PERFORMANCE OF LINEAR MODELS IN PREDICTING CATION EXCHANGE CAPACITY OF CALCAREOUS SOILS

Determination of soil cation exchange capacity (CEC) in lab is cumbersome, time consuming, and costly. Accordingly, this article attempted to formulate pedotransfer functions for predicting it using some soil physical and chemical properties e.g., sand (SA), silt (SI), clay (CL), organic matter (OM) and calcium carbonate (CC). This research included four steps: preparing soil database; selecting independent variables which are related to CEC value; formulating models using NCSS 12.0.2 software, and the last step is to achieve specific objective of the research which is the comparsion among models by a series of efficiency criteria: root mean square error (RMSE), Nash-Sutcliffe model efficiency coefficient (EF), average absolute percent error (AAPE), and percentage of improving model efficiency (PIME). The statistical results of the research indicated that CEC of calcareous soils could be predicted from models that have one variable (CL), two variables (CL and OM), and three variables (CL, OM, and CC) with slight decrease in the RMSE (2.95402, 2.81180, and 2.79268) respectively, and slight increase in the EF (0.887360, 0.898448, and 0.90023) respectively. While the reliable models to predict soil CEC are formulated from the fewer number of independent variables with having the lowest points of the standardized residual of CEC that greater than +2 cmolc kg-1).

Prediction of annual runoff using Artificial Neural Network and Regression approaches

Prediction of runoff is often important for optimal design of water storage and drainage works andmanagement of extreme events like floods and droughts. Rainfall-runoff (RR) models are considered to be most effectiveand expedient tool for runoff prediction. Number of models like stochastic, conceptual, deterministic, black-box, etc. iscommonly available for RR modelling. This paper details a study involving the use of Artificial Neural Network (ANN)and Regression (REG) approaches for prediction of runoff for Betwa and Chambal regions. Model performanceindicators such as model efficiency, correlation coefficient, root mean square error and root mean absolute error are usedto evaluate the performance of ANN and REG for runoff prediction. Statistical parameters are employed to find theaccuracy in prediction by ANN and REG for the data under study. The paper presents that ANN approach is found to besuitable for prediction of runoff for Betwa and Chambal regions.

Engine Oil- Crankshaft Interaction Fem Modelling of an Air-Cooled Diesel Engine under Dynamic Severe Functioning Conditions

Taking into account the interaction between the engine oil and the crankshaft to model crankshaft thermomechanical behavior under dynamic loading is very important. In particular, when the crankshaft is working in severe conditions. This paper deal with an air cooled direct injection-type engine crankshaft thermomechanical FEM modelling account for engine oil-cranks half interaction in severe working conditions. As case of application we consider the diesel engine Deutz F8L413. The model takes into account 2 forced convectives heat flux: engine oil and crankcase air. The severe mechanical and thermal characteristics of engine are experimentally measured on a bench test equipped with a hydraulic brake. The temperature distribution inside the crankshaft was computed using the measured temperature as boundary conditions. The most thermo-mechanical stressed zones of the crankshaft have been determined. The fatigue resistance of the crankshaft under thermo-mechanical conditions was examined using Dang-Van multi-axial fatigue criteria. To prove our model efficiency, we have compared crankshaft damage in service to the numerical simulation results. It was found the breakage occurred in an area where the numerical simulations give the highest stresses.

Verification of real-time WRF-ARW forecast in IMD during monsoon 2010

Performance of the mesoscale model WRF-ARW has been evaluated for whole monsoon season of 2011. The real-time model forecasts are generated day to day in India meteorological Department for short-range weather prediction over the Indian region. Verification of rainfall forecasts has been carried out against observed rainfall analysis whereas for all other meteorological parameters verification analysis which was generated using WRFDA assimilation system. Traditional continuous scores and categorical skill scores are computed over seven different zones in India in the verification of rainfall. For other parameters (upper-air as well as surface), continuous scores are evaluated with temporal and spatial features during whole season. The forecast errors of meteorological parameters other than rainfall are analyzed to portray the model efficiency in maintaining monsoon features in large scale along with localized pattern. In the study, time series of errors throughout the season also has been maneuvered to evaluate model forecasts during diverse phases of monsoon. Categorical scores suggest the model forecasts are reliable up to moderate rainfall category for all seven zones. But, rainfall areas with rainfall above 35.5 mm per day associated with migrated weather system from Indian seas could not be predicted as the model displaces them in the forecast. The verification for a whole monsoon season has shown that the model has capability to predict orographic rainfall for the interactive areas with low level monsoon flow over Western Ghats. The model efficiency are in general brought out for a single monsoon season and errors characteristics are discussed for further improvement which could not perceived during real-time use of the model.

LDA-CBOW-Based Mining Model for Risky Driving Behavior in Traffic Accidents

Traffic accident data of traffic management department is recorded in unstructured text form, which contains a large number of characteristic descriptions related to risky driving behavior. However, such data has short text length and abundant professional vocabulary. Many text mining techniques cannot effectively analyze such text data. This paper proposes an improved LDA algorithm based on CBOW—LDA-CBOW model for the study of traffic accident text data containing illegal behaviors. This model can better extract the topics of traffic accident data and filter the keywords under the corresponding topics, which provides a better way to study the dependence relationship between traffic data and illegal behaviors. Experiments show that compared to other models, this model can better extract related topics of traffic accident data with higher model efficiency and better robustness.

Addressing Spatial Heterogeneity in the Discrete Generalized Nash Model for Flood Routing

River flood routing is one of the key components of hydrologic modeling and the topographic heterogeneity of rivers has great effects on it. It is beneficial to take into consideration such spatial heterogeneity, especially for hydrologic routing models. The discrete generalized Nash model (DGNM) based on the Nash cascade model has the potential to address spatial heterogeneity by replacing the equal linear reservoirs into unequal ones. However, it seems impossible to obtain the solution of this complex high order differential equation directly. Alternatively, the strict mathematical derivation is combined with the deeper conceptual interpretation of the DGNM to obtain the heterogeneous DGNM (HDGNM). In this work, the HDGNM is explicitly expressed as a linear combination of the inflows and outflows, whose weight coefficients are calculated by the heterogeneous S curve. Parameters in HDGNM can be obtained in two different ways: optimization by intelligent algorithm or estimation based on physical characteristics, thus available to perform well in both gauged and ungauged basins. The HDGNM expands the application scope, and becomes more applicable, especially in river reaches where the river slopes and cross-sections change greatly. Moreover, most traditional routing models are lumped, whereas the HDGNM can be developed to be semidistributed. The middle Hanjiang River in China is selected as a case study to test the model performance. The results show that the HDGNM outperforms the DGNM in terms of model efficiency and smaller relative errors and can be used also for ungauged basins.

The role of senior managers’ positive self-image in supporting MIS implementation

Purpose Researchers have long been interested in how the psychology of senior managers affects their behaviours. This paper aims to present the results of a questionnaire into how positive self-image influences how well senior managers in UK manufacturing organisations support the implementation of management information system (MIS). This study developed two scales, one to measure senior managers’ attitudes and the other to measure support of MIS implementation. It also sought to investigate the impact of senior managers’ positive self-image on their support of MIS implementation in UK manufacturing organisations. Design/methodology/approach The authors tested the hypotheses on a data set of 400 senior managers from UK manufacturing organisations. Two unidimensional scales to measure senior managers’ attitude and support level towards MIS implementation were developed. Exploratory factor analysis (EFA) was used to validate the scales. The study also examined the impact of senior managers’ positive self-image on their attitude and support from the perspective of UK manufacturing organisations by using structural equation modelling. Findings The study found that senior managers’ positive self-image is a significant contributing factor to their attitude. Also, senior managers’ attitude has a strong positive impact on their support in the MIS implementation process. A strong mediating relationship was found to exist between senior managers’ positive self-image and support through their attitude towards MIS implementation. Originality/value Although past literature has examined the importance of senior managers’ attitude and support in successful MIS implementation, there has been no specific scale around management support and attitude towards MIS implementation developed to date. Thus, a contribution of this study is its development of two new scales based on a survey of senior managers of UK manufacturing organisations. The scales can be used to evaluate senior managers’ perception towards MIS implementation and the support they are willing to give whilst implementing MIS. Another contribution of this study is the analysis of positive self-image via item-parcelling which improves model efficiency and provides more stable estimates of the construct.

The role of land use and morphology representation in the setup and calibration of the conceptual TUW model

The processes of the transformation of rainfall to runoff are highly complicated, and the proper characterisation of these processes with conceptual hydrological models is a very challenging task. Morphology and land cover have a significant influence on a river basin’s hydrologic response. Thus, catchment characteristics of the topography and land use play an essential role in parametrising the runoff concentration processes in hydrological models. In the study, our goal was to detect which characteristics and their spatial distribution influence the efficiency of a conceptual rainfall-runoff model efficiency most. The spatially lumped and semi-distributed versions of the TUW conceptual rainfall model, which is an HBV type model, were compared. Both models use the concept of lumped storages associated with the surface and subsurface, interconnected by thresholds and links to simulate the runoff transformation. We focused on two land-use characteristics, the percentage cover of the agricultural land and percentage cover of the forests, and the mean slope of the terrain as a topography characteristic. The differences between runoff model efficiencies both in the calibration and validation periods were evaluated. Based on which version of the model was more effective in the simulation of the runoff, it was detected which types of catchment land use, and morphology were better represented by using the lumped or semi-distributed version of the TUW model, respectively. The analysis aimed to improve the understanding of the influence of spatial representation morphology and land cover in conceptual models on model efficiency and may help to improve model setup and calibration.

Studying and Mitigating the Effects of Data Drifts on ML Model Performance at the Example of Chemical Toxicity Data

Machine learning models are widely applied to predict molecular properties or the biological activity of small molecules on a specific protein. Models can be integrated in a conformal prediction (CP) framework which adds a calibration step to estimate the confidence of the predictions. CP models present the advantage of ensuring a predefined error rate under the assumption that test and calibration set are exchangeable. In cases where the test data have drifted away from the descriptor space of the training data, or where assay setups have changed, this assumption might not be fulfilled and the models are not guaranteed to be valid. In this study, the performance of internally valid CP models when applied to either newer time-split data or to external data was evaluated. In detail, temporal data drifts were analysed based on twelve datasets from the ChEMBL database. In addition, discrepancies between models trained on publicly available data and applied to proprietary data for the liver toxicity and MNT in vivo endpoints were investigated. In most cases, a drastic decrease in the validity of the models was observed when applied to the time-split or external (holdout) test sets. To overcome the decrease in model validity, a strategy for updating the calibration set with data more similar to the holdout set was investigated. Updating the calibration set generally improved the validity, restoring it completely to its expected value in many cases. The restored validity is the first requisite for applying the CP models with confidence. However, the increased validity comes at the cost of a decrease in model efficiency, as more predictions are identified as inconclusive. This study presents a strategy to recalibrate CP models to mitigate the effects of data drifts. Updating the calibration sets without having to retrain the model has proven to be a useful approach to restore the validity of most models.

Application of PCSWMM for the 1-D and 1-D–2-D Modeling of Urban Flooding in Damansara Catchment, Malaysia

Coupled with climate change, the urbanization-driven increase in the frequency and intensity of floods can be seen in both developing and developed countries, and Malaysia is no exemption. As part of flood hazard mitigation, this study aimed to simulate the urban flood scenarios in Malaysia’s urbanized catchments. The flood simulation was performed using the Personal Computer Storm Water Management Model (PCSWMM) modeling of the Damansara catchment as a case study. An integrated hydrologic-hydraulic model was developed for the 1-D river flow modeling and 1-D–2-D drainage overflow modeling. The reliability of the 1-D river flow model was confirmed through the calibration and validation, in which the water level in TTDI Jaya was satisfactorily predicted, supported by the coefficient of determination (R2), Nash–Sutcliffe model efficiency coefficient (NSE), and relative error (RE). The performance of the 1-D–2-D model was further demonstrated based on the flood depth, extent, and risk caused by the drainage overflow. Two scenarios were tested, and the comparison results showed that the current drainage effectively reduced the drainage overflow due to the increased size of drains compared to the historic drainage in 2015. The procedure and findings of this study could serve as references for the application in flood mitigation planning worldwide, especially for developing countries.