Artificial neural networks for infectious diarrhea prediction using meteorological factors in Shanghai (China)

Infectious diarrhea is an important public health problem around the world. Meteorological factors have been strongly linked to the incidence of infectious diarrhea. Therefore, accurately forecast the number of infectious diarrhea under the effect of meteorological factors is critical to control efforts. In recent decades, development of artificial neural network (ANN) models, as predictors for infectious diseases, have created a great change in infectious disease predictions. In this paper, a three layered feed-forward back-propagation ANN (BPNN) model trained by Levenberg–Marquardt algorithm was developed to predict the weekly number of infectious diarrhea by using meteorological factors as input variable. The meteorological factors were chosen based on the strongly relativity with infectious diarrhea. Also, as a comparison study, the support vector regression (SVR), random forests regression (RFR) and multivariate linear regression (MLR) also were applied as prediction models using the same dataset in addition to BPNN model. The 5-fold cross validation technique was used to avoid the problem of overfitting in models training period. Further, since one of the drawbacks of ANN models is the interpretation of the final model in terms of the relative importance of input variables, a sensitivity analysis is performed to determine the parametric influence on the model outputs. The simulation results obtained from the BPNN confirms the feasibility of this model in terms of applicability and shows better agreement with the actual data, compared to those from the SVR, RFR and MLR models. The BPNN model, described in this paper, is an efficient quantitative tool to evaluate and predict the infectious diarrhea using meteorological factors.     

Sensitivity of a common Land Use Cover Change (LUCC) model to the Minimum Mapping Unit (MMU) and Minimum Mapping Width (MMW) of input maps

Input maps are one of the main sources of uncertainty in Land Use Cover Change (LUCC) models. Such models are usually raster-based. Although extensive research has assessed the impact of the scale of input raster data in the modelling exercise, few studies have focused on the scale of input vector maps. This paper aims to investigate the effect that the Minimum Mapping Unit (MMU) and Minimum Mapping Width (MMW) of input vector maps have on a specific modelling application. To this end, we have set up different exercises with two input maps (SIOSE and CORINE) that have different MMU and MMW. Results prove the influence of these components of the scale on the simulations produced by the models. Modelled changes and quantities vary depending on the input maps. The modelled pattern is, however, very similar, despite the big differences between the reference maps.     

Near-surface air temperature retrieval from Chinese Geostationary FengYun Meteorological Satellite (FY-2C) data

Spatially distributed near-surface air temperature data are a very important input parameter for several land-surface models. Such data are often lacking because there are few traditional meteorological stations. It is of great significance in both theoretical research and practical applications to retrieve air temperature data from remote-sensing observations. Based on the radiative transfer theory, this article addresses the estimate of near-surface air temperature from data from the first Chinese operational geostationary meteorological satellite, FengYun-2C (FY-2C), in two thermal infrared channels (IR1, 10.3–11.3 μm and IR2, 11.5–12.5 μm) and the MODIS atmospheric profile (MOD07) product, which provide profiles of water vapour and air temperature in different atmospheric layers. The algorithm involves only two essential parameters (transmittance and emissivity). Sensitivity analysis of the algorithm has been performed for evaluation of probable near-surface air temperature estimation error due to the possible errors in transmittance and emissivity. Results from the analysis indicate that the proposed algorithm is able to provide an accurate estimation of near-surface air temperature from FY-2C data. Results from the sensitivity analysis indicate that the average air temperature estimation error is less than 1.2 K for a possible transmittance error of 0.05 in both channels under an emissivity range 0.95–0.98. Assuming an error of 0.005 in ground emissivity for the two thermal channels, the average near-surface air temperature error is 0.6 K. Measured air temperature datasets have been used to validate the algorithm. All the validated data indicate that the estimate error is less than 3 K in more than 80% of the samples. The high accuracy for this dataset confirms the applicability of the proposed algorithm as an alternative method for accurate near-surface air temperature retrieval from FY-2C data.     

Assimilation of meteorological and remote sensing data for snowmelt runoff forecasting

A versatile data assimilation scheme for remote sensing snow cover products and meteorological data was developed, aimed at operational use for short-term runoff forecasting. Spatial and temporal homogenisation of the various input data sets is carried out, including meteorological point measurements from stations, numerical weather predictions, and snow maps from satellites. The meteorological data are downscaled to match the scale of the snow products, derived from optical satellite images of MODIS and from radar images of Envisat ASAR. Snow maps from SAR and optical imagery reveal systematic differences which need to be compensated for use in snowmelt models. We applied a semi-distributed model to demonstrate the use of satellite snow cover data for short-term runoff forecasting. During the snowmelt periods 2005 and 2006 daily runoff forecasts were made for the drainage basin Ötztal (Austrian Alps) for time lags up to 6 days. Because satellite images were obtained intermittently, prognostic equations were applied to predict the daily snow cover extent for model update. Runoff forecasting uncertainty is estimated by using not only deterministic meteorological predictions as input, but also 51 ensemble predictions of the EPS system of the European Centre for Medium Range Weather Forecast. This is particularly important for water management tasks, because meteorological forecasts are the main error source for runoff prediction, as confirmed by simulation studies with modified input data from the various sources. Evaluation of the runoff forecasts reveals good agreement with the measurements, confirming the usefulness of the selected data processing and assimilation scheme for operational use.     

The main features of BAHUS — biometeorological system for messages on the occurrence of diseases in fruits and vines

Recently, there has been an increasing demand for providing a high level of production of wholesome plant food but without losing its quality from the consumer's point of view. In this regard, it is required to provide reliable information about the occurrence of plant diseases so as to ensure their efficient control. The reliability of this information increases substantially if both the meteorological and the biological quantities, measured or modelled, are properly integrated in a prognostic system. By the joint efforts of the authors' institutions the biometeorological system BAHUS for messages on the occurrence of the most important diseases in fruits and vines has been developed. This system has been developed in Microsoft FoxPro 2.6(X) following standards of analysis of a large amount of data. It consists of two modules. The first provides input for prediction in the form of the measured or modelled meteorological and biological data, while the second, on the basis of available input data, selects the corresponding method for messages on the occurrence of disease. Depending on the method selected, the meteorological data can be assimilated either from weather stations, atmospheric models or software packages LAPS (land–air parameterization schemes providing 10 min prognostic values) and KARLOS (providing their climatological values) integrated in the system as a whole. The BAHUS has been designed as an open system giving a wide range of possibilities for increasing its level of sophistication.     

Use of a weather generator for simulating climate change effects on ecosystems: A case study on Lake Constance

We present a new vector-autoregressive weather generator developed to generate meteorological time series for climate impact studies on ecosystems.As an example, the weather generator was applied in combination with a hydrodynamic-ecological lake model (DYRESM-CAEDYM). The effects of a warmer and more variable climate on hydrodynamics and phytoplankton in large monomictic lakes were analysed.The weather generator reproduced dependency structures of measured meteorological data. Variability was altered at a time scale similar to lengths of synoptic disturbances, resulting in longer than day-to-day fluctuation changes.Sensitivity of spring bloom development towards a warmer climate, increased climate variability and a combination of both was addressed. For this purpose, 500 meteorological time series per scenario were generated as input for the lake model. We found that onset and maximum of phytoplankton spring bloom are sensitive towards spring weather conditions and that an increase in variability favours early as well as late blooms.     

Multivariate adaptive regression spline (MARS) and least squares support vector machine (LSSVM) for OCR prediction

This article investigates the feasibility of multivariate adaptive regression spline (MARS) and least squares support vector machine (LSSVM) for the prediction of over consolidation ratio (OCR) of clay deposits based on Piezocone Penetration Tests (PCPT) data. MARS uses piece-wise linear segments to describe the non-linear relationships between input and output variables. LSSVM is firmly based on the theory of statistical learning, and uses regression technique. The input parameters of the models are corrected cone resistance (q _t ), vertical total stress (σ_v), hydrostatic pore pressure (u ₀), pore pressure at the cone tip (u ₁), and the pore pressure just above the cone base (u ₂). The developed LSSVM model gives error bar of predicted OCR. Equations have also been developed for prediction of OCR. The performance of MARS and LSSVM models has been compared with the traditional methods for OCR prediction. As the results reveal, the proposed MARS and LSSVM models are robust models for determination of OCR.     

基于气象大数据计算与资源共享教学平台设计

气象大数据具有4V“种类多”(variety)特性,即海量的数据规模(volume)、快速的数据流转和动态的数据体系(velocity)、多样的数据类型(variety)和巨大的数据价值(value)。在气象模式教学过程中,气象模式配置复杂,其需要的气象基础数据具有体量大的特点。针对传统气象模式教学过程复杂,气象模式配置过程繁琐,气象基础数据集需要重复下载的问题,提出气象大数据数字资源平台的建设问题。气象基础数据集与气象模式相结合,对气象基础数据集进行布局,使系统具有比较高的利用率。针对多数据中心,多个气象模式可运行,多个学生对气象基础数据共享的情况,提出一种基于Apriori的挖掘算法来分析数据集与气象模式的直接关系,并完成气象大数据数字资源系统设计,既为学生、教师提供方便的操作,又能提高系统性能。气象大数据数字资源平台不但提供气象计算,也提供各种气象基础数据集的共享访问,简化了气象模式教学过程。     

Long-term high-frequency validation of MODIS LST products in a Mediterranean mountain environment

The accuracy of Moderate-resolution Imaging Spectroradiometer (MODIS) level 3 1 km land surface temperature (LST) products was assessed through long-term validation carried out in a mountainous site in Sierra Nevada, southeast Spain. A total of 1458 day and night thermal images, acquired by Terra and Aqua satellites during 2008, were processed and compared to ground-truth data recorded at the meteorological station of Robledal de Cañar with a frequency of one measurement every 10 min. The purpose of this investigation was to understand whether MODIS LST data can be used as input for climate models to be constructed for mountainous environments. Several trends in the MODIS LST data were observed, including the underestimation of daytime values and the overestimation of night-time values. Although all the data sets (Terra and Aqua, diurnal and nocturnal) showed high correlation coefficients with ground measurements, only night values maintained a relatively high accuracy of approximately 2°C of annual average error. Factors that may cause errors in the MODIS LST data, like acquisition angle, cloud, and snow cover, were analysed without conclusive results. High accuracy levels, i.e. close to 1°C, similar to other validation studies carried out over simpler and much more homogenous land-cover types such as cultivated fields, have been achieved for night images acquired during the summer months, thus making these datasets reliable for their use in climatic models over mountainous regions.     

IMDIS — An integrated approach to Gaussian dispersion modeling

Gaussian dispersion models are well established tools for the estimation of ground level concentrations and regulatory purposes. These models are attractive for microcomputers, since the corresponding programs are fast and the input source and meteorological data are usually available. The purpose of this paper is to present a multisource bi-Gaussian dispersion computer program (IMDIS) applicable to stationary point sources, specifically written for the Apple Macintosh microcomputer. The program takes advantage of a user-friendly graphical interface for interactive data entry and retrieval and for displaying concentration isopleths. The model may be adapted to different situations, since it provides several alternatives for the estimation of plume rise, dispersion coefficients, wind profile power law, mean transport velocity and time averaging methods. Powerful numerical non-linear optimization procedures allow for ‘worst-case’ or actual maxima to be determined, independently of the formulas employed within the different submodels. The program was tested with literature data and compared with some other Gaussian models available, and preliminary results suggest its adequacy as a flexible tool for dispersion modeling.     

Interfacing environmental simulation models and databases using XML

Typically in environmental management tasks one needs to examine and explore data from several sources, use simulation models, develop scenarios, assess impacts, and provide support for decision makers. Here we consider the eXtensible Markup Language (XML) standard in developing information transfer techniques between databases and simulation models. Suitability of XML as the agreed data transfer format is studied in a sample application, where two snow models of different complexity are linked with input data extracted from a relational database. The simple case study demonstrated that with free and easily accessible tools it was relatively straightforward to develop an XML interface between a meteorological data set and simulation models. Based on the case study, a structure for a more comprehensive system comprising model and data resources, and a broker application that acts as an intermediate between the user and those resources, is presented. We believe that such an XML-based structure is worth exploring on the track towards an open modelling framework. Such a framework would allow models developed by various expert groups to connect easily to a common information system.     

基于智能适配器的气象数据入库通用模型

针对气象数据入库工作量较大的问题,提出一种基于智能适配器的气象数据入库通用模型。将可扩展标志语言作为元数据表示方法,利用JAXB技术读取和写入元数据。使用脚本语言处理适配器的规则配置问题,提高气象数据的智能性。基于该模型,构建气象数据通用入库系统。运行结果表明,该系统具有高度灵活性和可扩展性。     

西安市PM10污染预报仿真模型研究

为更好的反映西安市环境污染变化,对西安市2004年6月到2006年3月的PM10(可吸入颗粒)污染实测资料与同时期的气象资料进行了分析.首先采用一元线性同归方法,建立PM10污染与各个气象要素在不同季节的相关关系,并得到相关系数,选出对PM10污染影响显著的气象要素;然后采用主成分分析法[2]简化变量;最后用多元线性同归的方法建立回归方程,用最小二乘法[2,5]计算回归系数,并用F检验和t检验埘模型的线性性及回归系数的显著性进行检验.最终建立了西安市PM10预模型体系,计算机仿真结果给出了预报模趔命中率及误差.     

Developing data-driven models for quantifying Cochlodinium polykrikoides using the Geostationary Ocean Color Imager (GOCI)

Harmful algal blooms have caused critical problems worldwide because they pose serious threats to human health and aquatic ecosystems. In particular, red tide blooms of Cochlodinium polykrikoides have caused serious damage to aquaculture in Korean coastal waters. In this study, multiple linear regression, regression tree (RT), and Random Forest models were applied to detect C. polykrikoides blooms in coastal waters. Five types of input data sets were implemented to test the performance of the models. The observed number of C. polykrikoides cells and reflectance data from Geostationary Ocean Color Imager images obtained in a 3-year period (2013–2015) were used to train and validate the models. The RT model demonstrated the best prediction performance when four bands and three-band ratio data were simultaneously used as input data. The results obtained via iterative model development with randomly chosen input data indicate that the recognition of patterns in the training data caused variations in the prediction performance. This work provides useful tools for reliable estimation of the number of C. polykrikoides cells using reasonable coastal water reflectance data sets. It is expected that administrators and decision-makers whose work is associated with coastal waters will be able to easily access and manipulate the RT model.     

Probabilistic neural network training procedure based on Q(0)-learning algorithm in medical data classification

In this article, an iterative procedure is proposed for the training process of the probabilistic neural network (PNN). In each stage of this procedure, the Q(0)-learning algorithm is utilized for the adaptation of PNN smoothing parameter (σ). Four classes of PNN models are regarded in this study. In the case of the first, simplest model, the smoothing parameter takes the form of a scalar; for the second model, σ is a vector whose elements are computed with respect to the class index; the third considered model has the smoothing parameter vector for which all components are determined depending on each input attribute; finally, the last and the most complex of the analyzed networks, uses the matrix of smoothing parameters where each element is dependent on both class and input feature index. The main idea of the presented approach is based on the appropriate update of the smoothing parameter values according to the Q(0)-learning algorithm. The proposed procedure is verified on six repository data sets. The prediction ability of the algorithm is assessed by computing the test accuracy on 10 %, 20 %, 30 %, and 40 % of examples drawn randomly from each input data set. The results are compared with the test accuracy obtained by PNN trained using the conjugate gradient procedure, support vector machine algorithm, gene expression programming classifier, k–Means method, multilayer perceptron, radial basis function neural network and learning vector quantization neural network. It is shown that the presented procedure can be applied to the automatic adaptation of the smoothing parameter of each of the considered PNN models and that this is an alternative training method. PNN trained by the Q(0)-learning based approach constitutes a classifier which can be treated as one of the top models in data classification problems.     

Persistent changes in NDVI between 1982 and 2003 over India using AVHRR GIMMS (Global Inventory Modeling and Mapping Studies) data

The preliminary results of Normalized Difference Vegetation Index (NDVI) change studies over India using data from Advanced Very High Resolution Radiometer Global Inventory Modeling and Mapping Studies (AVHRR GIMMS) between 1982 and 2003 are presented. The three methodologies of univariate differencing, temporal profiling and anomaly analysis were undertaken. Univariate differencing was used to determine overall NDVI change between 1982 and 2003. A persistence filter was used to filter out ephemeral changes. The temporal profile analyses were carried out over different meteorological subdivisions to compare changes in NDVI with rainfall patterns. In the anomaly analysis, the areas of change were analysed over different land cover categories derived from IRS‐WiFS data. The preliminary results indicate that positive trends in vegetation change occurred over most parts of the country and these changes appear not to be highly correlated with rainfall data, indicating that land cover transformations may be the major driving force behind the changes. The land cover classifications experiencing the greatest increasing NDVI were tropical thorn forests and intensive agriculture and the land cover experiencing very slow growth included current jhum, tropical moist deciduous and temperate evergreen forest. Five‐year moving averages indicate a general increase in NDVI from 1986 to 1998 and then declining thereafter. This is a concern in most of the meteorological subdivisions.     

Visualizing and analyzing dynamic meteorological data with virtual globes: A case study of tropical cyclones

Visualization is an important component of the evaluation of meteorological models, forecasting research, and other applications. With advances in computing power, the volume of meteorological data generated by geoscience and climate researchers has been steadily increasing. The emerging technique of virtual globes has been regarded as an ideal platform for visualizing larger geospatial data over the Internet. To visualize and analyze meteorological data with the new virtual globes, this paper proposes a systematic meteorological data visualization (MDV) framework in World Wind, an open-source virtual globe. The key technologies, including a hierarchical octree-based multiresolution data organization, data scheduling, level of detail (LOD) and rendering are described in detail. The framework is then applied to a practical tropical cyclone simulation, including flow vectors, particle tracking, cross-sectional analysis, streamlines, pathway animation, and volume rendering. The results show that virtual globes are effective tools for meteorological data visualization and analysis.     

Fuzzy stochastic data envelopment analysis with application to base realignment and closure (BRAC)

Data envelopment analysis (DEA) is a non-parametric method for evaluating the relative efficiency of decision-making units (DMUs) on the basis of multiple inputs and outputs. Conventional DEA models assume that inputs and outputs are measured by exact values on a ratio scale. However, the observed values of the input and output data in real-world problems are often vague or random. Indeed, decision makers (DMs) may encounter a hybrid uncertain environment where fuzziness and randomness coexist in a problem. Several researchers have proposed various fuzzy methods for dealing with the ambiguous and random data in DEA. In this paper, we propose three fuzzy DEA models with respect to probability-possibility, probability-necessity and probability-credibility constraints. In addition to addressing the possibility, necessity and credibility constraints in the DEA model we also consider the probability constraints. A case study for the base realignment and closure (BRAC) decision process at the U.S. Department of Defense (DoD) is presented to illustrate the features and the applicability of the proposed models.