Search

Drowsiness detection is a crucial step for safe driving. A plethora of efforts has been invested on using pervasive sensor data (e.,g., video, physiology) empowered by machine learning to build an automatic drowsiness detection system. Nevertheless, most of the existing methods are based on complicated wearables (e.,g., electroencephalogram) or computer vision algorithms (e.,g., eye state analysis), which makes the relevant systems hardly applicable in the wild. Furthermore, data based on these methods are insufficient in nature due to limited simulation experiments. In this light, we propose a novel and easily implemented method based on full non-invasive multimodal machine learning analysis for the driver drowsiness detection task. The drowsiness level was estimated by self-reported questionnaire in pre-designed protocols. First, we consider involving environmental data (e.,g., temperature, humidity, illuminance, and further more), which can be regarded as complementary information for the human activity data recorded via accelerometers or actigraphs. Second, we demonstrate that the models trained by daily life data can still be efficient to make predictions for the subject performing in a simulator, which may benefit the future data collection methods. Finally, we make a comprehensive study on investigating different machine learning methods including classic `shallow' models and recent deep models. Experimental results show that, our proposed methods can reach 64.6% unweighted average recall for drowsiness detection in a subject-independent scenario.

Geographic Information System (GIS) a new tool for digital data management, Graphical representation of areas with actual location, analysis, planning, designing of data and many more uses. To understand the application, significance, functions and scope of GIS a review has done, using reference of previous published research which will fill the gap between technology and techniques and gives a better idea about the different area and use of GIS in Geotechnical engineering. We have Search more than 100 research papers between 1980 and 2020 from different sources. The data relevant to the study was checked physically and rest discarded. From literatures different Data, methods, software’s, limitation, and area of use is expected to determined. land use/landcover data, agricultural soil data, engineering soil data, environmental data, interpolation of data for missing data, ground water data and different types of data which have spatial value can be used to get different results. This review has explored scope of GIS in different field, their application and analysis methods. The systematic collection and identification of GIS Data can facilitate any project and save the time, cost, and effort and increase the accessibility to digital Maps, Bore log data, lithology etc. This study will definitely help the new researcher to proper understand the GIS and fill the research gap in areas where the GIS is used in lesser way or even not used in technical work.

Prediction of plantation productivity from environmental data is challenged by the complex relationships defining the growth and yield processes. Artificial neural network (ANN) can be used to model complex nonlinear interrelations but are challenged by the choice of the training algorithm and the structure and size of the network. The objective of the present study is to find an efficient ANN to estimate the eucalyptus productivity from biotic, abiotic and silvicultural data. We defined the efficiency of an ANN as the processing time to supply an accurate solution. We increase the efficiency of the network in two steps: one outside the ANN, through principal component analysis (PCA), and one inside the ANN, through dedicated pruning methods. To test different network configurations, we used data from 507 Eucalyptus plantations, 3 to 7 years old, located in Minas Gerais, Brazil. An ANN configuration is a combination of the number of neurons in the hidden layers, training algorithm and pruning method. Each ANN was trained five times to assess the impact of the initial weights on the results, which led to a factorial experiment with 9000 combinations. The most accurate result was supplied in 38.81 s by an ANN using the data trimmed with PCA, trained with the Scaled Conjugate Gradient algorithm with four neurons and Magnitude-Based Pruning method. However, an accuracy loss of less than 1% (i.e., the second most accurate result) was obtained in 1.7 s using the same ANN configuration, but no pruning. Our results indicate that an efficient prediction of Eucalyptus productivity does not use all the data or the most complex training algorithms. The proposed efficient ANN supplies the most precise results compared with the existing models. Furthermore, the efficient ANN produces more accurate results from environmental variables than some models that contain dimensional variables. Our study suggests that modeling the yield of Eucalyptus plantations should be executed using a large set of environmental variables, as no clear edaphic or climatic variables supplied accurate results.

The disaggregation of conventional soil maps is an active research line inside the Digital Soil Mapping framework that aims to generate new cartographies by disclosing the non-explicit soil distribution pattern within the polytaxic or multi-component cartographic units. This article shows a comprehensive review of methodologies found after a bibliographic search in the Web of Science and Scopus databases. They are analysed regarding common factors such as the conventional soil map, environmental data sources and covariates, classification methods, and evaluation; likewise, those specific to the leveraging of conventional maps as the main source of soil information such as sampling scheme and assignment of soil categories for the classification. The applications were frequently carried out in small and medium areas with intensive and extensive conventional soil maps and featuring supervised classification methods. The definition of the training sets is a critical task that has a strong influence on their performance. The comparative analysis noted the potential of the reviewed disaggregation methodologies that adopted two-stage strategies: first, areas potentially associated with soil categories are delimited; and second, supervised models are built on them. Ultimately, the development of new disaggregation methodologies is possible by combining those strategies within each factor that yielded the best results in terms of accuracy.

With the gradual transformation of chemical industry park to digital and intelligent, various types of environmental data in the park are extremely rich. It has high application value to provide safe production environment by deeply mining environmental data law and providing data support for industrial safety and workers’ health in the park through prediction means. This paper takes the noise data of the chemical industry park as the main research object, and innovatively applies the 3σ principle to the zero-value processing of the noise data, and builds an LSTM model that integrates multivariate information based on the characteristics of the wind direction classification noise data combined with the wind speed and vehicle flow information. The Prophet model integrating multi-site noise information was adopted, and the Multi-PL model was constructed by fitting the above two models to predict the noise. This paper designs and implements a comparative experiment with Kalman filter, BP neural network, Prophet, LSTM, Prophet + LSTM weighted combination prediction model. R2 was used to evaluate the fitting effect of single model in Multi-PL, RMSE and MAE that were used to evaluate the prediction effect of Multi-PL on noise time series. The experimental results show that the RMSE and MAE of the data processed by the 3σ principle are reduced by 32.2% and 23.3% in the multi-station ordered Prophet method, respectively. Compared with the above comparison models, the Multi-PL model prediction method is more stable and accurate. Therefore, the Multi-PL method proposed in this paper can provide a new idea for noise prediction in digital chemical parks.

Artificial intelligence through deep neural networks is now widely used in a variety of applications that have profoundly altered human livelihoods in a variety of ways. People's daily lives have become much more convenient. Image recognition, smart recommendations, self-driving vehicles, voice translation, and a slew of other neural network innovations have had a lot of success in their respective fields. The authors present the ANN applied in weather forecasting. The prediction technique relies solely upon learning previous input values from intervals in order to forecast future values. And also, Convolutional Neural Networks (CNNs) are a form of deep learning technique that can help classify, recognize, and predict trends in climate change and environmental data. However, due to the inherent difficulties of such results, which are often independently identified, non-stationary, and unstable CNN algorithms should be built and tested with each dataset and system separately. On the other hand, to eradicate error and provides us with data that is virtually identical to the real value we need Artificial Neural Networks (ANN) algorithms or benefit from it. The presented CNN model's forecasting efficiency was compared to some state-of-the-art ANN algorithms. The analysis shows that weather prediction applications become more efficient when using ANN algorithms because it is really easy to put into practice.

Geo-environmental information is an important basis for geohazard analysis and the integration of geo-environmental data is crucial in the construction of urban emergency management systems. In existing urban spatial information systems, the integration of geo-environmental data is neither intuitive nor efficient enough to support the analysis of geohazards well. On the basis of Web virtual globe, this paper proposes a comprehensive framework for the integration and analysis of geo-environmental data. This framework can effectively integrate geological data with a 3D geological model as a carrier, seamlessly connect geographic data, dynamically load real-time monitoring data, and build 3D visualisation and analysis scenes of urban full-space temporal information in the browser. The application example shows that the proposed framework can provide good geo-environmental data and practical data analysis functions for geohazard early warning and decision making, and improve the efficiency of government departments’ response to geohazards.

Vehicular networks, which are recognized as an innovative technology for information collection due to the powerful sensing capability and strong mobility, have been an important platform for geographic crowdsourcing services and are particularly useful in environmental data collection. Crowdsourced data collection in vehicular networks must be performed in a communication-efficient manner due to the resource-constrained wireless communication links. Moreover, it is a pressing problem to improve the quality of responses because workers may provide data of poor quality or even fabricate data to defraud rewards. While the existing work has focused on spatial/temporal task coverage and monetary rewards, in this work, we propose a cost-efficient framework for crowdsourced data collection in vehicular networks while ensuring the accuracy of the response. Crowdsourced data collection consists of two main steps: 1) task assignment and 2) crowdsourced answer gathering. We first propose a task assignment scheme that maximizes the overall data quality and reduces the amount of data transmission. We estimate the data quality level based on a Gaussian mixture model and reduce the amount of data transmission by carefully selecting a subset of vehicles for crowdsourced tasks. We then design an answer gathering scheme that considers both the length of the aggregation tree and data delivery and minimizes the communication cost for collecting answers from participants. Extensive experiments on both synthetic data sets and real data sets show that our proposed framework achieves promising results.

The increased usage of the environmental monitoring system and sensors, installed on a day-to-day basis to explore information and monitor the cities’ environment and pollution conditions, are in demand. Sensor networking advancement with quality and quantity of environmental data has given rise to increasing techniques and methodologies supporting spatiotemporal data interactive visualisation analyses. Moreover, Visualisation (Vis) and Visual Analytics (VA) of spatiotemporal data have become essential for research, policymakers, and industries to improve energy efficiency, environmental management, and cities’ air pollution planning. A platform covering Vis and VA of spatiotemporal data collected from a city helps to portray such techniques’ potential in exploring crucial environmental inside, which is still required. Therefore, this work presents Vis and VA interface for the spatiotemporal data represented in terms of location, including time, and several measured attributes like Particular Matter (PM) PM2.5 and PM10, along with humidity, and wind (speed and direction) to assess the detailed temporal patterns of these parameters in Stuttgart, Germany. The time series are analysed using the unsupervised HDBSCAN clustering on a series of (above mentioned) parameters. Furthermore, with the in-depth sensors nature understanding and trends, Machine Learning (ML) approach called Transformers Network predictor model is integrated, that takes successive time values of parameters as input with sensors’ locations and predict the future dominant (highly measured) values with location in time as the output. The selected parameters variations are compared and analysed in the spatiotemporal frame to provide detailed estimations on how average conditions would change in a region over the time. This work would help to get a better insight into the urban system and enable the sustainable development of cities by improving human interaction with the spatiotemporal data. Hence, the increasing environmental problems for big industrial cities could be alarmed and reduced for the future with proposed work.

Environmental investment prediction has attracted much attention in the last few years. However, there are still great challenges in investment prediction modeling, e.g., 1) effective environmental indicators must be accurately selected to avoid the curse of dimensionality; 2) effective environmental data must be reasonably selected to downsize the scale of historical data; 3) the higher interpretability and lower complexity of prediction models must be considered. To address the above three challenges, a new environmental investment prediction model using fuzzy rule-based system (FRBS), evidential reasoning (ER) approach, and subtractive clustering (SC) algorithm is proposed in the present work, called FRBS-ERSC. In this new model, the FRBS is the core component for the modeling of environmental investment prediction and therefore provides good interpretability and complexity to environmental managers. Meanwhile, the ER approach is used as an improvement technique of the FRBS to combine the strengths of different feature selection methods for better indicator selection, and the SC algorithm is used as another improvement technique of the FRBS to select effective environmental data. An empirical case of environmental investment prediction is studied based on data on 31 provinces in China ranged from 2005 to 2018. The experimental results show that the proposed FRBS-ERSC not only provides interpretable and scalable environmental investment prediction based on effective indicator selection and data selection, but also produces satisfactory accuracy compared to some existing models.

With the continuous improvement of people’s quality of life, air quality issues have become one of the topics of daily concern. How to achieve accurate predictions of air quality in a variety of complex situations is the key to the rapid response of local governments. This paper studies two problems: (1) how to predict the air quality of any monitoring station based on the existing weather and environmental data while considering the spatiotemporal correlation among monitoring stations and (2) how to maintain the accuracy and stability of the forecast even when the available data is severely insufficient. A prediction model combining Long Short-Term Memory networks (LSTM) and Graph Attention (GAT) mechanism is proposed to solve the first problems. A metalearning algorithm for the prediction model is proposed to solve the second problem. LSTM is used to characterize the temporal correlation of historical data and GAT is used to characterize the spatial correlation among all the monitoring stations in the target city. In the case of insufficient training data, the proposed metalearning algorithm can be used to transfer knowledge from other cities with abundant training data. Through testing on public data sets, the proposed model has obvious advantages in accuracy compared with baseline models. Combining with the metalearning algorithm, it gives a much better performance in the case of insufficient training data.

The preventive protection of cultural relics is the important topic of cultural relics protection research. Aiming at the shortage of cultural relics data analysis and disease prediction, in this paper, a wavelet correlation analysis relevance vector machine regression method is proposed, which can accurately predict the disease of immovable cultural relics by using the monitored environmental data and the corresponding disease degree of cultural relics. Firstly, the correlation of multivariate time series of immovable cultural relics is quantitatively obtained by using wavelet correlation analysis, and the validity of characteristic variables of cultural relics disease is identified. Then, according to the effective characteristic variables, the relevance vector machine prediction model is constructed. Finally, the good performance of the method is verified by using the environmental monitoring data of the rock mass fracture in the North Qianfo cliff of Dafo Temple in Binzhou City of Shaanxi Province in China. The experimental results show that the proposed method is more effective than the traditional disease prediction methods based on back propagation neural network, support vector machine, principal component analysis relevance vector machine, and random forest for immovable cultural relics. This method is universal and easy to implement for multi-source data prediction of immovable cultural relics diseases. It not only provides ideas for data analysis of the Internet of Things for cultural relics protection, but also gives a scientific theoretical reference for the preventive protection of cultural relics.

Environmental data such as pollutants, temperature, and humidity are data that have a role in the agricultural sector in predicting rainfall conditions. In fact, pollutant data is common to be used as a proxy to see the density of industry and transportation. With this need, it is necessary to have automated data from outside websites that are able to provide data faster than satellite confirmation. Data sourced from IQair, can be used as a benchmark or confirmative data for weather and environmental statistics in Indonesia. Data is taken by scraping method on the website. Scraping is done on the API available on the website. Scraping is divided into 2 stages, the first is to determine the location in Indonesia, the second is to collect statistics such as temperature, humidity, and pollutant data (AQI). The module used in python is the scrapy module, where the crawling is effective starting from May 2020. The data is recorded every three hours for all regions of Indonesia and directly displayed by the Power BI-based dashboard. We also illustrated that AQI data can be used as a proxy for socio-economic activity and also as an indicator in monitoring green growth in Indonesia.

The safety and health monitoring of dams has attracted increasing attention. In this paper, a novel prediction model based on variational autoencoder (VAE) and temporal attention-based long short-term memory (TALSTM) network is proposed for the long-term deformation of arch dams. In the proposed model, the convolutional neural network-based VAE is applied to extracting the features of environmental data. The TALSTM is employed to construct the relationship between the dam displacement and extracted features. For verification, an arch dam is taken as an example. Through the comparison among nine baseline prediction models, the proposed model is more stable and effective than other prediction models. Furthermore, the proposed model could capture the features of environmental data accurately and provide better prediction results. Therefore, the proposed model is more suitable for engineering applications.

International audience; Optimal management for solar energy systems requires quality data to build accurate models for predicting the behavior of solar radiation. Solar irradiance and environmental data are provided by satellite and in-situ measurements. It is usual that satellite measurements present high temporal resolution with limited spatial resolution, and in-situ measurements provide high accuracy but significant missing data. This paper proposes a methodology based on machine learning algorithms that: i) takes the best of both data sources to obtain an improved spatio-temporal resolution, known as site-adaptation; and ii) provides highly accurate forecasting solar-radiation models based on deep learning on the improved data. Through a study case with real data, we show the benefits of using the proposed methodology based on machine and deep learning techniques to integrate data from different sources and to construct precise solar radiation forecasting models in regions where solar energy systems are required. Results show that machine learning models for site-adaptation performed up to 38% better than traditional methods.

Delineating life circles is an essential prerequisite for urban community life circle planning. Recent studies combined the environmental contexts with residents’ global positioning system (GPS) data to delineate the life circles. This method, however, is constrained by GPS data, and it can only be applied in the GPS surveyed communities. To address this limitation, this study developed a generalizable delineation method without the constraint of behavioral data. According to previous research, the community life circle consists of the walking-accessible range and internal structure. The core task to develop the generalizable method was to estimate the spatiotemporal behavioral demand for each plot of land to acquire the internal structure of the life circle, as the range can be delineated primarily based on environmental data. Therefore, behavioral demand estimation models were established through logistic regression and machine learning techniques, including decision trees and ensemble learning. The model with the lowest error rate was chosen as the final estimation model for each type of land. Finally, we used a community without GPS data as an example to demonstrate the effectiveness of the estimation models and delineation method. This article extends the existing literature by introducing spatiotemporal behavioral demand estimation models, which learn the relationships between environmental contexts, population composition and the existing delineated results based on GPS data to delineate the internal structure of the community life circle without employing behavioral data. Furthermore, the proposed method and delineation results also contributes to facilities adjustments and location selections in life circle planning, people-oriented transformation in urban planning, and activity space estimation of the population in evaluating and improving the urban policies.

With the advent of the intelligent age of electronic information and the continuous improvement of application management, electronic information technology has penetrated into the fields of industry, agriculture, intelligent breeding, and smart home. The aquaculture industry is gradually changing from the traditional method of relying solely on human measurement, control and management to an intelligent, informatized, and automated modern aquaculture method. In order to design an intelligent breeding base, this article proposes to use “Internet+” technology to design an intelligent poultry breeding base environmental monitoring system based on the Internet of Things, starting from information and network, breeding industry and management. The system uses ESP-12F WIFI module as the control core, which has wireless transmission function. It can use sensors to collect the environmental temperature and humidity, light, air quality and other indicators of the breeding base, and upload it to the cloud platform. IN manual mode, users can use mobile terminals to perform operations such as online monitoring of environmental data, issuing instructions, and timing to achieve remote management. In the automatic mode, the system can automatically perform functions such as ventilation, humidification, and dehumidification according to the internal environmental thresholds, so as to ensure that the environment of the breeding base is in a good state. In view of the situation that different poultry may have different adaptability to the environment, the user can directly modify the environmental threshold on the mobile terminal.

Graphical data representation is very helpful when analyzing environmental data. It allows for discovering trends in data and analysis of phenomena occurring in the area. There are many possibilities to represent such values graphically. This article contains visualizations generated using Delauney triangulation to represent data on a map. Strengths and weaknesses, comparative analysis with another solution, performance, and usage suggestions will be presented.

The North Pacific Marine Salmon Diet Database is an open-access relational database built to centralize and make accessible salmon diet data through a standardized database structure. The initial data contribution contains 21,862 observations of salmon diet, and associated salmon biological parameters, prey biological parameters, and environmental data from the North Pacific Ocean. The data come from 907 unique spatial areas and mostly fall within two time periods, 1959–1969 and 1987–1997, during which there are more data available compared to other time periods. Data were extracted from 62 sources identified through a systematic literature review, targeting peer-reviewed and gray literature. The purpose of this database is to consolidate data into a common format to address gaps in our ecological understanding of the North Pacific Ocean, particularly with respect to salmon. This database can be used to address a variety of questions regarding salmon foraging, productivity, and marine survival. The North Pacific Marine Salmon Diet Database will continue to grow in the future as more data are digitized and become available., Measurement(s) Gastric Content • diet Technology Type(s) digital curation • microscopy Factor Type(s) predator capture method • year of data collection • longitude • latitude • predator life stage • predator lowest taxonomic level • predator characteristics • predator replicates • type of diet data • prey life stage • prey lowest taxonomic level • prey characteristics Sample Characteristic - Organism Oncorhynchus mykiss • Oncorhynchus kisutch • Oncorhynchus tshawytscha • Oncorhynchus nerka • Oncorhynchus keta • Oncorhynchus gorbuscha Sample Characteristic - Environment ocean Sample Characteristic - Location North Pacific Ocean Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.12981989

Malaria is an epidemic disease caused by protozoan parasites of the genus Plasmodium and transmitted using the chew of infected female mosquitoes of the species Anopheles. The main objective of this research was to map malaria-risk hot-spot site for selected woredas of Jimma zone, Oromia region using GIS-based multicriteria analysis and RS technology applications. To achieve the objectives of the study, a retrospective comparative study design was employed using data from local health services. Over five years and climatic data (rainfall and temperature) collected, as well as environmental data, socioeconomic data were collected using household questionnaires. Sample study kebeles for questioners and r interview was conducted using purposive sampling technique. The malaria hazard assessed based on the environmental factors, computed using GIS-based multicriteria decision-evaluation technique (MCDE). 17.8%, 34.7%, 18.0%, 14.5% and 15.0% of the study area were exposed to very high, high, moderate, low and very low malaria hazard area, respectively. The final result output based on this approach is malaria-risk map. Then, it was produced from overlay analysis using (MCDE). The result revealed that, out of the total area (4136.9 km2), 29.8% very high, 30.7% high, 26.6% moderate, 10.2% low, and 2.7% of the areas are very low malaria-risk level, respectively. The result of the findings of large areas of the districts are in high-risk area of malaria. It will help to take successful measures for malaria control and eradication program and considered one of the most significant inputs used for any aspect of the planning, execution, monitoring and assessment of the woredas growth process as well as malaria eradication programmes.

Areas that contain ecologically distinct biological content, called bioregions, are a central component to spatial and ecosystem‐based management. We review and describe a variety of commonly used and newly developed statistical approaches for quantitatively determining bioregions. Statistical approaches to bioregionalization can broadly be classified as two‐stage approaches that either ‘Group First, then Predict’ or ‘Predict First, then Group’, or a newer class of one‐stage approaches that simultaneously analyse biological data with reference to environmental data to generate bioregions. We demonstrate these approaches using a selection of methods applied to simulated data and real data on demersal fish. The methods are assessed against their ability to answer several common scientific or management questions. The true number of simulated bioregions was only identified by both of the one‐stage methods and one two‐stage method. When the number of bioregions was known, many of the methods, but not all, could adequately infer the species, environmental and spatial characteristics of bioregions. One‐stage approaches, however, do so directly via a single model without the need for separate post‐hoc analyses and additionally provide an appropriate characterization of uncertainty. One‐stage approaches provide a comprehensive and consistent method for objectively identifying and characterizing bioregions using both biological and environmental data. Potential avenues of future development in one‐stage methods include incorporating presence‐only and multiple data types as well as considering functional aspects of bioregions.

With the development of remote sensing and large-scale environmental modelling, large amount of environmental data are continuously becoming available. An intuitive and comprehensive visualization of these data could facilitate data exploration, communication and collaboration between the stakeholders for informed decisions making. In Poyang lake basin regions, we demonstrate how to develop a software platform that can visualize three-dimensionally environmental data layers including terrain, weather, river net, water level, land use changes and interrelations between these data layers for environmental system monitoring and decision supporting. The tool is built by combining several prevailing projects including Unity, Paraview, and hydrological models, etc. We develop an open standardized framework for the software tool to host environmental data layers permitting the application of the tool, which could be employed for the intuitive and comprehensive data visualization in other regions facing environmental challenges.

The statistical analysis of environmental data from remote sensing and Earth system simulations often entails the analysis of gridded spatio-temporal data, with a hypothesis test being performed for each grid cell. When the whole image or a set of grid cells are analyzed for a global effect, the problem of multiple testing arises. When no global effect is present, we expect $$ \alpha $$α% of all grid cells to be false positives, and spatially autocorrelated data can give rise to clustered spurious rejections that can be misleading in an analysis of spatial patterns. In this work, we review standard solutions for the multiple testing problem and apply them to spatio-temporal environmental data. These solutions are independent of the test statistic, and any test statistic can be used (e.g., tests for trends or change points in time series). Additionally, we introduce permutation methods and show that they have more statistical power. Real-world data are used to provide examples of the analysis, and the performance of each method is assessed in a simulation study. Unlike other simulation studies, our study compares the statistical power of the presented methods in a comprehensive simulation study. In conclusion, we present several statistically rigorous methods for analyzing spatio-temporal environmental data and controlling the false positives. These methods allow the use of any test statistic in a wide range of applications in environmental sciences and remote sensing.

Production systems equipped with industrial internet-of-things devices are on the rise allowing smart manufacturing within the trend of industry 4.0 by implementing decentralized decision making. The interconnected devices allow for high transparency in systems by tracking environmental data and actions performed by the actors of the systems. However, they are an easy target for attackers to tamper the authenticity, accountability, and integrity of systems. Therefore, trusted data within systems is required. The trust bases on well-behavior over a period of time of a dedicated entity. Therefore, entities have to be identified to track their behavior. Here, a system of verifiable distributed identities is presented and verified by a simulation. Using a newly introduced zero-knowledge-proof with only two packages exchanged a secure replacement of parts of a product such as a production machine can be achieved without relying on a central authority during the product’s utilization phase.

The ocean is an indispensable source of materials and energy for the survival of human beings and social development. It is also an essential factor affecting climate change and ecological balance. In view of the dynamic, three-dimensional (3D), and complex marine environment, this study proposes the construction and dynamic visualization of a marine spatio-temporal process model based on Network Common Data Form (NetCDF) and optimal interpolation. The proposed model combines the advantages of NetCDF data models, which store and share high-performance multidimensional data, visualize marine spatio-temporal processes based on optimal interpolation, eliminate the time crack of large time resolution data, and ensure continuous, smooth, dynamic visualization. Weekly-averaged survival data of Chinese seas and optimal global interpolation daily-averaged sea surface temperature data of centralized advanced very high-resolution radiometer-only products are selected, and 3D visual expression and analysis of multidimensional, dynamic marine environmental data are realized. Experimental results indicate that the proposed method efficiently and intuitively expresses marine environmental data, thus providing a powerful visualization tool for the expression, change regularity analysis, and trend prediction of complex phenomena.

The accurate forecast of wastewater treatment plant (WWTP) key features can comprehend and predict the plant behavior to support process design and controls, improve system reliability, reduce operational costs, and endorse optimization of overall performances. Deep learning technologies as proven data-driven soft-sensors should be developed for WWTP applications to tackle the process of non-linearity and the dynamic nature of environmental data. This study adopts deep learning-based models as soft-sensors to forecast WWTP key features, such as influent flow, influent temperature, influent biochemical oxygen demand (BOD), effluent chloride, effluent BOD, and power consumption. We constructed six deep learning models derived from long short-term memory (LSTM) and gated recurrent unit (GRU), namely traditional LSTM and GRU, the exponentially smoothed LSTM, and the adaptive version of LSTM and smoothed LSTM. The employment of a smoothed LSTM technique is expected to reduce the outlier effect and to improve forecasting accuracy. Meanwhile, the usage of adaptive deep models will enhance the capabilities of the LSTM to quickly and accurately follow the trend of future data. We compared the performance of these models with Bi-directional LSTM (BiLSTM) and the seasonal decomposition using local regression. The historical records from a coastal municipal WWTP in Saudi Arabia are used to verify the investigated models’ effectiveness. The proposed models provide promising forecasting results but require no assumptions on the data distributions. In terms of efficiency, GRU based models converge faster than LSTM based models. In terms of accuracy, the LSTM soft-sensor shows overall the optimal result for all key features followed by the exponentially-smoothed GRU and LSTM. By contrast, the adaptive models achieved the lowest forecasting performance compared to the other models. These findings will benefit practitioners to achieve data-driven WWTP management.

The estimation of indoor thermal comfort and the associated occupant feedback in office buildings is important to provide satisfactory and safe working environments, enhance the productivity of personnel, and to reduce complaints. The assessment of thermal comfort is a difficult task due to many environmental, physiological, and cultural variables that influence occupants’ thermal perception and the way they judge their working environment. Traditional physics-based methods for evaluating thermal comfort have shown shortcomings when compared to actual responses from the occupants due to the incapacity of these methods to incorporate information of various natures. In this paper, a hybrid approach based on machine learning and building dynamic simulation is presented for the prediction of indoor thermal comfort feedback in an office building in Le Bour-get-du-Lac, Chambéry, France. The office was equipped with Internet of Things (IoT) environmental sensors. Occupant feedback on thermal comfort was collected during an experimental campaign. A calibrated building energy model was created for the building. Various machine learning models were trained using information from the occupants, environmental data, and data extracted from the calibrated dynamic simulation model for the prediction of thermal comfort votes. When compared to traditional predictive approaches, the proposed method shows an increase in accuracy of about 25%.

Biological invasions are accelerating worldwide, causing major ecological and economic impacts in aquatic ecosystems. The urgent decision-making needs of invasive species managers can be better met by the integration of biodiversity big data with large-domain models and data-driven products. Remotely sensed data products can be combined with existing invasive species occurrence data via machine learning models to provide the proactive spatial risk analysis necessary for implementing coordinated and agile management paradigms across large scales. We present a workflow that generates rapid spatial risk assessments on aquatic invasive species using occurrence data, spatially explicit environmental data, and an ensemble approach to species distribution modeling using five machine learning algorithms. For proof of concept and validation, we tested this workflow using extensive spatial and temporal hybridization and occurrence data from a well-studied, ongoing, and climate-driven species invasion in the upper Flathead River system in northwestern Montana, USA. Rainbow Trout (RBT; Oncorhynchus mykiss), an introduced species in the Flathead River basin, compete and readily hybridize with native Westslope Cutthroat Trout (WCT; O. clarkii lewisii), and the spread of RBT individuals and their alleles has been tracked for decades. We used remotely sensed and other geospatial data as key environmental predictors for projecting resultant habitat suitability to geographic space. The ensemble modeling technique yielded high accuracy predictions relative to 30-fold cross-validated datasets (87% 30-fold cross-validated accuracy score). Both top predictors and model performance relative to these predictors matched current understanding of the drivers of RBT invasion and habitat suitability, indicating that temperature is a major factor influencing the spread of invasive RBT and hybridization with native WCT. The congruence between more time-consuming modeling approaches and our rapid machine-learning approach suggest that this workflow could be applied more broadly to provide data-driven management information for early detection of potential invaders.

This study investigates various machine learning models for estimating individual emotions based on collected indoor environment data for human participants. Our previous study developed an individual emotion prediction system using environmental data regarding human perception. Emotions were estimated from indoor environmental data by various machine learning methods. This study investigates which machine learning method is effective for estimating individual emotions. The experimental results show that our system achieves about 80% or more estimation correspondence by using multiple types of sensors. We also found that Random Forest and Gradient Boosting Decision Tree are suitable for our system in terms of both estimation accuracy and computational speed.

Wetland ecosystems in arid and semi-arid regions are under increasing stress due to demands for water resources, encroachment of urban and agricultural land use, and changes in climate and hydrologic regimes. An integrated geospatial and remote sensing approach is required to understand the current state and expected range of variability in these systems. Here we describe a research tool called the Wetland Analysis Toolbar (WetBar) and its application in a multi-agency restoration effort for the threatened Lahontan cutthroat trout in the Great Basin region of the United States. A significant amount of research for restoring this species has been performed at the field scale, but remote sensing and GIS methods are required to scale these efforts to the species’ historic range. This will include methods for riparian mapping, determining an appropriate spatial scale for schemes for disaggregating the historic range, and developing metrics for choosing which regions should be targeted for habitat protection or restoration activities. The WetBar software integrates Google Earth Engine cloud computing directly into the ESRI ArcMap environment, enabling decades-long time series of multispectral satellite and climate data to be used within a querying environment. WetBar disaggregates the network of wetland environments to appropriate spatial units based on elevation and geometric operators and automatically tags these subunits with land use attributes, environmental data, and statistics that capture multi-decadal trends observed by satellite remote sensing. This information will then be used in objective functions to allocate the limited resources for restoration in a coordinated and effective manner.

The Environmental Data Portal EnviDat aims to fuse data publication repository functionalities with next-generation web-based environmental geospatial information systems (web-EGIS) and Earth Observation (EO) data cube functionalities. User requirements related to mapping and visualization represent a major challenge for current environmental data portals. The new Cloud Optimized Raster Encoding (CORE) format enables an efficient storage and management of gridded data by applying video encoding algorithms. Inspired by the cloud optimized GeoTIFF (COG) format, the design of CORE is based on the same principles that enable efficient workflows on the cloud, addressing web-EGIS visualization challenges for large environmental time series in geosciences. CORE is a web-native streamable format that can compactly contain raster imagery as a data hypercube. It enables simultaneous exchange, preservation, and fast visualization of time series raster data in environmental repositories. The CORE format specifications are open source and can be used by other platforms to manage and visualize large environmental time series.

Online, open access databases for biological knowledge serve as central repositories for research communities to store, find and analyze integrated, multi-disciplinary datasets. With increasing volumes, complexity and the need to integrate genomic, transcriptomic, metabolomic, proteomic, phenomic and environmental data, community databases face tremendous challenges in ongoing maintenance, expansion and upgrades. A common infrastructure framework using community standards shared by many databases can reduce development burden, provide interoperability, ensure use of common standards and support long-term sustainability. Tripal is a mature, open source platform built to meet this need. With ongoing improvement since its first release in 2009, Tripal provides full functionality for searching, browsing, loading and curating numerous types of data and is a primary technology powering at least 31 publicly available databases spanning plants, animals and human data, primarily storing genomics, genetics and breeding data. Tripal software development is managed by a shared, inclusive governance structure including both project management and advisory teams. Here, we report on the most important and innovative aspects of Tripal after 11 years development, including integration of diverse types of biological data, successful collaborative projects across member databases, and support for implementing FAIR principles.

Mosquitoes are the most important vectors of human diseases in tropical countries. In particular, Aedes aegypti is the main vector for Chikungunya, Dengue and Zika in South America and Asia. In recent years, transmission of these diseases has increased predominantly in urban areas and has become a major public health problem. This study presents an algorithm for dengue risk prediction in Brazil. It is based in machine learning techniques and uses environmental and socioeconomic variables to predict the risk of dengue propagation all over Brazil, at municipality level. Data from 2010 to 2013 of monthly dengue episodes distribution have been obtained from the Notifiable Diseases Information System (SINAN), developed by the Brazil ministry of health. In addition, environmental data had been obtained from the distributed products of earth observation satellite missions that acquire globally and periodically data. Three types of machine learning algorithms have been applied and compared. The best results have been obtained when using random forests.

Aim of this paper is to propose the use of a Generative Adversarial Imputation Nets (GAIN) to evaluate the quality of time series of environmental data. These time series are becoming more and more popular because they are used by many services available online such as weather forecasting, weather alert systems, etc. The performance of these systems is strictly correlated to the quality of their input data. For this reason, the quality of meteorological time series is becoming a key point for many services.The GAIN method is used to impute missing data in meteorological time series derived by two different kinds of sensors (terrestrial weather station and virtual sensor). The quality of the rebuilt series can be used as a measure of the quality of the original one.

Large-scale ecological sampling can be difficult and costly, especially for organisms that are too small to be easily identified in a natural environment by eye. Typically, these microscopic floral and fauna are sampled by collecting substrates from nature and then separating organisms from substrates in the laboratory. In many cases, diverse organisms can be identified to the species-level using molecular barcodes. To facilitate large-scale ecological sampling of microscopic organisms, we used a geographic data-collection platform for mobile devices called Fulcrum that streamlines the organization of geospatial sampling data, substrate photographs, and environmental data at natural sampling sites. These sampling data are then linked to organism isolation data from the laboratory. Here, we describe the easyFulcrum R package, which can be used to clean, process, and visualize ecological field sampling and isolation data exported from the Fulcrum mobile application. We developed this package for wild nematode sampling, but it is extensible to other organisms. The advantages of using Fulcrum combined with easyFulcrum are (1) the elimination of transcription errors by replacing manual data entry and/or spreadsheets with a mobile application, (2) the ability to clean, process, and visualize sampling data using a standardized set of functions in the R software environment, and (3) the ability to join disparate data to each other, including environmental data from the field and the molecularly defined identities of individual specimens isolated from samples.

The paper characterizes the architecture of an IoT system for measuring and visualizing environmental data. The first part describes the construction of a solar panel powered, IoT-based datalogger of environmental values such as temperature, humidity, and pressure. The second part then outlines a solution to the related cloud system. The datalogger is built as a setup driven by a microcontroller. The program for the microcontroller was written in the C language. Functionally, the microcontroller communicates with the sensors through an I2C bus; the configuration and control of the measurement are performed via a PC application compiled in C# and connected to the device over a USB bus. The measured data are stored in a Micro SD card and transmitted by means of the LoRa technology to the local LoRa cloud provider. The data are then resent from this local provider to a cloud-based Amazon MySQL database and can be visualized through a web application coded in the ASP.NET Core framework. This paper presents the entire, ready-to-use system.

Accurate monitoring of air quality can no longer meet people’s needs. People hope to predict air quality in advance and make timely warnings and defenses to minimize the threat to life. This paper proposed a new air quality spatiotemporal prediction model to predict future air quality and is based on a large number of environmental data and a long short-term memory (LSTM) neural network. In order to capture the spatial and temporal characteristics of the pollutant concentration data, the data of the five sites with the highest correlation of time-series concentration of PM2.5 (particles with aerodynamic diameter ≤2.5 mm) at the experimental site were first extracted, and the weather data and other pollutant data at the same time were merged in the next step, extracting advanced spatiotemporal features through long- and short-term memory neural networks. The model presented in this paper was compared with other baseline models on the hourly PM2.5 concentration data set collected at 35 air quality monitoring sites in Beijing from January 1, 2016, to December 31, 2017. The experimental results show that the performance of the proposed model is better than other baseline models.

Collecting high-frequency social-environmental data about farming practices in sub-Saharan Africa can provide new insight into environmental changes that farmers face and how they respond within smallholder agro-ecosystems. Traditional data collection methods such as agricultural censuses are costly and not useful for understanding intra-annual and real-time decisions. Short-message service (SMS) has the potential to transform the nature of data collection in coupled social-ecological systems. We present a system for collecting, managing, and synthesizing weekly data from farmers, including data infrastructure for management of big and heterogeneous datasets; probabilistic data quality assessment tools; and visualization and analysis tools such as mapping and regression techniques. We discuss limitations of collecting social-environmental data via SMS and data integration challenges that arise when linking these data with other social and environmental data. In combination with high-frequency environmental data, such data will help ameliorate issues of scale mismatch and build resilience in environmental systems.

Machine learning is not a tool that is available for use by computer scientists, but one that can and should be used by all researchers in this technological era. Gone are the days of humans solely relying on older techniques for decision support. The age of information we live in is filled with countless pieces of data and we need to use the correct tools to help make sense of it all. Using MATLAB and its machine learning tools is an excellent resource for environmental scientists to conduct deep-dives into their data. We use this software title to demonstrate some of its capabilities to enhance our research projects. Regression learning examines the capability of developing the best linear regression model based upon the selected independent and dependent variables. Clustering analysis displays how data can be grouped by similar characteristics and how distant they are from one another. Classification analysis can predict future outcomes depending upon historical input data, a crucial tool in developing models for impending environmental events. It is suggested that environmental scientists who have not incorporated machine learning into their research to begin to add it to their data analyses.

Indoor environmental monitoring and management system has played an essential role in public health sustainability. By monitoring the indoor air quality in public areas such as schools, offices, home or other buildings, the authorities will be given a better picture of the indoor air quality to take the right steps to ensure the better air quality for people inside the buildings. This system also can give information about indoor air quality information for the society. Therefore, to achieve this goal, we need to develop a monitoring system by using Information Technology based on Big Data and Cloud Computing environment to give warning. In this paper, we propose Intelligent Indoor Environment Monitoring System (iDEMS) combined with ZigBee wireless sensor network technology to store and process environmental data in HBase. The mechanism of the proposed system is classified into three stages: data collection, data processing, and information monitoring. To understand an Intelligent Indoor Environmental Monitoring, first, we collected the gas from Intelligent Indoor Environmental Monitoring through the environmental sensors with ZigBee wireless sensor network technology. We build a platform for iDEMS to collect the data related to the indoor gases. Second, the environmental data collected in the first stage will be stored and processed in HBase which support massive data storage and free to increase storage capacity for the analysis and processing of Big Data. In this stage, we also compared several data-input methods to import data in HBase much more efficient. Third, the intelligent-control socket is integrated into iDEMS and give the warning if the air quality exceeds the absolute legal limit based on the air quality index rule from the authority. Finally, iDEMS presents the resulting information by a web-based Monitoring Platform so that users can use the Internet to monitor the environment and enable them to utilize these informed decisions on managing and improving the environments.

The spatial distribution of Ceratitis capitata Wiedemann (Diptera: Tephritidae) trap catch was classified and related to a set of geographic variables to identify its main geographical drivers. Trap catch data were sourced from an area-wide integrated pest management (AW-IPM) 1 programme and classified into statistically significant hot- and cold spots (HCSs) 2 . Trap data of four consecutive fruiting seasons were combined to identify monthly and seasonal long-term HCSs. The main geographic drivers of the HCSs were identified using variable importance lists produced by the random forest (RF) machine learning (ML) algorithm. Long-term climate, topography, landscape and fruit fly management variables were used as predictor variables in RF to classify HCSs. The resulting RF models produced classification accuracies of up to 80%. In most cases, the most important variable was long-term rainfall, suggesting that this was the most prominent driver of C. capitata HCSs in our study region. The result of this study highlights the value of long-term pest monitoring data and long-term environmental data in understanding the spatial distribution of C. capitata trap catch in complex agricultural systems. This study sets out a framework to spatially quantify C. capitata trap catch into HCSs using monitoring data from AW-IPM programmes, enabling the investigation of complex ecological relationships through the use of ML algorithms. The results of these analyses could improve area-wide integrated fruit fly management programmes through more precise spatial planning of management actions, such as the sterile insect technique (SIT) 3 , leading to better programme performance and reduced costs.

An accurate estimation of PM2.5 (fine particulate matters with diameters ≤ 2.5 μm) concentration is critical for health risk assessment and generating air pollution control strategies. In this study, a hybrid remote sensing and machine learning approach, named RSRF model is proposed to estimate daily ground-level PM2.5 concentrations, which integrates Random Forest (RF), one of machine learning (ML) models, and aerosol optical depth (AOD), one of remote sensing (RS) products. The proposed RSRF model provides an opportunity for an adequate characterization of real-time spatiotemporal PM2.5 distributions at uninhabited places and complex surfaces. It also offers advantages in handling complicated non-linear relationships among a large number of meteorological, environmental and air pollutant factors, as well as ever-increasing environmental data sets. The applicability of the proposed RSRF model is tested in the Beijing-Tianjin-Hebei region (BTH region) during 2015–2017. Deep Blue (DB) AOD from Aqua-retrieved Collection 6.1 (C_61) aerosol products of Moderate Resolution Imaging Spectroradiometer (MODIS) is validated with Aerosol Robotic Network. The validation results indicate C_61 DB AOD has a high correlation with ground based AOD in the BTH region. The proposed RSRF model performed well in characterizing spatiotemporal variations of annual and seasonal PM2.5 concentrations. It not only is useful to quantify the relationships between PM2.5 and relevant factors such as DB AOD, meteorological and air pollutant variables, but also can provide decision support for air pollution control at a regional environment during haze periods.

The automatic identification system (AIS) has become a key element in maritime domains of inquiry and the number of related articles has increased rapidly. The systematic integration of AIS data with other datatypes has received less attention and has mostly resulted in application-specific datasets that are small relative to the available AIS data. This work presents an accumulating multi-purpose database for the northern Baltic Sea that combines nine years of AIS data with marine environmental data. The main application is winter navigation research, for which purpose the environmental data is from ice charts and ice drift models. The AIS data is from terrestrial stations and amounts to 6 billion messages. It has a full update rate which is also required for the analysis of ice navigation as this involves close encounters, icebreaker assistance, convoy operations, and rapid speed changes. To identify and study such traffic features, distances between ships that are close to each other are included in the database. Application examples are given for spatial traffic statistics, reduction of ship speed with increasing ice thickness, and for icebreaker assistance.

Large amounts of data at various temporal and spatial scales require terabyte (TB) level storage and computation, both of which are not easy for researchers to access. Cloud data and computing services provide another solution to store, process, share and explore environmental data with low costs, stronger computation capacity and easy access. The purpose of this paper is to examine the benefits and challenges of using freely available satellite data products from Australian Geoscience DataCube and Google Earth Engine (GEE) online data with time series for integrative environmental analysis of the Macquarie-Castlereagh Basin in the last 15 years as a case study. Results revealed that the cloud platform simplifies the procedure of traditional catalog data processing and analysis. The integrated analysis based on the cloud computing and traditional methods represents a great potential as a low-cost, efficient and user-friendly method for global and regional environmental study. The user can save considerable time and cost on data integration. The research shows that there is an excellent promise in performing regional environmental analysis by using a cloud platform. The incoming challenge of the cloud platform is that not all kinds of data are available on the cloud platform. How data are integrated into a single platform while protecting or recognizing the data property, or how one portal can be used to explore data archived on different platforms represent considerable challenges.

Social media, particularly Twitter, is increasingly used to improve resilience during extreme weather events/emergency management situations, including floods: by communicating potential risks and their impacts, and informing agencies and responders. In this paper, we developed a prototype national-scale Twitter data mining pipeline for improved stakeholder situational awareness during flooding events across Great Britain, by retrieving relevant social geodata, grounded in environmental data sources (flood warnings and river levels). With potential users we identified and addressed three research questions to develop this application, whose components constitute a modular architecture for real-time dashboards. First, polling national flood warning and river level Web data sources to obtain at-risk locations. Secondly, real-time retrieval of geotagged tweets, proximate to at-risk areas. Thirdly, filtering flood-relevant tweets with natural language processing and machine learning libraries, using word embeddings of tweets. We demonstrated the national-scale social geodata pipeline using over 420,000 georeferenced tweets obtained between 20 and 29th June 2016.

Flexible, rapid, and predictive approaches that do not require the use of large numbers of vertebrate test animals are needed because the chemical universe remains largely untested for potential hazards. Development of robust new approach methodologies and nontesting approaches requires the use of existing information via curated, integrated data sets. The ecological threshold of toxicological concern (ecoTTC) represents one such new approach methodology that can predict a conservative de minimis toxicity value for chemicals with little or no information available. For the creation of an ecoTTC tool, a large, diverse environmental data set was developed from multiple sources, with harmonization, characterization, and information quality assessment steps to ensure that the information could be effectively organized and mined. The resulting EnviroTox database contains 91 217 aquatic toxicity records representing 1563 species and 4016 unique Chemical Abstracts Service numbers and is a robust, curated database containing high‐quality aquatic toxicity studies that are traceable to the original information source. Chemical‐specific information is also linked to each record and includes physico‐chemical information, chemical descriptors, and mode of action classifications. Toxicity data are associated with the physico‐chemical data, mode of action classifications, and curated taxonomic information for the organisms tested. The EnviroTox platform also includes 3 analysis tools: a predicted‐no‐effect concentration calculator, an ecoTTC distribution tool, and a chemical toxicity distribution tool. Although the EnviroTox database and tools were originally developed to support ecoTTC analysis and development, they have broader applicability to the field of ecological risk assessment. Environ Toxicol Chem 2019;9999:1–12. © 2019 The Authors. Environmental Toxicology and Chemistry published by Wiley Periodicals, Inc. on behalf of SETAC.

Driving behavior has a large impact on vehicle fuel consumption. Dedicated study on the relationship between the driving behavior and fuel consumption can contribute to decreasing the energy cost of transportation and the development of the behavior assessment technology for the ADAS system. Therefore, it is vital to evaluate this relationship in order to develop more ecological driving assistance systems and improve the vehicle fuel economy. However, modeling driving behavior under the dynamic driving conditions is complex, making a quantitative analysis of the relationship between the driving behavior and the fuel consumption difficult. In this paper, we introduce two kinds of machine learning methods for evaluating the fuel efficiency of driving behavior using the naturalistic driving data. In the first stage, we use an unsupervised spectral clustering algorithm to study the macroscopic relationship between driving behavior and fuel consumption, using the data collected during the natural driving process. In the second stage, the dynamic information from the driving environment and natural driving data is integrated to generate a model of the relationship between various driving behaviors and the corresponding fuel consumption features. The dynamic environment factors are coded into a processable, digital form using a deep learning-based object detection method so that the environmental data can be linked with the vehicle's operating signal data to provide the training data for the deep learning network. The training data are labeled according to its fuel consumption feature distribution, which is obtained from the road segment data and historical driving data. This deep learning-based model can then be used as a predictor of the fuel consumption associated with different driving behaviors. Our results show that the proposed method can effectively identify the relationship between the driving behavior and the fuel consumption on both macro and micro levels, allowing for end-to-end fuel consumption feature prediction, which can then be applied in the advanced driving assistance systems.