排序方式： 共有50条查询结果，搜索用时 140 毫秒
11.
Md. Sumon Shahriar Mohammad Kamruzzaman John McCulloch Simon Beecham 《Earth Science Informatics》2016,9(3):271-279
We develop multiple step ahead prediction models of river flow for locations in Tasmania (Australia) for decision support in aquaculture. In predicting river flows for multiple days ahead, we first statistically determine the maximum input lags of rainfall and river flow. We then use machine learning techniques in building models. In multiple step ahead prediction, we consider both static and dynamic approaches. In dynamic approach, one day prediction is served as input to two days ahead prediction. The experimental results demonstrate that, in general, a dynamic approach provides better accuracy in multiple day’s ahead prediction. For Duck Bay location using dynamic approach, support vector regression performs best over linear regression, M5P and multilayer perceptron. However, at Montagu Bay location, we find that M5P performs best over methods. We find that multiple step ahead prediction of river flow for each location requires modelling of lags with associated machine learning techniques. 相似文献
12.
13.
W. Ngan L. Van Waerbeke A. Mahdavi C. Heymans H. Hoekstra † 《Monthly notices of the Royal Astronomical Society》2009,396(2):1211-1216
The precision study of dark matter using weak lensing by large-scale structure is strongly constrained by the accuracy with which one can measure galaxy shapes. Several methods have been devised but none has demonstrated the ability to reach the level of precision required by future weak lensing surveys. In this paper, we explore new avenues to the existing 'Shapelets' approach, combining a priori knowledge of the galaxy profile with the power of orthogonal basis function decomposition. This paper discusses the new issues raised by this matched filter approach and proposes promising alternatives to shape measurement techniques. In particular, it appears that the use of a matched filter (e.g. Sérsic profile) restricted to elliptical radial fitting functions resolves several well-known Shapelet issues. 相似文献
14.
15.
16.
Ship hulls, as well as bridges, port dock pilings, dams, and various underwater structures need to be inspected for periodic maintenance. Additionally, there is a critical need to provide protection against sabotage activities, and to establish effective countermeasures against illegal smuggling activities. Unmanned underwater vehicles are suitable platforms for the development of automated inspection systems, but require integration with appropriate sensor technologies. This paper describes a vision system for automated ship-hull inspection, based on computing the necessary information for positioning, navigation, and mapping of the hull from stereo images. Binocular cues are critical in resolving a number of complex visual artifacts that hamper monocular vision in shallow-water conditions. Furthermore, they simplify the estimation of vehicle pose and motion, which is fundamental for successful automatic operation. The system has been implemented on a commercial remotely operated vehicle (ROV), and tested in pool and dock tests. Results from various trials are presented to demonstrate the system capabilities 相似文献
17.
The potential mineralization and immobilization of soil nitrogen (N), phosphorus (P) and sulfur (S) are relatively high in natural ecosystems. This study was conducted to investigate the changes in essential plant macronutrients; N, P, and S status in response to different soil depth in rangeland ecosystems in vitro. The net nutrient mineralization was measured during 90 days at different depths (0–15, 15–30, 30–45 and 45–60 cm), using kinetic models to estimate the release rate. The net ammonification and mineralization of P and S were described using parabolic diffusion equation, while the power function equation was used to describe the net nitrification. The results indicated that the amount of released ammonium (NH4 +) decreased with time and depth and the rates of net ammonification were negative in all samples. Conversely, nitrification increased with time and depth and the rates were all positive. The net mineralization for both P and S reduced with time. The concentration of mineralized SO4 2? increased with depth like nitrate (NO3 ?). Accumulation of SO4 2? and NO3 ? in subsurface soils and NH4 + and P at surface horizons can increase the potential of their loss by leaching or volatilization. 相似文献
18.
Prediction of global stability in room and pillar coal mines 总被引：1，自引：0，他引：1
Global stability is a necessary prerequisite for safe retreat mining and one of the crucial and complex problems in room and pillar mining, so its prediction plays an important role in the safety of retreat mining and the reduction of pillar failure risk. In this study, we have tried to develop predictive models for anticipating global stability. For this purpose, two of the most popular techniques, logistic regression analysis and fuzzy logic, were taken into account and a predictive model was constructed based on each. For training and testing of these models, a database including 80 retreat mining case histories from 18 room and pillar coal mines, located in West Virginia State, USA, was used. The models predict global stability based on the major contributing parameters of pillar stability. It was found that both models can be used to predict the global stability, but the comparison of two models, in terms of statistical performance indices, shows that the fuzzy logic model provides better results than the logistic regression. These models can be applied to identify the susceptibility of pillar failure in panels of coal mines, and this may help to reduce the casualties resulting from pillar instability. Finally, the sensitivity analysis was performed on database to determine the most important parameters on global stability. The results revealed that the pillar width is the most important parameter, whereas the depth of cover is the least important one. 相似文献
19.
This study challenges the use of three nature‐inspired algorithms as learning frameworks of the adaptive‐neuro‐fuzzy inference system (ANFIS) machine learning model for short‐term modeling of dissolved oxygen (DO) concentrations. Particle swarm optimization (PSO), butterfly optimization algorithm (BOA), and biogeography‐based optimization (BBO) are employed for developing predictive ANFIS models using seasonal 15 min data collected from the Rock Creek River in Washington, DC. Four independent variables are used as model inputs including water temperature (T), river discharge (Q), specific conductance (SC), and pH. The Mallow's Cp and R2 parameters are used for choosing the best input parameters for the models. The models are assessed by several statistics such as the coefficient of determination (R2), root‐mean‐square error (RMSE), Nash–Sutcliffe efficiency, mean absolute error, and the percent bias. The results indicate that the performance of all‐nature‐inspired algorithms is close to each other. However, based on the calculated RMSE, they enhance the accuracy of standard ANFIS in the spring, summer, fall, and winter around 13.79%, 15.94%, 6.25%, and 12.74%, respectively. Overall, the ANFIS‐PSO and ANFIS‐BOA provide slightly better results than the other ANFIS models. 相似文献
20.