Search

Initiatives of open data promote the online publication and sharing of large amounts of geologic data. How to retrieve information and discover knowledge from the big data is an ongoing challenge. In this paper, we developed an ontology-driven data integration and visualization pilot system for exploring information of regional geologic time, paleontology, and fundamental geology. The pilot system ( http://www2.cs.uidaho.edu/∼max/gts/ ) implemented the following functions: modeling and visualization of a geologic time scale ontology of North America, interactive retrieval and display of fossil information, geologic map information query and comparison with fossil information. A few case studies were carried out in the pilot system for querying fossil occurrence records from Plaeobiology Database and comparing them with information from the USGS geologic map services. The results show that, to improve the compatibility between local and global geologic standards, bridge gaps between different data sources, and create smart geoscience data services, it is necessary to further extend and improve the existing geoscience ontologies and use them to support functions to explore the open data. [ABSTRACT FROM AUTHOR]

Geoscience literature published online is an important part of open data, and brings both challenges and opportunities for data analysis. Compared with studies of numerical geoscience data, there are limited works on information extraction and knowledge discovery from textual geoscience data. This paper presents a workflow and a few empirical case studies for that topic, with a focus on documents written in Chinese. First, we set up a hybrid corpus combining the generic and geology terms from geology dictionaries to train Chinese word segmentation rules of the Conditional Random Fields model. Second, we used the word segmentation rules to parse documents into individual words, and removed the stop-words from the segmentation results to get a corpus constituted of content-words. Third, we used a statistical method to analyze the semantic links between content-words, and we selected the chord and bigram graphs to visualize the content-words and their links as nodes and edges in a knowledge graph, respectively. The resulting graph presents a clear overview of key information in an unstructured document. This study proves the usefulness of the designed workflow, and shows the potential of leveraging natural language processing and knowledge graph technologies for geoscience. [ABSTRACT FROM AUTHOR]

The National Climate Assessment of the U.S. Global Change Research Program (USGCRP) analyzes and presents the impacts of climate change on the United States. The provenance information in the assessment is important because the assessment findings are of great public and academic concern and are used in policy and decision-making. By applying a use case-driven iterative methodology, we developed information models and ontology to represent the content structure of the recent National Climate Assessment draft report and its associated provenance information. We tested the ontology by using it in pilot systems serving information about instances of chapters, scientific findings, figures, tables, images, datasets, references, people, and organizations, etc. in the draft report, as well as interrelationships among those instances. The results successfully help users trace provenance in the draft report, such as finding all the journal articles from which a figure in the report was derived. The provenance information in our work was maintained in the context of the “Web of Data”. In addition to the pilot systems we developed, other tools and services are also able to retrieve and utilize the provenance information. Our work is part of a Global Change Information System coordinated by the USGCRP that will eventually cover provenance information for the entire scope of global change research. Such a system will greatly increase understanding, credibility and trust in the global change research and foster reproducibility of scientific results and conclusions. [ABSTRACT FROM AUTHOR]

Abstract: Geological maps are increasingly published and shared online, whereas tools and services supporting information retrieval and knowledge discovery are underdeveloped. In this study, we developed an ontology of geological time scale by using a Resource Description Framework model to represent the ordinal hierarchical structure of the geological time scale and to encode collected annotations of geological time scale concepts. We also developed an animated graphical view of the developed ontology, and functions for interactions between the ontology, the animation and online geological maps published as layers of OGC Web Map Service. The featured functions include automatic annotations for geological time concepts recognized from a geological map, changing layouts in the animation to highlight a concept, showing legends of geological time contents in an online map with the animation, and filtering out and generalizing geological time features in an online map by operating the map legend shown in the animation. We set up a pilot system and carried out a user survey to test and evaluate the usability and usefulness of the developed ontology, animation and interactive functions. Results of the pilot system and the user survey demonstrate that our works enhance features of online geological map services and they are helpful for users to understand and to explore geological time contents and features, respectively, of a geological map. [Copyright &y& Elsevier]

Abstract: The usefulness of online geological maps is hindered by linguistic barriers. Multilingual geoscience thesauri alleviate linguistic barriers of geological maps. However, the benefits of multilingual geoscience thesauri for online geological maps are less studied. In this regard, we developed a multilingual thesaurus of geological time scale (GTS) to alleviate linguistic barriers of GTS records among online geological maps. We extended the Simple Knowledge Organization System (SKOS) model to represent the ordinal hierarchical structure of GTS terms. We collected GTS terms in seven languages and encoded them into a thesaurus by using the extended SKOS model. We implemented methods of characteristic-oriented term retrieval in JavaScript programs for accessing Web Map Services (WMS), recognizing GTS terms, and making translations. With the developed thesaurus and programs, we set up a pilot system to test recognitions and translations of GTS terms in online geological maps. Results of this pilot system proved the accuracy of the developed thesaurus and the functionality of the developed programs. Therefore, with proper deployments, SKOS-based multilingual geoscience thesauri can be functional for alleviating linguistic barriers among online geological maps and, thus, improving their interoperability. [Copyright &y& Elsevier]

Abstract: Semantic interoperability of mineral exploration geodata is a long-term concern in mining projects. Inconsistent conceptual schemas and heterogeneous professional terms among various geodata sources in a mining project often hinder their efficient use and/or reuse. Our study of a controlled vocabulary focuses on interoperability of mineral exploration geodata of different mining projects of a mining group in China. In order to achieve this purpose, a proper representation of concepts and their inter-relationships in the knowledge domain of mineral exploration for mining projects is proposed. In addition, we propose that for wider interoperability of mining project geodata the controlled vocabulary underpinning them should be interoperable with concepts in related applications in the mineral exploration domain. In developing our controlled vocabulary, we adopted/adapted national standards of geosciences taxonomies and terminologies. The organization structure of terms, coding method, metadata schema for database applications and an extensible structure of our controlled vocabulary are discussed. The controlled vocabulary we developed was then used to reconcile heterogeneous geodata and to set up integrated databases for various mining projects of the mining group. Our study shows that a properly organized controlled vocabulary not only allows for efficient reconciliation of heterogeneous geodata sources in similar or related projects, but also makes related geodata to be interoperable with extramural applications in the same knowledge domain. [ABSTRACT FROM AUTHOR]

Abstract: Compositing of borehole assay intervals based on economic aspects is a primary step when the cross-sectional method is applied in orebody modelling and mineral resources estimation. The compositing is important because the resulting ore composites eventually determine the outlines of orebody models. However, numerous boreholes and borehole intervals make ore compositing tedious and time-consuming for manual work. A computer program for compositing is desirable to facilitate the task and to obtain accurate results. In the design of computer algorithms for such a computer program, dilution is the most difficult part because dilution means adding waste intervals into an ore composite in order to transfer it from unminable to minable and this causes some special situations in a compositing procedure. In order to obtain economically optimized compositing results, we paid special attention to dilution in the designed algorithms. A demo program has been developed to test and implement these algorithms using borehole assay datasets from a mine site in China. Results show the accuracy of designed computer algorithms and the feasibility of applying a computer program in compositing of borehole assay intervals. [Copyright &y& Elsevier]

Remediating the agricultural soil polluted by cadmium (Cd) is a serious issue in China. Hydrochar showed its potential to purify Cd-contaminated water and improve Cd-contaminated soil due to its vast amounts of macro- and microporous structures. In this study, three concentration gradients of nitric acid (HNO 3 , mass fraction: 5%, 10%, 15%) were implemented to age pristine wheat straw hydrochar (N0-HC) aiming to improve surface physiochemical properties. Four HNO 3 -aging hydrochars named N0-HC, N5-HC, N10-HC, N15-HC were used to both remove Cd2+ from aqueous solution and improve soil properties. Results showed that HNO 3 -aging significantly improved the Cd2+ adsorption capacity by 1.9–9.9 folds compared to crude hydrochar due to the increased specific surface area (by 1.5–6.5 folds) and oxygen-containing functional group abundance (by 4.5–22.1%). Besides, initial solution pH of 8 or environmental temperature of 318.15 K performed the best Cd2+ adsorption capacity. Furthermore, the process of Cd2+ adsorption was fitted best to pseudo-second-order (R 2 = 0.95) and Langmuir models (R 2 = 0.98), respectively. Nanjing 46 (Oryza sativa L) and HNO 3 -aging hydrochars were furtherly applied into Cd-contaminated paddy soil to investigate the mitigation of Cd translation from soil to rice. N15-HC-1% (w/w) performed the best effect on reducing cadmium accumulation in various parts of rice plants. Overall, this research provided an approach to improve hydrochar capacity to remove Cd2+ from aqueous solution and mitigate Cd translation from soil to rice. [Display omitted] • Nitric acid modification increased specific surface area by 1.5–6.5 folds. • Nitric acid modification enhanced oxygen-containing groups abundance by 4.5–22.1%. • The Cd2+ sorption was improved best by 9.9 folds after nitric acid modification. • N15-HC-1% (w/w) performed best on reducing cadmium accumulation in rice plant. [ABSTRACT FROM AUTHOR]

Ontologies and vocabularies are an effective way to promote data interoperability in open data and open science. The deep time knowledge graph is one of the most discussed and studied topics in geoscience ontologies and vocabularies. The continuous evolution of deep time concepts calls for a mechanism of version control and organization to reduce the semantic ambiguity. In this paper we propose a new structure for version control and tracking of concepts, attributes and topological relationships in the deep time knowledge graph. In our work we have reused the existing ontologies for geologic time scale and vocabularies for the International (Chrono)stratigraphic Chart (ISC). Through the new structure, we are able to represent the whole version history of the ISC charts (from 2004 to 2018) in a single knowledge graph. Moreover, the resulting knowledge graph is consistent with the existing ontologies and vocabularies. Experiments of SPARQL queries prove the efficiency of this structure for version tracking of concepts and attributes. We are now extending the knowledge graph with concepts from regional and local geologic time standards, such as North America, Europe, Britain, China, and Australia, and building a graphic user interface for the services. In a future work, we will implement the knowledge graph in data integration workflows. We hope this research will spur more discussion and development of methods for version control of knowledge graphs in geoscience and other disciplines. • A novel structure is designed for version control in the deep time knowledge graph. • Existing ontologies and vocabularies are fully reused and accredited. • A vocabulary is built to include all versions of international geologic time scale. • Vocabulary service allows tracking version information of concepts and attributes. [ABSTRACT FROM AUTHOR]

Artificial intelligence and big data technology are important technical means to improve quantitative understanding of natural phenomena in Earth sciences. Large-scale spatial data provides a basic geospatial background for geoscience research. An effective and efficient distributed computing frame for spatial data is an indispensable infrastructure. It is still a challenge for disk-based distributed computing framework to analyze and process large-scale data efficiently. Such a challenge has driven the rapid development of various memory-based distributed computing platforms such as Spark, Flink, Apex, and more. Now, it is urgent to develop an efficient platform-independent distributed computing framework with a unique focus on large-scale spatial data. This paper provides a memory-based distributed computing framework named GeoBeam. It abstracts all the operations of spatial data into spatial pipeline, collection and transforms. Finally, they are encapsulated as feature dataset and feature store interfaces in GIS to shield the details of the underlying distributed operations. Experimental results show that GeoBeam can support efficient range query and processing of large-scale spatial data on Spark cluster and Flink cluster. GeoBeam provides an effective cross-platform distributed computing solution for fast processing of large-scale spatial data. •GeoBeam: An open-source distributed computing framework for spatial big data. •Provide feature set and store interfaces to shield the details of the underlying distributed operations. •Support multiple distributed processing back-ends including Spark, Flink and Apex. •Results prove the effectiveness and efficiency of GeoBeam on processing of big spatial data. [ABSTRACT FROM AUTHOR]

In digital cartography, the automatic generation of random planar patterns and symbols is still an ongoing challenge. Those patterns and symbols of randomness have randomly variated configurations and boundaries, and their generating algorithms are constrained by the shape features, cartographic standards and many other conditions. The fractal geometry offers favorable solutions to simulate random boundaries and patterns. In the work presented in this paper, we used both fractal theory and random Iterated Function Systems (IFS) to develop a method for the automatic generation of random planar patterns and symbols. The marshland and the trough cross-bedding patterns were used as two case studies for the implementation of the method. We first analyzed the morphological characteristics of those two planar patterns. Then we designed algorithms and implementation schemes addressing the features of each pattern. Finally, we ran the algorithms to generate the patterns and symbols, and compared them with the requirements of a few digital cartographic standards. The method presented in this paper has already been deployed in a digital mapping system for practical uses. The flexibility of the method also allows it to be reused and/or adapted in various software platforms for digital mapping. [ABSTRACT FROM AUTHOR]

The Spatiotemporal Weighted Regression (STWR) model is an extension of the Geographically Weighted Regression (GWR) model for exploring the heterogeneity of spatiotemporal processes. A key feature of STWR is that it utilizes the data points observed at previous time stages to make better fit and prediction at the latest time stage. Because the temporal bandwidths and a few other parameters need to be optimized in STWR, the model calibration is computationally intensive. In particular, when the data amount is large, the calibration of STWR becomes heavily time-consuming. For example, with 10,000 points in 10 time stages, it takes about 2307 s for a single-core PC to process the calibration of STWR. Both the distance and the weighted matrix in STWR are memory intensive, which may easily cause memory insufficiency as data amount increases. To improve the efficiency of computing, we developed a parallel computing method for STWR by employing the Message Passing Interface (MPI). A cache in the MPI processing approach was proposed for the calibration routine. Also, a matrix splitting strategy was designed to address the problem of memory insufficiency. We named the overall design as Fast STWR (F-STWR). In the experiment, we tested F-STWR in a High-Performance Computing (HPC) environment with a total number of 204,611 observations in 19 years. The results show that F-STWR can significantly improve STWR's capability of processing large-scale spatiotemporal data. • A parallel method (F-STWR) for the Spatiotemporal Weighted Regression (STWR). • A matrix splitting approach is developed for memory saving in STWR. • F-STWR significantly improves STWR's capability of processing large-scale data. • F-STWR extends the scope of STWR for various research topics in the real world. [ABSTRACT FROM AUTHOR]

• Super-resolution images generated by the deep learning models can facilitate the extraction of mangrove features. • The image quality evaluation metrics of PSNR and SSIM are unsuitable for evaluating the mangrove extraction from super-resolution images. • In terms of mangrove extraction, the deep learning-based super-resolution images may even be better than the original high-resolution images used for model training. Mangroves are an essential component of coastal ecosystems. Accurate and effective identification and extraction of mangrove areas from remote sensing imagery is crucial for monitoring changes in the nearshore ecological environment. High-resolution remote sensing imagery is often difficult or expensive to obtain and usually lacks sufficient temporal coverage, so most monitoring of mangrove forests still relies on medium- or low-resolution imagery, resulting in inaccurate distribution of extracted mangrove areas. The super-resolution (SR) images generated by increasingly widely used deep learning (DL) models may be an alternative. To validate this, we evaluated the extraction of mangroves from SR images generated by four DL models (i.e., enhanced super-resolution generative adversarial networks (ESRGAN), Real-ESRGAN, vast-receptive-field pixel attention network (VapSR), and image restoration methods using swin transformer (SwinIR)). The models were trained on paired (high-resolution) Chinese GF-1 satellite images and (low-resolution) Landsat 8 datasets. The performance of model fitting, vegetation indices, and extracted mangrove areas was evaluated using three commonly used classifiers (i.e., support vector machines (SVM), random forest (RF), and gradient-boosted decision tree (GBDT)) in combination with ground-truth sampling points and public mangrove datasets. Results showed that: (1) the SR images generated by DL-based models can facilitate the extraction of mangrove features. (2) The quality evaluation metrics peak signal-to-noise ratio (PSNR) and structural similarity index measurements (SSIM) cannot be regarded as absolute criteria for SR images, especially when the SR images were used for mangrove feature extractions. (3) The SR image generated by the VapSR model was best suited for extracting mangrove forests and performed even better than the original high-resolution images. (4) Taking a public dataset as a benchmark, the mangrove areas extracted from the SR image generated by the VapSR model were closer to the benchmark than the original Landsat-8 and GF-1. Overall, the DL-based SR models can enhance mangrove extractions and potentially have widespread applications. [ABSTRACT FROM AUTHOR]

As deep learning (DL) gains popularity for its ability to make accurate predictions in various fields, its applications in geosciences are also on the rise. Many studies focus on achieving high accuracy in DL models by selecting models, developing more complex architectures, and tuning hyperparameters. However, the interpretability of these models, or the ability to understand how they make their predictions, is less frequently discussed. To address the challenge of high accuracy but low interpretability of DL models in geosciences, we study rock classification from thin-section photomicrographs of six types of sedimentary rocks, including quartz arenite, feldspathic arenite, lithic arenite, siltstone, oolitic packstone, and dolomite. These rocks' characteristic framework grains and grain textures are their distinguishing features, such as the rounded or oval ooids in oolitic packstone. We first train regular DL models, such as ResNet-50, on these photomicrographs and achieve an accuracy of over 0.94. However, these models make classifications based on features like cracks, cements, and scale bars, which are irrelevant for distinguishing sedimentary rocks in real-world applications. We then propose an attention-based dual network incorporating both global (overall photomicrograph) and local (distinguishing framework grains) features to address this issue. Our proposed model achieves not only high accuracy (0.99) but also provides interpretable feature extractions. Our study highlights the need to consider interpretability and geological knowledge in developing DL models, in addition to aiming for high accuracy. [Display omitted] • Proposed dual network achieves high accuracy (0.99) and interpretable feature extractions for sedimentary rock classification. • Regular DL models achieved high accuracy (>0.94), but relied on irrelevant features for classification. • This study emphasizes importance of interpretability and geological knowledge in developing DL models for geosciences. [ABSTRACT FROM AUTHOR]

Multiple-point statistics (MPS) has shown promise in representing complicated subsurface structures, such as the sedimentary system. The Quaternary sedimentary system possesses prominent anisotropy characteristics. For a practical three-dimensional (3D) application, therefore, the critical challenges come not only from the difficulty of obtaining credible 3D training images, but also from the serious non-stationarity. Moreover, MPS-based simulations are usually performed on a regular Cartesian grid so that they cannot realistically reflect the actual shape and distribution of geological structures. In our work, an integrated MPS-based 3D modeling framework is presented by incorporating the characteristics of Quaternary sediments and the datasets obtained from geological exploration. The framework is embedded into a 3D modeling grid to achieve more precise visualization for the subsurface structures. Following the proposed workflow, we perform the 3D modeling practices for Quaternary sedimentary facies and Quaternary stratigraphic structures by using the datasets from a Quaternary geological survey project at a southeast coastal city in China. The multiple-scale models are constructed by performing the MPS simulations which take into account the constraints of structural conditions. The application verifies the rationality and applicability of the presented workflow where the various structural features are integrated into a unified 3D model to achieve a more realistic characterization. • A 3D stochastic modeling framework for Quaternary sediments using MPS. • MPS realizations and various attributes are integrated into a unified 3D modeling grid. • The workflow reduces the workload in the 3D modeling for Quaternary structures. • Two practical applications demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

The development of analytical and computational techniques and growing scientific funds collectively contribute to the rapid accumulation of geoscience data. The massive amount of existing data, the increasing complexity, and the rapid acquisition rates require novel approaches to efficiently discover scientific stories embedded in the data related to geochemistry and cosmochemistry. Machine learning methods can discover and describe the hidden patterns in intricate geochemical and cosmochemical big data. In recent years, considerable efforts have been devoted to the applications of machine learning methods in geochemistry and cosmochemistry. Here, we review the main applications including rock and sediment identification, digital mapping, water and soil quality prediction, and deep space exploration. Research method improvements, such as spectroscopy interpretation, numerical modeling, and molecular machine learning, are also discussed. Based on the up-to-date machine learning/deep learning techniques, we foresee the vast opportunities of implementing artificial intelligence and developing databases in geochemistry and cosmochemistry studies, as well as communicating geochemists/cosmochemists and data scientists. • Machine learning (ML) can greatly enhance the efficiency of research workflow. • ML opens the door to new opportunities in Earth and Space sciences. • Successful ML applications rely on specialized and curated geochemical databases. • Communication between geochemists and data scientists is mutually beneficial. [ABSTRACT FROM AUTHOR]

In recent years, Earth system sciences are urgently calling for innovation on improving accuracy, enhancing model intelligence level, scaling up operation, and reducing costs in many subdomains amid the exponentially accumulated datasets and the promising artificial intelligence (AI) revolution in computer science. This paper presents work led by the NASA Earth Science Data Systems Working Groups and ESIP machine learning cluster to give a comprehensive overview of AI in Earth sciences. It holistically introduces the current status, technology, use cases, challenges, and opportunities, and provides all the levels of AI practitioners in geosciences with an overall big picture and to "blow away the fog to get a clearer vision" about the future development of Earth AI. The paper covers all the majorspheres in the Earth system and investigates representative AI research in each domain. Widely used AI algorithms and computing cyberinfrastructure are briefly introduced. The mandatory steps in a typical workflow of specializing AI to solve Earth scientific problems are decomposed and analyzed. Eventually, it concludes with the grand challenges and reveals the opportunities to give some guidance and pre-warnings on allocating resources wisely to achieve the ambitious Earth AI goals in the future. • A bird's eye view of the AI application in all spectrum of geosciences is provided. • The mandatory modular steps of typical Earth AI workflows are summarized. • Twelve grand challenges in Earth AI and potential opportunities are introduced. [ABSTRACT FROM AUTHOR]

Data sharing benefits the researcher, the scientific community, and the public by allowing the impact of data to be generalized beyond one project and by making science more transparent. However, many scientific communities have not developed protocols or standards for publishing, citing, and versioning datasets. One community that lags in data management is that of low-temperature geochemistry (LTG). This paper resulted from an initiative from 2018 through 2020 to convene LTG and data scientists in the U.S. to strategize future management of LTG data. Through webinars, a workshop, a preprint, a townhall, and a community survey, the group of U.S. scientists discussed the landscape of data management for LTG – the data-scape. Currently this data-scape includes a "street bazaar" of data repositories. This was deemed appropriate in the same way that LTG scientists publish articles in many journals. The variety of data repositories and journals reflect that LTG scientists target many different scientific questions, produce data with extremely different structures and volumes, and utilize copious and complex metadata. Nonetheless, the group agreed that publication of LTG science must be accompanied by sharing of data in publicly accessible repositories, and, for sample-based data, registration of samples with globally unique persistent identifiers. LTG scientists should use certified data repositories that are either highly structured databases designed for specialized types of data, or unstructured generalized data systems. Recognizing the need for tools to enable search and cross-referencing across the proliferating data repositories, the group proposed that the overall data informatics paradigm in LTG should shift from "build data repository, data will come" to "publish data online, cybertools will find". Funding agencies could also provide portals for LTG scientists to register funded projects and datasets, and forge approaches that cross national boundaries. The needed transformation of the LTG data culture requires emphasis in student education on science and management of data. • Scientists use a wide variety of data repositories for heterogeneous LTG datasets. • Both structured and unstructured databases are needed to store LTG data online. • Powerful search tools and data portals are needed to enable LTG data discovery. [ABSTRACT FROM AUTHOR]

Multiple-point geostatistical (MPS) simulation methods have attracted an enormous amount of attention in earth and environmental sciences due to their ability to enhance extraction and synthesis of heterogeneous patterns. To characterize the subtle features of heterogeneous structures and phenomena, large-scale and high-resolution simulations are often required. Accordingly, the size of simulation grids has increased dramatically. Since MPS is a sequential process for each grid unit along a simulation path, it results in severe computational consumption. In this work, a new hybrid parallel framework is proposed for the case of MPS simulation on large areas with enormous amount of grid cells. Both inter-node-level and intra-node-level parallel strategies are combined in this framework. To maintain the quality of the realizations, we implement a conflict control method adapting to the Monte-Carlo process. Also, an optimization method for the simulation information is embedded to reduce the inter-node communication overhead. A series of synthetic tests were used to verify the availability and performance of the proposed hybrid parallel framework. The results corroborate that the proposed framework can efficiently achieve the high-resolution reproduction and characterization of complex structures and phenomena in earth sciences. • A hybrid parallel framework for MPS is implemented on Tianhe-2 supercomputer. • A multiple-supervisors coordinating parallel strategy is implemented. • An improved conflict control strategy for the Monte-Carlo process is exploited. • Simulation information transform interface for inter-node communication optimization is performed. • A fine-grained parallel method with regional division strategy is proposed. [ABSTRACT FROM AUTHOR]

• Isolation Forest based on a Sliding window algorithm was proposed to identify concrete mixtures outliers. • A dataset of 1030 concrete mixtures were used to show how outliers were identified by three different methods. • Each concrete mixture had seven ingredients and four window sizes were used. • The outcome of the IFS-LOF demonstrated improvement in the accuracy rate than other state-of-the-art LOF algorithms. The rapid development in construction industry, induce a large amounts of concrete data that are usually measured and analyzed everyday naming that concrete is the second usable material on earth. Concrete is made from numerous ingredients that have huge variability either at the design stage or at the testing stage. The main goal of this paper is to quantify the anomalies and outliers during the design phase of concrete mixtures. Concrete mixtures have various percentages of ingredients such as cement, slag, fly ash, water, superplasticizer, fine and coarse aggregates. Machine learning and data mining is considered a very thriving topic in many research fields and its implementation in the construction industry still limited. Concrete community is in need for such a tool to produce an efficient way to efficiently design concrete mixtures. Outliers could occur during the evaluation of samples' measurements that might include human or system errors. The Local Outlier Factor (LOF) algorithm is the most common method used to determine outliers, however, the LOF has some challenges. In this paper, an anomaly-based outlier detection algorithm called Isolation Forest based on a Sliding window for the Local Outlier Factor (IFS-LOF) algorithm, is proposed to solve the limitations of the LOF in evaluating 1030 concrete mixtures. The proposed algorithm works without any previous knowledge of data distribution and executes the process within limited memory and with minimal computational effort. The evaluation of results proved that the IFS-LOF algorithm is more efficient in detecting the sequence of outliers and provided more efficient accuracy that other state of the art LOF algorithms. [ABSTRACT FROM AUTHOR]