Database Building Research Articles

Nest traits for the world's birds

AbstractMotivationA well‐constructed nest is a key element of successful reproduction in most species of birds, and nest morphology varies widely across the class. Macroecological and macroevolutionary studies tend to group nest design into a small number of discrete categories, often based on taxonomic inference. In reality, however, many species display considerable intraspecific variation in their nest‐building behaviour, and broad‐level categories may include several functionally distinct nest types. To address this imprecision in the literature and facilitate future studies of broad‐scale variation in avian parental care, we here introduce a detailed, global comparative database of nest building in birds, together with preliminary correlations between these traits and species‐level environmental variables.Main types of variables containedWe present species‐level data for nest structure, location, height, material composition, sex of builder, building time and nest dimensions.Spatial location and grainGlobal. Maps are presented at the 10 × 10 level.Time period and grainIncluded species are generally extant, although we present some data for recently extinct taxa. The data were collected in 2017–2021 and was drawn from secondary sources published in 1992–2021.Major taxa and level of measurementPartial or complete trait data is presented for 8601 species of birds, representing 36 of 36 orders and 239 of 243 families.Software formatData have been uploaded as Supplementary Material in .csv format and are separated by species and source for all traits (Dataset , and Metadata) as well as summarized at the species level for the major structure and location variables (Dataset , and Metadata).

Pelatihan Building Information Modeling kepada Praktisi Konstruksi di Kalimantan Selatan

Due to the rapid developments in the current digitalization era, information technology has affected almost every aspect of life. In the construction world, the influence of developments in information technology has led to the emergence of a building database concept called Building Information Modeling (BIM). The Ministry of Public Works and Housing has issued Ministerial Regulation Number 22/PRT/M/2018 and strengthened by PP Number 16 of 2021 regarding the implementation of BIM. Thus, the application of BIM in building projects, especially those owned by the government, has become necessary. Therefore, it is important to carry out BIM training to prepare human resources (HR) who can use BIM-based building design software. The BIM training was held in collaboration with the Human Settlements section of the Public Works and Spatial Planning Agency (PUPR Agency) of South Kalimantan Province. The participants were not only workers of the PUPR Agency but also construction practitioners in the South Kalimantan Province. From the pre-test results, it can be seen that the participants still lack understanding and mastery of BIM software. Meanwhile, after the BIM training was held, there was a significant increase in the participants' mastery and understanding based on the post-test results.

Multi-objective optimization of energy-efficient retrofitting strategies for single-family residential homes: Minimizing energy consumption, CO2 emissions and retrofit costs

The retrofitting of buildings for improved energy efficiency has been recognized as crucial for achieving climate mitigation goals in Bosnia and Herzegovina (B&H). However, performing multi-objective optimizations for retrofitting existing buildings poses challenges, as it requires balancing conflicting objectives such as retrofit costs, energy savings, and CO2 reduction. To tackle this challenge, we employed a multi-objective analysis approach that aims to identify Pareto-optimal solutions for retrofitting, striking a balance between energy consumption, CO2 emissions, and retrofit costs. In this study, we utilized a combination of Full Factorial Design (FFD) and the state-of-the-art NSGA-III framework to evaluate energy-efficient (EE) retrofit strategies for residential buildings in B&H. The analysis was based on the existing building database from the national TABULA study, serving as a fundamental reference. By analyzing this data, we aimed to determine the optimal approach for EE retrofitting in single-family homes (SFH). Key results indicate that upgrading external walls and improving heating system efficiency are the most effective measures for reducing energy consumption and CO2 emissions. However, these measures come with higher retrofit costs. A multi-objective optimization approach identifies a set of non-dominated solutions representing energy efficiency retrofit measures with the lowest specific final energy for heating, specific CO2 emissions, and overall retrofit costs. The top-ranked set of measures achieves a Simple Payback Period (SPP) of 19.9 years. The insights gained from this study are intended to provide valuable guidance to decision-makers in formulating cost-effective and energy-efficient retrofitting strategies that simultaneously minimize annual energy consumption, CO2 emissions, and retrofit costs.

Custom Transient Finite Element for the Modelling of Ultrasonic Control Methods for Downhole Well Integrity

The transient spectral element method can be understood as a specific high-order finite element method that is particularly accurate and fast with a low memory footprint, hence enabling 3D ultrasonic testing simulations on a standard PC. However, particular care must be taken in its settings when seeking both practicality and performance. In comparison, fast semi-analytical simulation using ray tracing is easily accessible to nondestructive testing experts, through the CIVA simulation software. Although this approximate model effectively deals with a wide range of industrial applications, it reaches its limits in certain cases, particularly at relatively low frequencies involving resonance phenomena. To deal with these challenging inspection configurations, CEA-List is working on dedicated finite element models in the CIVA framework to meet specific needs in a compromise between efficiency and accuracy. The case study considered in partnership with SLB perfectly illustrates the benefits of developing such a modelling approach. SLB provides cased-well imaging services using ultrasonic resonance methods to evaluate oil and gas well integrity. Defective cased wells have irregularities, such as corroded casings with pitting, localized cement debonding and channelings. Simulated ultrasonic signals of the actual wells are useful to understand the measurements and are available by finite element modelling with sufficient accuracy. However, the associated computational costs for numerous model cases limit the building of the model database as the digital twin of the actual well logging. The development strategy of dedicated hybrid finite element applications adopted by CEA-List is presented in broad outline. Cross-model comparisons on a reference configuration of pristine cases are presented, highlighting the effective limits of standard CIVA ray models. The contribution offered by the new hybrid finite element approach is then discussed. We discuss the evolution of model functionalities to handle geometries that differ from the canonical case (interface defects, loss of thickness in arbitrary geometries, etc.) from the perspective of a digital twin of this control.

Effect of realistically estimated building lifespan on life cycle assessment: A case study in Korea

In the construction industry, estimating the realistic lifespan of buildings is essential to properly perform life cycle assessments (LCAs). It is impractical to consider all of the different factors affecting building lifespan; therefore, most LCAs assume a standard building lifespan for each major type of building structure. However, the lifespans of buildings vary significantly in practice, and applying a uniform lifespan to all buildings with the same structural type may lead to completely erroneous LCA results. In this study, LCAs of waterproofing methods on building models and actual buildings in Korea are used to empirically demonstrate the effect of realistic lifespan prediction using big data. Applying a more representative building lifespan of 5–39 years in the waterproofing LCAs of an architectural model decreased the carbon emissions in all phases (construction, operation and maintenance, and demolition) by 78–24%, respectively, relative to a 50-year lifespan assumption. During the maintenance phase, the reductions were 100–31%, respectively. The accuracy of the waterproofing LCAs of 17 real buildings became more irregular as the percentage error of the predicted lifespan increased, although the LCA analysis results had 0% error for buildings with a predicted lifespan error of 6% or less. Therefore, depending on the research purpose, a low-error predictive building lifespan model can evidently support accurate LCA results. This study proves that the use of a big data-based building lifespan prediction method is essential for LCA and is an effective tool for business planning and critical decision-making throughout the construction process.

Methods of building database to establish flooding map for coastal areas using a combination of artificial intelligence and GIS technology

As a country with a coastline stretching from North to South, in recent years natural disasters, especially floods and inundation, have severely affected people and properties in Vietnam. In order to prevent and control natural disasters and adapt to climate change, there have been many researches to establish the flood-related map in the country. Among the methods of creating flood maps, the application of AI (Artificial Intelligence) combined with GIS (Geography Information System) has outstanding advantages due to its ability to handle a mixture of many types of input data in a geographical space unification. This method is also used widely in the world in general and Vietnam in particular. When applying the aforementioned method, building the input database of machine learning and artificial intelligence models is an essential issue. Based on the Sentinel-1, Landsat 8/9 images, digital elevation model (DEM), and soil maps, the authors have built the input database for modeling by using AI models. This paper introduces the method of building the input database for making flood maps using machine learning, and artificial intelligence combined with GIS. The computation process is divided into two steps: (1) Editing the component data layers from input data and (2) Standardization of data to transfer the component data layers into the same unit with the standard data format of Weka software. The research’s results are 11 data layers including the flood map in the past, elevation, slope, slope direction, curvature, terrain energy, geology, land use, soil, NDVI, NDWI for Quang Nam province.

Integrating Cadastral Data with Seismic Risk Data in an Online Building Database for the Historical Centre of Bucharest City

The Historical Centre of Bucharest City is a highly populated area and a popular tourist attraction, known for its old buildings, some of which were built before the year 1900 and were severely damaged by the 7.4 magnitude earthquake in 1977. Seismic risk available data consist of lists published by the Municipal Administration for the Consolidation of Buildings with Seismic Risk, and include various information about the buildings for which technical expertise was conducted. Available cadastral data can provide additional information about the buildings, including the buildings’ location and area. In this article, we aim to integrate the available cadastral data with seismic risk data in an online building database for the Historical Centre of Bucharest City. Such a database can be used for further 3D city modelling, which can be helpful in disaster management and emergency situations response planning. Previous initiatives in this regard did not provide precise geospatial data or important attributes regarding the situation of these buildings. It is vital to take into account the official data related to the property, mentioned in the National Land Registry.

Normative Data for Macular Thickness and Volume for Optical Coherence Tomography in a Diabetic Population without Maculopathies.

The purpose was to establish normative data for the macular thicknesses and volume using spectral-domain optical coherence tomography (SD-OCT) in a diabetic population without maculopathies for use as a reference in diabetic retinopathy (DR) and diabetic macular edema screening programs. This was an observational study nested in a cohort of diabetics from a telemedicine DR screening program. Each patient underwent SD-OCT centered on the fovea. Macular thickness and volume were described and compared using the built-in normative database of the device. Quantile regression models for the 97.5% percentile were fitted to evaluate the predictors of macular thickness and volume. A total of 3410 eyes (mean age, 62.25 (SD, 0.22) years) were included. Mean (SD) central subfield thickness (CST) was 238.2 (23.7) µm, while center thickness (CT), average thickness (AT), and macular volume (MV) were 205.4 (31.6) µm, 263.9 (14.3) µm, and 7.46 (0.40) mm3, respectively. Para- and perifoveal thicknesses were clinically and statistically significantly thinner in our population than in the normative reference database. The 97.5% percentile of the thickness of all sectors was increased in males and in the para- and perifovea among those with DR. All ETDRS sectors were thinner in patients with diabetes than in the reference population, except for the CST, which was the most stable parameter that only changed with sex. The upper cutoff limit to detect diabetic macular edema (DME) was different from that of the reference population and was influenced by conditions related to diabetes, such as DR. Therefore, specific normative data for diabetic patients should be used for the screening and diagnosis of DME using SD-OCT.

Modernization of Databases in the Cloud Era: Building Databases that Run Like Legos

Utilizing cloud for common and critical computing infrastructures has already become the norm across the board. The rapid evolvement of the underlying cloud infrastructure and the revolutionary development of AI present both challenges and opportunities for building new database architectures and systems. It is crucial to modernize database systems in the cloud era, so that next generation cloud native databases may run like legos-they are adaptive, flexible, reliable, and smart towards dynamic workloads and varying requirements. That said, we observe four critical trends and requirements for the modernization of cloud databases: embracing cloud-native architecture, full integration with cloud platform and orchestration, co-design for data fabric, and moving towards being AI augmented. Modernizing database systems by adopting these critical trends and addressing key challenges associated with them provide ample opportunities for data management communities from both academia and industry to explore. We will provide an in-depth case study of how we modernize PolarDB with respect to embracing these four trends in the cloud era. Our ultimate goal is to build databases that run just like playing with legos, so that a database system fits for rich and dynamic workloads and requirements in a self-adaptive, performant, easy-/intuitive-to use, reliable, and intelligent manner.

High Myopia Normative Database of Peripapillary Retinal Nerve Fiber Layer Thickness to Detect Myopic Glaucoma in a Chinese Population

To develop and validate the performance of a high myopia (HM)-specific normative database of peripapillary retinal nerve fiber layer (pRNFL) thickness in differentiating HM from highly myopic glaucoma (HMG). Cross-sectional multicenter study. A total of 1367 Chinese participants (2325 eyes) with nonpathologic HM or HMG were included from 4 centers. After quality control, 1108 eyes from 694 participants with HM were included in the normative database; 459 eyes from 408 participants (323 eyes with HM and 136 eyes with HMG) and 322 eyes from 197 participants (131 eyes with HM and 191 eyes with HMG) were included in the internal and external validation sets, respectively. Only HMG eyes with an intraocular pressure > 21 mmHg were included. The pRNFL thickness was measured with swept-source (SS) OCT. Four strategies of pRNFL-specified values were examined, including global and quadrantic pRNFL thickness below the lowest fifth or the lowest first percentile of the normative database. The accuracy, sensitivity, and specificity of the HM-specific normative database for detecting HMG. Setting the fifth percentile of the global pRNFL thickness as the threshold, using the HM-specific normative database, we achieved an accuracy of 0.93 (95% confidence interval [CI], 0.90-0.95) and 0.85 (95% CI, 0.81-0.89), and, using the first percentile as the threshold, we acheived an accuracy of 0.85 (95% CI, 0.81-0.88) and 0.70 (95% CI, 0.65-0.75) in detecting HMG in the internal and external validation sets, respectively. The fifth percentile of the global pRNFL thickness achieved high sensitivities of 0.75 (95% CI, 0.67-0.82) and 0.75 (95% CI, 0.68-0.81) and specificities of 1.00 (95% CI, 0.99-1.00) and 1.00 (95% CI, 0.97-1.00) in the internal and external validation datasets, respectively. Compared with the built-in database of the OCT device, the HM-specific normative database showed a higher sensitivity and specificity than the corresponding pRNFL thickness below the fifth or first percentile (P < 0.001 for all). The HM-specific normative database is more capable of detecting HMG eyes than the SS OCT built-in database, which may be an effective tool for differential diagnosis between HMG and HM. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Direct analysis in real time of high-quality extra virgin olive oils for the rapid and automatic identification of origin trademark.

Following our previous research on the differentiation of Italian extra virgin olive oils (EVOOs) by rapid evaporative ionization mass spectrometry coupled to a tandem high resolution mass analyser, the present study deals with the evaluation of another direct mass spectrometry (direct-MS) approach for the rapid and automatic discrimination of EVOOs. In particular, direct analysis in real time (DART-MS) was explored as an ambient MS (AMS) source for the building of a top-quality Italian EVOOs database and fast identification of unknown samples. A single quadrupole detector (QDa) was coupled with DART, taking advantage of a cost-saving, user-friendly and less sophisticated instrumental setup. Particularly, quickstrip cards, located on a moving rail holder, were employed, allowing for the direct analysis of 12 EVOO spots in a total analysis time of 6 min. The aim was to develop a reliable statistical model by applying principal component and linear discriminant analyses to clusterize and classify EVOOs according to geographical origin and cultivar, as main factors determining their nutritional and sensory profiles. Satisfactory results were achieved in terms of identification reliability of unknown EVOOs, as well as false positive risk, thus confirming that the use of AMS combined with chemometrics is a powerful tool against fraudulent activities, without the need for mass accuracy data, which would increase the analysis cost. A DART ionization source with a compact and reliable QDa MS analyser allowed for rapid fingerprinting analysis. Furthermore, MS spectra provided quali-quantitative information successfully related to EVOO differentiation. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

A computationally inexpensive method to outsource facility maintenance services through the internet in real-time

The paper introduces a real-time framework for selecting maintenance contractors to address building facility breakdowns promptly and cost-effectively. A faster and resource-efficient approach utilizing a Mixed Integer Linear Programming (MILP) method is proposed to achieve this. The method optimizes contractor selection by leveraging structured linked data and integrating maintenance into the Internet of Things (IoT) framework, reducing processing time. Implemented initially for elevator systems, this framework can be extended to other mechanical and electrical systems in buildings. It consists of three modules: the building's integrated data module, the application module, and the maintenance provider module. The first module integrates building databases through structured linked data, establishing a centralized information source. The second module employs mixed integer linear programming to select contractors based on cost, time, previous services quality score, and maintenance urgency. The third module facilitates communication between contractors and the building facility manager, enabling maintenance requests and offers. The MILP model considers budget and time constraints, as well as maintenance urgency to prioritize immediate maintenances. A case study demonstrates that this model offers a fast and effective information processing solution. The results indicate that the proposed framework significantly reduces decision-making time for facility managers, streamlining contractor selection. Furthermore, compared to conventional methods, this framework provides a more efficient and effective automated maintenance decision-making solution, thus making a valuable contribution to the field of building maintenance management.

Versa DB: Assisting 13C NMR and MS/MS Joint Data Annotation Through On‐Demand Databases

AbstractCompound identification in complex mixtures by NMR and MS is best achieved through experimental databases (DB) mining. Experimental DB frequently show limitations regarding their completeness, availability or data quality, thus making predicted database of increasing common use. Querying large databases may lead to select unlikely structure candidates. Two approaches to dereplication are thus possible: filtering of a large DB before search or scoring of the results after a large scale search. The present work relies on the former approach. As far as we know, nmrshiftdb2 is the only open‐source 13NMR chemical shift predictor that can be freely operated in batch mode. CFM‐ID 4.0 is one of the best‐performing open‐source tools for ESI‐MS/MS spectra prediction. LOTUS is a freely usable and comprehensive collection of secondary metabolites. Integrating the open source database and software LOTUS, CFM‐ID, and nmrshiftdb2 in a dereplication workflow requires presently programming skills, owing to the diversity of data encoding and processing procedures. A graphical user interface that integrates seamlessly chemical structure collection, spectral data prediction and database building still does not exist, as far as we know. The present work proposes a stand–alone software tool that assists the identification of mixture components in a simple way.

RNAenrich: a web server for non-coding RNA enrichment.

With the rapid advances of RNA sequencing and microarray technologies in non-coding RNA (ncRNA) research, functional tools that perform enrichment analysis for ncRNAs are needed. On the one hand, because of the rapidly growing interest in circRNAs, snoRNAs, and piRNAs, it is essential to develop tools for enrichment analysis for these newly emerged ncRNAs. On the other hand, due to the key role of ncRNAs' interacting target in the determination of their function, the interactions between ncRNA and its corresponding target should be fully considered in functional enrichment. Based on the ncRNA-mRNA/protein-function strategy, some tools have been developed to functionally analyze a single type of ncRNA (the majority focuses on miRNA); in addition, some tools adopt predicted target data and lead to only low-confidence results. Herein, an online tool named RNAenrich was developed to enable the comprehensive and accurate enrichment analysis of ncRNAs. It is unique in (i) realizing the enrichment analysis for various RNA types in humans and mice, such as miRNA, lncRNA, circRNA, snoRNA, piRNA, and mRNA; (ii) extending the analysis by introducing millions of experimentally validated data of RNA-target interactions as a built-in database; and (iii) providing a comprehensive interacting network among various ncRNAs and targets to facilitate the mechanistic study of ncRNA function. Importantly, RNAenrich led to a more comprehensive and accurate enrichment analysis in a COVID-19-related miRNA case, which was largely attributed to its coverage of comprehensive ncRNA-target interactions. RNAenrich is now freely accessible at https://idrblab.org/rnaenr/.

Workshop report: Challenges faced in developing inhalation thresholds of Toxicological Concern (TTC) - State of the science and next steps

A challenging step in human risk assessment of chemicals is the derivation of safe thresholds. The Threshold of Toxicological Concern (TTC) concept is one option which can be used for the safety evaluation of substances with a limited toxicity dataset, but for which exposure is sufficiently low. The application of the TTC is generally accepted for orally or dermally exposed cosmetic ingredients; however, these values cannot directly be applied to the inhalation route because of differences in exposure route versus oral and dermal. Various approaches of an inhalation TTC concept have been developed over recent years to address this. A virtual workshop organized by Cosmetics Europe, held in November 2020, shared the current state of the science regarding the applicability of existing inhalation TTC approaches to cosmetic ingredients. Key discussion points included the need for an inhalation TTC for local respiratory tract effects in addition to a systemic inhalation TTC, dose metrics, database building and quality of studies, definition of the chemical space and applicability domain, and classification of chemicals with different potencies. The progress made to date in deriving inhalation TTCs was highlighted, as well as the next steps envisaged to develop them further for regulatory acceptance and use.

Preliminary study on the use of Big Data for environmental benchmarks of residential buildings in Flanders

Building construction and operation both have a high environmental impact. In Flanders (Belgium), public authorities have defined clear targets for improved building energy performance, but a strategy to reduce construction (embodied) impact is still lacking. Environmental benchmarks based on Life Cycle Assessment (LCA) have been identified as a means to limit embodied impacts. Such benchmarks are often derived with a bottom-up approach consisting of a statistical analysis of the building stock, which is usually modelled based on a limited set of representative buildings or archetypes. In this paper, a data-driven approach is applied based on building data from the Flemish Energy Performance of Buildings (EPB) database. In a recent study, the buildings from the EPB database were clustered based on geometric and energy-related parameters, and for each cluster representative buildings were selected. This resulted in 54 buildings representative of newly built residential buildings in Flanders. The building set distinguishes itself from other existing sets because it was automatically generated from a large building database. Up until now, the EPB building set has only been used to evaluate the financial feasibility of energy performance levels in Flanders. In this preliminary study, an LCA is performed to assess the life cycle environmental impacts of five sample cases in view of benchmarking. The sample includes two detached, two semi-detached, and one terraced house, all solid construction and in line with the Flemish EPB requirements of 2014. The results show that the environmental score of the buildings is comparable to benchmark values obtained based on the analysis of Belgian archetypes. Further, the building geometry and compactness are identified as key parameters, whereas the materialisation has a more limited influence on the environmental impact. Next research steps will focus on the modelling of more cases, including different construction types, energy performance levels, and potential impact mitigation strategies. The study concludes that the EPB buildings are promising to define environmental benchmarks for the Flemish dwelling stock.

Extraction of Building Information Based on Multi-Source Spatiotemporal Data for Earthquake Insurance in Urban Areas

Establishing a database of building exposures is an important basic work in earthquake insurance research. How to efficiently, accurately, and scientifically construct the risk exposure database of buildings has become a hot topic these days. Based on multi-source data, a system for extracting seismic information from urban buildings was constructed in the Tangshan urban area, and a perfect earthquake insurance risk database was established in this study. In the extraction system, the U-net identification method, spatial overlay and kernel density estimation method, Kriging interpolation method, statistical analysis, and multi-temporal land cover data analysis were used, respectively, to extract the information of footprint areas, use function, story number, structure type, and construction age of the urban buildings. The extraction results are stratified and randomly sampled, and the confusion matrix is introduced to verify the extraction effect. The results show that the building covers an area of about 50 million square meters in the urban area of Tangshan City. With the training and validation of the U-net model, the global accuracy of the building footprint areas recognition model is 71%. By comparing the results of manually determined real data with the extraction results of this study for a sample of 660 buildings, it was found that the overall accuracy rates of the extraction results of building function, story number, structure type, and construction age were 88.62%, 86.65%, 86.49%, and 85.58%, respectively, and kappa coefficients were all over 0.8. These indicate that the information on buildings extracted by the method of this study is accurate and reliable. This study can provide data and methods for the establishment of the exposure database of earthquake insurance and provide strong data support for pre-earthquake disaster prevention, post-earthquake emergency rescue, and disaster loss assessment.

MeRgeION: a Multifunctional R Pipeline for Small Molecule LC-MS/MS Data Processing, Searching, and Organizing.

Small molecule structure elucidation using tandem mass spectrometry (MS/MS) plays a crucial role in life science, bioanalytical, and pharmaceutical research. There is a pressing need for increased throughput of compound identification and transformation of historical data into information-rich spectral databases. Meanwhile, molecular networking, a recent bioinformatic framework, provides global displays and system-level understanding of complex LC-MS/MS data sets. Herein we present meRgeION, a multifunctional, modular, and flexible R-based toolbox to streamline spectral database building, automated structural elucidation, and molecular networking. The toolbox offers diverse tuning parameters and the possibility to combine various algorithms in the same pipeline. As an open-source R package, meRgeION is ideally suited for building spectral databases and molecular networks from privacy-sensitive and preliminary data. Using meRgeION, we have created an integrated spectral database covering diverse pharmaceutical compounds that was successfully applied to annotate drug-related metabolites from a published nontargeted metabolomics data set as well as reveal the chemical space behind this complex data set through molecular networking. Moreover, the meRgeION-based processing workflow has demonstrated the usefulness of a spectral library search and molecular networking for pharmaceutical forced degradation studies. meRgeION is freely available at: https://github.com/daniellyz/meRgeION2.

Application of back propagation neural networks and random forest algorithms in material research of hydrogels

AbstractIn the fourth paradigm of science, which is data‐driven discovery, the big data collected from the first three paradigms can be analyzed to gain information of the research object. Especially in the field of material science, various big data‐driven methods are applied in the tasks, such as material detection, material analysis and material design. In the current research, we focus on how data‐driven methods, e.g., machine learning algorithms, play a big role in deciphering processing‐properties‐performance (PPP) relationships in hydrogels. We present the procedure of (i) normalization of hydrogel properties, (ii) feature engineering of hydrogels, which is to summarize the decisive features in each PPP section of hydrogels, and (iii) database building by data extraction from scientific literature of hydrogels. Finally, we select the two most promising machine learning algorithms, back propagation neural network and random forest algorithm. The back propagation neural network can contribute to prediction of hydrogels properties and the random forest algorithm can be applied to obtain deeper understanding of hydrogels in the early stage of the research.

Evaluation of deploying data-driven predictive controls in buildings on a large scale for greenhouse gas emission reduction

Buildings consume more than 70% of electricity in the U.S. In order to reduce building energy consumption, advanced building controls have been developed. However, most building controls are using physics-based models and lack of scalability. Recent development of data-driven control models could overcome this challenge and be automatically developed and implemented on large scale. The purpose of this study was to evaluate the effectiveness, robustness, and scalability of automatic and systematic data-driven predictive control (DDPC) for a large-scale real-world deployment. We first used collected data from 78 buildings in RTEM database to train deep neural network models. Then we applied the models to optimize the HVAC control for energy savings. We focused on over 1000 HVAC units in five different commonly used types, including air handling units, rooftop units, variable air volume systems, fan coil units, and unit ventilators. Next, we evaluated the energy-saving potential and the reduction of greenhouse gas emissions of the proposed method. We found that DDPC was robust and scalable in buildings, with an average energy saving of 65% and peak load reduction of 15% compared to current control systems. The average reduction of GHG emissions for CO2, CH4, and N2O was 15.18 kg, 5.76e-4 kg, and 5.48e-5 kg per m2 per year, respectively. New York State can benefit 11% reduction in carbon emission from DDPC in buildings. For scalability, we also identified and categorized the challenging conditions when DDPC may not work properly and summarized the lessons learned from large-scale DDPC deployment.