Temporal Datasets Research Articles

The Brettenham storm of 25 July 2021

The <scp>Brettenham</scp> storm of 25 <scp>July</scp> 2021

A New Coordinate System for Magnetic Resonance Imaging of the Vestibular System.

Objectives: To develop and evaluate a new coordinate system for MRI of the vestibular system.Methods: In this study, 53 internal auditory canal MRI and 78 temporal bone CT datasets were analyzed. Mimics Medical software version 21.0 was used to visualize and three-dimensionally reconstruct the image data. We established a new coordinate system, named W–X, based on the center of the bilateral eyeballs and vertex of the bilateral superior semicircular canals. Using the W–X coordinate system and Reid's coordinate system, we measured the orientations of the planes of the anterior semicircular canal (ASCC), the lateral semicircular canal (LSCC), and the posterior semicircular canal (PSCC).Results: No significant differences between the angles measured using CT and MRI were found for any of the semicircular canal planes (p > 0.05). No statistical differences were found between the angles measured using Reid's coordinate system (CT) and the W–X coordinate system (MRI). The mean values of ∠ASCC & LSCC, ∠ASCC & PSCC, and ∠LSCC & PSCC were 84.67 ± 5.76, 94.21 ± 3.81, and 91.79 ± 5.22 degrees, respectively. The angle between the LSCC plane and the horizontal imaging plane was 15.64 ± 3.92 degrees, and the angle between the PSCC plane and the sagittal imaging plane was 48.79 ± 4.46 degrees.Conclusion: A new W–X coordinate system was developed for MRI studies of the vestibular system and can be used to measure the orientations of the semicircular canals.

MOVIS: A multi-omics software solution for multi-modal time-series clustering, embedding, and visualizing tasks

Thanks to recent advances in sequencing and computational technologies, many researchers with biological and/or medical backgrounds are now producing multiple data sets with an embedded temporal dimension. Multi-modalities enable researchers to explore and investigate different biological and physico-chemical processes with various technologies. Motivated to explore multi-omics data and time-series multi-omics specifically, the exploration process has been hindered by the separation introduced by each omics-type. To effectively explore such temporal data sets, discover anomalies, find patterns, and better understand their intricacies, expertise in computer science and bioinformatics is required. Here we present MOVIS, a modular time-series multi-omics exploration tool with a user-friendly web interface that facilitates the data exploration of such data. It brings into equal participation each time-series omic-type for analysis and visualization. As of the time of writing, two time-series multi-omics data sets have been integrated and successfully reproduced. The resulting visualizations are task-specific, reproducible, and publication-ready. MOVIS is built on open-source software and is easily extendable to accommodate different analytical tasks. An online version of MOVIS is available under https://movis.mathematik.uni-marburg.de/ and on Docker Hub (https://hub.docker.com/r/aanzel/movis).

A Hypergraph Approach for Estimating Growth Mechanisms of Complex Networks

Temporal datasets that describe complex interactions between individuals over time are increasingly common in various domains. Conventional graph representations of such datasets may lead to information loss since higher-order relationships between more than two individuals must be broken into multiple pairwise relationships in graph representations. In those cases, a hypergraph representation is preferable since it can preserve higher-order relationships by using hyperedges. However, existing hypergraph models of temporal complex networks often employ some data-independent growth mechanism, which is the linear preferential attachment in most cases. In principle, this pre-specification is undesirable since it completely ignores the data at hand. Our work proposes a new hypergraph growth model with a data-driven preferential attachment mechanism estimated from observed data. A key component of our method is a recursive formula that allows us to overcome a bottleneck in computing the normalizing factors in our model. We also treat an often-neglected selection bias in modeling the emergence of new edges with new nodes. Fitting the proposed hypergraph model to 13 real-world datasets from diverse domains, we found that all estimated preferential attachment functions deviates substantially from the linear form. This demonstrates the need of doing away with the linear preferential attachment assumption and adopting a data-driven approach. We also showed that our model outperformed conventional models in replicating the observed first-order and second-order structures in these real-world datasets.

Tencent AVS: A Holistic Ads Video Dataset for Multi-Modal Scene Segmentation

Temporal video segmentation and classification have been advanced greatly by public benchmarks in recent years. However, such research still mainly focuses on human actions, failing to describe videos in a holistic view. In addition, previous research tends to pay much attention to visual information yet ignores the multi-modal nature of videos. To fill this gap, we construct an ‘Ads Video Segmentation’ dataset (AVS) in the ads domain to escalate multi-modal video analysis to a new level. AVS describes videos from three independent perspectives as ‘presentation form’, ‘place’, and ‘style’, and contains rich multi-modal information such as video, audio, and text. AVS is organized hierarchically in semantic aspects for comprehensive temporal video segmentation with three levels of categories for multi-label classification, e.g., ‘place’ - ‘working place’ - ‘office’. Therefore, AVS is distinguished from previous temporal segmentation datasets due to its multi-modal information, holistic view of categories, and hierarchical granularities. It includes 12,000 videos, 82 classes, 33,900 segments, 121,100 shots, and 168,500 labels. Accompanied with AVS, we also present a strong multi-modal video segmentation baseline coupled with multi-label class prediction. Extensive experiments are conducted to evaluate our proposed method as well as existing representative methods to reveal key challenges of our dataset AVS.

Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion

Recent years, Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a Knowledge Graph (KG) into a geometric space and thus have gained increasing attentions. In addition, many recent Knowledge Graphs involve evolving data, e.g., the fact (Obama, PresidentOf, USA) is valid only from 2009 to 2017. This introduces important challenges for knowledge representation learning since such temporal KGs change over time. In this work, we strive to move beyond the complex or hypercomplex space for KGE and propose a novel geometric algebra based embedding approach, GeomE, which uses multivector representations and the geometric product to model entities and relations. GeomE subsumes several state-of-the-art KGE models and is able to model diverse relations patterns. On top of this, we extend GeomE to TGeomE for temporal KGE, which performs 4th-order tensor factorization of a temporal KG and devises a new linear temporal regularization for time representation learning. Moreover, we study the effect of time granularity on the performance of TGeomE models. Experimental results show that our proposed models achieve the state-of-the-art performances on link prediction over four commonly-used static KG datasets and four well-established temporal KG datasets across various metrics.

Behavior Algorithm — a Novel Time-series Clustering Approach

Clustering time-series values is an established technique for organizations employing machine learning to analyze temporal datasets. Generally speaking, the goal of time-series methodology is to generate predictions. Such predictions could help organizations understand potential future cyberattacks, financial market changes, weather, or disease outbreaks. However, computational limitations lead existing algorithms to fail to group individual series together based the actual behavior of the series. A feature that can be used or derived to explain the time-series behavior had not been identified in the literature despite there being a need to have numeric values to describe the pattern of values over time. To address this gap, this work presents a behavior algorithm which addresses clustering time-series data based solely on the behavior of the series. Further, the algorithm is designed to operate effectively regardless of absolute values or temporal shifts. First, we describe the algorithm through mathematical examples. We provide the design approach for the algorithm numerically and through data visualizations. Then, we validated the algorithm on sample random data. Finally, we offer conclusions along with notions for future work based on this study.

Assessment of ERA5-Land Volumetric Soil Water Layer Product Using In Situ and SMAP Soil Moisture Observations

In preparation for the NISAR mission soil moisture algorithm, this study performs the validation of the European Centre for Medium-Range Weather Forecast (ECMWF) ERA5-Land volumetric soil water (soil moisture) layer product with in-situ measurements from the Soil Moisture Active Passive (SMAP) core validation sites (CVS) for 2015 – 2021. The ERA5-Land soil water layer was also compared against the SMAP-enhanced radiometer soil moisture product (gridded at 9 km) at a global extent. For comparison between the ERA5-Land and the SMAP soil moisture products, a matching temporal dataset was generated from ERA5-Land based on the acquisition time of SMAP for each 9 km grid. In comparison with the CVS in-situ measurement, the ERA5-Land data exhibits an overall ubRMSE of about ~0.05 m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> /m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> but has high wet bias over most of the sites except for sites in Australia, Denmark, and Argentina. The global comparison of the ERA5-Land soil moisture with the SMAP 9 km gridded product shows an overall wet bias with a high correlation in the tropical and temperate regions. The lowest bias was observed over the desert region but has poor correlation as it doesn’t have enough soil moisture variability. Poor correlation with high bias and high RMSD observed over dense vegetated and tundra regions is possibly due to the inferior performance of the SMAP soil moisture product, which has not been validated for these areas.

DeepTSQP: Temporal-aware service QoS prediction via deep neural network and feature integration

Quality of service (QoS) has been mostly applied to represent non-functional properties of web services and differentiate those with the same functionality. How to accurately predict unknown service QoS has become a hot research issue. Although existing researches have been investigated on temporal-aware service QoS prediction, conventional approaches are restricted to a couple of limitations. (1) most of them cannot well mine the time-series relationships and the interaction invocation information among users and services. (2) even although some sophisticated approaches make use of recurrent neural networks for temporal service QoS prediction, they mainly focus on the learning of user-service temporal relationship and have paid less attention to more effectively represent implicit features, resulting in low accuracy on service QoS prediction. To deal with the challenges, we propose a novel deep learning based approach called DeepTSQP to perform the task of temporal-aware service QoS prediction by feature integration. In DeepTSQP, we first present an improved temporal feature representation of users and services by integrating binarization feature and similarity feature. Then, we propose a deep neural network with gated recurrent units (GRU), learning and mining temporal features among users and services. Finally, DeepTSQP model can be trained by parameter optimization and applied to predict unknown service QoS. Extensive experiments are conducted on a large-scale real-world temporal QoS dataset WS-Dream with 27,392,643 historical QoS invocation records. The results demonstrate that DeepTSQP significantly outperforms state-of-the-art approaches for temporal-aware service QoS prediction in terms of multiple evaluation metrics.

Monitoring Small Water Bodies Using High Spatial and Temporal Resolution Analysis Ready Datasets

Basemap and Planet Fusion—derived from PlanetScope imagery—represent the next generation of analysis ready datasets that minimize the effects of the presence of clouds. These datasets have high spatial (3 m) and temporal (daily) resolution, which provides an unprecedented opportunity to improve the monitoring of on-farm reservoirs (OFRs)—small water bodies that store freshwater and play important role in surface hydrology and global irrigation activities. In this study, we assessed the usefulness of both datasets to monitor sub-weekly surface area changes of 340 OFRs in eastern Arkansas, USA, and we evaluated the datasets main differences when used to monitor OFRs. When comparing the OFRs surface area derived from Basemap and Planet Fusion to an independent validation dataset, both datasets had high agreement (r2 ≥ 0.87), and small uncertainties, with a mean absolute percent error (MAPE) between 7.05% and 10.08%. Pairwise surface area comparisons between the two datasets and the PlanetScope imagery showed that 61% of the OFRs had r2 ≥ 0.55, and 70% of the OFRs had MAPE &lt;5%. In general, both datasets can be employed to monitor OFRs sub-weekly surface area changes, and Basemap had higher surface area variability and was more susceptible to the presence of cloud shadows and haze when compared to Planet Fusion, which had a smoother time series with less variability and fewer abrupt changes throughout the year. The uncertainties in surface area classification decreased as the OFRs increased in size. In addition, the surface area time series can have high variability, depending on the OFR environmental conditions (e.g., presence of vegetation inside the OFR). Our findings suggest that both datasets can be used to monitor OFRs sub-weekly, seasonal, and inter-annual surface area changes; therefore, these datasets can help improve freshwater management by allowing better assessment and management of the OFRs.

Deep Learning Model for Wind Forecasting: Classification Analyses for Temporal Meteorological Data

This paper proposes a multiple CNN architecture with multiple input features, combined with multiple LSTM, along with densely connected convolutional layers, for temporal wind nature analyses. The designed architecture is called Multiple features, Multiple Densely Connected Convolutional Neural Network with Multiple LSTM Architecture, i.e. MCLT. A total of 58 features in the input layers of the MCLT are designed using wind speed and direction values. These empirical features are based on percentage difference, standard deviation, correlation coefficient, eigenvalues, and entropy, for efficiently describing the wind trend. Two successive LSTM layers are used after four densely connected convolutional layers of the MCLT. Moreover, LSTM has memory units that utilise learnt features from the current as well as previous outputs of the neurons, thereby enhancing the learning of patterns in the temporal wind dataset. Densely connected convolutional layer helps to learn features of other convolutional layers as well. The MCLT is used to predict dominant speed and direction classes in the future for the wind datasets of Stuttgart and Netherlands. The maximum and minimum overall accuracies for dominant speed prediction are 99.1% and 94.9%, (for Stuttgart) and 99.9% and 97.5% (for Netherlands) and for dominant direction prediction are 99.9% and 94.4% (for Stuttgart) and 99.6% and 96.4% (for Netherlands), respectively, using MCLT with 58 features. The MCLT, therefore, with multiple features at different levels, i.e. the input layers, the convolutional layers, and LSTM layers, shows promising results for the prediction of dominant speed and direction. Thus, this work is useful for proper wind utilisation and improving environmental planning. These analyses would also help in performing Computational Fluid Dynamics (CFD) simulations using wind speed and direction measured at a nearby meteorological station, for devising a new set of appropriate inflow boundary conditions.

Tucker decomposition-based temporal knowledge graph completion

Knowledge graphs have been demonstrated to be an effective tool for numerous intelligent applications. However, a large amount of valuable knowledge still exists implicitly in the knowledge graphs. To enrich the existing knowledge graphs, recent years have witnessed that many algorithms for link prediction and knowledge graphs embedding have been designed to infer new facts. But most of these studies focus on the static knowledge graphs and ignore the temporal information which reflects the validity of knowledge. Developing the model for temporal knowledge graphs completion is an increasingly important task. In this paper, we build a new tensor decomposition model for temporal knowledge graphs completion inspired by the Tucker decomposition of order-4 tensor. Furthermore, to further improve the basic model performance, we provide three kinds of methods including cosine similarity, contrastive learning, and reconstruction-based to incorporate the prior knowledge into the proposed model. Because the core tensor contains a large number of parameters on the proposed model, thus we present two embedding regularization schemes to avoid the over-fitting problem. By combining these two kinds of regularization with the proposed model, our model outperforms baselines with an explicit margin on three temporal datasets (i.e. ICEWS2014, ICEWS05-15, GDELT).

XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification

Multivariate Time Series (MTS) classification has gained importance over the past decade with the increase in the number of temporal datasets in multiple domains. The current state-of-the-art MTS classifier is a heavyweight deep learning approach, which outperforms the second-best MTS classifier only on large datasets. Moreover, this deep learning approach cannot provide faithful explanations as it relies on post hoc model-agnostic explainability methods, which could prevent its use in numerous applications. In this paper, we present XCM, an eXplainable Convolutional neural network for MTS classification. XCM is a new compact convolutional neural network which extracts information relative to the observed variables and time directly from the input data. Thus, XCM architecture enables a good generalization ability on both large and small datasets, while allowing the full exploitation of a faithful post hoc model-specific explainability method (Gradient-weighted Class Activation Mapping) by precisely identifying the observed variables and timestamps of the input data that are important for predictions. We first show that XCM outperforms the state-of-the-art MTS classifiers on both the large and small public UEA datasets. Then, we illustrate how XCM reconciles performance and explainability on a synthetic dataset and show that XCM enables a more precise identification of the regions of the input data that are important for predictions compared to the current deep learning MTS classifier also providing faithful explainability. Finally, we present how XCM can outperform the current most accurate state-of-the-art algorithm on a real-world application while enhancing explainability by providing faithful and more informative explanations.

Measuring Similarity of Deforestation Patterns in Time and Space across Differences in Resolution

This article demonstrated an easily applicable method for measuring the similarity between a pair of point patterns, which applies to spatial or temporal data sets. Such a measurement was performed using similarity-based pattern analysis as an alternative to conventional approaches, which typically utilize straightforward point-to-point matching. Using our approach, in each point data set, two geometric features (i.e., the distance and angle from the centroid) were calculated and represented as probability density functions (PDFs). The PDF similarity of each geometric feature was measured using nine metrics, with values ranging from zero (very contrasting) to one (exactly the same). The overall similarity was defined as the average of the distance and angle similarities. In terms of sensibility, the method was shown to be capable of measuring, at a human visual sensing level, two pairs of hypothetical patterns, presenting reasonable results. Meanwhile, in terms of the method′s sensitivity to both spatial and temporal displacements from the hypothetical origin, the method is also capable of consistently measuring the similarity of spatial and temporal patterns. The application of the method to assess both spatial and temporal pattern similarities between two deforestation data sets with different resolutions was also discussed.

Dynamic Structural Role Node Embedding for User Modeling in Evolving Networks

Complex user behavior, especially in settings such as social media, can be organized as time-evolving networks. Through network embedding, we can extract general-purpose vector representations of these dynamic networks which allow us to analyze them without extensive feature engineering. Prior work has shown how to generate network embeddings while preserving the structural role proximity of nodes. These methods, however, cannot capture the temporal evolution of the structural identity of the nodes in dynamic networks. Other works, on the other hand, have focused on learning microscopic dynamic embeddings. Though these methods can learn node representations over dynamic networks, these representations capture the local context of nodes and do not learn the structural roles of nodes. In this article, we propose a novel method for learning structural node embeddings in discrete-time dynamic networks. Our method, called HR2vec , tracks historical topology information in dynamic networks to learn dynamic structural role embeddings. Through experiments on synthetic and real-world temporal datasets, we show that our method outperforms other well-known methods in tasks where structural equivalence and historical information both play important roles. HR2vec can be used to model dynamic user behavior in any networked setting where users can be represented as nodes. Additionally, we propose a novel method (called network fingerprinting) that uses HR2vec embeddings for modeling whole (or partial) time-evolving networks. We showcase our network fingerprinting method on synthetic and real-world networks. Specifically, we demonstrate how our method can be used for detecting foreign-backed information operations on Twitter.

Evaluating different machine learning methods to simulate runoff from extensive green roofs

Abstract. Green roofs are increasingly popular measures to permanently reduce or delay storm-water runoff. The main objective of the study was to examine the potential of using machine learning (ML) to simulate runoff from green roofs to estimate their hydrological performance. Four machine learning methods, artificial neural network (ANN), M5 model tree, long short-term memory (LSTM) and k nearest neighbour (kNN), were applied to simulate storm-water runoff from 16 extensive green roofs located in four Norwegian cities across different climatic zones. The potential of these ML methods for estimating green roof retention was assessed by comparing their simulations with a proven conceptual retention model. Furthermore, the transferability of ML models between the different green roofs in the study was tested to investigate the potential of using ML models as a tool for planning and design purposes. The ML models yielded low volumetric errors that were comparable with the conceptual retention models, which indicates good performance in estimating annual retention. The ML models yielded satisfactory modelling results (NSE &gt;0.5) in most of the roofs, which indicates an ability to estimate green roof detention. The variations in ML models' performance between the cities was larger than between the different configurations, which was attributed to the different climatic characteristics between the four cities. Transferred ML models between cities with similar rainfall events characteristics (Bergen–Sandnes, Trondheim–Oslo) could yield satisfactory modelling performance (Nash–Sutcliffe efficiency NSE &gt;0.5 and percentage bias |PBIAS| &lt;25 %) in most cases. However, we recommend the use of the conceptual retention model over the transferred ML models, to estimate the retention of new green roofs, as it gives more accurate volume estimates. Follow-up studies are needed to explore the potential of ML models in estimating detention from higher temporal resolution datasets.

Development and validation of the 3D U-Net algorithm for segmentation of pelvic lymph nodes on diffusion-weighted images

BackgroundThe 3D U-Net model has been proved to perform well in the automatic organ segmentation. The aim of this study is to evaluate the feasibility of the 3D U-Net algorithm for the automated detection and segmentation of lymph nodes (LNs) on pelvic diffusion-weighted imaging (DWI) images.MethodsA total of 393 DWI images of patients suspected of having prostate cancer (PCa) between January 2019 and December 2020 were collected for model development. Seventy-seven DWI images from another group of PCa patients imaged between January 2021 and April 2021 were collected for temporal validation. Segmentation performance was assessed using the Dice score, positive predictive value (PPV), true positive rate (TPR), and volumetric similarity (VS), Hausdorff distance (HD), the Average distance (AVD), and the Mahalanobis distance (MHD) with manual annotation of pelvic LNs as the reference. The accuracy with which the suspicious metastatic LNs (short diameter > 0.8 cm) were detected was evaluated using the area under the curve (AUC) at the patient level, and the precision, recall, and F1-score were determined at the lesion level. The consistency of LN staging on an hold-out test dataset between the model and radiologist was assessed using Cohen’s kappa coefficient.ResultsIn the testing set used for model development, the Dice score, TPR, PPV, VS, HD, AVD and MHD values for the segmentation of suspicious LNs were 0.85, 0.82, 0.80, 0.86, 2.02 (mm), 2.01 (mm), and 1.54 (mm) respectively. The precision, recall, and F1-score for the detection of suspicious LNs were 0.97, 0.98 and 0.97, respectively. In the temporal validation dataset, the AUC of the model for identifying PCa patients with suspicious LNs was 0.963 (95% CI: 0.892–0.993). High consistency of LN staging (Kappa = 0.922) was achieved between the model and expert radiologist.ConclusionThe 3D U-Net algorithm can accurately detect and segment pelvic LNs based on DWI images.

Characterization of temporal PM2.5, nitrate, and sulfate using deep learning techniques

Water-soluble inorganic salts (WIS) contribute a large fraction of PM2.5, which are responsible for the adverse effects on human health and environment. It is important to investigate the long-term variation trend of PM2.5 and WIS for exposure assessment and effective abatement strategies development. In this study, a multi-step ahead artificial neural network (MSA-ANN) and a long short-term memory fully connected (LSTM-FC) model for PM2.5, nitrate (NO3−), and sulfate (SO42−) prediction were developed to provide high temporal resolution datasets. Results show that the kinetic formation rate of HNO3 and HSO3− used as input variables can improve the accuracy of the present model for PM2.5, NO3−, and SO42− prediction. The MSA-ANN is able to predict 80–83%, 93%, and 91% of PM2.5, NO3−, and SO42−, respectively, with t+1 prediction horizon. With increasing prediction horizon to t+4 and t+8, the present model still can track the temporal variation of PM2.5, NO3−, and SO42− very well and capture the peak values during a severe pollution event. The proposed method is applicable to predict regional temporal variation trend of PM2.5, NO3−, and SO42− and fill the data gap in area with limited WIS measurement.

Numerical modeling of cough airflow: Establishment of spatial–temporal experimental dataset and CFD simulation method

In this study, the boundary conditions to simulate the cough airflow of a human using computational fluid dynamics (CFD) simulation have been defined. Spatial–temporal datasets of cough airflow were obtained from particle image velocimetry (PIV) experiments conducted previously, and an ensemble-average analysis was performed for CFD calculations and to validate simulated results. The air velocity corresponding to the boundary conditions for the opening of the mouth for CFD simulation could not be obtained directly from PIV experiments. Hence, the experimental results of airflow near the mouth were used to explore the boundary conditions of the cough for CFD simulation, assuming that the velocities near the mouth and the boundary conditions are highly correlated. The time-series velocity boundary conditions for the simulation of cough were explored using two methods. The conditions for Method 1 were closer to that for the overall cough airflow distribution obtained from the experimental datasets, while the conditions for Method 2 most closely matched the maximum velocity at a specific location of the cough airflow. The cough airflow reproduced by CFD using Method 1 showed RMSE values of 0.24–0.32 m/s compared to the experimental results when the maximum velocities at boundary conditions were 15.5–15.8 m/s. Moreover, for Method 2, the maximum velocity was reproduced with an error of 0.02 m/s. This study obtains the detailed boundary conditions for cough simulation, which, coupled with droplets and droplet nuclei dispersion models, can be applied to investigate the risk of infection and transmission routes of human cough.

TreeNet–The Biological Drought and Growth Indicator Network

The TreeNet research and monitoring network has been continuously collecting data from point dendrometers and air and soil microclimate using an automated system since 2011. The goal of TreeNet is to generate high temporal resolution datasets of tree growth and tree water dynamics for research and to provide near real-time indicators of forest growth performance and drought stress to a wide audience. This paper explains the key working steps from the installation of sensors in the field to data acquisition, data transmission, data processing, and online visualization. Moreover, we discuss the underlying premises to convert dynamic stem size changes into relevant biological information. Every 10 min, the stem radii of about 420 trees from 13 species at 61 sites in Switzerland are measured electronically with micrometer precision, in parallel with the environmental conditions above and below ground. The data are automatically transmitted, processed and stored on a central server. Automated data processing (R-based functions) includes screening of outliers, interpolation of data gaps, and extraction of radial stem growth and water deficit for each tree. These long-term data are used for scientific investigations as well as to calculate and display daily indicators of growth trends and drought levels in Switzerland based on historical and current data. The current collection of over 100 million data points forms the basis for identifying dynamics of tree-, site- and species-specific processes along environmental gradients. TreeNet is one of the few forest networks capable of tracking the diurnal and seasonal cycles of tree physiology in near real-time, covering a wide range of temperate forest species and their respective environmental conditions.