Search

Background: Accurate prediction of healthcare costs is important for optimally managing health costs. However, methods leveraging the medical richness from data such as health insurance claims or electronic health records are missing., Methods: Here, we developed a deep neural network to predict future cost from health insurance claims records. We applied the deep network and a ridge regression model to a sample of 1.4 million German insurants to predict total one-year health care costs. Both methods were compared to existing models with various performance measures and were also used to predict patients with a change in costs and to identify relevant codes for this prediction., Results: We showed that the neural network outperformed the ridge regression as well as all considered models for cost prediction. Further, the neural network was superior to ridge regression in predicting patients with cost change and identified more specific codes., Conclusion: In summary, we showed that our deep neural network can leverage the full complexity of the patient records and outperforms standard approaches. We suggest that the better performance is due to the ability to incorporate complex interactions in the model and that the model might also be used for predicting other health phenotypes., (© 2022. The Author(s).)

Electric vehicles (EVs) are expected to be vital in transitioning to a low-carbon energy system. However, integrating EVs into the power grid poses significant challenges for grid operators and energy suppliers, especially regarding the uncertainty and variability of EV charging demand. Accurate forecasting of EV charging demand is essential for optimal power system integration, yet previous studies have often only considered point predictions that are inadequate for risk assessment. Therefore, this paper compares different probabilistic forecasting models for the short-term prediction of EV charging demand at various aggregation levels, using a large and novel dataset of over 350,000 charging processes at more than 500 locations across Germany. The performance of both machine learning and deep learning methods is evaluated against a naïve benchmark model, and the impact of data availability on the forecasting models is investigated. Further, the paper examines the effects of forecast accuracy on energy procurement, which has so far received minor attention in the literature. The results show that machine learning methods such as Ada Boosting and Random Forest yield robust results with a normalized root mean square error of 0.42 and 0.41 and a mean absolute scaled error of 0.36 and 0.34 at the highest aggregation level. Furthermore, the results show the influence of different site compositions on the forecast quality and how many charging points are likely to yield a robust forecast. Energy and fleet managers can use the described method to reliably predict the required energy quantities for fleets of sufficient size and procure them at low risk. [ABSTRACT FROM AUTHOR]

The quantification of emissions of greenhouse gases and air pollutants through the inversion of plumes in satellite images remains a complex problem that current methods can only assess with significant uncertainties. The anticipated launch of the CO2M (Copernicus Anthropogenic Carbon Dioxide Monitoring) satellite constellation in 2026 is expected to provide high-resolution images of CO2 (carbon dioxide) column-averaged mole fractions (XCO2), opening up new possibilities. However, the inversion of future CO2 plumes from CO2M will encounter various obstacles. A challenge is the low CO2 plume signal-to-noise ratio due to the variability in the background and instrumental errors in satellite measurements. Moreover, uncertainties in the transport and dispersion processes further complicate the inversion task. To address these challenges, deep learning techniques, such as neural networks, offer promising solutions for retrieving emissions from plumes in XCO2 images. Deep learning models can be trained to identify emissions from plume dynamics simulated using a transport model. It then becomes possible to extract relevant information from new plumes and predict their emissions. In this paper, we develop a strategy employing convolutional neural networks (CNNs) to estimate the emission fluxes from a plume in a pseudo- XCO2 image. Our dataset used to train and test such methods includes pseudo-images based on simulations of hourly XCO2 , NO2 (nitrogen dioxide), and wind fields near various power plants in eastern Germany, tracing plumes from anthropogenic and biogenic sources. CNN models are trained to predict emissions from three power plants that exhibit diverse characteristics. The power plants used to assess the deep learning model's performance are not used to train the model. We find that the CNN model outperforms state-of-the-art plume inversion approaches, achieving highly accurate results with an absolute error about half of that of the cross-sectional flux method and an absolute relative error of ∼ 20 % when only the XCO2 and wind fields are used as inputs. Furthermore, we show that our estimations are only slightly affected by the absence of NO2 fields or a detection mechanism as additional information. Finally, interpretability techniques applied to our models confirm that the CNN automatically learns to identify the XCO2 plume and to assess emissions from the plume concentrations. These promising results suggest a high potential of CNNs in estimating local CO2 emissions from satellite images. [ABSTRACT FROM AUTHOR]

This paper introduces a novel nothing-on-road (NOR) bridge weigh-in-motion (BWIM) approach with deep learning (DL) and non-invasive ground-based radar (GBR) time-series data. BWIMs allow site-specific structural health monitoring (SHM) but are usually difficult to attach and maintain. GBR measures the bridge deflection contactless. In this study, GBR and an unmanned aerial vehicle (UAV) monitor a two-span bridge in Germany to gather ground-truth data. Based on the UAV data, we determine vehicle type, lane, locus, speed, axle count, and axle spacing for single-presence vehicle crossings. Since displacement is a global response, using peak detection like conventional strain-based BWIMs is challenging. Therefore, we investigate data-driven machine learning approaches to extract the vehicle configurations directly from the displacement data. Despite a small and imbalanced real-world dataset, the proposed approaches classify, e.g., the axle count for trucks with a balanced accuracy of 76.7% satisfyingly. Additionally, we demonstrate that, for the selected bridge, high-frequency vibrations can coincide with axles crossing the junction between the street and the bridge. We evaluate whether filtering approaches via bandpass filtering or wavelet transform can be exploited for axle count and axle spacing identification. Overall, we can show that GBR is a serious contender for BWIM systems. [ABSTRACT FROM AUTHOR]

The utilization of stationary underwater cameras is a modern and well-adapted approach to provide a continuous and cost-effective long-term solution to monitor underwater habitats of particular interest. A common goal of such monitoring systems is to gain better insight into the dynamics and condition of populations of various marine organisms, such as migratory or commercially relevant fish taxa. This paper describes a complete processing pipeline to automatically determine the abundance, type and estimate the size of biological taxa from stereoscopic video data captured by the stereo camera of a stationary Underwater Fish Observatory (UFO). A calibration of the recording system was carried out in situ and, afterward, validated using the synchronously recorded sonar data. The video data were recorded continuously for nearly one year in the Kiel Fjord, an inlet of the Baltic Sea in northern Germany. It shows underwater organisms in their natural behavior, as passive low-light cameras were used instead of active lighting to dampen attraction effects and allow for the least invasive recording possible. The recorded raw data are pre-filtered by an adaptive background estimation to extract sequences with activity, which are then processed by a deep detection network, i.e., Yolov5. This provides the location and type of organisms detected in each video frame of both cameras, which are used to calculate stereo correspondences following a basic matching scheme. In a subsequent step, the size and distance of the depicted organisms are approximated using the corner coordinates of the matched bounding boxes. The Yolov5 model employed in this study was trained on a novel dataset comprising 73,144 images and 92,899 bounding box annotations for 10 categories of marine animals. The model achieved a mean detection accuracy of 92.4%, a mean average precision (mAP) of 94.8% and an F1 score of 93%. [ABSTRACT FROM AUTHOR]

During recent years, maintaining scientific and medical databases has turned out to be a major challenge in the medical sector. The medical data regarding the patients comprise diverse diagnostic medical reports and features for such disease need to be recorded carefully for providing high-quality treatments. Therefore, this paper proposes a hybrid deep convolutional neural network (HDCNN)-based COOT approach to predict the risk of diseases. Initially, an improved crossover-based levy flight optimization algorithm (ICLFDO) algorithm is employed in selecting and processing the unstructured textual data. Then later, the HDCNN-COOT approach predicts the diseases more accurately. In addition to this, the classifier predicts whether the patient is at risk of disease in the future or not. The efficiency of the proposed model is evaluated by using a dataset obtained from University Hospital of Ludwig Maximilian University of Munich, Germany. The data collected in the data center include 29,477,035 data items from 36,082 patients. The proposed model is capable of using structured data and uses textual data of the patients. Finally, the higher classification accuracy and improved performance of the classifiers can be viewed using the experimental results conducted on five different datasets. [ABSTRACT FROM AUTHOR]

Copyright of ZFA: Zeitschrift für Allgemeinmedizin is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class ‘Artificial Intelligence in Medicine Challenge’, which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 ‘AF Classification from a Short Single Lead ECG Recording’. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1 scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge. [ABSTRACT FROM AUTHOR]

Evidence-based STI (science, technology, and innovation) policy making requires accurate indicators of innovation in order to promote economic growth. However, traditional indicators from patents and questionnaire-based surveys often lack coverage, granularity as well as timeliness and may involve high data collection costs, especially when conducted at a large scale. Consequently, they struggle to provide policy makers and scientists with the full picture of the current state of the innovation system. In this paper, we propose a first approach on generating web-based innovation indicators which may have the potential to overcome some of the shortcomings of traditional indicators. Specifically, we develop a method to identify product innovator firms at a large scale and very low costs. We use traditional firm-level indicators from a questionnaire-based innovation survey (German Community Innovation Survey) to train an artificial neural network classification model on labelled (product innovator/no product innovator) web texts of surveyed firms. Subsequently, we apply this classification model to the web texts of hundreds of thousands of firms in Germany to predict whether they are product innovators or not. We then compare these predictions to firm-level patent statistics, survey extrapolation benchmark data, and regional innovation indicators. The results show that our approach produces reliable predictions and has the potential to be a valuable and highly cost-efficient addition to the existing set of innovation indicators, especially due to its coverage and regional granularity., Competing Interests: The authors DL and JK founded and are employed by istari.ai. Istari.ai develops a “InnoProb” innovation prediction service based on the methodology presented in this article. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

The quantification of emissions of greenhouse gases and air pollutants through the inversion of plumes in satellite images remains a complex problem that current methods can only assess with significant uncertainties. The anticipated launch of the CO2M satellite constellation in 2026 is expected to provide high-resolution images of CO2 column-averaged mole fractions (XCO2), opening up new possibilities. However, the inversion of future CO2 plumes from CO2M will encounter various obstacles. A challenge is the CO2 plume low signal-to-noise ratio, due to the variability of the background and instrumental errors in satellite measurements. Moreover, uncertainties in the transport and dispersion processes further complicate the inversion task. To address these challenges, deep learning techniques, such as neural networks, offer promising solutions for retrieving emissions from plumes in XCO2 images. Deep learning models can be trained to identify emissions from plume dynamics simulated using a transport model. It then becomes possible to extract relevant information from new plumes and predict their emissions. In this paper, we employ convolutional neural networks (CNN) to estimate the emission fluxes from a plume in a pseudo XCO2 image. Our dataset used to train and test such methods includes pseudo images based on simulations of hourly XCO2, NO2 and wind fields near various power plants in Eastern Germany, tracing plumes from anthropogenic and biogenic sources. CNN models are trained to predict emissions from three power plants that exhibit diverse characteristics. The power plants used to assess the deep learning model's performance are not used to train the model. We find that the CNN model outperforms state of the art plume inversion approaches, achieving highly accurate results with an absolute error about half of that of the cross-sectional flux method. Furthermore, we show that our estimations are only slightly affected by the absence of NO2 fields or a detection mechanism as additional information. Finally, interpretability techniques applied to our models confirm that the CNN automatically learns to identify the XCO2 plume and to assess emissions from the plume concentrations. These promising results suggest a high potential of CNNs in estimating local CO2 emissions from satellite images. [ABSTRACT FROM AUTHOR]

The use of deep learning (DL) with convolutional neural networks (CNN) to monitor surface water can be a valuable supplement to costly and labour-intense standard gauging stations. This paper presents the application of a recent CNN semantic segmentation method (SegNet) to automatically segment river water in imagery acquired by RGB sensors. This approach can be used as a new supporting tool because there are only a few studies using DL techniques to monitor water resources. The study area is a medium-scale river (Wesenitz) located in the East of Germany. The captured images reflect different periods of the day over a period of approximately 50 days, allowing for the analysis of the river in different environmental conditions and situations. In the experiments, we evaluated the input image resolutions of 256 × 256 and 512 × 512 pixels to assess their influence on the performance of river segmentation. The performance of the CNN was measured with the pixel accuracy and IoU metrics revealing an accuracy of 98% and 97%, respectively, for both resolutions, indicating that our approach is efficient to segment water in RGB imagery. [ABSTRACT FROM AUTHOR]

Solar power integration has shown a significant growth in many power systems during the last decade. The intermittent nature of solar irradiance tends to vary the amount of solar power in the system and an accurate solar power forecasting method can be used to tackle this in power system planning and operation. In this paper, authors have proposed a generalized ensemble model integrating deep learning techniques to generate accurate solar power forecasts for 21 solar photovoltaic facilities located in Germany. Most important weather parameters for solar power generation are selected through a feature selection process. In addition, a weather classification approach is used to cluster the dataset and for each cluster, a separate ensemble algorithm is assigned. Finally, considering the prediction errors in each cluster, a novel ensemble model is developed. The proposed models are evaluated using root mean square error and results are compared with single machine learning techniques and available forecasting models in the literature. Compared to deep belief network, support vector regression and random forest regression models, the proposed ensemble model with cloud classification reduces RMSE error by 10.49%, 7.78%, and 7.95% respectively. Results show that the weather classification approach reduces the forecasting error by a considerable margin and the proposed ensemble model provides a better forecasting accuracy than single machine learning methods. [ABSTRACT FROM AUTHOR]

Dough fermentation plays an essential role in the bread production process, and its success is critical to producing high-quality products. In Germany, the number of stores per bakery chain has increased within the last years as well as the trend to finish the bakery products local at the stores. There is an unsatisfied demand for skilled workers, which leads to an increasing number of untrained and inexperienced employees at the stores. This paper proposes a method for the automatic monitoring of the fermentation process based on optical techniques. By using a combination of machine learning and superellipsoid model fitting, we have developed an instance segmentation and parameter estimation method for dough objects that are positioned inside a fermentation chamber. In our method we measure the given topography at discrete points in time using a movable laser sensor system that is located at the back of the fermentation chamber. By applying the superellipsoid model fitting method, we estimated the volume of each object and achieved results with a deviation of approximately 10% on average. Thereby, the volume gradient is monitored continuously and represents the progress of the fermentation state. Exploratory tests show the reliability and the potential of our method, which is particularly suitable for local stores but also for high volume production in bakery plants. [ABSTRACT FROM AUTHOR]

We present an approach for detecting early signs for upcoming forest damages by training a Convolutional Neural Network (CNN) for the pixel-wise prediction of the remaining life-time (RLT) of trees in forests based on Sentinel-2 imagery. We focus on a scenario in which reference data are only available for a related task, namely for a bi-temporal pixel-wise classification of forest degradation. This reference is used to train a CNN for the pixel-wise prediction of forest degradation. In this context, we propose a new sub-sampling-based approach for compensating the effects of a heavy class imbalance in the training data. Using the resulting classification model, we predict semi-labels for images of a Sentinel-2 time series, from which training data for a CNN designed to regress the RLT can be derived after some label cleansing. However, due to data gaps in the time series, e.g. caused by clouds, only intervals can be derived for the target variable to be regressed, and for some training pixels one of the interval limits may even be unknown. Consequently, we propose a new loss function for training a CNN for regressing the RLT that only requires the known interval limits. The method is evaluated on a data set in Germany, covering a time-span of 5 years. We show that the proposed sub-sampling strategy for dealing with strong label imbalance when training the classifier significantly reduces the training time compared to other approaches. We further show that our model predicts the RLT with a maximum error of two months for 80% of the forest pixels that die within one year from the acquisition date of the Sentinel-2 image. [ABSTRACT FROM AUTHOR]

• Soil reflectance composites were generated with Sentinel-2 L2A data. • A multi-channel CNN learning framework for soil organic carbon prediction is proposed. • A dual input deep learning architecture improves the predictions. • The framework produced results that can be interpreted. The Copernicus Sentinel-2 multispectral imagery data may be aggregated to extract large-scale, bare soil, reflectance composites, which enable soil mapping applications. In this paper, this approach was tested in the German federal state of Bavaria, to provide estimations for soil organic carbon (SOC). Different temporal ranges were considered for the generation of the composites, including multi-annual and seasonal ranges. A novel multi-channel convolutional neural network (CNN) is proposed. By leveraging the advantages of deep learning techniques, it utilizes complementary information from different spectral pre-treatment techniques. The SOC predictions indicated little dissimilarity amongst the different composites, with the best performance attained for the six-year composite containing only spring months (RMSE = 12.03 g C · kg−1, R2 = 0.64, RPIQ = 0.89). It has been demonstrated that these outcomes outperform other well-known machine learning techniques. An ablation analysis was accordingly performed to evaluate the interplay of the CNN's different components to disentangle the advantages of each aspect of the proposed framework. Finally, a DUal inPut deep LearnIng architecture, named DUPLICITE, is proposed, which concatenates deep spectral features derived from the CNN mentioned earlier, as well as topographical and environmental covariates through an artificial neural network (ANN) to exploit their complementarity. The proposed approach was demonstrated to provide an improvement in the overall prediction performance (RMSE = 11.60 gC · kg−1, R2 = 0.67, RPIQ = 0.92). [ABSTRACT FROM AUTHOR]

Renewable energy production is one of the most important strategies to reduce the emission of greenhouse gases. However, wind and solar energy especially depend on time-varying properties of the environment, such as weather. Hence, for the control and stabilization of electricity grids, the accurate forecasting of energy production from renewable energy sources is essential. This study provides an empirical comparison of the forecasting accuracy of electricity generation from renewable energy sources by different deep learning methods, including five different Transformer-based forecasting models based on weather data. The models are compared with the long short-term memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA) models as a baseline. The accuracy of these models is evaluated across diverse forecast periods, and the impact of utilizing selected weather data versus all available data on predictive performance is investigated. Distinct performance patterns emerge among the Transformer-based models, with Autoformer and FEDformer exhibiting suboptimal results for this task, especially when utilizing a comprehensive set of weather parameters. In contrast, the Informer model demonstrates superior predictive capabilities for onshore wind power and photovoltaic (PV) power production. The Informer model consistently performs well in predicting both onshore wind and PV energy. Notably, the LSTM model outperforms all other models across various categories. This research emphasizes the significance of selectively using weather parameters for improved performance compared to employing all parameters and a time reference. We show that the suitability and performance of a prediction model can vary significantly, depending on the specific forecasting task and the data that are provided to the model. [ABSTRACT FROM AUTHOR]

The application of machine learning (ML) including deep learning models in hydrogeology to model and predict groundwater level in monitoring wells has gained some traction in recent years. Currently, the dominant model class is the so-called single-well model, where one model is trained for each well separately. However, recent developments in neighbouring disciplines including hydrology (rainfall–runoff modelling) have shown that global models, being able to incorporate data of several wells, may have advantages. These models are often called "entity-aware models", as they usually rely on static data to differentiate the entities, i.e. groundwater wells in hydrogeology or catchments in surface hydrology. We test two kinds of static information to characterize the groundwater wells in a global, entity-aware deep learning model set-up: first, environmental features that are continuously available and thus theoretically enable spatial generalization (regionalization), and second, time-series features that are derived from the past time series at the respective well. Moreover, we test random integer features as entity information for comparison. We use a published dataset of 108 groundwater wells in Germany, and evaluate the performance of the models in terms of Nash–Sutcliffe efficiency (NSE) in an in-sample and an out-of-sample setting, representing temporal and spatial generalization. Our results show that entity-aware models work well with a mean performance of NSE >0.8 in an in-sample setting, thus being comparable to, or even outperforming, single-well models. However, they do not generalize well spatially in an out-of-sample setting (mean NSE <0.7 , i.e. lower than a global model without entity information). Strikingly, all model variants, regardless of the type of static features used, basically perform equally well both in- and out-of-sample. The conclusion is that the model in fact does not show entity awareness, but uses static features merely as unique identifiers, raising the research question of how to properly establish entity awareness in deep learning models. Potential future avenues lie in bigger datasets, as the relatively small number of wells in the dataset might not be enough to take full advantage of global models. Also, more research is needed to find meaningful static features for ML in hydrogeology. [ABSTRACT FROM AUTHOR]

The increase of electric vehicles (EVs) in the power system, in addition to environmental benefits, also has economic advantages. Charging parking lots can perform better economically through aggregators the benefits of participating in energy markets and developing different charging programs. The main challenge for participating in the electricity market for parking lots is the uncertainties in the behavior of EV owners and the day-ahead market (DAM) price. Therefore, this paper proposes a deep learning-based framework for day-ahead optimal charging scheduling, which is in three stages. In the first stage, the parameters of charging sessions are modeled using the proposed Copula generative adversarial network (CopulaGAN). In the second stage, the DAM price is forecasted using the time series multi-input nonlinear autoregressive neural network for 24 h ahead. In addition, in the proposed framework, the balancing energy market (BEM) is used to keep the charging power balance on the implementation day of the optimal charging program. In the third stage, optimal day-ahead EV scheduling is performed. The simulation is carried out using Grey Wolf Optimization (GWO) based on the Caltech charging sessions dataset and the Germany energy market dataset. The simulation results show that using the proposed deep learning framework reduces the charging cost for the parking lots compared to the fixed price approaches, the use of the BEM, the time of use (TOU) program, and using normal distribution modeling about 19.94 €, 159.97 €, 14.27 €, and 114.03 € respectively. • Presenting a deep learning framework for modeling day-ahead scheduling. • The proposed framework is applied to Caltech and the German energy market dataset. • Results show a 15% reduction in charging costs compared to conventional methods. [ABSTRACT FROM AUTHOR]

Detecting changes in soil micro-relief in farmland helps to understand degradation processes like sheet erosion. Using the high-resolution technique of terrestrial laser scanning (TLS), we generated point clouds of three 2 × 3 m plots on a weekly basis from May to mid-June in 2022 on cultivated farmland in Germany. Three well-known applications for eliminating vegetation points in the generated point cloud were tested: Cloth Simulation Filter (CSF) as a filtering method, three variants of CANUPO as a machine learning method, and ArcGIS PointCNN as a deep learning method, a sub-category of machine learning using deep neural networks. We assessed the methods with hard criteria such as F1 score, balanced accuracy, height differences, and their standard deviations to the reference surface, resulting in data gaps and robustness, and with soft criteria such as time-saving capacity, accessibility, and user knowledge. All algorithms showed a low performance at the initial measurement epoch, increasing with later epochs. While most of the results demonstrate a better performance of ArcGIS PointCNN, this algorithm revealed an exceptionally low performance in plot 1, which is describable by the generalization gap. Although CANUPO variants created the highest amount of data gaps, we recommend that CANUPO include colour values in combination with CSF. [ABSTRACT FROM AUTHOR]

The estimation of the electrical power output and energy yield of high concentration photovoltaic (HCPV) modules is a hard task because of the many parameters involved. In this work, we propose the usage of an Artificial Neural Networks (ANN) method to estimate the maximum power output of a FLATCON® CPV-module manufactured by Fraunhofer ISE. The advantage of the ANN is that it is a part of the Artificial Intelligence Deep Learning domain, which makes it easy to model complex systems. A detailed knowledge about the underlying module technology is not necessary. In this work, various meteorological parameters are tested as inputs of the ANN including spectral matching ratios for considering the spectral variation of the solar irradiance to evaluate the maximum power output of the HCPV module under study. Eleven scenarios considering different combinations of input parameters have been investigated. It is demonstrated that the ANN gives excellent results and allows for an accurate prediction of the HCPV module's instantaneous power output with only a few amount of data used on training the ANN. The model has been tested using the measured data set of a FLATCON® CPV-module located on the rooftop of the Fraunhofer ISE in Freiburg, Germany. The module has been electrically characterized outdoors in the period from April 2013 to April 2014. The accuracy of the proposed ANN approach was analyzed using this measurement data in combination with error metrics. It was found that the best agreement between the measured and the predicted maximum power output was achieved when using direct normal irradiance, wind speed, ambient temperature and spectral matching ratios as input. The normalized root mean square error for the maximum power output over one year is found to be between 2.2 and 4.6%. The deviation of the modelled energy yield to the measured one is in the range of 0.2–2.2%. • We use ANN method to predict the maximum power output of a FLATCON® CPV-module. • The accuracy of model used was validated through measurements and metrics errors. • The spectral effect of DNI through the use of SMRs has improved the model performance. • The knowledge of module technology is not necessary for performance prediction. • Only small amount of data are needed for performance prediction using this approach. Short Abstract: This paper uses the artificial Neural Networks model to estimate the electrical power and the energy yield of high concentration photovoltaic modules. The model has been verified using a whole year measurement data of power output of FLATCON CPV Module manufactured by Fraunhofer ISE, Germany. A best agreement between the measured and computed energy output was found trough the analysis of eleven scenarios where different input parameters were combined. [ABSTRACT FROM AUTHOR]

Today's methods for data acquisition usually involve a considerable amount of manual work and, depending on the level of detail, must find a compromise between accuracy and workload. As a result, various typologies of building stocks have been developed. These typologies provide engineers and architects with rough descriptions for classifying buildings into certain periods and construction types. However, real-world applications lack objective decision-making, as these classifications are usually conducted by manual investigations of buildings. To overcome this subjective approach and to ensure the reproducibility of data acquisition, this paper proposes an image-based classification using Deep Learning (DL) methods. We present the acquisition of ground truth and describe the training and testing routines on a dataset of 5,307 images obtained in the city of Weimar (located in the Free State of Thuringia, Germany), a mid-sized city representative of eastern Germany. All building images are linked to an existing building typology, allowing a classification of buildings in ten predefined and acknowledged periods. These periods are ranging from pre-1859 to post-2002. As a benchmark, an expert human baseline is acquired, showing a lower prediction accuracy than the results obtained by DL methods. Our results highlight the potential for automation in image analysis and beneficial impacts for Building Energy Modeling (BEM) on urban scale. Thus, a trustworthy data acquisition regarding the building age holds benefits for various stakeholders in BEM (engineers, architects, policymakers as well as customers). • Two CNN-architectures (ResNet50 and AlexNet) are used for image-classification. • Extraction of annotated image-patches facilitates an enhancement of the image set. • Quantity of training images and applied optimizer significantly influence results. • CNN-based estimations successfully linked to existing and popular building typology. • Accuracies of CNN-based estimation of building age outperform the human baseline. [ABSTRACT FROM AUTHOR]

Our subject is a new catalogue of radar-based heavy rainfall events (CatRaRE) over Germany and how it relates to the concurrent atmospheric circulation. We classify daily ERA5 fields of convective indices according to CatRaRE, using an array of 13 statistical methods, consisting of 4 conventional ("shallow") and 9 more recent deep machine learning (DL) algorithms; the classifiers are then applied to corresponding fields of simulated present and future atmospheres from the Coordinated Regional Climate Downscaling Experiment (CORDEX) project. The inherent uncertainty of the DL results from the stochastic nature of their optimization is addressed by employing an ensemble approach using 20 runs for each network. The shallow random forest method performs best with an equitable threat score (ETS) around 0.52, followed by the DL networks ALL-CNN and ResNet with an ETS near 0.48. Their success can be understood as a result of conceptual simplicity and parametric parsimony, which obviously best fits the relatively simple classification task. It is found that, on summer days, CatRaRE-convective atmospheres over Germany occur with a probability of about 0.5. This probability is projected to increase, regardless of method, both in ERA5-reanalyzed and CORDEX-simulated atmospheres: for the historical period we find a centennial increase of about 0.2 and for the future period one of slightly below 0.1. [ABSTRACT FROM AUTHOR]

Monkeypox is a double-stranded DNA virus with an envelope and is a member of the Poxviridae family's Orthopoxvirus genus. This virus can transmit from human to human through direct contact with respiratory secretions, infected animals and humans, or contaminated objects and causing mutations in the human body. In May 2022, several monkeypox affected cases were found in many countries. Because of its transmitting characteristics, on July 23, 2022, a nationwide public health emergency was proclaimed by WHO due to the monkeypox virus. This study analyzed the gene mutation rate that is collected from the most recent NCBI monkeypox dataset. The collected data is prepared to independently identify the nucleotide and codon mutation. Additionally, depending on the size and availability of the gene dataset, the computed mutation rate is split into three categories: Canada, Germany, and the rest of the world. In this study, the genome mutation rate of the monkeypox virus is predicted using a deep learning-based Long Short-Term Memory (LSTM) model and compared with Gated Recurrent Unit (GRU) model. The LSTM model shows "Root Mean Square Error" (RMSE) values of 0.09 and 0.08 for testing and training, respectively. Using this time series analysis method, the prospective mutation rate of the 50th patient has been predicted. Note that this is a new report on the monkeypox gene mutation. It is found that the nucleotide mutation rates are decreasing, and the balance between bi-directional rates are maintained. [ABSTRACT FROM AUTHOR]

Abstract Background Several recent publications have demonstrated the use of convolutional neural networks to classify images of melanoma at par with board-certified dermatologists. However, the non-availability of a public human benchmark restricts the comparability of the performance of these algorithms and thereby the technical progress in this field. Methods An electronic questionnaire was sent to dermatologists at 12 German university hospitals. Each questionnaire comprised 100 dermoscopic and 100 clinical images (80 nevi images and 20 biopsy-verified melanoma images, each), all open-source. The questionnaire recorded factors such as the years of experience in dermatology, performed skin checks, age, sex and the rank within the university hospital or the status as resident physician. For each image, the dermatologists were asked to provide a management decision (treat/biopsy lesion or reassure the patient). Main outcome measures were sensitivity, specificity and the receiver operating characteristics (ROC). Results Total 157 dermatologists assessed all 100 dermoscopic images with an overall sensitivity of 74.1%, specificity of 60.0% and an ROC of 0.67 (range = 0.538–0.769); 145 dermatologists assessed all 100 clinical images with an overall sensitivity of 89.4%, specificity of 64.4% and an ROC of 0.769 (range = 0.613–0.9). Results between test-sets were significantly different (P < 0.05) confirming the need for a standardised benchmark. Conclusions We present the first public melanoma classification benchmark for both non-dermoscopic and dermoscopic images for comparing artificial intelligence algorithms with diagnostic performance of 145 or 157 dermatologists. Melanoma Classification Benchmark should be considered as a reference standard for white-skinned Western populations in the field of binary algorithmic melanoma classification. Highlights • This paper provides the first open access melanoma classification benchmark for both non-dermoscopic and dermoscopic images. • Algorithms can now be easily compared to the performance of dermatologists in terms of sensitivity, specificity and ROC. • The melanoma benchmark allows comparability between algorithms of different publications and provides a new reference standard. [ABSTRACT FROM AUTHOR]

The used car market has a high global economic importance, with more than 35 million cars sold yearly. Accurately predicting prices is a crucial task for both buyers and sellers to facilitate informed decisions in terms of opportunities or potential problems. Although various machine learning techniques have been applied to create robust prediction models, a comprehensive approach has yet to be studied. This research introduced two datasets from different markets, one with over 300,000 entries from Germany to serve as a training basis for deep prediction models and a second dataset from Romania containing more than 15,000 car quotes used mainly to observe local traits. As such, we included extensive cross-market analyses by comparing the emerging Romanian market versus one of the world's largest and most developed car markets, Germany. Our study used several neural network architectures that captured complex relationships between car model features, individual add-ons, and visual features to predict used car prices accurately. Our models achieved a high R2 score exceeding 0.95 on both datasets, indicating their effectiveness in estimating used car prices. Moreover, we experimented with advanced convolutional architectures to predict car prices based solely on visual features extracted from car images. This approach exhibited transfer-learning capabilities, leading to improved prediction accuracy, especially since the Romanian training dataset was limited. Our experiments highlighted the most important factors influencing the price, while our findings have practical implications for buyers and sellers in assessing the value of vehicles. At the same time, the insights gained from this study enable informed decision making and provide valuable guidance in the used car market. [ABSTRACT FROM AUTHOR]

In colorectal cancer (CRC), artificial intelligence (AI) can alleviate the laborious task of characterization and reporting on resected biopsies, including polyps, the numbers of which are increasing as a result of CRC population screening programs ongoing in many countries all around the globe. Here, we present an approach to address two major challenges in the automated assessment of CRC histopathology whole-slide images. We present an AI-based method to segment multiple ( n = 14 ) tissue compartments in the H &E-stained whole-slide image, which provides a different, more perceptible picture of tissue morphology and composition. We test and compare a panel of state-of-the-art loss functions available for segmentation models, and provide indications about their use in histopathology image segmentation, based on the analysis of (a) a multi-centric cohort of CRC cases from five medical centers in the Netherlands and Germany, and (b) two publicly available datasets on segmentation in CRC. We used the best performing AI model as the basis for a computer-aided diagnosis system that classifies colon biopsies into four main categories that are relevant pathologically. We report the performance of this system on an independent cohort of more than 1000 patients. The results show that with a good segmentation network as a base, a tool can be developed which can support pathologists in the risk stratification of colorectal cancer patients, among other possible uses. We have made the segmentation model available for research use on https://grand-challenge.org/algorithms/colon-tissue-segmentation/. [ABSTRACT FROM AUTHOR]

• This paper explores probabilistic extensions to Deep Learning algorithms and their application on energy time series forecasting. • The methods tested are concrete Dropouts, deep Ensembles, bayesian neural Networks, deep gaussian Processes, and functional neural processes. • The methods are evaluated in terms of calibration, sharpness, and how well they indicate a lack of knowledge (Epistemic Uncertainty). • Good epistemic uncertainty estimates were given using functional neural Processes, deep Ensembles, and deep gaussian processes methods, while concrete dropouts and bayesian neural networks needed tunning for better performance. • The application of the methods was feasible for energy time series forecasting, and they produced good estimates of their confidence in a forecast. Deep Learning methods are widely successful and continue to be applied in new fields, including forecasting for energy time series. However, they lack an indication of their confidence in predictions, which helps evaluate, interpret, and improve the forecasting. This paper explores probabilistic extensions to Deep Learning algorithms and their application on energy time series forecasting. The methods tested are Concrete Dropouts, Deep Ensembles, Bayesian Neural Networks, Deep Gaussian Processes, and Functional Neural Processes. For evaluation, two load forecasting scenarios are considered: 1-hour-ahead and 24-hour-ahead load forecasting. The methods are evaluated in terms of calibration, sharpness, and how well they indicate a lack of knowledge (Epistemic Uncertainty). As a reference, simple Neural Network and Quantile Regression models are used. Also, the ARIMA model and Persistence model are implemented to compare the results. Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and Continuous Ranked Probability Score (CRPS) are computed to measure the error performance. Based on endogenous load time series in Germany, the results showed that Concrete Dropout, Deep Ensembles, and Bayesian Neural Networks performed similarly well and better than the reference methods. They also indicated that the simpler Concrete Dropout and Deep Ensembles have an advantage in both speed and convergence time. Good Epistemic Uncertainty estimates were given using Functional Neural Processes, Deep Ensembles, and Deep Gaussian Processes methods, while Concrete dropouts and Bayesian Neural Networks needed tunning for better performance. The application of the methods was feasible for energy time series forecasting, and they produced good estimates of their confidence in a forecast. [ABSTRACT FROM AUTHOR]

In this paper, we propose a Stack Auto-encoder (SAE)-Driven and Semi-Supervised (SSL)-Based Deep Neural Network (DNN) to extract buildings from relatively low-cost satellite near infrared images. The novelty of our scheme is that we employ only an extremely small portion of labeled data for training the deep model which constitutes less than 0.08% of the total data. This way, we significantly reduce the manual effort needed to complete an annotation process, and thus the time required for creating a reliable labeled dataset. On the contrary, we apply novel semi-supervised techniques to estimate soft labels (targets) of the vast amount of existing unlabeled data and then we utilize these soft estimates to improve model training. Overall, four SSL schemes are employed, the Anchor Graph, the Safe Semi-Supervised Regression (SAFER), the Squared-loss Mutual Information Regularization (SMIR), and an equal importance Weighted Average of them (WeiAve). To retain only the most meaning information of the input data, labeled and unlabeled ones, we also employ a Stack Autoencoder (SAE) trained under an unsupervised manner. This way, we handle noise in the input signals, attributed to dimensionality redundancy, without sacrificing meaningful information. Experimental results on the benchmarked dataset of Vaihingen city in Germany indicate that our approach outperforms all state-of-the-art methods in the field using the same type of color orthoimages, though the fact that a limited dataset is utilized (10 times less data or better, compared to other approaches), while our performance is close to the one achieved by high expensive and much more precise input information like the one derived from Light Detection and Ranging (LiDAR) sensors. In addition, the proposed approach can be easily expanded to handle any number of classes, including buildings, vegetation, and ground. [ABSTRACT FROM AUTHOR]

An ongoing outbreak of monkeypox virus (MPXV) was first reported in the United Kingdom on 6 May 2022. As of 17 November, there had been a total of 80 221 confirmed MPXV cases in over 110 countries. Based on data reported between 6 May and 30 June 2022 in the United Kingdom, Spain, and Germany, we applied a deep learning approach using convolutional neural networks to evaluate the parameters of the 2022 MPXV outbreak. The basic reproduction number (R0) of MPXV was estimated to be 2.32 in the United Kingdom, which indicates the active diffusion of MPXV since the beginning of the outbreak. The data from Spain and Germany produced higher median R0 values of 2.42 and 2.88, respectively. Importantly, the estimated R0 of MPXV in the three countries tends to the previously calculated R0 of smallpox (3.50 to 6.00). Furthermore, the incubation (1/ε) and infectious (1/γ) period was predicted between 9 and 10 days and 4−5 days, respectively. The R0 value derived from MPXV is consistent with the significantly increasing number of cases, indicating the risk of a rapid spread of MPXV worldwide, which would provide important insights for the prevention and control of MPXV epidemic. [ABSTRACT FROM AUTHOR]

For load forecasting, numerous machine learning (ML) approaches have been published. Besides fully connected feedforward neural networks (FFNNs), also called multilayer perceptron, more advanced ML approaches like deep, recurrent or convolutional neural networks or ensemble methods have been applied. However, evaluating the added benefit by novel approaches is difficult. Statistical or rule-based methods constitute a too low benchmark. FFNNs need extensive tuning due to their manifold design choices. To address this issue, a structured, comprehensible five-step FFNN model creation methodology is presented, which constitutes of initial model creation, internal parameter selection, feature engineering, architecture tuning and final model creation. The methodology is then applied to forecast real world heat load data of a hospital in Germany. The forecast constitutes of 192 values (upcoming 48 h in 15 min resolution) and is composed of a multi-model univariate forecasting strategy, with three test models developed at first. As a result, the test models show great similarities which simplifies creation of the remaining models. A performance increase of up to 18% between initial and final models points out the importance of model tuning. As a conclusion, comprehensible model tuning is vital to use FFNN models as benchmark. The effort needed can be reduced by the experience gained through repeated application of the presented methodology. [ABSTRACT FROM AUTHOR]

Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is with a colonoscopy. During this procedure, the gastroenterologist searches for polyps. However, there is a potential risk of polyps being missed by the gastroenterologist. Automated detection of polyps helps to assist the gastroenterologist during a colonoscopy. There are already publications examining the problem of polyp detection in the literature. Nevertheless, most of these systems are only used in the research context and are not implemented for clinical application. Therefore, we introduce the first fully open-source automated polyp-detection system scoring best on current benchmark data and implementing it ready for clinical application. To create the polyp-detection system (ENDOMIND-Advanced), we combined our own collected data from different hospitals and practices in Germany with open-source datasets to create a dataset with over 500,000 annotated images. ENDOMIND-Advanced leverages a post-processing technique based on video detection to work in real-time with a stream of images. It is integrated into a prototype ready for application in clinical interventions. We achieve better performance compared to the best system in the literature and score a F1-score of 90.24% on the open-source CVC-VideoClinicDB benchmark. [ABSTRACT FROM AUTHOR]

Benefiting from the high cadence and spatial resolution of the new generation of Earth observation satellites, remote sensing technology is allowing us to derive more valuable information for the agricultural sector. Crop classification is one of the fundamental information derivatives from Earth observation data researchers used for food security, crop monitoring, and economic assessment. The robustness of a crop classification model to variations in environmental and management conditions due to time and location is one of the crucial requirements. To achieve this, we developed a novel self-supervised method using the advantage of unlabeled samples and transformer architectures. We used six different areas in Germany and four years to evaluate the robustness of the model. Our experiments showed that self-supervised deep learning methods could provide a significant advantage in handling these variations. In some cases, we observed around 30 percentage points improvements in F1-score performance compared to a Random Forest based model. [ABSTRACT FROM AUTHOR]

Tropospheric ozone is a secondary air pollutant that is harmful to living beings and crops. Predicting ozone concentrations at specific locations is thus important to initiate protection measures, i.e. emission reductions or warnings to the population. Ozone levels at specific locations result from emission and sink processes, mixing and chemical transformation along an air parcel's trajectory. Current ozone forecasting systems generally rely on computationally expensive chemistry transport models (CTMs). However, recently several studies have demonstrated the potential of deep learning for this task. While a few of these studies were trained on gridded model data, most efforts focus on forecasting time series from individual measurement locations. In this study, we present a hybrid approach which is based on time-series forecasting (up to 4 d) but uses spatially aggregated meteorological and chemical data from upstream wind sectors to represent some aspects of the chemical history of air parcels arriving at the measurement location. To demonstrate the value of this additional information, we extracted pseudo-observation data for Germany from a CTM to avoid extra complications with irregularly spaced and missing data. However, our method can be extended so that it can be applied to observational time series. Using one upstream sector alone improves the forecasts by 10 % during all 4 d, while the use of three sectors improves the mean squared error (MSE) skill score by 14 % during the first 2 d of the prediction but depends on the upstream wind direction. Our method shows its best performance in the northern half of Germany for the first 2 prediction days. Based on the data's seasonality and simulation period, we shed some light on our models' open challenges with (i) spatial structures in terms of decreasing skill scores from the northern German plain to the mountainous south and (ii) concept drifts related to an unusually cold winter season. Here we expect that the inclusion of explainable artificial intelligence methods could reveal additional insights in future versions of our model. [ABSTRACT FROM AUTHOR]

Storms can cause significant damage to forest areas, affecting biodiversity and infrastructure and leading to economic loss. Thus, rapid detection and mapping of windthrows are crucially important for forest management. Recent advances in computer vision have led to highly-accurate image classification algorithms such as Convolutional Neural Network (CNN) architectures. In this study, we tested and implemented an algorithm based on CNNs in an ArcGIS environment for automatic detection and mapping of damaged areas. The algorithm was trained and tested on a forest area in Bavaria, Germany.. It is a based on a modified U-Net architecture that was optimized for the pixelwise classification of multispectral aerial remote sensing data. The neural network was trained on labeled damaged areas from after-storm aerial orthophotos of a ca. 109 k m 2 forest area with RGB and NIR bands and 0.2-m spatial resolution. Around 10 7 pixels of labeled data were used in the process. Once the network is trained, predictions on further datasets can be computed within seconds, depending on the size of the input raster and the computational power used. The overall accuracy on our test dataset was 92 % . During visual validation, labeling errors were found in the reference data that somewhat biased the results because the algorithm in some instance performed better than the human labeling procedure, while missing areas affected by shadows. Our results are very good in terms of precision, and the methods introduced in this paper have several additional advantages compared to traditional methods: CNNs automatically detect high- and low-level features in the data, leading to high classification accuracies, while only one after-storm image is needed in comparison to two images for approaches based on change detection. Furthermore, flight parameters do not affect the results in the same way as for approaches that require DSMs and DTMs as the classification is only based on the image data themselves, and errors occurring in the computation of DSMs and DTMs do not affect the results with respect to the z component. The integration into the ArcGIS Platform allows a streamlined workflow for forest management, as the results can be accessed by mobile devices in the field to allow for high-accuracy ground-truthing and additional mapping that can be synchronized back into the database. Our results and the provided automatic workflow highlight the potential of deep learning on high-resolution imagery and GIS for fast and efficient post-disaster damage assessment as a first step of disaster management. [ABSTRACT FROM AUTHOR]

In recent years, wind power has emerged as an important source of renewable energy. When onshore and offshore wind farm regions are connected to the grid for power generation, consistent multi-location short-term wind power predictions are extremely valuable in terms of assuring the power system's safety, sustainability, and economic operation. An abrupt variation in wind power generation influences the efficiency of the regional power grid. This makes accurate short-term forecasting essential for high-level planning and scheduling of power grids. To address the issue, this paper presents two variants of recurrent neural networks (RNN): gated recurrent unit (GRU) and long short-term memory (LSTM) models considering substantially better prediction accuracy to forecast a country-wide (Germany) wind power data for daily (t + 1), and multi-step (t + 3, t + 5 , and t + 12) hours ahead. In addition, wind velocities [m/s] measured at heights of 2, 10, and 50-m (above ground level) are exploited as an essential characteristic among the available input variables and evaluated each feature subset based on four training divisions (80-20%, 70-30%, 60-40%, and 50-50%) and compared the results with ARIMA and SVR approaches in the literature. The findings reveal that the RNN-GRU model not only can achieve higher predicting accuracy but also has a faster learning speed over long sequences. • Multivariate analysis of hourly wind power predictions is carried out. • The prediction model integrated RNN-GRU and RNN-LSTM. • A countrywide dataset for Germany in 2016 is employed for the forecast. • Accuracy and computational efficiency were used to evaluate the performance of proposed time series models. • Comparison with reported models and ablation strategies supports the design of individual modules in RNN-GRU. • RNN-GRU with multi-step/multi-location demonstrated potential for large-scale wind farm applications. [ABSTRACT FROM AUTHOR]

The energy generated by a solar photovoltaic (PV) system depends on uncontrollable factors, including weather conditions and solar irradiation, which leads to uncertainty in the power output. Forecast PV power generation is vital to improve grid stability and balance the energy supply and demand. This study aims to predict hourly day-ahead PV power generation by applying Temporal Fusion Transformer (TFT), a new attention-based architecture that incorporates an interpretable explanation of temporal dynamics and high-performance forecasting over multiple horizons. The proposed forecasting model has been trained and tested using data from six different facilities located in Germany and Australia. The results have been compared with other algorithms like Auto Regressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP), and Extreme Gradient Boosting (XGBoost), using statistical error indicators. The use of TFT has been shown to be more accurate than the rest of the algorithms to forecast PV generation in the aforementioned facilities. [ABSTRACT FROM AUTHOR]

Germany is the largest market for natural gas in the European Union, with an annual consumption of approx. 95 billion cubic meters. The German high‐pressure gas pipeline network's length is roughly 40 000 km, which enables highly fluctuating quantities of gas to be transported safely over long distances. Considering that similar amounts of gas are also transshipped through Germany to other EU states, it is clear that Germany's gas transport system is essential to the European energy supply. Since the average velocity of gas in a pipeline is only 25 km/h, an adequate high‐precision, high‐frequency forecasting of supply and demand is crucial for efficient control and operation of such a transmission network. We propose a deep learning model based on spatio‐temporal convolutional neural networks (DLST) to tackle the problem of gas flow forecasting in a complex high‐pressure transmission network. Experiments show that our model effectively captures comprehensive spatio‐temporal correlations through modeling gas networks and consistently outperforms state‐of‐the‐art benchmarks on real‐world data sets by at least 15%. The results demonstrate that the proposed model can deal with complex nonlinear gas network flow forecasting with high accuracy and effectiveness. [ABSTRACT FROM AUTHOR]

In this study we investigate how climate change will directly influence the groundwater resources in Germany during the 21st century. We apply a machine learning groundwater level prediction approach based on convolutional neural networks to 118 sites well distributed over Germany to assess the groundwater level development under different RCP scenarios (2.6, 4.5, 8.5). We consider only direct meteorological inputs, while highly uncertain anthropogenic factors such as groundwater extractions are excluded. While less pronounced and fewer significant trends can be found under RCP2.6 and RCP4.5, we detect significantly declining trends of groundwater levels for most of the sites under RCP8.5, revealing a spatial pattern of stronger decreases, especially in the northern and eastern part of Germany, emphasizing already existing decreasing trends in these regions. We can further show an increased variability and longer periods of low groundwater levels during the annual cycle towards the end of the century. Future groundwater levels in Germany are expected to decrease considerably under the influence of changing climate, exacerbating the trends and patterns already occurring. Simulations also show substantially reduced effects under stringent mitigation scenarios. [ABSTRACT FROM AUTHOR]

Crop yield forecasting depends on many interactive factors, including crop genotype, weather, soil, and management practices. This study analyzes the performance of machine learning and deep learning methods for winter wheat yield prediction using an extensive dataset of weather, soil, and crop phenology variables in 271 counties across Germany from 1999 to 2019. We proposed a Convolutional Neural Network (CNN) model, which uses a 1-dimensional convolution operation to capture the time dependencies of environmental variables. We used eight supervised machine learning models as baselines and evaluated their predictive performance using RMSE, MAE, and correlation coefficient metrics to benchmark the yield prediction results. Our findings suggested that nonlinear models such as the proposed CNN, Deep Neural Network (DNN), and XGBoost were more effective in understanding the relationship between the crop yield and input data compared to the linear models. Our proposed CNN model outperformed all other baseline models used for winter wheat yield prediction (7 to 14% lower RMSE, 3 to 15% lower MAE, and 4 to 50% higher correlation coefficient than the best performing baseline across test data). We aggregated soil moisture and meteorological features at the weekly resolution to address the seasonality of the data. We also moved beyond prediction and interpreted the outputs of our proposed CNN model using SHAP and force plots which provided key insights in explaining the yield prediction results (importance of variables by time). We found DUL, wind speed at week ten, and radiation amount at week seven as the most critical features in winter wheat yield prediction. [ABSTRACT FROM AUTHOR]

The current reliability of species identifications by the Nature Identification API (NIA) of the app ObsIdentify is tested with a Coleoptera (Insecta) sample set from Germany. Seventy-five photographic beetle records taken with a smartphone camera under "average user" conditions are analysed in terms of correctness of the app's identification result on various taxonomic levels, the displayed confidence level of the identification and the time until validation of the results. More than 60% of samples were identified correctly at the species level, but only 53% were validated within a month. The mechanisms by which users can upload pictures of their observations to be identified by the artificial intelligence and the validation process by experts are briefly explained. Regional specifics and further opportunities for data usage as well as currently existing problems are discussed and improvements are suggested. The expert validation of records is identified as a huge quality advantage of the Obs-Services. They are generally found to be a promising tool for lay people and professional institutions, despite still existing deficiencies such as identification failure in mutilated specimens, cryptic and rare species, doubtful species rarity ratings as well as the still insufficient capacity of validation. Experts and institutions are encouraged to volunteer as validators and collaborators. [ABSTRACT FROM AUTHOR]

Load forecasting is of crucial importance for operations of electric power systems. In recent years, deep learning based methods are emerging for load forecasting because their strong nonlinear approximation capabilities can provide more forecasting precision than conventional statistical methods. However, they usually suffer from some problems, e.g., the gradient vanishment and over-fitting. In order to address these problems, an unshared convolution based deep learning model with densely connected network is proposed. In this model, the backbone is the unshared convolutional neural network and a densely connected structure is adopted, which could alleviate the gradient vanishment. What is more, we use a regularization method named clipped $L_2$ -norm to overcome over-fitting, and design a trend decomposition strategy to address the possible distribution differences between the training and validation data. Finally, we conduct five case studies to verify the outperformance of our proposed deep learning model for deterministic and interval load forecasting. Two high-voltage and an medium-voltage real load datasets from Australia, Germany and America are used for model training and validation, respectively. Results show that the proposed model can achieve higher load forecasting accuracy, compared with other existing methods including the popular conventional methods such as naive forecast and generalized additive model, and deep learning methods, e.g., long short-term memory network, convolutional neural network, fully connected network, etc. [ABSTRACT FROM AUTHOR]

Background: Accurate and robust pathological image analysis for colorectal cancer (CRC) diagnosis is time-consuming and knowledge-intensive, but is essential for CRC patients' treatment. The current heavy workload of pathologists in clinics/hospitals may easily lead to unconscious misdiagnosis of CRC based on daily image analyses.Methods: Based on a state-of-the-art transfer-learned deep convolutional neural network in artificial intelligence (AI), we proposed a novel patch aggregation strategy for clinic CRC diagnosis using weakly labeled pathological whole-slide image (WSI) patches. This approach was trained and validated using an unprecedented and enormously large number of 170,099 patches, > 14,680 WSIs, from > 9631 subjects that covered diverse and representative clinical cases from multi-independent-sources across China, the USA, and Germany.Results: Our innovative AI tool consistently and nearly perfectly agreed with (average Kappa statistic 0.896) and even often better than most of the experienced expert pathologists when tested in diagnosing CRC WSIs from multicenters. The average area under the receiver operating characteristics curve (AUC) of AI was greater than that of the pathologists (0.988 vs 0.970) and achieved the best performance among the application of other AI methods to CRC diagnosis. Our AI-generated heatmap highlights the image regions of cancer tissue/cells.Conclusions: This first-ever generalizable AI system can handle large amounts of WSIs consistently and robustly without potential bias due to fatigue commonly experienced by clinical pathologists. It will drastically alleviate the heavy clinical burden of daily pathology diagnosis and improve the treatment for CRC patients. This tool is generalizable to other cancer diagnosis based on image recognition. [ABSTRACT FROM AUTHOR]

Objective: To assess the utility of machine learning algorithms for automatically estimating prognosis in patients with repaired tetralogy of Fallot (ToF) using cardiac magnetic resonance (CMR).Methods: We included 372 patients with ToF who had undergone CMR imaging as part of a nationwide prospective study. Cine loops were retrieved and subjected to automatic deep learning (DL)-based image analysis, trained on independent, local CMR data, to derive measures of cardiac dimensions and function. This information was combined with established clinical parameters and ECG markers of prognosis.Results: Over a median follow-up period of 10 years, 23 patients experienced an endpoint of death/aborted cardiac arrest or documented ventricular tachycardia (defined as >3 documented consecutive ventricular beats). On univariate Cox analysis, various DL parameters, including right atrial median area (HR 1.11/cm², p=0.003) and right ventricular long-axis strain (HR 0.80/%, p=0.009) emerged as significant predictors of outcome. DL parameters were related to adverse outcome independently of left and right ventricular ejection fraction and peak oxygen uptake (p<0.05 for all). A composite score of enlarged right atrial area and depressed right ventricular longitudinal function identified a ToF subgroup at significantly increased risk of adverse outcome (HR 2.1/unit, p=0.007).Conclusions: We present data on the utility of machine learning algorithms trained on external imaging datasets to automatically estimate prognosis in patients with ToF. Due to the automated analysis process these two-dimensional-based algorithms may serve as surrogates for labour-intensive manually attained imaging parameters in patients with ToF. [ABSTRACT FROM AUTHOR]

Deep learning (DL)—in particular convolutional neural networks (CNN)—methods are widely spread in object detection and recognition of remote sensing images. In the domain of DL, there is a need for large numbers of training samples. These samples are mostly generated based on manual identification. Identifying and labelling these objects is very time-consuming. The developed approach proposes a partially automated procedure for the sample creation and avoids manual labelling of rooftop photovoltaic (PV) systems. By combining address data of existing rooftop PV systems from the German Plant Register, the Georeferenced Address Data and the Official House Surroundings Germany, a partially automated generation of training samples is achieved. Using a selection of 100,000 automatically generated samples, a network using a RetinaNet-based architecture combining ResNet101, a feature pyramid network, a classification and a regression network is trained, applied on a large area and post-filtered by intersection with additional automatically identified locations of existing rooftop PV systems. Based on a proof-of-concept application, a second network is trained with the filtered selection of approximately 51,000 training samples. In two independent test applications using high-resolution aerial images of Saarland in Germany, buildings with PV systems are detected with a precision of at least 92.77 and a recall of 84.47. [ABSTRACT FROM AUTHOR]

Energy system modeling is essential in analyzing present and future system configurations motivated by the energy transition. Energy models need various input data sets at different scales, including detailed information about energy generation and transport infrastructure. However, accessing such data sets is not straightforward and often restricted, especially for energy infrastructure data. We present a detection model for the automatic recognition of pipeline pathways using a Convolutional Neural Network (CNN) to address this lack of energy infrastructure data sets. The model was trained with historical low-resolution satellite images of the construction phase of British gas transport pipelines, made with the Landsat 5 Thematic Mapper instrument. The satellite images have been automatically labeled with the help of high-resolution pipeline route data provided by the respective Transmission System Operator (TSO). We have used data augmentation on the training data and trained our model with four different initial learning rates. The models trained with the different learning rates have been validated with 5-fold cross-validation using the Intersection over Union (IoU) metric. We show that our model can reliably identify pipeline pathways despite the comparably low resolution of the used satellite images. Further, we have successfully tested the model's capability in other geographic regions by deploying satellite images of the NEL pipeline in Northern Germany. [ABSTRACT FROM AUTHOR]

An accurate understanding of urban objects is critical for urban modeling, intelligent infrastructure planning and city management. The semantic segmentation of light detection and ranging (LiDAR) point clouds is a fundamental approach for urban scene analysis. Over the last years, several methods have been developed to segment urban furniture with point clouds. However, the traditional processing of large amounts of spatial data has become increasingly costly, both time-wise and financially. Recently, deep learning (DL) techniques have been increasingly used for 3D segmentation tasks. Yet, most of these deep neural networks (DNNs) were conducted on benchmarks. It is, therefore, arguable whether DL approaches can achieve the state-of-the-art performance of 3D point clouds segmentation in real-life scenarios. In this research, we apply an adapted DNN (ARandLA-Net) to directly process large-scale point clouds. In particular, we develop a new paradigm for training and validation, which presents a typical urban scene in central Europe (Munzingen, Freiburg, Baden-Württemberg, Germany). Our dataset consists of nearly 390 million dense points acquired by Mobile Laser Scanning (MLS), which has a rather larger quantity of sample points in comparison to existing datasets and includes meaningful object categories that are particular to applications for smart cities and urban planning. We further assess the DNN on our dataset and investigate a number of key challenges from varying aspects, such as data preparation strategies, the advantage of color information and the unbalanced class distribution in the real world. The final segmentation model achieved a mean Intersection-over-Union (mIoU) score of 54.4% and an overall accuracy score of 83.9%. Our experiments indicated that different data preparation strategies influenced the model performance. Additional RGB information yielded an approximately 4% higher mIoU score. Our results also demonstrate that the use of weighted cross-entropy with inverse square root frequency loss led to better segmentation performance than when other losses were considered. [ABSTRACT FROM AUTHOR]

Undocumented building constructions are buildings or stories that were built years ago, but are missing in the official digital cadastral maps (DFK). The detection of undocumented building constructions is essential to urban planning and monitoring. The state of Bavaria, Germany, uses two semi-automatic detection methods for this task that suffer from a high false alarm rate. To solve this problem, we propose a novel framework to detect undocumented building constructions using a Convolutional Neural Network (CNN) and official geodata, including high resolution optical data and the Normalized Digital Surface Model (nDSM). More specifically, an undocumented building pixel is labeled as "building" by the CNN but does not overlap with a building polygon of the DFK. The class of old or new undocumented building can be further separated when a Temporal Digital Surface Model (tDSM) is introduced in the stage of decision fusion. In a further step, undocumented story construction is detected as the pixels that are "building" in both DFK and predicted results from CNN, but shows a height deviation from the tDSM. By doing so, we have produced a seamless map of undocumented building constructions for one-quarter of the state of Bavaria, Germany at a spatial resolution of 0.4 m, which has proved that our framework is robust to detect undocumented building constructions at large-scale. Considering that the official geodata exploited in this research is advantageous because of its high quality and large coverage, a transferability analysis experiment is also designed in our research to investigate the sampling strategies for building detection at large-scale. Our results indicate that building detection results in unseen areas at large-scale can be improved when training samples are collected from different districts. In an area where training samples are available, local training sampless collection and training can save much time and effort. [ABSTRACT FROM AUTHOR]

Field mapping and information on agricultural landscapes is of increasing importance for many applications. Monitoring schemes and national cadasters provide a rich source of information but their maintenance and regular updating is costly and labor-intensive. Automatized mapping of fields based on remote sensing imagery may aid in this task and allow for a faster and more regular observation. Although remote sensing has seen extensive use in agricultural research topics, such as plant health monitoring, crop type classification, yield prediction, and irrigation, field delineation and extraction has seen comparatively little research interest. In this study, we present a field boundary detection technique based on deep learning and a variety of image features, and combine it with the graph-based growing contours (GGC) method to extract agricultural fields in a study area in northern Germany. The boundary detection step only requires red, green, and blue (RGB) data and is therefore largely independent of the sensor used. We compare different image features based on color and luminosity information and evaluate their usefulness for the task of field boundary detection. A model based on texture metrics, gradient information, Hessian matrix eigenvalues, and local statistics showed good results with accuracies up to 88.2%, an area under the ROC curve (AUC) of up to 0.94, and F1 score of up to 0.88. The exclusive use of these universal image features may also facilitate transferability to other regions. We further present modifications to the GGC method intended to aid in upscaling of the method through process acceleration with a minimal effect on results. We combined the boundary detection results with the GGC method for field polygon extraction. Results were promising, with the new GGC version performing similarly or better than the original version while experiencing an acceleration of 1.3× to 2.3× on different subsets and input complexities. Further research may explore other applications of the GGC method outside agricultural remote sensing and field extraction. [ABSTRACT FROM AUTHOR]