Search

This note presents the application of the functional network (FN) and the sequential learning neural network (SLNN) for accurate prediction of tides during surge using short-term observation. Based on 34-day observed data, the proposed functional network model can predict the time series data of hourly tides directly, using an efficient learning process that minimizes the error. In the functional network, a simple equation in the form of a finite-difference equation is derived, using the tidal levels at two previous time steps. The sequential learning neural network uses one hidden neuron to predict the current tidal level. Hourly tidal data for the Typhoon Herb, measured at Taichung Harbor along the Taiwan coastal region, is used for testing the capacity of the functional network and sequential neural network models. Numerical results demonstrate that the proposed models can predict the tidal level during typhoon surge with a high correlation coefficient, based on 1-month hourly data. DOI: 10.1061/(ASCE)0733-950X(2005) 131:6(321) CE Database subject headings: Typhoons; Surge; Neural networks; Tidal water; Forecasting; Taiwan.

Grazing-incidence x-ray diffraction was used to study Si/Ge films grown by surfactant mediated molecular beam epitaxy on Si(001).

Ultrahigh vacuum/chemical vapor deposition system (UHV/CVD) facilitated the growth of high quality Si/Si(1-x)Ge(x) superlattices with 1.5 nanometer thin layers. X-ray diffraction and transmission electron microscopy were used to analyze the crystalline quality.

Conventional and high-resolution transmission electron microscopy, Auger electron spectroscopy and X-ray diffraction are used to study interfacial reactions that occur in ultrahigh vacuum deposited Y-Si multilayer thin films. Multilayers composed of YSi2 form a 65-nm-thick amorphous Y-Si intermixing layer at room temperature. Annealing of the samples at 250-350 degrees Celsius leads to homogenization of atomic composition, although the multilayer maintains its amorphous state.

The low-temperature behavior of ultrahigh vacuum deposited yttrium thin films on an atomically clean (111)Si substrate was investigated. Experiments were performed wherein yttrium thin films were deposited on an atomically clean, phosphorous-doped (111)Si substrate at room temperature. The profile of the resulting structure was then analyzed by high-resolution transmission electron microscopy. Results show that the thickness of the thin films is strongly dependent on the annealing time and temperature.

Conventional and high-resolution transmission electronmicroscopy were used to analyze the evolution of vacancy ordering and defect structure in epitaxial YSi thin films on Si. Epitaxial YSi 2-x were formed whensamples were annealed at 500 degrees celsius for 120 seconds. When the temperature reached 600 degrees celsius for a period of 15 seconds, an ordered vacancy superstructure was formed and additional diffraction spots appeared. Atthe same temperature but for longer periods, or at higher temperatures, an out-of-step structure was formed and the extra diffraction spots were split.

The formation of amorphous interlayers in yttrium thin films grown by ultrahigh vacuum deposition on (111)Si substrates was investigated. The results showed that the thickness of the amorphous interlayer increased with greater annealing times and temperatures. As the critical thickness was surpassed, further intermixing between Y and Si took place but was eventually superseded by crystalline phase formation.

The strain relaxation in SmNi[O.sub.3] epitaxial films deposited by chemical vapor deposition on SrTi[O.sub.3] substrates is studied. A phenomenological model is used for particular planar faults that give rise to extended diffuse scattering on transverse scans.