Abstract. This paper presents a new approach using an Artificial Neural Network technique to improve rainfall forecast performance. A real world case study was set up in Bangkok; 4 years of hourly data from 75 rain gauge stations in the area were used to develop the ANN model. The developed ANN model is being applied for real time rainfall forecasting and flood management in Bangkok, Thailand. Aimed at providing forecasts in a near real time schedule, different network types were tested with different kinds of input information. Preliminary tests showed that a generalized feedforward ANN model using hyperbolic tangent transfer function achieved the best generalization of rainfall. Especially, the use of a combination of meteorological parameters (relative humidity, air pressure, wet bulb temperature and cloudiness), the rainfall at the point of forecasting and rainfall at the surrounding stations, as an input data, advanced ANN model to apply with continuous data containing rainy and non-rainy period, allowed model to issue forecast at any moment. Additionally, forecasts by ANN model were compared to the convenient approach namely simple persistent method. Results show that ANN forecasts have superiority over the ones obtained by the persistent model. Rainfall forecasts for Bangkok from 1 to 3 h ahead were highly satisfactory. Sensitivity analysis indicated that the most important input parameter besides rainfall itself is the wet bulb temperature in forecasting rainfall.

In this study, the biosorption mechanisms of methylene blue (MB) and Cr(iii) onto pomelo peel collected from our local fruits are investigated by combining experimental analysis with ab initio simulations.

their advantages over other fuel cells in terms of the clean and efficient power generation and lower operating temperature. [1] They are expected to reduce the fossil fuel consumption, which is believed to be the primary sources causing the climate change. PEM, which consists of super acid groups (i.e., sulfonic acid), has been considered as one of the key components in achieving the high fuel cell performance because of its unique fuel cell properties such as ionic conductance, mechanical strength, and thermal and chemical stabilities. When a dry PEM is immersed in water, the hydrophilic chains with sulfonic ion groups can absorb water and consequently form the interconnected ion channels inside the hydrated regions. The macro and microphase separations, viz., crystalline morphologies, conducting layers (ion channels), characteristic domain sizes, and the connection and distribution of the ionic groups and water in the conducting layers and around the crystalline phases are believed to play an important role in the conductivity and mechanical integrity of the PEMs. [2][3][4] Currently, the main challenges to improve the conductivity and mechanical strength of the PEMs are the lack of detailed informationThe changes of the lamellar periods (L 1D ), thickness of lamellar crystals (L c ), and amorphous layers (L a ) within the stacked lamellae of poly(styrenesulfonic acid)-grafted poly(ethylene-co-tetrafluoroethylene) polymer electrolyte membranes (ETFE-PEMs), induced by the preparation and water-absorbing steps are investigated using the small-angle X-ray scattering method. The L 1D values of all the samples quickly increase at a grafting degree (GD) range of less than 19% and then level off. The solvent-induced recrystallization is observed at the early stage of grafting (GD < 10%) and at successive sulfonation and hydration steps. The L 1D , L a , and L c of dry and hydrated PEMs show similar values at higher GD ranges (>34%), leading to the conclusion that most water molecules in the PEMs with higher GDs exist at the outside of the lamellar stacks. Accordingly, for the PEMs with low GD (<19%), all the hydrophilic graft-polymers (ion-channels) locate in the lamellar stacks and are strongly restricted by lamellar crystalline layers, which suppress the swelling of the PEMs. The unique lamellar structures of ETFE-PEMs characterized by L a and L c are well connected with the high conductance and mechanical properties of the membranes, and are suitable for fuel cell applications.

Nuclear pairing properties are studied within an approach that includes the quasiparticle-number fluctuation (QNF) and coupling to the quasiparticle-pair vibrations at finite temperature and angular momentum. The formalism is developed to describe non-collective rotations about the symmetry axis. The numerical calculations are performed within a doubly-folded equidistant multilevel model as well as several realistic nuclei. The results obtained for the pairing gap, total energy and heat capacity show that the QNF smoothes out the sharp SN phase transition and leads to the appearance of a thermally assisted pairing gap in rotating nuclei at finite temperature. The corrections due to the dynamic coupling to SCQRPA vibrations and particle-number projection are analyzed. The effect of backbending of the momentum of inertia as a function of squared angular velocity is also discussed.Comment: 30 pages and 9 figures. Accepted in Phys. Rev.

No abstract

No abstract

This paper presents a new approach using an Artificial Neural Network technique to improve rainfall forecast performance. A real world case study was set up in Bangkok; 4 years of hourly data from 75 rain gauge stations in the area were used to develop the ANN model. The developed ANN model is being applied for real time rainfall forecasting and flood management in Bangkok, Thailand. Aimed at providing forecasts in a near real time schedule, different network types were tested with different kinds of input information. Preliminary tests showed that a generalized feed-forward ANN model using hyperbolic tangent transfer function achieved the best generalization of rainfall. Especially, the use of a combination of meteorological parameters (rela-tive humidity, air pressure, wet bulb temperature and cloudi-ness), the rainfall at the point of forecasting and rainfall at the surrounding stations, as an input data, advanced ANN model to apply with continuous data containing rainy and non-rainy period, allowed model to issue forecast at any moment. Additionally, forecasts by ANN model were compared to the convenient approach namely simple persistent method. Results show that ANN forecasts have superiority over the ones obtained by the persistent model. Rainfall forecasts for Bangkok from 1 to 3 h ahead were highly satisfactory. Sensitivity analysis indicated that the most important input parameter besides rainfall itself is the wet bulb temperature in forecasting rainfall.

No abstract