Multi-source Datasets Research Articles

(ChinaVis 2019) uncertainty visualization in stratigraphic correlation based on multi-source data fusion

As a most important step in geological interpretation, stratigraphic correlation plays important roles in reservoir estimation and geologic modeling. A variety of datasets are used for stratigraphic correlation, such as well-logging data and seismic data, which are collected by different kinds of sensors. However, much uncertainty will be generated in the traditional course of stratigraphic correlation, because the complex underground geological structures cannot be comprehensively depicted by single dataset. Therefore, in this paper, we propose a visualization system to present and reduce the uncertainty in stratigraphic correlation based on the fusion analysis of multi-source datasets. First, a synthetic seismogram is modeled for each drilling well and a traditional time-depth conversion is conducted to match the seismic data and logging data. Then, an uncertainty model is proposed to quantify the depth difference between seismic horizons and stratigraphic structures extracted from different datasets. Furthermore, a set of visual designs are integrated into an uncertainty visualization system, enabling users to conduct intuitive uncertainty exploration and supervised optimization of stratigraphic correlation. Case studies based on real-world datasets and interviews with domain experts have demonstrated the effectiveness of our system in analyzing the uncertainty of stratigraphic correlation and refining the results of geological interpretation.

Visual exploration of mobility dynamics based on multi-source mobility datasets and POI information

Learning more about human mobility is crucial for official decision makers and urban planners. Mobility datasets characterize human daily travel behaviors. Most current researches only studied human dynamics from one kind of mobility dataset. However, people may use different means of transportation to different places for different purposes. Besides, the spatial distributions of different types of point of interests (POIs) reflect the land-use types. How to jointly analyze the multi-source mobility datasets and POI information is a great challenge. In this paper, we adopt multi-source datasets, including taxi dataset, public bicycle system dataset and POI dataset, and propose a visual analytics methodology to explore human mobility dynamics insightfully. Two region–feature–time tensors are constructed first, and a tensor decomposition method is employed to classify the mobility patterns automatically. Then, a new POI–mobility glyph is designed to visualize multi-source datasets in a compact manner. Several interactive visual views are also designed to visualize the spatiotemporal patterns from global, regional and locational perspectives. Case studies based on real-world datasets demonstrate the effectiveness of our method, which supports the visual reasoning of trip purposes and mixed urban functions.

Airborne and spaceborne remote sensing for archaeological and cultural heritage applications: A review of the century (1907–2017)

Archaeological and cultural heritage (ACH), one of the core carriers of cultural diversity on our planet, has a direct bearing on the sustainable development of mankind. Documenting and protecting ACH is the common responsibility and duty of all humanity. It is governed by UNESCO along with the scientific communities that foster and encourage the use of advanced non-invasive techniques and methods for promoting scientific research into ACH and conservation of ACH sites. The use of remote sensing, a non-destructive tool, is increasingly popular by specialists around the world as it allows fast prospecting and mapping at multiple scales, rapid analysis of multisource datasets, and dynamic monitoring of ACH sites and their surrounding environments. The cost of using remote sensing is lower or even zero in practical applications. In this review, in order to discuss the advantages of airborne and spaceborne remote sensing (ASRS), the principles that make passive (photography, multispectral and hyperspectral) and active (synthetic aperture radar (SAR) and light detection and ranging radar (LiDAR)) imaging techniques suitable for ACH applications are first summarized and pointed out; a review of ASRS and the methodologies used over the past century is then presented together with relevant highlights from well-known research projects. Selected case studies from Mediterranean regions to East Asia illustrate how ASRS can be used effectively to investigate and understand archaeological features at multiple -scales and to monitor and assess the conservation status of cultural heritage sites in the context of sustainable development. An in-depth discussion on the limitations of ASRS and associated remaining challenges is presented along with conclusions and a look at future trends.

A global land cover map produced through integrating multi-source datasets

ABSTRACTIn the past decades, global land cover datasets have been produced but also been criticized for their low accuracies, which have been affecting the applications of these datasets. Producing a new global dataset requires a tremendous amount of efforts; however, it is also possible to improve the accuracy of global land cover mapping by fusing the existing datasets. A decision-fuse method was developed based on fuzzy logic to quantify the consistencies and uncertainties of the existing datasets and then aggregated to provide the most certain estimation. The method was applied to produce a 1-km global land cover map (SYNLCover) by integrating five global land cover datasets and three global datasets of tree cover and croplands. Efforts were carried out to assess the quality: 1) inter-comparison of the datasets revealed that the SYNLCover dataset had higher consistency than these input global land cover datasets, suggesting that the data fusion method reduced the disagreement among the input datasets; 2) quality assessment using the human-interpreted reference dataset reported the highest accuracy in the fused SYNLCover dataset, which had an overall accuracy of 71.1%, in contrast to the overall accuracy between 48.6% and 68.9% for the other global land cover datasets.

Multi-granulation Rough Sets and Uncertainty Measurement for Multi-source Fuzzy Information System

Rough set theory is an effective mathematical tool to deal with uncertain information. With the arrival of the information age, we need to handle not only single-source data sets, but also multi-source data sets. In real life; most of the data we face are fuzzy multi-source data sets. However, the rough set model has not been found for multi-source fuzzy information systems. This paper aims to study how to use the rough set model in multi-source fuzzy environment. Firstly, we define a distance formula between two objects in an information table and further propose a tolerance relation through this formula. Secondly, the supporting characteristic function is proposed by the inclusion relation between tolerance classes and concept set X. And then, from the perspective of multi-granulation, each information source is regarded as a granularity. The optimistic, pessimistic, generalized multi-granulation rough set model and some important properties are discussed in multi-source fuzzy information systems. At the same time, the uncertainty measurement are considered for the different models. Finally, some experiments are carried out to interpret and evaluate the validity and significance of the approach.

An online log template extraction method based on hierarchical clustering

The raw log messages record extremely rich system, network, and application running dynamic information that is a good data source for abnormal detection. Log template extraction is an important prerequisite for log sequence anomaly detection. The problems of the existing log template extraction methods are mostly offline, and the few online methods have insufficient F1-score in multi-source log data. In view of the shortcomings of the existing methods, an online log template extraction method called LogOHC is proposed. Firstly, the raw log messages are preprocessed, and the word distributed representation (word2vec) is used to vectorize the log messages online. Then, the online hierarchical clustering algorithm is applied, and finally, log templates are generated. The experimental analysis shows that LogOHC has a higher F1-score than the existing log template extraction methods, is suitable for multi-source log data sets, and has a shorter single-step execution time, which can meet the requirements of online real-time processing.

Discovering cryptic species in the Aspiciliella intermutans complex (Megasporaceae, Ascomycota) - First results using gene concatenation and coalescent-based species tree approaches.

Taxonomic identifications in some groups of lichen-forming fungi have been challenge largely due to the scarcity of taxonomically relevant features and limitations of morphological and chemical characters traditionally used to distinguish closely related taxa. Delineating species boundaries in closely related species or species complexes often requires a range of multisource data sets and comprehensive analytical methods. Here we aim to examine species boundaries in a group of saxicolous lichen forming fungi, the Aspiciliella intermutans complex (Megasporaceae), widespread mainly in the Mediterranean. We gathered DNA sequences of the nuclear ribosomal internal transcribed spacer (nuITS), the nuclear large subunit (nuLSU), the mitochondrial small subunit (mtSSU) ribosomal DNA, and the DNA replication licensing factor MCM7 from 80 samples mostly from Iran, Caucasia, Greece and eastern Europe. We used a combination of phylogenetic strategies and a variety of empirical, sequence-based species delimitation approaches to infer species boundaries in this group. The latter included: the automatic barcode gap discovery (ABGD), the multispecies coalescent approach *BEAST and Bayesian Phylogenetics and Phylogeography (BPP) program. Different species delimitation scenarios were compared using Bayes factors species delimitation analysis. Furthermore, morphological, chemical, ecological and geographical features of the sampled specimens were examined. Our study uncovered cryptic species diversity in A. intermutans and showed that morphology-based taxonomy may be unreliable, underestimating species diversity in this group of lichens. We identified a total of six species-level lineages in the A. intermutans complex using inferences from multiple empirical operational criteria. We found little corroboration between morphological and ecological features with our proposed candidate species, while secondary metabolite data do not corroborate tree topology. The present study on the A. intermutans species-complex indicates that the genus Aspiciliella, as currently circumscribed, is more diverse in Eurasia than previously expected.

Geological characterization of the Chang'e-4 landing area on the lunar farside

On January 3, 2019, China's Chang'e-4 probe, accomplishes the first-ever soft landing on Moon's farside in the Von Kármán crater floor mare volcanism plain (177.59°E, 45.46°S) within the South Pole-Aitken (SPA) basin. Its surface in-situ measurements would provide the first “ground truth” for lunar farside volcanism and SPA materials. We present a detailed geologic context, topographical, morphological, quantitative geochemical and mineralogical characterization of a 20 × 20 km area centered at the Chang'e-4 landing site, using the latest multi-source high-resolution orbital data sets. The landing area is very flat at a baseline of 30 m, with 90% of surface having slope <5°, and deficient of surface boulder exposures. The landing area mare is superposed by abundant sub-kilometer, block-poor circular impact craters and secondary craters in chains and clusters. Mare basalts at the landing site is dominated by low-titanium basalts, and appear to be less mafic and iron-depleted than all typical kinds of retuned lunar basalt samples and may represent a new kind of mare basalt. The landing site mare is heavily sculptured by a set of linear parallel ridged and furrowed textures formed by ballistic ejecta from the Finsen crater, which are characterized by a more feldspathic composition, while with elevated orthopyroxene abundance, and may represent compositional properties of the primitive SPA basin floor materials. We propose the Finsen ejecta and mare basalt outcrops at the landing area as prioritized targets for Chang'e-4 surface geological and spectroscopic explorations. Follow-on mission data interpretations should consider the mixing effect of local mare basalts and distant feldspathic materials.

Structure from Motion Multisource Application for Landslide Characterization and Monitoring: The Champlas du Col Case Study, Sestriere, North-Western Italy.

Structure from Motion (SfM) is a powerful tool to provide 3D point clouds from a sequence of images taken from different remote sensing technologies. The use of this approach for processing images captured from both Remotely Piloted Aerial Vehicles (RPAS), historical aerial photograms, and smartphones, constitutes a valuable solution for the identification and characterization of active landslides. We applied SfM to process all the acquired and available images for the study of the Champlas du Col landslide, a complex slope instability reactivated in spring 2018 in the Piemonte Region (north-western Italy). This last reactivation of the slide, principally due to snow melting at the end of the winter season, interrupted the main road used to reach Sestriere, one of the most famous ski resorts in north-western Italy. We tested how SfM can be applied to process high-resolution multisource datasets by processing: (i) historical aerial photograms collected from five diverse regional flights, (ii) RGB and multi-spectral images acquired by two RPAS, taken in different moments, and (iii) terrestrial sequences of the most representative kinematic elements due to the evolution of the landslide. In addition, we obtained an overall framework of the historical development of the area of interest, and distinguished several generations of landslides. Moreover, an in-depth geomorphological characterization of the Champlas du Col landslide reactivation was done, by testing a cost-effective and rapid methodology based on SfM principles, which is easily repeatable to characterize and investigate active landslides.

Exploring the Spatial Pattern and Influencing Factors of Land Carrying Capacity in Wuhan

Land carrying capacity is an important factor for urban sustainable development. It provides essential insights into land resource allocation and management. In this article, we propose a framework to evaluate land carrying capacity with multiple data sources from the first geographical census and socioeconomic statistics. In particular, an index, Land Resource Pressure (LRP), is proposed to evaluate the land carrying capacity, and a case study was carried out in Wuhan. The LRP of Wuhan was calculated on 250 m * 250 m grids, and showed a circularly declining pattern from central to outer areas. We collected its influencing factors in terms of nature resources, economy, transportation and urban construction, and then analyzed its causes via geographically weighted (GW) models. Firstly, pair-wise correlations between LRP and each influencing factor were explored via the GW correlation coefficients. These local estimates provide an important precursor for the following quantitative analysis via the GW regression (GWR) technique. The GWR coefficient estimates interpret the influences on LRP in a localized view. Results show that per capita gross domestic product (PerGDP) showed a higher absolute estimate among all factors, which proves that PerGDP has a relieving effect on LRP, especially in the southwestern areas. Overall, this study provides a technical framework to evaluate land carrying capacity with multi-source data sets and explore its localized influences via GW models, which could provide practical guidance for similar studies in other cities.

Estimation of Net Rice Production by Remote Sensing and Multi Source Datasets

Estimation of Net Rice Production by Remote Sensing and Multi Source Datasets

A Comparative Study of Aggressive Driving Behavior Recognition Algorithms Based on Vehicle Motion Data

Aggressive driving, amongst inappropriate driving behaviors, is largely responsible for leading to traffic accidents, which threatens both the safety and property of human beings. With the objective to reduce traffic accidents and improve road safety, effective and reliable aggressive driving recognition methods, which enables the development of driving behavior analysis and early warning systems, are urgently needed. Most recently, the research focus of aggressive recognition has shifted to the use of vehicle motion data, which has emerged as a new tool for traffic phenomenon explanation. As aggressive driving corresponds to sudden variations in data, they can be recognized based on the recorded vehicle motion data. In this paper, several kinds of anomaly recognition algorithms are studied and compared, using the motion data collected by the accelerometer and gyroscope of a smartphone mounted on the vehicle. Gaussian mixture model (GMM), partial least squares regression (PLSR), wavelet transformation, and support vector regression (SVR) are considered as the representative algorithms of statistical regression, time series analysis, and machine learning, respectively. These algorithms are evaluated by the three widely used validation metrics, including F1-score, precision, and recall. The empirical results show that GMM, PLSR, and SVR are promising methods for aggressive driving recognition. GMM and SVR outperform PLSR when only single-source dataset is used. The improvement of F1-score is almost 0.1. PLSR performs the best when multi-source datasets are used, and the F1-score is 0.77. GMM and SVR are more robust to hyperparameter. In addition, incorporating multi-source datasets helps improve the accuracy of aggressive driving behavior recognition.

Three-Way Decision in a Multi-Source Information System and Its Applications

Three-way decision (3WD) is a decision that conforms to human's cognitive pattern and offers a new visual angle for solving practical decision-making problems. An information system (IS) represents relationships between objects and attributes. And a multi-source information system (MSIS) is an IS which composes of multi-source data sets. This paper presents 3WD in an MSIS as well as gives its application in petroleum project investment. Considering that risks are uncertain, loss functions are first given by means of interval numbers. Then, multi-granulation decision-theoretic rough set (MGDTRS) models in a given MSIS are proposed from the point of view of multi-granulation. Next, based on the idea of a decision-theoretic rough set (DTRS), the optimistic and pessimistic 3WDs in the MSIS are proposed. Finally, an example of petroleum project investment is used to support the feasibility of the proposed decision method.

Towards a unified multi-source-based optimization framework for multi-label learning

In the era of Big Data, a practical yet challenging task is to make learning techniques more universally applicable in dealing with the complex learning problem, such as multi-source multi-label learning. While some of the early work have developed many effective solutions for multi-label classification and multi-source fusion separately, in this paper we learn the two problems together, and propose a novel method for the joint learning of multiple class labels and data sources, in which an optimization framework is constructed to formulate the learning problem, and the result of multi-label classification is induced by the weighted combination of the decisions from multiple sources. The proposed method is responsive in exploiting the label correlations and fusing multi-source data, especially in the fusion of long-tail data. Experiments on various multi-source multi-label data sets reveal the advantages of the proposed method.

Evaluation of All-for-One Tourism in Mountain Areas Using Multi-Source Data

All-for-one tourism is a new viewpoint of tourism development involving overall planning and cooperative mechanisms. Over the past few years, the researchers have put forward many conceptual models to guide the top-level design and specific practice of all-for-one tourism. However, these studies mainly focus on social, economic and cultural effect in mature tourism areas, lacking comprehensive analysis from geographical perspective and neglecting the underdeveloped regions. In this paper, we attempt to apply geographic information system technology to tourism evaluation, exploring the approach of all-for-one tourism development in mountain regions. Zunyi city is selected as the research region and evaluated on the abundance, quality and spatial pattern of tourism resources, climate comfort, natural disaster possibility, and convenience of infrastructure or social service. Multi-source datasets collected from websites, reanalysis data, remote sensing products and observation stations are used. Based on data analysis, some recommendations including enriching cultural tourism products through cultural creativity, ensuring regional coordinated development through spatial optimization, respecting the spatiotemporal characteristics of climate and the laws of nature, and strengthening construction of infrastructure, are discussed to promote the healthy development of all-for-one tourism.

A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data

The primary objective of this study is to investigate how the deep learning approach contributes to citywide short-term crash risk prediction by leveraging multi-source datasets. This study uses data collected from Manhattan in New York City to illustrate the procedure. The following multiple datasets are collected: crash data, large-scale taxi GPS data, road network attributes, land use features, population data and weather data. A spatiotemporal convolutional long short-term memory network (STCL-Net) is proposed for predicting the citywide short-term crash risk. A total of nine prediction tasks are conducted and compared, including weekly, daily and hourly models with 8 × 3, 15 × 5 and 30 × 10 grids, respectively. The results suggest that the prediction performance of the proposed model decreases as the spatiotemporal resolution of prediction task increases. Moreover, four commonly-used econometric models, and four state-of-the-art machine-learning models are selected as benchmark methods to compare with the proposed STCL-Net for all the crash risk prediction tasks. The comparative analyses suggest that in general the proposed STCL-Net outperforms the benchmark methods for different crash risk prediction tasks in terms of higher prediction accuracy rate and lower false alarm rate. The results verify that the proposed spatiotemporal deep learning approach performs better at capturing the spatiotemporal characteristics for the citywide short-term crash risk prediction. In addition, the comparative analyses also reveal that econometric models perform better than machine-learning models in weekly crash risk prediction tasks, while they exhibit worse results than machine-learning models in daily crash risk prediction tasks. The results can potentially guide transportation safety engineers to select appropriate methods for different crash risk prediction tasks.

Evaluation of Citrus Gummosis disease dynamics and predictions with weather and inversion based leaf optical model

One of the major threats for crops around the world due to pest and diseases, which can impact the health, economy, environment, and society at large. In general, several issues related to crop yield improvement arises due to insufficient and inadequate knowledge. Therefore, there is a need to develop viable models that incorporate various weather-soil-plant factors, which can give better understanding of the crop and enable timely interventions for yield improvement. To overcome Citrus Gummosis disease related issues and increase the Citrus productivity, seven different datasets Temperature (T), Humidity (Rh), Rainfall (R), Soil Moisture (SM), Soil Temperature (ST), Leaf Area Index (LAI) and Chlorophyll (Cab) were used. Considering various plant, soil and environmental factors, the Citrus Gummosis prediction model has been developed with the multi-source datasets from June 2014 to November 2016 using Support vector regression (SVR) and multilinear regression (MLR). The research is carried out for healthy (5–10 Yrs. and 11–15 Yrs.) and unhealthy (5–10 Yrs. and 11–15 Yrs.) age group of plants. Inverse PROSAIL model has been simulated for retrieving citrus Cab and LAI values. These values were validated with the actual field data. Both the weather and soils based disease prediction models has been developed and validated with MLR and SVR. Further, the influence of Gummosis disease on plant parameters was also studies with the new contribution of Biophysical variables (LAI and Cab) based statistical prediction model. The SVR model gave fairly good performance as compared to MLR. In addition to the separate models a the combined scenario approach (Integrated Gummosis Disease Forecast Model: IGDFM) is designed to understand the interconnectivity of the parametric conditions (weather-soil- plant parameters) with disease physiology with respect to different age group of the plants. The RMSE of proposed approach for higher age group plants (i.e. 11–15 years) in the combined scenario was 0.9061 and 0.8518 for SVR and MLR methods, respectively. It is envisaged that this study could enable farmers to recognize and predict the timing and severity of the Gummosis disease in Citrus and thereby achieve yield improvement.

Feature Importance Analysis for Local Climate Zone Classification Using a Residual Convolutional Neural Network with Multi-Source Datasets

Global Local Climate Zone (LCZ) maps, indicating urban structures and land use, are crucial for Urban Heat Island (UHI) studies and also as starting points to better understand the spatio-temporal dynamics of cities worldwide. However, reliable LCZ maps are not available on a global scale, hindering scientific progress across a range of disciplines that study the functionality of sustainable cities. As a first step towards large-scale LCZ mapping, this paper tries to provide guidance about data/feature choice. To this end, we evaluate the spectral reflectance and spectral indices of the globally available Sentinel-2 and Landsat-8 imagery, as well as the Global Urban Footprint (GUF) dataset, the OpenStreetMap layers buildings and land use and the Visible Infrared Imager Radiometer Suite (VIIRS)-based Nighttime Light (NTL) data, regarding their relevance for discriminating different Local Climate Zones (LCZs). Using a Residual convolutional neural Network (ResNet), a systematic analysis of feature importance is performed with a manually-labeled dataset containing nine cities located in Europe. Based on the investigation of the data and feature choice, we propose a framework to fully exploit the available datasets. The results show that GUF, OSM and NTL can contribute to the classification accuracy of some LCZs with relatively few samples, and it is suggested that Landsat-8 and Sentinel-2 spectral reflectances should be jointly used, for example in a majority voting manner, as proven by the improvement from the proposed framework, for large-scale LCZ mapping.

Assessing the Variability of Corn and Soybean Yields in Central Iowa Using High Spatiotemporal Resolution Multi-Satellite Imagery

The utility of remote sensing data in crop yield modeling has typically been evaluated at the regional or state level using coarse resolution (&gt;250 m) data. The use of medium resolution data (10–100 m) for yield estimation at field scales has been limited due to the low temporal sampling frequency characteristics of these sensors. Temporal sampling at a medium resolution can be significantly improved, however, when multiple remote sensing data sources are used in combination. Furthermore, data fusion approaches have been developed to blend data from different spatial and temporal resolutions. This paper investigates the impacts of improved temporal sampling afforded by multi-source datasets on our ability to explain spatial and temporal variability in crop yields in central Iowa (part of the U.S. Corn Belt). Several metrics derived from vegetation index (VI) time-series were evaluated using Landsat-MODIS fused data from 2001 to 2015 and Landsat-Sentinel2-MODIS fused data from 2016 and 2017. The fused data explained the yield variability better, with a higher coefficient of determination (R2) and a smaller relative mean absolute error than using a single data source alone. In this study area, the best period for the yield prediction for corn and soybean was during the middle of the growing season from day 192 to 236 (early July to late August, 1–3 months before harvest). These findings emphasize the importance of high temporal and spatial resolution remote sensing data in agricultural applications.

Controlled feature selection and compressive big data analytics: Applications to biomedical and health studies.

The theoretical foundations of Big Data Science are not fully developed, yet. This study proposes a new scalable framework for Big Data representation, high-throughput analytics (variable selection and noise reduction), and model-free inference. Specifically, we explore the core principles of distribution-free and model-agnostic methods for scientific inference based on Big Data sets. Compressive Big Data analytics (CBDA) iteratively generates random (sub)samples from a big and complex dataset. This subsampling with replacement is conducted on the feature and case levels and results in samples that are not necessarily consistent or congruent across iterations. The approach relies on an ensemble predictor where established model-based or model-free inference techniques are iteratively applied to preprocessed and harmonized samples. Repeating the subsampling and prediction steps many times, yields derived likelihoods, probabilities, or parameter estimates, which can be used to assess the algorithm reliability and accuracy of findings via bootstrapping methods, or to extract important features via controlled variable selection. CBDA provides a scalable algorithm for addressing some of the challenges associated with handling complex, incongruent, incomplete and multi-source data and analytics challenges. Albeit not fully developed yet, a CBDA mathematical framework will enable the study of the ergodic properties and the asymptotics of the specific statistical inference approaches via CBDA. We implemented the high-throughput CBDA method using pure R as well as via the graphical pipeline environment. To validate the technique, we used several simulated datasets as well as a real neuroimaging-genetics of Alzheimer’s disease case-study. The CBDA approach may be customized to provide generic representation of complex multimodal datasets and to provide stable scientific inference for large, incomplete, and multisource datasets.