imaging (MRI) to subsample the number of data points in k-space, reducing acquisition times at the cost of decreased image quality. A popular approach is to employ undersampling patterns following various strategies, e.g., variable density sampling or radial trajectories. In this work, we propose a method that directly learns the undersampling masks from data points, thereby also providing task- and domain-specific patterns. To solve the resulting discrete optimization problem, we propose a general optimization routine called ProM: A fully probabilistic, differentiable, versatile, and model-free framework for mask optimization that enforces acceleration factors through a convex constraint. Analyzing knee, brain, and cardiac MRI datasets with our method, we discover that different anatomic regions reveal distinct optimal undersampling masks, demonstrating the benefits of using custom masks, tailored for a downstream task. For example, ProM can create undersampling masks that maximize performance in downstream tasks like segmentation with networks trained on fully-sampled MRIs. Even with extreme acceleration factors, ProM yields reasonable performance while being more versatile than existing methods, paving the way for data-driven all-purpose mask generation., Comment: accepted at WACV 2024

Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence systems can take over this task but usually need a large number of already-labeled training images to achieve sufficient performance. This requirement necessitates human expert labor and poses a particular challenge for projects with few cameras or short durations. We propose a label-efficient learning strategy that enables researchers with small or medium-sized image databases to leverage the potential of modern machine learning, thus freeing crucial resources for subsequent analyses. Our methodological proposal is two-fold: (1) We improve current strategies of combining object detection and image classification by tuning the hyperparameters of both models. (2) We provide an active learning (AL) system that allows training deep learning models very efficiently in terms of required human-labeled training images. We supply a software package that enables researchers to use these methods directly and thereby ensure the broad applicability of the proposed framework in ecological practice. We show that our tuning strategy improves predictive performance. We demonstrate how the AL pipeline reduces the amount of pre-labeled data needed to achieve a specific predictive performance and that it is especially valuable for improving out-of-sample predictive performance. We conclude that the combination of tuning and AL increases predictive performance substantially. Furthermore, we argue that our work can broadly impact the community through the ready-to-use software package provided. Finally, the publication of our models tailored to European wildlife data enriches existing model bases mostly trained on data from Africa and North America.

We present the free and open source software TAS-Paths, a novel system which calculates optimal, collision-free paths for the movement of triple-axis spectrometers. The software features an easy to use graphical user interface, but can also be scripted and used as a library. It allows the user to plan and visualise the motion of the instrument before the experiment and can be used during measurements to circumvent obstacles. The instrument path is calculated in angular configuration space in order to keep a maximum angular distance from any obstacle., Comment: 6 pages, 4 figures

While recent advances in large-scale foundational models show promising results, their application to the medical domain has not yet been explored in detail. In this paper, we progress into the realms of large-scale modeling in medical synthesis by proposing Cheff - a foundational cascaded latent diffusion model, which generates highly-realistic chest radiographs providing state-of-the-art quality on a 1-megapixel scale. We further propose MaCheX, which is a unified interface for public chest datasets and forms the largest open collection of chest X-rays up to date. With Cheff conditioned on radiological reports, we further guide the synthesis process over text prompts and unveil the research area of report-to-chest-X-ray generation., Comment: accepted at PAKDD 2023

The release of ChatGPT, a language model capable of generating text that appears human-like and authentic, has gained significant attention beyond the research community. We expect that the convincing performance of ChatGPT incentivizes users to apply it to a variety of downstream tasks, including prompting the model to simplify their own medical reports. To investigate this phenomenon, we conducted an exploratory case study. In a questionnaire, we asked 15 radiologists to assess the quality of radiology reports simplified by ChatGPT. Most radiologists agreed that the simplified reports were factually correct, complete, and not potentially harmful to the patient. Nevertheless, instances of incorrect statements, missed key medical findings, and potentially harmful passages were reported. While further studies are needed, the initial insights of this study indicate a great potential in using large language models like ChatGPT to improve patient-centered care in radiology and other medical domains.

The application of deep learning in survival analysis (SA) allows utilizing unstructured and high-dimensional data types uncommon in traditional survival methods. This allows to advance methods in fields such as digital health, predictive maintenance, and churn analysis, but often yields less interpretable and intuitively understandable models due to the black-box character of deep learning-based approaches. We close this gap by proposing 1) a multi-task variational autoencoder (VAE) with survival objective, yielding survival-oriented embeddings, and 2) a novel method HazardWalk that allows to model hazard factors in the original data space. HazardWalk transforms the latent distribution of our autoencoder into areas of maximized/minimized hazard and then uses the decoder to project changes to the original domain. Our procedure is evaluated on a simulated dataset as well as on a dataset of CT imaging data of patients with liver metastases., Comment: NeurIPS 2021 Workshop, Deep Generative Models and Downstream Applications

Deep learning excels in the analysis of unstructured data and recent advancements allow to extend these techniques to survival analysis. In the context of clinical radiology, this enables, e.g., to relate unstructured volumetric images to a risk score or a prognosis of life expectancy and support clinical decision making. Medical applications are, however, associated with high criticality and consequently, neither medical personnel nor patients do usually accept black box models as reason or basis for decisions. Apart from averseness to new technologies, this is due to missing interpretability, transparency and accountability of many machine learning methods. We propose a hazard-regularized variational autoencoder that supports straightforward interpretation of deep neural architectures in the context of survival analysis, a field highly relevant in healthcare. We apply the proposed approach to abdominal CT scans of patients with liver tumors and their corresponding survival times., Comment: NeurIPS 2021 Workshop, Bridging the Gap: From Machine Learning Research to Clinical Practice

Polarised neutron scattering is the method of choice to study magnetism in condensed matter. Polarised neutrons are typically very low in flux, and complex experimental configurations further reduce the count rate. Neutron polarisation corrections would therefore be needed. Here we analytically derive formulae of the corrected partial differential scattering cross-sections. The analytical method is designed for the longitudinal polarisation analysis, and the correction generally holds for time-independent polarised neutrons with a triple-axis spectrometer. We then apply the correction to recent results of our $P_x$ experiment on Y$_3$Fe$_5$O$_{12}$. Although there is a difficulty with the experimental determination of inefficiency parameters of neutron spin polarisers and flippers, the correction appears to work properly., Comment: 8 pages, 2 figures

Automated classification of metadata of research data by their discipline(s) of research can be used in scientometric research, by repository service providers, and in the context of research data aggregation services. Openly available metadata of the DataCite index for research data were used to compile a large training and evaluation set comprised of 609,524 records, which is published alongside this paper. These data allow to reproducibly assess classification approaches, such as tree-based models and neural networks. According to our experiments with 20 base classes (multi-label classification), multi-layer perceptron models perform best with a f1-macro score of 0.760 closely followed by Long Short-Term Memory models (f1-macro score of 0.755). A possible application of the trained classification models is the quantitative analysis of trends towards interdisciplinarity of digital scholarly output or the characterization of growth patterns of research data, stratified by discipline of research. Both applications perform at scale with the proposed models which are available for re-use.

We use inelastic neutron scattering to show that long-range spin waves arising from the static bicollinear antiferromagnetic (AF) order in FeTe, which have twofold rotational symmetry in a fully detwinned crystal, rapidly dissolve above $E\approx 26$ meV into ridges of scattering with fourfold rotational symmetry and a nearly isotropic magnetic fluctuation spectrum. With increasing temperature above $T_N\approx 68$ K, the twofold spin waves change into broad regions of scattering with fourfold symmetry. Since the scattering patterns from plaquette magnetic order generated within a bilinear biquadratic Hamiltonian have fourfold rotational symmetry consistent with the high-energy, spin-isotropic spin waves of FeTe, we conclude that the bicollinear AF state in FeTe is quasidegenerate with plaquette magnetic order, providing evidence for the strongly frustrated nature of the local moments in iron chalcogenide family of iron-based superconductors., Comment: 12 pages, 11 figures

We report spin-polarized inelastic neutron scattering of the dynamical structure factor of the conical magnetic helix in the cubic chiral magnet MnSi. We find that the spectral weight of spin-flip scattering processes is concentrated on single branches for wavevector transfer parallel to the helix axis as inferred from well-defined peaks in the neutron spectra. In contrast, for wavevector transfers perpendicular to the helix the spectral weight is distributed among different branches of the magnon band structure as reflected in broader features of the spectra. Taking into account the effects of instrumental resolution, our experimental results are in excellent quantitative agreement with parameter-free theoretical predictions. Whereas the dispersion of the spin waves in MnSi appears to be approximately reciprocal at low energies and small applied fields, the associated spin-resolved spectral weight displays a pronounced non-reciprocity that implies a distinct non-reciprocal response in the limit of vanishing uniform magnetization at zero magnetic field., Comment: 6 pages, 5 figures. Added journal reference to published version

Lifecycle models for research data are often abstract and simple. This comes at the danger of oversimplifying the complex concepts of research data management. The analysis of 90 different lifecycle models lead to two approaches to assess the quality of these models. While terminological issues make direct comparisons of models hard, an empirical evaluation seems possible.

A large number of services for research data management strive to adhere to the FAIR guiding principles for scientific data management and stewardship. To evaluate these services and to indicate possible improvements, use-case-centric metrics are needed as an addendum to existing metric frameworks. The retrieval of spatially and temporally annotated images can exemplify such a use case. The prototypical implementation indicates that currently no research data repository achieves the full score. Suggestions on how to increase the score include automatic annotation based on the metadata inside the image file and support for content negotiation to retrieve the images. These and other insights can lead to an improvement of data integration workflows, resulting in a better and more FAIR approach to manage research data., Comment: This is a preprint for a paper accepted for the 2018 IEEE conference

Using two cold-neutron triple-axis spectrometers we have succeeded in fully mapping out the field-dependent evolution of the non-reciprocal magnon dispersion relations in all magnetic phases of MnSi. The non-reciprocal nature of the dispersion manifests itself in a full asymmetry (non-reciprocity) of the dynamical structure factor $S(q, E, \mu_0 H_{int})$ with respect to flipping either the direction of the applied magnetic field $\mu_0 H_{int}$, the reduced momentum transfer $q$, or the energy transfer $E$., Comment: Contribution to the International Conference on Magnetism 2018. 5 pages, 4 figures