Temporal Datasets Research Articles

CaliPro: A Calibration Protocol That Utilizes Parameter Density Estimation to Explore Parameter Space and Calibrate Complex Biological Models.

Mathematical and computational modeling have a long history of uncovering mechanisms and making predictions for biological systems. However, to create a model that can provide relevant quantitative predictions, models must first be calibrated by recapitulating existing biological datasets from that system. Current calibration approaches may not be appropriate for complex biological models because: 1) many attempt to recapitulate only a single aspect of the experimental data (such as a median trend) or 2) Bayesian techniques require specification of parameter priors and likelihoods to experimental data that cannot always be confidently assigned. A new calibration protocol is needed to calibrate complex models when current approaches fall short. Herein, we develop CaliPro, an iterative, model-agnostic calibration protocol that utilizes parameter density estimation to refine parameter space and calibrate to temporal biological datasets. An important aspect of CaliPro is the user-defined pass set definition, which specifies how the model might successfully recapitulate experimental data. We define the appropriate settings to use CaliPro. We illustrate the usefulness of CaliPro through four examples including predator-prey, infectious disease transmission, and immune response models. We show that CaliPro works well for both deterministic, continuous model structures as well as stochastic, discrete models and illustrate that CaliPro can work across diverse calibration goals. We present CaliPro, a new method for calibrating complex biological models to a range of experimental outcomes. In addition to expediting calibration, CaliPro may be useful in already calibrated parameter spaces to target and isolate specific model behavior for further analysis.

Spatial and Temporal Ecological Uniqueness of Andean Diatom Communities Are Correlated With Climate, Geodiversity and Long-Term Limnological Change

National Socio-Environmental Synthesis Center (SESYNC) from the US NSF DBI-1639145 National Geographic Society 8672-09 Comision Nacional de Investigacion Cientifica y Tecnologica (CONICYT) CONICYT FONDECYT LIFE14/IPE/FI/023 project FRESHABIT LIFE IP LIFE14/IPE/FI/023 National Science Foundation (NSF) EAR-1338694

Evaluating the performance of high-resolution satellite imagery in detecting ephemeral water bodies over West Africa

Pastoralism is a major occupation in Africa’s Sahel region, which spans from Senegal in the west to Ethiopia in the east and has a semi-arid climate. Pastoralists from the region are usually nomadic, moving regularly in search of water and pasture, often for hundreds of kilometers. Traditionally, pastoralists have relied on historical knowledge and transhumance pathways to reach the water bodies (WB). Due to climatic conditions, a vast majority of the WBs in this region are small, sporadic, and ephemeral, therefore there is a need to map and frequently monitor water availability. Remote sensing observations can be used to complement current monitoring efforts. High-resolution near-daily imagery from the recently launched PlanetScope (PS) constellation of small satellites has the potential to complement the existing medium-resolution and infrequent but well established and extensively calibrated sensors like Landsat. The aim of this study is to investigate the performance and applicability of high-resolution PS data to detect and monitor WBs in the Ferlo region of West Africa, in comparison to Landsat-8 imagery. The results indicate that for cloud-free days, PS data was comparable (r >0.88; ubRMSE <0.01) to Landsat, but due to inadequate cloud masking, the results were poor for cloudy days (r < 0.49 and ubRMSE>0.058). The PS images were able to detect nearly 95% of the WBs, whereas Landsat was able to identify only 32% at the water fraction threshold >40%. Initial results from this study show that the high spatial and temporal resolution PS datasets show promise in monitoring WBs in arid regions of West Africa.

COMPARATIVE EVALUATION OF DERIVED IMAGE AND LIDAR POINT CLOUDS FROM UAV-BASED MOBILE MAPPING SYSTEMS

Abstract. Unmanned aerial vehicles (UAVs) have been widely used for 3D reconstruction/modelling in various applications such as precision agriculture, coastal monitoring, and emergency management. For such mapping applications, camera and LiDAR are the two most commonly used sensors. Mapping with imagery-based approaches is considered to be an economical and effective option and is often conducted using Structure from Motion (SfM) techniques where point clouds and orthophotos are generated. In addition to UAV photogrammetry, point clouds of the area of interest can also be directly derived from LiDAR sensors onboard UAVs equipped with global navigation satellite systems/inertial navigation systems (GNSS/INS). In this study, a custom-built UAV-based mobile mapping system is used to simultaneously collect imagery and LiDAR data. Derived LiDAR and image-based point clouds are investigated and compared in terms of their absolute and relative accuracy. Furthermore, stability of the system calibration parameters for the camera and LiDAR sensors are studied using temporal datasets. The results show that while LiDAR point clouds demonstrate a high absolute accuracy over time, image-based point clouds are not as accurate as LiDAR due to instability of the camera interior orientation parameters.

Extracting Insights From Temporal Data by Integrating Dynamic Modeling and Machine Learning.

Biological processes are dynamic. As a result, temporal analyses are necessary to fully understand the complex interactions that occurs within these systems. One example of a multifaceted biological process is restitution: the initial step in complex wound repair. Restitution is a dynamic process that depends on an elegant orchestration between damaged cells and their intact neighbors. Such orchestration enables the quick repair of the damaged area, which is essential to preserve epithelial integrity and prevent further injury. High quality dynamic data of the cellular and molecular events that make up the gastric restitution process has been documented. However, comprehensive dynamic models that connect all relevant molecular interactions to cellular behaviors are challenging to construct and experimentally validate. In order to efficiently provide feedback to ongoing experimental work, we have integrated dynamical modeling and machine learning to efficiently extract data-driven insights without incorporating detailed mechanisms. Dynamical models convert time course data into a set of static features, which are then subjected to machine learning analysis. The integrated analysis provides data-driven insights into how repair might be regulated in individual gastric organoids. We have provided a “proof of concept” of how such an analysis pipeline can be used to analyze any temporal dataset and provide timely data-driven insights.

Integrative Genomic Enrichment Analysis Identified the Brain Regions and Development Stages Related to Anorexia Nervosa and Obsessive-Compulsive Disorder.

Our aim is to explore the spatial and temporal features of anorexia nervosa (AN) and obsessive-compulsive disorder (OCD) considering different brain regions and development stages. The gene sets related to 16 brain regions and nine development stages were obtained from a brain spatial and temporal transcriptomic dataset. Using the genome-wide association study data, transcriptome-wide association study (TWAS) was conducted to identify the genes whose imputed expressions were associated with AN and OCD, respectively. The mRNA expression profiles were analyzed by GEO2R to obtain differentially expressed genes. Gene set enrichment analysis was conducted to detect the spatial and temporal features related to AN and OCD using the TWAS and mRNA expression analysis results. We observed multiple common association signals shared by TWAS and mRNA expression analysis of AN, such as the primary auditory cortex vs. cerebellar cortex in fetal development and earlier vs. later fetal development in the somatosensory cortex. For OCD, we also detected multiple common association signals, such as medial prefrontal cortex vs. amygdala in adulthood and fetal development vs. infancy in mediodorsal nucleus of thalamus. Our study provides novel clues for describing the spatial and temporal features of brain development in the pathogenesis of AN and OCD.

Dry biomass estimation of paddy rice with Sentinel-1A satellite data using machine learning regression algorithms

Despite the growing use of Sentinel-1 in retrieving crop growth information, its potential for obtaining improved estimates of rice biophysical parameters has not been fully investigated. This study therefore assesses the capabilities of Sentinel-1A temporal datasets, of the interferometric wide-swath (IW) mode that include the vertical transmitted and horizontal received (VH), and vertical transmitted and vertical received (VV) polarizations, and the linear combination of VH and VV (VHVV), to estimate rice dry biomass over a test site located in southeast China. To this end, four machine learning regression algorithms; Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Gradient Boosting Decision Tree (GBDT), were applied to assess the aforementioned datasets. The results indicated that for the estimation of rice dry biomass over the entire growing season, VHVV data with RF produced the most accurate estimates with an R2 of 0.73 and an RMSE of 462.4 g/m2. However, this study suggests that a consideration of the rice growth phases could produce more accurate estimates of dry biomass as evident by an R2 of 0.72 and an RMSE of 362.4 g/m2 recorded at the reproductive phase (elongation to milking) with VH data and k-NN. Hence research works that would investigate the estimation of rice dry biomass at the vegetative (transplanting to elongation) and maturity (milking to ripening) phases are required to ascertain whether a growth-phase approach could obtain more accurate rice biomass estimates that better meet precision agriculture data needs.

A Data Fusion Modeling Framework for Retrieval of Land Surface Temperature from Landsat-8 and Modis Data.

Land surface temperature (LST) is a critical state variable of land surface energy equilibrium and a key indicator of environmental change such as climate change, urban heat island, and freezing-thawing hazard. The high spatial and temporal resolution datasets are urgently needed for a variety of environmental change studies, especially in remote areas with few LST observation stations. MODIS and Landsat satellites have complementary characteristics in terms of spatial and temporal resolution for LST retrieval. To make full use of their respective advantages, this paper developed a pixel-based multi-spatial resolution adaptive fusion modeling framework (called pMSRAFM). As an instance of this framework, the data fusion model for joint retrieval of LST from Landsat-8 and MODIS data was implemented to generate the synthetic LST with Landsat-like spatial resolution and MODIS temporal information. The performance of pMSRAFM was tested and validated in the Heihe River Basin located in China. The results of six experiments showed that the fused LST was high similarity to the direct Landsat-derived LST with structural similarity index (SSIM) of 0.83 and the index of agreement (d) of 0.84. The range of SSIM was 0.65–0.88, the root mean square error (RMSE) yielded a range of 1.6–3.4 °C, and the averaged bias was 0.6 °C. Furthermore, the temporal information of MODIS LST was retained and optimized in the synthetic LST. The RMSE ranged from 0.7 °C to 1.5 °C with an average value of 1.1 °C. When compared with in situ LST observations, the mean absolute error and bias were reduced after fusion with the mean absolute bias of 1.3 °C. The validation results that fused LST possesses the spatial pattern of Landsat-derived LSTs and inherits most of the temporal properties of MODIS LSTs at the same time, so it can provide more accurate and credible information. Consequently, pMSRAFM can be served as a promising and practical fusion framework to prepare a high-quality LST spatiotemporal dataset for various applications in environment studies.

SPATIAL PROCESSING OF SENTINEL IMAGERY FOR MONITORING OF ACACIA FOREST DEGRADATION IN LAKE NAKURU RIPARIAN RESERVE

Abstract. Tree degradation in National Parks poses a serious risk to the birds and animals and to a larger extent the general ecosystem. The essence of Forest degradation mapping is to detect the extent of damage on the trees over time, hence providing stakeholders with a basis for forest rehabilitation and intervention. The study proposes a workflow for detection and classification of degrading acacia vegetation along Lake Nakuru riparian reserve. Inspired by previous research on the use of Dual Polarized Sentinel 1 Ground Range Detected (GRD) data for vegetation detection, a set of six Sentinel 1 GRD and Sentinel 2 MSI of corresponding dates (2018–2019) were used. Our study confirms the existing correlation between vegetation indices derived from optical sensors and the backscatter indices from S1 SAR image of the same land cover classes. Factors that were used in validating the results include some comparisons between pixelwise and object-based classification, with a focus on the underlying segmentation and classification algorithms, the polarimetric attributes (VV+VH intensity bands) and the reflectance bands (NIR, SWIR &amp;amp; GREEN), the Haralick features (GLCM) vs. some geometric attributes (area &amp;amp; moment of inertia). Classification carried out on the temporal datasets considering geometric attributes and the Random Forest classifier yielded the highest Overall Accuracy (OA) with 94.25 %, and a Kappa coefficient of 0.90.

An intensive multilocation temporal dataset of fungal and bacterial communities in the root and rhizosphere of Brassica napus.

The plant microbiome has been recently recognized as a plant phenotype to help in the food security of the future population. However, global plant microbiome datasets are insufficient to be used effectively for breeding this new generation of crop plants. We surveyed the diversity and temporal composition of bacterial and fungal communities in the root and rhizosphere of Brassica napus, the world's second largest oilseed crop, weekly in eight diverse lines at one site and every three weeks in sixteen lines, at three sites in 2016 and 2017 in the Canadian Prairies. We sequenced the bacterial 16S ribosomal RNA gene generating a total of 127.7 million reads and the fungal internal transcribed spacer (ITS) region generating 113.4 million reads. 14,944 unique fungal amplicon sequence variants (ASV) were detected, with an average of 43 ASVs per root and 105 ASVs per rhizosphere sample. We detected 10,882 unique bacterial ASVs with an average of 249 ASVs per sample. Temporal, site-to-site, and line-driven variability were key determinants of microbial community structure. This dataset is a valuable resource to systematically extract information on the belowground microbiome of diverse B. napus lines in different environments, at different times in the growing season, in order to adapt effective varieties for sustainable crop production systems.

Lake outburst accelerated permafrost degradation on Qinghai-Tibet Plateau

Lakes and permafrost on Qinghai-Tibet Plateau (QTP) are both important indicators of climate change. Previous literatures have shown the usefulness of optical remote sensing in lake expansion monitoring and the effectiveness of synthetic aperture radar (SAR) interferometry (InSAR) in retrieving permafrost deformation on QTP. However, none of them incorporated both optical remote sensing and InSAR to investigate an event that may exhibit causal links between lake outburst and permafrost degradation. This study integrated both the Google Earth Engine (GEE) analysis on optical images and the small baseline subset (SBAS) processing on SAR datasets to evaluate the potential impact of a lake outburst event on permafrost degradation. The outburst of Zonag Lake (headwater lake) that occurred on 14 September 2011 was focused, and its consequential influence on the permafrost degradation surrounding Salt Lake (tailwater lake) was investigated. The GEE processing on Landsat and HJ-1 imageries allowed an efficient monitoring of the Salt Lake expansion over past 20 years. In addition, the SBAS-InSAR analysis on temporal Envisat and Sentinel-1 datasets further discovered the accelerated permafrost degradation surrounding Salt Lake after 2014. The results provide an evidence that on QTP the outburst of a headwater lake may significantly accelerate the permafrost degradation surrounding the tailwater lake. Such degradation may be attributed to the thermal alteration of the permafrost thawing-freezing cycle and the melting ground ice, along with the subsequent changes on hydrological connectivity and soil permeability. With the continuous trend of the permafrost degradation surrounding Salt Lake, potential risks may be further exposed to the regional environment and infrastructures such as the Qinghai-Tibet railway and highway, thus deserving a particular attention in the near future. The novelties of this study are: 1) technically, the preliminary attempt to integrate the GEE and InSAR techniques for a joint analysis of lake expansion and permafrost degradation, and 2) scientifically, the finding that lake outburst may accelerate permafrost degradation on QTP.

Directional trends in species composition over time can lead to a widespread overemphasis of year‐to‐year asynchrony

AbstractQuestionsCompensatory dynamics are described as one of the main mechanisms that increase community stability, e.g., where decreases of some species on a year‐to‐year basis are offset by an increase in others. Deviations from perfect synchrony between species (asynchrony) have therefore been advocated as an important mechanism underlying biodiversity effects on stability. However, it is unclear to what extent existing measures of synchrony actually capture the signal of year‐to‐year species fluctuations in the presence of long‐term directional trends in both species abundance and composition (species directional trends hereafter). Such directional trends may lead to a misinterpretation of indices commonly used to reflect year‐to‐year synchrony.MethodsAn approach based on three‐term local quadrat variance (T3) which assesses population variability in a three‐year moving window, was used to overcome species directional trend effects. This “detrending” approach was applied to common indices of synchrony across a worldwide collection of 77 temporal plant community datasets comprising almost 7,800 individual plots sampled for at least six years. Plots included were either maintained under constant “control” conditions over time or were subjected to different management or disturbance treatments.ResultsAccounting for directional trends increased the detection of year‐to‐year synchronous patterns in all synchrony indices considered. Specifically, synchrony values increased significantly in ~40% of the datasets with the T3 detrending approach while in ~10% synchrony decreased. For the 38 studies with both control and manipulated conditions, the increase in synchrony values was stronger for longer time series, particularly following experimental manipulation.ConclusionsSpecies’ long‐term directional trends can affect synchrony and stability measures potentially masking the ecological mechanism causing year‐to‐year fluctuations. As such, previous studies on community stability might have overemphasised the role of compensatory dynamics in real‐world ecosystems, and particularly in manipulative conditions, when not considering the possible overriding effects of long‐term directional trends.

EHRtemporalVariability: delineating temporal data-set shifts in electronic health records.

BackgroundTemporal variability in health-care processes or protocols is intrinsic to medicine. Such variability can potentially introduce dataset shifts, a data quality issue when reusing electronic health records (EHRs) for secondary purposes. Temporal data-set shifts can present as trends, as well as abrupt or seasonal changes in the statistical distributions of data over time. The latter are particularly complicated to address in multimodal and highly coded data. These changes, if not delineated, can harm population and data-driven research, such as machine learning. Given that biomedical research repositories are increasingly being populated with large sets of historical data from EHRs, there is a need for specific software methods to help delineate temporal data-set shifts to ensure reliable data reuse.ResultsEHRtemporalVariability is an open-source R package and Shiny app designed to explore and identify temporal data-set shifts. EHRtemporalVariability estimates the statistical distributions of coded and numerical data over time; projects their temporal evolution through non-parametric information geometric temporal plots; and enables the exploration of changes in variables through data temporal heat maps. We demonstrate the capability of EHRtemporalVariability to delineate data-set shifts in three impact case studies, one of which is available for reproducibility.ConclusionsEHRtemporalVariability enables the exploration and identification of data-set shifts, contributing to the broad examination and repurposing of large, longitudinal data sets. Our goal is to help ensure reliable data reuse for a wide range of biomedical data users. EHRtemporalVariability is designed for technical users who are programmatically utilizing the R package, as well as users who are not familiar with programming via the Shiny user interface.Availability: https://github.com/hms-dbmi/EHRtemporalVariability/Reproducible vignette: https://cran.r-project.org/web/packages/EHRtemporalVariability/vignettes/EHRtemporalVariability.htmlOnline demo: http://ehrtemporalvariability.upv.es/

Tryptophan-like fluorescence as a high-level screening tool for detecting microbial contamination in drinking water

Regular monitoring of drinking water quality is vital to identify contamination of potable water supplies. Testing for microbial contamination is important to prevent transmission of waterborne disease, but establishing and maintaining a water quality monitoring programme requires sustained labour, consumables and resources. In low resource settings such as developing countries, this can prove difficult, but measuring microbial contamination is listed as a requirement of reaching the UN's Sustainable Development Goal 6 for water and sanitation. A nine-month water quality monitoring programme was conducted in rural Malawi to assess the suitability of tryptophan-like fluorescence (TLF), an emerging method for rapidly detecting microbial contamination, as a drinking water quality monitoring tool. TLF data was compared with thermotolerant coliforms (TTCs, E. coli) and inorganic hydrochemical parameters. A large (n = 235) temporal dataset was collected from five groundwater drinking water sources, with samples collected once or twice weekly depending on the season. The results show that TLF can indicate a broader contamination risk but is not as sensitive to short term variability when compared to other faecal indicators. This is likely due to a broad association of TLF with elevated DOC concentrations from a range of different sources. Elevated TLF may indicate preferential conditions for the persistence of TTCs and/or E. coli, but not necessarily a public health risk from microbial contamination. TLF is therefore a more precautionary risk indicator than microbial culturing techniques and could prove useful as a high-level screening tool for initial risk assessment. For widespread use of TLF to be successful, standardisation of TLF values associated with different levels of risk is required, however, this study highlights the difficulties of equating TLF thresholds to TTCs or E. coli data because of the influence of DOC/HLF on the TLF signal.

Remote sensing of 10years changes in the vegetation cover of the northwestern coastal land of Red Sea, Saudi Arabia.

Accurate and up to date land use and land cover (LU/LC) changes information is the main source to understanding and assessing the environmental outcomes of such changes and is important for development plans. Thus, this study quantified the outlines of land cover variation of 10-years in the northwestern costal land of the Red Sea, Saudi Arabia. Two different supervised classification algorithms are visualized and evaluated to preparing a policy recommendation for the proper improvements towards better determining the tendency and the proportion of the vegetation cover changes. Firstly, to determine present vegetation structure of study area, 78 stands with a size of 50 × 50 m were analysed. Secondly, to obtain the vegetation dynamics in this area, two satellite images of temporal data sets were used; therefore, SPOT-5 images were obtained in 2004 and 2013. For each data set, four SPOT-5 scenes were placed into approximately 250-km intervals to cover the northwestern coastal land of the Red Sea. Both supervised and non-supervised cataloguing methods were attained towards organise the study area in 4-major land cover classes through using 5 various organizations algorithms. Approximately 900 points were evenly distributed within each SPOT-5 image and used for assessment accuracy. The floristic composition exhibits high diversity with 142 species and seven vegetation types were identified after multivariate analysis (VG I: Acacia tortilis-Acacia ehrenbergiana, VG II: Acacia tortilis-Stipagrostis plumosa, VG III: Zygophyllum coccineum-Zygophyllum simplex, VG IV: Acacia raddiana-Lycium shawii-Anabasis setifera, VG V: Tamarix aucheriana-Juncus rigidus, VG VI: Capparis decidua-Zygophyllum simplex and VG VII: Avicennia marina-Aristida adscensionis) and ranged between halophytic vegetation on the coast to xerophytic vegetation with scattered Acacia trees inland. The dynamic results showed rapid, imbalanced variations arises between 3-land cover classes (areas as urban, vegetation and desert). However, these findings shall serve as the baseline data for the design of rehabilitation programs that conserve biodiversity in arid regions and form treasured resources for an urban planner and decision makers to device bearable usage of land and environmental planning.

Enabling Time-Centric Computation for Efficient Temporal Graph Traversals From Multiple Sources

Temporal graph traversal is an approach for analyzing how information spreads throughout a network over time. A system has been recently proposed as an initial effort for efficient analyses against higher time complexity and infinitely evolving data unlike static graph. However, with the system, the response time for traversals from multiple sources is proportional to the number of sources; thus, application domains of the system can be limited. To resolve this problem, the state-of-the-art vertex-centric paradigm can be considered; however, we have found that the paradigm is not fitted into this computation. The paper proposes a novel time-centric computation approach for efficient all-pairs temporal graph traversals. One benefit of this approach is that users only need to focus on designing a repetitive task for graph elements that are valid at each sliding time, which simplifies the program logic and alleviates the burden of writing codes. Another benefit is that the approach is expected to enhance the performance by facilitating the reuse of intermediate results of multiple sources. The proposed approach is evaluated with a prototyped system, the recipes for existing algorithms, and the experiments with open temporal datasets. In addition, we also discuss how to handle ever-evolving real-world temporal networks.

“Brittle structural facies” analysis: A diagnostic method to unravel and date multiple slip events of long-lived faults

Regional-scale faults typically experience complex, long-lasting histories, commonly recording evidence of multiple reactivation events. Therefore, they contain multiscalar structural domains characterised by varying microstructures, mineralogical compositions and kinematics. These domains result from differential strain partitioning during the recorded faulting stages, and, as a result, can preserve the isotopic and kinematic signature of the different slip periods. Their detailed structural analysis integrated with K-Ar dating of the fault rock assemblage can help to identify these commonly tightly juxtaposed, although not coeval, domains, which we refer herein to as “Brittle Structural Facies” (BSF). BSF analysis is pivotal (i) to understand the structural heterogeneity of fault zones, (ii) the diachronic formation of geometrically and kinematically complex fault cores and (iii) to reconstruct faults' evolution in time and through space. Following this approach, this study relies on meso- and microstructural analysis, chemical characterisation and K-Ar dating to unravel the evolution of the Lærdal-Gjende Fault (LGF, southwestern Norway). The LGF is a multiply reactivated top-to-the-NW extensional fault with a 1 m thick poorly consolidated core. We recognised, sampled and characterised five BSF: I) Indurated dark reddish gouge, (II) Poorly consolidated cataclasite, (III) Weakly foliated greenish gouge, (IV) Clay-rich gouge and (V) A few mm-thick clay smear decorating the principal slip surface. Samples were separated into five grain size fractions (from <0.1 to 6-10 μm) and analysed by X-Ray Diffraction, Transmission Electron Microscopy and K-Ar geochronology. A c. 180 Ma age cluster defined by 10 ages of the coarsest grain size fractions (2-10 μm) likely documents fault nucleation during Jurassic rifting in the North Sea. The ages of the finest fractions, enriched in synkinematic K-bearing minerals (illite, smectite and K-feldspar), constrain four periods of faulting at c. 121 ± 3, 87 ± 2, 78 ± 2 and 57 ± 1 Ma. Ages indicate that the LGF accommodated strain due to hyperextension of the Mid-Norwegian margin down to the Late Cretaceous and finally slipped again during the Paleogene. The alternating widening and narrowing of the active fault zone in response to varying deformation mechanisms, including coseismic rupturing, formed the present complex fault architecture. This study highlights the importance of BSF characterisation as part of a multidisciplinary workflow to derive structural and temporal datasets of complex fault zones. BSF analysis, moreover, is demonstrated to be key for investigating the diachronic evolution of fault cores and to resolve multiple slip events of faults.

Memetic algorithm for multivariate time-series segmentation

In recent years, analyzing time-series data has become an ever important research topic due to an increased number of temporal datasets in science and engineering. Segmentation is widely used in time-series data analysis because it provides a more compact representation by dividing the series into segments. Segmentation approaches based on genetic algorithms have been proposed to extract segments and patterns with a given objective, such as a low rate of change or periodicity from time-series data. However, they may not be effective in obtaining the precise solution because they perform global search. In this study, we propose a memetic algorithm for multivariate time-series segmentation. For efficient local refinement, we calculate a likelihood-based score for all time points and use it in the evolutionary process. Experiments demonstrate that the proposed method is superior to conventional segmentation methods. The source code of the proposed method can be downloaded from https://github.com/hlim-kist/ma_mts

Machine Learning and Deep Learning Methods in Mining Operations: a Data-Driven SAG Mill Energy Consumption Prediction Application

Semi-autogenous grinding mills play a critical role in the processing stage of many mining operations. They are also one of the most intensive energy consumers of the entire process. Current forecasting techniques of energy consumption base their inferences on feeding ore mineralogical features, SAG dimensions, and operational variables. Experts recognize their capabilities to provide adequate guidelines but also their lack of accuracy when real-time forecasting is desired. As an alternative, we propose the use of real-time operational variables (feed tonnage, bearing pressure, and spindle speed) to forecast the upcoming energy consumption via machine learning and deep learning techniques. Several predictive methods were studied: polynomial regression, k-nearest neighbor, support vector machine, multilayer perceptron, long short-term memory, and gated recurrent units. A step-by-step workflow on how to deal with real datasets, and how to find optimum models and final model selection is presented. In particular, recurrent neural networks achieved the best forecasting metrics in the energy consumption prediction task. The workflow has the potential of being extended to any other temporal and multivariate mineral processing datasets.

Identifying temporal molecular signatures underlying cardiovascular diseases: A data science platform

ObjectiveDuring cardiovascular disease progression, molecular systems of myocardium (e.g., a proteome) undergo diverse and distinct changes. Dynamic, temporally-regulated alterations of individual molecules underlie the collective response of the heart to pathological drivers and the ultimate development of pathogenesis. Advances in high-throughput omics technologies have enabled cost-effective, temporal profiling of targeted systems in animal models of human diseases. However, computational analysis of temporal patterns from omics data remains challenging. In particular, bioinformatic pipelines involving unsupervised statistical approaches to support cardiovascular investigations are lacking, which hinders one's ability to extract biomedical insights from these complex datasets. Approach and resultsWe developed a non-parametric data analysis platform to resolve computational challenges unique to temporal omics datasets. Our platform consists of three modules. Module I preprocesses the temporal data using either cubic splines or principal component analysis (PCA), and it simultaneously accomplishes the tasks on missing data imputation and denoising. Module II performs an unsupervised classification by K-means or hierarchical clustering. Module III evaluates and identifies biological entities (e.g., molecular events) that exhibit strong associations to specific temporal patterns. The jackstraw method for cluster membership has been applied to estimate p-values and posterior inclusion probabilities (PIPs), both of which guided feature selection. To demonstrate the utility of the analysis platform, we employed a temporal proteomics dataset that captured the proteome-wide dynamics of oxidative stress induced post-translational modifications (O-PTMs) in mouse hearts undergoing isoproterenol (ISO)-induced hypertrophy. ConclusionWe have created a platform, CV.Signature.TCP, to identify distinct temporal clusters in omics datasets. We presented a cardiovascular use case to demonstrate its utility in unveiling biological insights underlying O-PTM regulations in cardiac remodeling. This platform is implemented in an open source R package (https://github.com/UCLA-BD2K/CV.Signature.TCP).