Data Science Symposium No. 7 programme

<p> Current and future data-driven scientific applications from explorative methods to operational systems require suitable data strategies. The necessary requirements for this are presented in the context of earth system science and their embedding in POF 4 and NFDI. In particular, exemplary examples are presented which stand for consistent data management as a data strategy from data collection to the data product including the data processing steps. </p>

<p> Those who operate autonomous vehicles under or above water want to know where they are, if they are doing well and if they are doing what they supposed to do. Sometimes it makes sense to interfere in the mission or to request a status of a vehicle. When the GEOMAR AUV team were asked to bring two Hover AUVs (part of the MOSES Helmholtz Research Infrastructure Program; “Modular Observation Solutions for Earth Systems”) into operational service, that was exactly what we wanted. We decided to create our own tool: BELUGA. <br/> After almost 3 years BELUGA is a core tool for our operational work with our GIRONA 500 AUVs and their acoustic seafloor beacons. BELUGA allows communication and data exchange between those devices mentioned above and the ship. <br/> Every component inside this kind of ad hoc network has an extended driver installed. This driver handles the messages and their content and decides which communication channels to use: Wi-Fi, satellite or acoustical communication. The driver of the shipborne component has additionally a module for a data model, which allows to add more network devices, sensors and messages in future. The user works on a web based graphical interface, which visualizes all the …</p>

<p> Compliant with the FAIR data principles, long-term archiving of bathymetry data from multibeam echosounders –a highly added value for the data life cycle - is the challenging task in the data information system PANGAEA. To cope with the increasing amount of data (“bathymetry puzzle pieces”) acquired from research vessels and the demand for easy “map-based” means to find valuable data, new semi-automated processes and standard operating procedures (SOPs) for bathymetry data publishing and simultaneous visualization are currently developed. </p> <p> This research is part of the “Underway Research Data” project, an initiative of the German Marine Research Alliance (Deutsche Allianz Meeresforschung e.V., DAM). The DAM “Underway Research Data” project, spanning across different institutions, started in mid-2019. The aim of the project is to improve and unify the constant data flow from German research vessels to data repositories like PANGAEA. This comprises multibeam-echosounder and other permanently installed scientific devices and sensors following the FAIR data management aspects. Thus, exploiting the full potential of German research vessels as instant “underway” mobile scientific measuring platforms. </p>

<p> <span> <span> <span> In an ongoing effort within the Helmholtz association to make research data FAIR, i.e. findable, accessible, interoperable and reusable we also need to make biological samples visible and searchable. To achieve this a first crucial step is to inventory already available samples, connect them to relevant metadata and assess the requirements for various sample types (e.g. experimental, time series, cruise samples). This high diversity is challenging for when creating standardized workflows to provide a uniform metadata collection with complete and meaningful metadata for each sample. As part of the Helmholtz DataHub at GEOMAR the <b> B </b> iosample <b> I </b> nformation <b> S </b> ystem (BIS) has been set up, turning the former decentral sample management into a fully digital and centrally managed long-term sample storage. </span> </span> </span> </p> <p> <span> <span> <span> The BIS is based on the open-source research data management system CaosDB, which offers a framework for managing diverse and heterogeneous data.  It supports fine-grained access permissions and regular backups, has a powerfull search engine, different APIs and an extendable WebUI. We have designed a flexible datamodel and multiple WebUI modules to support scientists, technicans and datamanagers in digitalizing and centralising sample metadata and making the metadata visible in data portals (e.g. https://marine-data.de). </span> </span> </span> </p> <p> <span> <span> <span> The system allows us to manage …</span></span></span></p>

<p> The International Generic Sample Number (IGSN) is a globally unique and persistent identifier for physical objects, such as samples. IGSNs allow to cite, track and locate physical samples and to link samples to corresponding data and publications. The metadata schemata is modular and can be extended by domain-specific metadata. </p> <p> Within the FAIR WISH projected funded by the Helmholtz Metadata Collaboration, domain-specific metadata schemes for different sample types within Earth and Environment are developed based on three different use cases. These use cases represent all states of digitization, from hand-written notes only to information stored in relational databases. For all stages of digitization, workflows and templates to generate machine-readable IGSN metadata are developed, which allow automatic IGSN registration. These workflows and templates will be published and will contribute to the standardization of IGSN metadata. </p>

<p> Facilitating and monitoring the ingestion and processing of continuous data streams is a challanging exercise that is often only addressed for individual scientific projects and/ or stations and thus results in a heterogeneous data environment. </p> <p> In order to reduce duplication and to enhance data quality we built a prototypical data ingestion pipeline using open-source frameworks with the goal to a) unify the data flow for various data sources, b) enhance observability at all stages of the pipeline, c) introduce a multi-stage QA/ QC procedure to increase data quality and reduce the lag of data degradation or data failure detection. The system is orchestrated using <a href="http://Prefect.io"> Prefect </a> , QA/ QC is handled by <a href="https://greatexpectations.io"> Great Expectations </a> and <a href="https://rdm-software.pages.ufz.de/saqc"> SaQC </a> , and the <a href="https://www.ogc.org/standards/sensorthings"> SensorThings API </a> and <a href="https://www.unidata.ucar.edu/software/tds/"> THREDDS Data Server </a> are used to facilitate data access and integration with other services. </p> <p> The prototype workflow also features a human-in-the-loop aspect so scientific PIs can act on incoming data problems early and with little effort. The framework is flexible enough so specific needs of individual projects can be addressed while still using a common platform. The final outcome of the pipeline are aggregated data products that are served to the scientists and/ or the public via data catalogues. …</p>

<p align="justify"> <font color="#000000"> <font size="3"> <font face="Arial, serif"> The NFDI ₄ Earth Academy is a network of early career scientists interested in linking Earth System and Data Sciences </font> <font face="Arial, serif"> beyond institutional borders </font> <font face="Arial, serif"> . </font> <font face="Arial, serif"> The research networks Geo.X, Geoverbund ABC/J, and DAM </font> <font face="Arial, serif"> offer an open science and learning environment that covers specialized training courses, collaborations </font> <font face="Arial, serif"> within the NFDI4Earth consortium </font> <font face="Arial, serif"> and access to all NFDI </font> _{<font face="Arial, serif"> 4 </font>} <font face="Arial, serif"> Earth innovations and services. Fellows of the Academy advance their research projects by exploring and integrating new methods and connect with like-minded scientists in an agile, bottom-up, and peer-mentored community. We support young scientists in developing skills and mindset for open and data-driven science across disciplinary boundaries. </font> </font> </font> </p>

<p> The recent introduction of machine learning techniques in the field of numerical geophysical prediction has expanded the scope so far assigned to data assimilation, in particular through efficient automatic differentiation, optimisation and nonlinear functional representations.  Data assimilation together with machine learning techniques, can not only help estimate the state vector but also the physical system dynamics or some of the model parametrisations. This addresses a major issue of numerical weather prediction: model error. <br/> I will discuss from a theoretical perspective how to combine data assimilation and deep learning techniques to assimilate noisy and sparse observations with the goal to estimate both the state and dynamics, with, when possible, a proper estimation of residual model error. I will review several ways to accomplish this using for instance offline, variational algorithms and online, sequential filters. The skills of these solutions with be illustrated on low-order and intermediate chaotic dynamical systems, as well as data from meteorological models and real observations. </p> <p> Examples will be taken from collaborations with J. Brajard, A. Carrassi, L. Bertino, A. Farchi, Q. Malartic, M. Bonavita, P. Laloyaux, and M. Chrust. </p>

<p dir="ltr"> Mantle convection plays a fundamental role in the long-term thermal evolution of terrestrial planets like Earth, Mars, Mercury and Venus. The buoyancy-driven creeping flow of silicate rocks in the mantle is modeled as a highly viscous fluid over geological time scales and quantified using partial differential equations (PDEs) for conservation of mass, momentum and energy. Yet, key parameters and initial conditions to these PDEs are poorly constrained and often require a large sampling of the parameter space to find constraints from observational data. </p> <p dir="ltr"> Since it is not computationally feasible to solve hundreds of thousands of forward models in 2D or 3D, scaling laws have been the go-to alternative. These are computationally efficient, but ultimately limited in the amount of physics they can model (e.g., depth-dependent material properties). More recently, machine learning techniques have been used for advanced surrogate modeling. For example, Agarwal et al. (2020) used feedforward neural networks to predict the evolution of entire 1D laterally averaged temperature profile in time from five parameters: reference viscosity, enrichment factor for the crust in heat producing elements, initial mantle temperature, activation energy and activation volume of the diffusion creep. In Agarwal et al. (2021), we extended that study to predict the …</p>

<p> <span lang="EN-US"> <span> <span> For some time, large scale analyses and data-driven approaches have become increasingly popular in all research fields of hydrology. Many advantages are seen in the ability to achieve good predictive accuracy with comparatively little time and financial investment. </span> </span> </span> <span lang="EN-US"> <span> <span> It has been shown by previous studies that complex hydrogeological processes can be learned from artificial neural networks, whereby Deep Learning demonstrates its strengths particularly in combination with large data sets. However, there are limitations in the interpretability of the predictions and the transferability with such methods. Furthermore, most groundwater data are not yet ready for data-driven applications and </span> </span> </span> <span lang="EN-US"> <span> <span> the data availability often remains insufficient for training neural networks. The larger the scale, the more difficult it becomes to obtain sufficient information and data on local processes and environmental drivers in addition to groundwater data. For example, groundwater dynamics are very sensitive to pumping activities, but information on their local effects and magnitude – especially in combination with natural fluctuations – is often missing or inaccurate. Coastal regions are often particularly water-stressed. Exemplified by the important coastal aquifers, novel data-driven approaches are presented that have the potential to both contribute to process understanding of groundwater dynamics and groundwater level prediction on large …</span></span></span></p>

<p> Together, the creatures of the oceans and the physical features of their habitat play a significant role in sequestering carbon and taking it out of the atmosphere. Through the biological processes of photosynthesis, predation, decomposition, and the physical movements of the currents, the oceans take in more carbon than they release. With sediment accumulation in the deep seafloor, carbon gets stored for a long time, making oceans big carbon sinks, and protecting our planet from the devastating effects of climate change. </p> <p> <br/> Despite the significance of seafloor sediments as a major global carbon sink, direct observations on the mass accumulation rates(MAR) of sediments are sparse. The existing sparse data set is inadequate to quantify the change in the composition of carbon and other constituents at the seabed on a global scale. Machine learning techniques such as the k-nearest neighbour’s algorithm have provided predictions of sparse sediment accumulation rates, by correlating known features(predictors) such as bathymetry, bottom currents, distance to coasts and river mouths, etc. </p> <p> In my current work, global maps of the sediment accumulation rates at the seafloor are predicted using the known fea ture maps and the sparse dataset of sediment accumulation rates using multi-layer perceptrons(supervised models). Despite a good …</p>

<p> The Lagrangian perspective on Ocean currents describes trajectories of individual virtual or physical particles which move passively or semi-actively with the Ocean currents. The analysis of such trajectory data offers insights about pathways and connectivity within the Ocean. To date, studies using trajectory data typically identify pathways and connections between regions of interest in a manual way. Hence, they are limited in their capability in finding previously unknown structures, since  the person analyzing the data set can not foresee them. An unsupervised approach to trajectories could allow for using the potential of such collections to a fuller extent. </p> <p> This study aims at identifying and subsequently quantifying pathways based on collections of millions of simulated Lagrangian trajectories. It develops a stepwise multi-resolution clustering approach, which substantially reduces the computational complexity of quantifying similarity between pairs of trajectories and it allows for parallelized cluster construction. </p> <p> It is found that the multi-resolution clustering approach makes unsupervised analysis of large collections of trajectories feasible. Moreover, it is demonstrated that for selected example research questions the unsupervised results can be applied. </p>

<p> The frequent presence of cloud cover in polar regions limits the use of the Moderate Resolution Imaging Spectroradiometer (MODIS) and similar instruments for the investigation and monitoring of sea-ice polynyas compared to passive-microwave-based sensors. The very low thermal contrast between present clouds and the sea-ice surface in combination with the lack of available visible and near-infrared channels during polar nighttime results in deficiencies in the MODIS cloud mask and dependent MODIS data products. This leads to frequent misclassifications of (i) present clouds as sea ice or open water (false negative) and (ii) open-water and/or thin-ice areas as clouds (false positive), which results in an underestimation of actual polynya area and subsequently derived information. Here, we present a novel machine-learning-based approach using a deep neural network that is able to reliably discriminate between clouds, sea-ice, and open-water and/or thin-ice areas in a given swath solely from thermal-infrared MODIS channels and derived additional information. Compared to the reference MODIS sea-ice product for the year 2017, our data result in an overall increase of 20 % in annual swath-based coverage for the Brunt Ice Shelf polynya, attributed to an improved cloud-cover discrimination and the reduction of false-positive classifications. At the same time, the …</p>

<p> <span> <span> Funded by the Helmholtz Foundation, the aim of the Artificial Intelligence for COld REgions (AI-CORE) project is to develop methods of Artificial Intelligence for solving some of the most challenging questions in cryosphere research by the example of four use cases. These use cases are of high relevance in the context of climate change but very difficult to tackle with common image processing techniques. Therefore, different AI-based imaging techniques are applied on the diverse, extensive, and inhomogeneous input data sets. </span> </span> </p> <p> <span lang="EN-US"> <span> In a collaborative approach, the German Aerospace Center, the Alfred-Wegener-Institute, and the Technical University of Dresden work together to address not only the methodology of how to solve these questions, but also how to implement procedures for data integration on the infrastructures of the partners. Within the individual Helmholtz centers already existing competences in data science, AI implementation, and processing infrastructures exist but are decentralized and distributed among the individual centers. Therefore, AI-CORE aims at bringing these experts together to jointly work on developing state of the art tools to analyze and quantify processes currently occurring in the cryosphere. The presentation will give a brief overview of the geoscientific use cases and then address the different challenges that emerged so …</span></span></p>

<p dir="ltr"> In the context of global climate change and environmental challenges, one research question is how different ocean regions take up carbon dioxide and which bio-physical drivers are responsible for these patterns. The carbon uptake at the sea surface is different in different areas. It depends on several drivers (sea surface temperature, the salinity of the water, alkalinity, dissolved inorganic carbon, phytoplankton, etc.), which enormously vary on both a spatial and seasonal time scale. We name a carbon regime a region having common relationships (on a seasonal and spatial scale) between carbon uptake and its drivers (sea surface temperature, etc.). </p> <p> <br/> We are using the output of a global ocean biogeochemistry model providing surface fields of carbon uptake and its drivers on a monthly time scale. We aim to use spatial and seasonal correlations to detect the regimes.  We take advantage of both supervised and unsupervised machine learning methodologies to find different carbon states. The aim is to determine individual local correlations in each carbon state. We build a top-down grid-based algorithm that incorporates both regression and clustering algorithms. The technique divides the entire ocean surface into smaller grids. The regression model detects a linear relationship between carbon uptake and other ocean …</p>

<p> Artificial neural networks (ANNs) are known to be powerful methods for many hard problems (e.g. image classification or timeseries prediction). However, these models tend to produce black-box results and are often difficult to interpret. Here we present Echo State Networks (ESNs) as a certain type of recurrent ANNs, also known as reservoir computing. ESNs are easy to train and only require a small number of trainable parameters. They can be used not only for timeseries prediction but also for image classification, as shown here: Our ESN model serves as a detector for El Nino Southern Oscillation (ENSO) from sea-surface temperature anomalies. ENSO is actually a well-known problem and has been widely discussed before. But here we use this simple problem to open the black-box and apply layerwise relevance propagation to Echo State Networks. </p>

<p> The Hereon operates a larger number of continuously measuring sensors on mobile and stationary platforms outside the Hereon Campus. Transferring the data from the sensors to the internal network is a critical step , as data is often required to be accessible for researchers in near-real-time (NRT) and needs be retrieved from the outside in a secure way that does not pose a threat to the internal infrastructure. </p> <p> Therefore, we developed the <u> He </u> reon <u> L </u> ayer for <u> M </u> anaging <u> I </u> ncoming data (HELMI). Using HELMI, data from external sensor systems is moved securely via a Virtual Private Network solution ( Wireguard ) to the Hereon internal infrastructure. The Wireguard client can be either installed directly on the sensor system or on a piece of hardware dedicated for data transfer that is connected to the sensor. Data is transferred as files via the RSYNC or as NRT data via the Message Queuing Telemetry Transport (MQTT) protocol, respectively. After transfer researchers can retrieve their files and access telemetry from an internal endpoint. NRT-Data can be automatically visualized using web applications and parameters at the client can be remotely controlled . </p> <p> The automatic data transfer via HELMI minimizes the risk of data loss, …</p>

<p> <span> <span> <span> Biomolecules, such as DNA and RNA, make up all ocean life, and biomolecular research in the marine realm is pursued across several Helmholtz Centres. Biomolecular (meta)data (i.e. DNA and RNA sequences and all steps involved in their creation) provide a wealth of information about the distribution and function of marine organisms. However, high-quality (meta)data management of biomolecular data is not yet well developed in environmentally focused Helmholtz Centres. This impedes every aspect of FAIR data exchange internally and externally, and the pursuit of scientific objectives that depend on this data. In this Helmholtz Metadata Collaboration project between the Alfred-Wegener-Institut Helmholtz Zentrum für Polar- und Meeresforschung and the GEOMAR Helmholtz-Zentrum für Ozeanforschung Kiel (with scientific PIs rooted in POFIV Topic 6), we will develop sustainable solutions and digital cultures to enable high-quality, standards-compliant curation and management of marine biomolecular metadata, to better embed biomolecular science in broader digital ecosystems and research domains. The approach will build on locally administered relational databases and establish a web-based hub to exchange metadata compliant with domain-specific standards, such as the MIxS (Minimum Information about any (x) Sequence). To interface with and enhance the Helmholtz digital ecosystem, we aim to link the operations and archiving workflows …</span></span></span></p>

<p> The shallow water equations (SWEs) are widely employed for governing a large-scale fluid flow system, for example, in the coastal regions, oceans, estuaries, and rivers. These partial differential equations (PDEs) are often solved using semiimplicit schemes that solve a linear system iterativelyat each time step, resulting in high computational costs. Here we use physics constrained deep learning to train a convolutoinal network to solve the SWEs, while training on the discretized PDE directly without any need for numerical simulations as training data data. To improve accuracy and stability over longer integration times, we utilise group equivariant convolutional networks, so that the the learned model respects rotational and translational symmetries in the PDEs as hard constraints at every point in the training process. After training, our networks accurately predict the evolution of SWEs for freely chosen initial conditions and multiple time steps. Overall, we find that symmetry constraints signficantly improve performance compared to standard  convolution networks. </p> <p> </p>

<p> This contribution is an introduction to the data management process in the MOSAiC - Virtual Research Environment (M-VRE) project. The M-VRE project aims to make the unique and interdisciplinary data set of MOSAiC easily accessible to the field of scientists from different research areas [ADD22]. In addition, a virtual environment is available to analyze and visualize them directly online. This supports the research in improving transparency, traceability, reproducibility and visibility. <br/> One tool that is incorporated within M-VRE is webODV, the online version of Ocean Data View (ODV) [Sch22]. ODV is a software for visualization of oceanographic data in oceanography since almost 30 years. Given its software structure, it is equally suitable for data of the atmosphere, on land, on ice. Yet, there are requirements of ODV regarding the format of the data set which is why a conversion of the data is required. <br/> In the following, the workflow of data from archive to webODV is described. <br/> First of all, the data source needed to be defined. As part of the MOSAiC project, an agreement was reached through the MOSAiC Data Policy to upload the data to the long-term archive PANGAEA [Imm+19]. For this reason, PANGAEA is used as the data …</p>

<p> <span> <span> <span> Knowledge transfer requires, first, meaningful approaches and products to transfer knowledge amongst different users and, second, appropriate measures for the creation of knowledge across scientific disciplines. The <i> Coastal Pollution Toolbox </i> ( <a href="https://www.coastalpollutiontoolbox.org/index.php.en"> https://www.coastalpollutiontoolbox.org/index.php.en </a> ), a central product of the program-oriented funding topic on “Coastal Transition Zones under Natural and Human Pressures”, serves as a digital working environment for scientists and knowledge hub and information platform for decision-makers. It supports action and optimisation of scientific concepts to investigate pollution in the land-to-sea continuum. </span> </span> </span> </p> <p> <span> <span> <span> In order to address demands of various users the toolbox comprises of three compartments: <i> Science Tools </i> provide expert users with information on new methods, approaches or indicators for baseline assessments or for the re-evaluation of complex problems. <i> Synthesis Tools </i> address challenges of global environmental change. They are information-rich products based on consolidated data of different types and origin and provide expert users with knowledge. <i> Management Tools </i> provide usable information and options for action. Ready-to-use tools grounded on evidence-based science are available to those involved in planning and management of coastal and marine challenges. </span> </span> </span> </p> <p> <span> <span> <span> As part of the development process coastal pollution information services will be created and co-developed with stakeholders and end-users. This will ensure optimal interest and use …</span></span></span></p>

<p> The Data Analytics Software Framework (DASF, <a href="https://doi.org/10.5880/GFZ.1.4.2021.004"> https://doi.org/10.5880/GFZ.1.4.2021.004 </a> ) supports scientists to conduct data analysis in distributed IT infrastructures by sharing data analysis tools and data. For this purpose, DASF defines a remote procedure call (RPC) messaging protocol that uses a central message broker instance. Scientists can augment their tools and data with this protocol to share them with others or re-use them in different contexts. </p> <p> Our framework takes standard python code developed by a scientist, and automatically transforms the functions and classes of the scientists code into an abstract layer. This abstraction, the server stub as it is called in RPC, is connected to the message broker and can be accessed by submitting JSON-formatted data through a websocket in the so-called client stub. Therefore the DASF RPC messaging protocol  in general is language independent, so all languages with Websocket support can be utilized. As a start DASF provides two ready-to-use  language bindings for the messaging protocol, one for Python and one for  the Typescript programming language. </p> <p> DASF is developed at the GFZ German Research Centre for Geosciences and was funded by the Initiative and Networking Fund of the Helmholtz Association through the Digital Earth project ( <a href="https://www.digitalearth-hgf.de/"> https://www.digitalearth-hgf.de/ </a> ). In this …</p>

<p> Advances in imaging technology for in situ observation of marine life has significantly increased the size and quality of available datasets, but methods for automatic image analysis have not kept pace with these advances. On the other hand, knowing about distributions of different species of plankton for example would help us to better understand their lifecycles, interactions with each other or the influence of environmental changes on different species. While machine learning methods have proven useful in solving and automating many image processing tasks, three major challenges currently limit their effectiveness in practice. First, expert-labeled training data is difficult to obtain in practice, requiring high time investment whenever the marine species, imaging technology or environmental conditions change. Second, overconfidence in learned models often prevents efficient allocation of human time. Third, human experts can exhibit considerable disagreement in categorizing images, resulting in noisy labels for training. To overcome these obstacles, we combine recent developments in self-supervised feature learning based with temperature scaling and divergence-based loss functions. We show how these techniques can reduce the required amount of labeled data by ~100-fold, reduce overconfidence, cope with disagreement among experts and improve the efficiency of human-machine interactions. Compared to existing methods, these techniques …</p>

<p> Introduction </p> <p> MOSAiC (https://mosaic-expedition.org/) has been the largest polar expedition in history. The German icebreaker Polarstern was trapped in the ice from October 2019 to October 2020, and rich data have been collected during the polar year. The M-VRE project (The MOSAiC Virtual Research Environment, https://mosaic-vre.org/) has the aim to support the analysis and exploitation of the MOSAiC data by providing online software tools for the easy, interdisciplinary and efficient exploration and visualization of the data. One service provided by M-VRE is webODV, the online version of the Ocean Data View Software (ODV, https://odv.awi.de/). </p> <p> Setup </p> <p> The MOSAiC webODV is available via https://mosaic-vre.org/services/ or dirctly at https://mvre.webodv.cloud.awi.de/. Due to a moratorium until the end of 2022, the data can only be accessed by the MOSAiC consortium. From 2023 on, MOSAiC data and thus webODV will be available for the science community and the general public. In the webODV configuration, datasets as well as the ODV software reside and run on a server machine, not on the client computer. The browser client communicates with the server over the Internet using secure websockets. Up to now we provide two webODV services, which are described in the following. </p> <p> Data Extraction </p> <p> The Data Extraction service is …</p>

<p> <span> <span> Cloud dynamics are integral to forecasting and monitoring weather and climate processes. Due to a scarcity of high-quality datasets, limited research has been done to realistically model clouds. This proposal applies state-of-the art machine-learning techniques to address this shortage,using a real-life dataset,CloudCast. </span> </span> </p> <p> <span> <span> Potential techniques, such as RNNs and CNNs paired with data augmentations are explored.  Preliminary results show promise for the task of supervised video frame interpolation and video prediction. High performance is achieved with a supervised approach. </span> </span> </p> <p> <span> <span> These video techniques demonstrate a potential to lower the cost for satellite capture, restoration, and calibration of errors in remote sensing data. Future work is proposed to develop more robust video predictions on this and other similar datasets. With these additions, climate scientists and other practitioners could successfully work at a higher frequency. </span> </span> </p>

<p> Environmental simulations in high spatio-temporal resolution consisting of large-scale dynamic systems are compute-intensive, thus usually demand parallelization of the simulations as well as high performance computing (HPC) resources. Furthermore, the parallelization of existing sequential simulations involves potentially a large configuration overhead and requires advanced programming expertise of domain scientists. On the other hand, despite the availability of modern powerful computing technologies, and under the perspective of saving energy, there is a need to address the issues such as complexity and scale reduction of large-scale systems’ simulations. In order to tackle these issues, we propose two approaches: 1. Approximation of simulations by model order reduction and unsupervised machine learning methods, and 2. Approximation of simulations by supervised machine learning methods. </p> <p> In the first method, we approximate large-scale and high-resolution environmental simulations and reduce their computational complexity by employing model order reduction techniques and unsupervised machine learning algorithms. In detail, we cluster functionally similar model units to reduce model redundancies, particularly similarities in the functionality of simulation model units and computation complexity. The underlying principle is that the simulation dynamics depend on model units’ static properties, current state, and external forcing. Based on this, we assume that similar model units’ settings lead …</p>

<p> <span> <span> <span> <span> <span> <span> <span> Thousands of ocean temperature and salinity measurements are collected every day around the world. Controlling the quality of this data is a human resource-intensive task because the control procedures still produce many false alarms only detected by a human expert. Indeed, quality control (QC) procedures have not yet benefited from the recent development of efficient machine learning methods to predict simple targets from complex multi-dimensional features. With increasing amounts of big data, algorithmic help is urgently needed, where artificial intelligence (AI) could play a dominant role. Developments in data mining and machine learning in automatic oceanographic data quality control need to be revolutionized. Such techniques provide a convenient framework to improve automatic QC by using supervised learning to reduce the discrepancy with the human expert evaluation. </span> </span> </span> </span> </span> </span> </span> </p> <p> <span> <span> <span> <span> <span> <span> <span> This scientific work proposes a comparative analysis of machine learning classification algorithms for ocean data quality control to detect the suspect temperature gradient error. The objective of this work is to obtain a very effective QC classification method from ocean data using a representative set of supervised machine learning algorithms. The work to be presented consists of the second step of our overall system, in which the first is based on a deep convolutional …</span></span></span></span></span></span></span></p>

<p dir="ltr"> In weather and climate models, physical processes that can’t be explicitly resolved are often parameterized. Among them is cloud microphysics that often works in tandem with the convective parameterization to control the formation of clouds and rain. </p> <p dir="ltr"> Existing parameterization schemes available for cloud microphysics suffer from an accuracy/speed trade-off. The most accurate schemes based on Lagrangian droplet methods are computationally expensive and are only used for research and development. On the other hand, more widely used approaches such as bulk moment schemes simplify the particle size distributions into the total mass and number density of cloud and rain droplets. While these approximations are fairly realistic in many cases, they struggle to represent more complex microphysical scenarios. </p> <p dir="ltr"> We develop a machine learning based parameterization to emulate the warm rain formation process in the Super droplet scheme (a type of Lagrangian scheme) in a dimensionless control volume. We show that the ML based emulator matches the Lagrangian simulations better than the bulk moment schemes, especially in the cases of very skewed droplet distributions. Compared to previous attempts in emulating warm rain, our ML model shows a better performance. The ML model inference runs fast thereby reducing the computational time otherwise needed for …</p>

<p> <span> <span> <span> <span lang="EN-US"> <span> The collaborative project “MuSSeL” investigates various natural and anthropogenic changes, such as climate change, increase of fishing and the development of offshore wind farms, and the effect these changes have on the biodiversity and well-being of benthic communities in the North Sea. A central part of this project is to make any data gathered, easily accessible to stakeholders and the general public alike. To streamline this process it was decided to use ESRI software solutions, for data management and public outreach. The live demo will demonstrate how data can be visualised, analysied and made available on the project website, all using ESRI solutions. </span> </span> </span> </span> </span> </p>

<p> <span> <span> <span> The River Plume Workflow is a part of the Digital Earth Flood event explorer (FEE), which was designed to compile different aspects of riverine flood events. </span> </span> </span> </p> <p> <span> <span> <span> The focus of the River Plume Workflow is the impact of riverine flood events on the marine environment, when, at the end of a flood event chain, an unusual amount of nutrients and pollutants is washed into the coastal waters. The River Plume Workflow provides scientists with tools to detect river plumes in marine data during or after an extreme event and to investigate their spatio-temporal extent, their propagation and impact. This is achieved through the combination of in-situ data from autonomous measuring devices, drift model data produced especially for the observational data and satellite data of the observed area. In the North Sea, we use measurements from the FerryBox mounted on the Büsum-Helgoland ferry to obtain regular in-situ data and offer model trajectories from drift simulations around the time of extreme events in the Elbe River. </span> </span> </span> </p> <p> <span> <span> <span> The River Plume Workflow helps scientists identify river plume candidates either manually within a visual interface or through an automatic anomaly detection algorithm, using Gaussian regression. Combining the observational data with model trajectories that show the position …</span></span></span></p>

<h1 dir="ltr"> Introduction </h1> <p dir="ltr"> Existing marine technology introduces the capability for every marine vehicle to integrate in a timely manner a large collection of global ship positioning data along with instructed higher safety and reduced emission intensity routes. New AI-assisted navigational devices could quickly integrate unsupervised routing predictions based on assimilated and forecasted global ocean and weather. </p> <h1 dir="ltr"> Description of goals </h1> <p dir="ltr"> Here we design a route optimization algorithm for taking advantage of current predictions from ocean circulation models. We develop validation scenarios for a marine vehicle and show how it can propagate in a safer environment. Our optimization is designed to fulfill emission goals by achieving a lower fuel use. </p> <h1 dir="ltr"> Results and Achievements </h1> <p dir="ltr"> The weather data from the European Observational Marine Copernicus Center allows leveraging both satellite observations and high resolution wind, wave and current predictions at any position in the global ocean. We propose a low fuel consumption, carbon emission ship routing optimization that employs these real time high resolution data in a stochastic optimization algorithm. </p> <p dir="ltr"> The proposed optimization method is based on local continuous random modifications subsequently applied to an initial shortest-distance route between two points. It is parallelised using a genetic approach. The model is validated using both vessel noon reports …</p>

<p> Over the last few years, a very active field of research has aimed at exploring new data-driven and learning-based methodologies to propose computationally efficient strategies able to benefit from the large amount of observational remote sensing and numerical simulations for the reconstruction, interpolation and prediction of high-resolution derived products of geophysical fields. These approaches now reach state-of-the performance for the reconstruction of satellite-derived geophysical fields. In this context, deep emulators emerge as new means to bridge model-driven and learning-based frameworks. Here, we focus on deep emulators for reconstruction and data assimilation issues, and more specifically on 4DVarNet schemes. These schemes bridge variational data assimilation formulation and deep learning schemes to learn 4DVar models and solvers from data. Here, we present an application of 4dVarNet schemes to the reconstruction of sea surface dynamics. More specifically, we aim at learning deep emulators for the interpolation from altimetry data. Similarly to a classic optimal interpolation, we leverage a minimization-based strategy but we benefit from the modeling flexibility of deep learning framework to embed non-linear and multi-scale priors and learn jointly a gradient-based solver for the underlying variational cost. Overall, the proposed 4dVarNet scheme defines an end-to-end neural architecture which use irregularly-sampled altimetry data …</p>

<p dir="ltr"> The European Space Agency (ESA) launched the AI4EO initiative to bridge the gap between the artificial intelligence (AI) and the Earth observation (EO) communities [1]. In the AI4FoodSecurity challenge [2], the goal is to identify crops in agricultural fields using time series remote sensing data from different satellites. In the first challenge track, predictions were made for a region in South Africa, including a spatial domain shift. In the second challenge track, predictions were made for a region in Germany (Brandenburg), including a spatio-temporal domain shift. </p> <p dir="ltr"> We here present our contribution to the AI4FoodSecurity challenge. As data sources we selected both radar wavelength images from the Sentinel-1 satellite, as well as visual and infrared images from the Planet Fusion Monitoring satellites. We implemented a Pixel-Set Encoder with Lightweight Temporal Attention (PseLTae) [3]. Samples are constructed by randomly selecting pixels from a given agricultural field. We train separate encoders for each data source. Attention heads are used to extract characteristic changes of the distinct crop types throughout the growing season. At the decoder stage, both sources are combined to yield a prediction for the crop type. We used data augmentation by oversampling the agricultural fields, as well as cross validation. </p> <p dir="ltr"> The …</p>

<p> Forest mortality is a complex phenomenon because of the interaction of multiple drivers over <br/> a long period. Understanding these interactions and their relevant time scale is important for <br/> forest management. Unlike climate data which are continuous (daily or hourly resolutions), <br/> forest mortality related observations are discrete (e.g. the number of trees, mortality fraction) <br/> with lower frequencies (once/twice a year). Forests also have persistent memory with a large <br/> buffering capacity. All the above-mentioned reasons make the analysis of forest mortality <br/> difficult with the conventional tools. Deep learning is well suited for modelling multivariate <br/> time series with persistent non-linear interactions. In this study, we generate 200,000 years of <br/> hourly climate data using a weather generator (AWE-GEN). We aggregate the hourly data to <br/> daily values and feed it to a process based forest model (FORMIND). The forest model gives <br/> us mortality fractions per year, in line with the forest mortality related observations. For the <br/> method development phase, we use these simulated data. First, we use a variationalautoencoder <br/> to extract climatic features and use that for the prediction of forest mortality. In <br/> the second stage, we do the prediction of forest mortality and feature extraction together and <br/> illustrate the difference between the extracted features. …</p>

<p> <span> <span> <span> <span> <span lang="EN-GB"> <span> <span> <span> Extreme impacts can be caused by the compounding effects of multiple drivers, such as weather events that might not individually be considered extreme. An example of this is the phenomenon of ‘false spring’, where a combination of a warm late winter or early spring, followed by a frost once the plants have entered a vulnerable stage of development, results in severe crop damage. The relationships between growing-season climate conditions and end-of-season crop yield are complex and nonlinear, and improving our understanding of such interactions could aid in narrowing the uncertainty in estimates of climate risk to food security. Additionally, data-driven methods that are capable of identifying such compounding effects could be useful for the study of other sectoral impacts. </span> </span> </span> </span> </span> </span> </span> </span> </p> <p> <span> <span> <span> <span> <span lang="EN-GB"> <span> <span> <span> Machine learning is an option for capturing such complex and nonlinear relationships for yield prediction. In order to extract these relationships, explainable or interpretable machine learning has been identified as a potential tool. However, the usefulness of those extracted interpretations is dependent on the assumption that the model has learned the expected relationships. One prerequisite for this assumption is that the model has sufficient predictive skill. The method chosen for measuring model performance is therefore an important methodological decision, but as …</span></span></span></span></span></span></span></span></p>

<p dir="ltr"> This presentation reports on support done under the aegis of Helmholtz AI for a wide range of machine learning based solutions for research questions related to Earth and Environmental sciences. We will give insight into typical problem statements from Earth observation and Earth system modeling that are good candidates for experimentation with ML methods and report on our accumulated experience tackling such challenges with individual support projects. We address these projects in an agile, iterative manner and during the definition phase, we direct special attention towards assembling practically meaningful demonstrators within a couple of months. A recent focus of our work lies on tackling software engineering concerns for building ML-ESM hybrids. </p> <p> </p> <p dir="ltr"> Our implementation workflow covers stages from data exploration to model tuning. A project may often start with evaluating available data and deciding on basic feasibility, apparent limitations such as biases or a lack of labels, and splitting into training and test data. Setting up a data processing workflow to subselect and compile training data is often the next step, followed by setting up a model architecture. We have made good experience with automatic tooling to tune hyperparameters and test and optimize network architectures. In typical implementation projects, these stages …</p>

<p> <span> <span> Underwater images are used to explore and monitor ocean habitats, generating huge datasets with unusual data characteristics that preclude traditional data management strategies. Due to the lack of universally adopted data standards, image data collected from the marine environment are increasing in heterogeneity, preventing objective comparison. The extraction of actionable information thus remains challenging, particularly for researchers not directly involved with the image data collection. Standardized formats and procedures are needed to enable sustainable image analysis and processing tools, as are solutions for image publication in long-term repositories to ascertain reuse of data. The FAIR principles (Findable, Accessible, Interoperable, Reusable) provide a framework for such data management goals. We propose the use of image FAIR Digital Objects (iFDOs) and present an infrastructure environment to create and exploit such FAIR digital objects. We show how these iFDOs can be created, validated, managed, and stored, and which data associated with imagery should be curated. The goal is to reduce image management overheads while simultaneously creating visibility for image acquisition and publication efforts and to provide a standardised interface to image (meta) data for data science applications such as annotation, visualization, digital twins or machine learning. </span> </span> </p>

<p> Numerical simulations of Earth's weather and climate require substantial amounts of computation. This has led to a growing interest in replacing subroutines that explicitly compute physical processes with approximate machine learning (ML) methods that are fast at inference time. Within weather and climate models, atmospheric radiative transfer (RT) calculations are especially expensive. This has made them a popular target for neural network-based emulators. However, prior work is hard to compare due to the lack of a comprehensive dataset and standardized best practices for ML benchmarking. <br/> To fill this gap, we introduce the ClimART dataset, which is based on the Canadian Earth System Model, and comes with more than 10 million samples from present, pre-industrial, and future climate conditions. </p> <p> ClimART poses several methodological challenges for the ML community, such as multiple out-of-distribution test sets, underlying domain physics, and a trade-off between accuracy and inference speed. We also present several novel baselines that indicate shortcomings of the datasets and network architectures used in prior work. </p>

<p> <span> <span> The impacts from anthropogenic climate change are directly felt through extremes. The existing research skills in assessing future changes in impacts from climate extremes is however still limited. Despite the fact that a multitude of climate simulations is now available that allows the analysis of such climatic events, available approaches have not yet sufficiently analysed the complex and dynamic aspects that are relevant to estimate what climate extremes mean for society in terms of impacts and damages. Machine Learning (ML) algorithms have the ability to model multivariate and nonlinear relationships, with possibilities for non-parametric regression and classification, and are therefore well-suited to model highly complex relations between climate extremes and their impacts. </span> </span> </p> <p> <span> <span> In this presentation, I will highlight some recent ML applications, focussing on monetary damages from floods and windstorms. For these extremes, ML models are built using observational datasets of extremes and their impacts. Here I will also address the sample selection bias, which occurs between observed moderate impact events, and more extreme events sampled in current observed and projected future data. This can be addressed by adjusting weighting for such variable values, as is demonstrated for extreme windstorm events. </span> </span> </p> <p> <span> <span> Another application focusses on health outcomes, in this case …</span></span></p>

<p> <span> <span> <span lang="EN-GB"> <span> The ocean economy is growing and the pressures on our seas and the ocean, including from over </span> </span> <span lang="EN-GB"> exploitation, <span> pollution and climate change, have asserted significant stresses on the marine system. </span> <span> Digital twins are rich, virtual representations of objects and systems, in this case the ocean system, or a part of it. They allow us to track how and why the things we care about are changing and simulate what their futures could be, including by exploring ‘what if?’ scenarios. They can provide critical knowledge to plan and guide human activities in the ocean and coastal spaces to safeguard a healthy ocean and support a sustainable green-blue economy. </span> </span> </span> </span> </p> <p> </p> <p> <span> <span> <span lang="EN-GB"> <span> Digital twins </span> </span> <span lang="EN-GB"> depend upon: </span> </span> </span> <span> <span> <span lang="EN-GB"> an <span> int </span> egrated, and sustainable, ocean <span> observing system </span> ; </span> </span> </span> <span> <span> <span lang="EN-GB"> <span> well </span> </span> <span lang="EN-GB"> -managed, accessible and interoperable data and software; <span> <span> <span lang="EN-GB"> <span> predictive processes or data-driven models with which users can interact, to support their needs; sharing of good and best practive and traing, education and outreach. </span> </span> </span> </span> </span> </span> </span> </p> <p> <br/> <span> <span> <span lang="EN-GB"> <span> The connection between </span> a <span> digital twin and </span> its real-world counterpart <span> requires a well-formulated interface between the digital twin, environmental </span> and societal <span> data, and the user. User interaction is an essential function embedded in the design of digital </span> twins, to ensure maximum information value for investment in ocean …</span></span></span></p>

<p> <br/> Digital hydromorphological twin of the Trilateral Wadden Sea </p> <p> The project “Digital hydromorphological twin of the Trilateral Wadden Sea” focuses <br/> on cooperation of cross-border data innovations between The Netherlands, Germany and Denmark, <br/> the provision / harmonization of data together with a new digital geodata and <br/> analysis infrastructure for the trilateral Wadden Sea World Heritage Site These <br/> data and information are linked via Web portals and services to form a <br/> versatile assistance system. </p> <p> Different demands, requirements and restrictive environ­mental legislation pose major <br/> challenges for the planning and maintenance of transport infra­structure in the <br/> marine environment. TrilaWatt aims at developing and implementing a powerful <br/> spatial data and analysis infra­structure on a homogenized database comprising <br/> the Trilateral Wadden Sea area of the Netherlands, Germany and Denmark. </p> <p> High-resolution hydrographic data series are locally available for the German Bight. <br/> These can be combined into spatial models. Due to the high mapping effort, area-wide <br/> morphological and especially sedimentological surveys can only be conducted at <br/> intervals of several years or decades. On the other hand, current issues <br/> require much higher temporal resolution for the analysis and assessment of <br/> environmental impacts in the entire Wadden Sea. Pressures are addressed in the <br/> MSFD Annex III among others as descriptors "seabed …</p>

<p> Today's Earth-System Models (ESM) are not designed to be interactive. They follow a configure, setup, run, and data analysis scheme. Thus, researchers often have to wait for hours or days until they can inspect model runtime diagnostic data. This causes time-consuming round trips between setup and analysis and limits interaction and insights into an ESM at runtime. </p> <p> We aim to overcome this static scientific modeling process with interactive exploration of ESMs. It will allow to monitor the state of the simulation via dashboards presenting real-time diagnostics within a digital twin world. It will support to halt simulations, move back in time, and explore divergent setup at any given point in the simulation. Therefore, we have to include code in ESMs to access, store, and change data in every part, and make it available to interactive visualization dashboards. </p> <p> In today's monolithic implementation of ESMs and and other scientific models, we have to modularize models and discover or recover interfaces between these modules. The modularization does not only help with restructuring existing ESMs, it also allows to integrate additional scientific domains into the interactive simulation environment. </p> <p> We apply a domain-driven modularization approach utilizing reverse engineering techniques combining static and dynamic analysis of …</p>

<p> The Digital Earth Viewer is a visualisation platform capable of ingesting data from heterogeneous sources and performing spatial and temporal contextualisation upon them. Its web-based nature enables several users to access and visualise large geo-scientific datasets. Here we present the latest development of this viewer: collaborative capabilities that allow parallel, live exploration and annotation of 4 dimensional environments by multiple remote users. </p>

<p> A comprehensive study of the Earth System and its different environments requires understanding of multi-dimensional data acquired with a multitude of different sensors or produced by various complex models. Geoscientists use state of the art instruments and tecniques  to aquire and analise said data, which is in stark contrast with the outdated means that are often selected to present the resulting findings: today's most popular presentation software chocies (PowerPoint, Keynote, etc.) were developed to support a presentation style that has seen slim to none development over the last 70 years. Here I present a software framework for creating dynamic data presentations. This combination of different web based resources enables a new paradigm in data visualisation for scientific presentations. </p>