Detecting and Classifying Typhoon Information from Chinese News Based on a Neural Network Model

Typhoons are major natural disasters in China. Much typhoon information is contained in a large number of network media resources, such as news reports and volunteered geographic information (VGI) data, and these are the implicit data sources for typhoon research. However, two problems arise when using typhoon information from Chinese news reports. Since the Chinese language lacks natural delimiters, word segmentation error results in trigger mismatches. Additionally, the polysemy of Chinese affects the classification of triggers. Second, there is no authoritative classification system for typhoon events. This paper defines a classification system for typhoon events, and then uses the system in a neural network model, lattice-structured bidirectional long–short-term memory with a conditional random field (BiLSTM-CRF), to detect these events in Chinese online news. A typhoon dataset is created using texts from the China Weather Typhoon Network. Three other datasets are generated from general Chinese web pages. Experiments on these four datasets show that the model can tackle the problems mentioned above and accurately detect typhoon events in Chinese news reports.

Lattice Gas Automata Applications to Estimate Effective Porosity and Permeability Barrier Model of the Triangle with a Height Variation

Penelitian ini bertujuan untuk menghitung porositas efektif (фeff) dan permeabilitas (k) menggunakan model segitiga dengan variasi tinggi yaitu 3, 4, 5, 6 dan 7 cm. Perhitungan porositas dan permeabilitas yang efektif dilakukan dengan menggunakan model Lattice Gas Automata (LGA), yang diimplementasikan dengan bahasa pemrograman Delphi 7.0. Untuk model segitiga penghalang dengan tinggi 3, 4, 5, 6 dan 7 cm, nilai porositas efektif dan permeabilitas, masing-masing: фeff (T1) = 0,1690, k (T1) = 0 , 001339 pixel2; фeff (T2) = 0,1841, k (T2) = 0,001904 pixel2; фeff (T3) = 0,1885, k (T3) = 0,001904 pixel2; фeff (T4) = 0,1938, k (T4) = 0001925 pixel2; dan фeff (T5) = 0,2053, k (T5) = 0,002400 pixel2. Dari hasil simulasi, diperoleh tinggi segitiga akan berpengaruh signifikan terhadap nilai porositas efektif dan permeabilitas. Pada segitiga lebih tinggi, menyebabkan tabrakan model aliran fluida LGA mengalami lebih banyak hambatan untuk penghalang, sehingga porositas efektif dan permeabilitas menurun. Sebaliknya, jika segitiga lebih rendah, menyebabkan tabrakan model aliran fluida LGA mengalami lebih sedikit hambatan untuk penghalang, sehingga porositas efektif dan permeabilitas meningkat.This research purposed to calculate the effective porosity (feff) and permeability (k) using the barrier model of the triangle with a high varying are 3, 4, 5, 6 and 7 cm. Effective porosity and permeability calculations performed using the model Lattice Gas Automata (LGA), which is implemented with Delphi 7.0 programming language. For model the barrier triangle with a high of 3, 4, 5, 6 and 7 cm, the value of effective porosity and permeability, respectively: feff(T1)=0,1690, k(T1)=0,001339 pixel2; feff(T2)=0,1841, k(T2)=0,001904 pixel2; feff(T3)=0,1885, k(T3)=0,001904 pixel2; feff(T4)=0,1938, k(T4)= 0001925 pixel2; and feff(T5)=0,2053, k(T5)=0,002400 pixel2. From the simulation results, obtained by the high of the triangle will be a significant effect on the value of effective porosity and permeability. If the triangle highest, causing the collision of fluid flow models LGA experience more obstacles to the barrier, so that the effective porosity and permeability decrease. Conversely, if the triangle lower, causing the collision of fluid flow models LGA experience less obstacles to the barrier, so that the effective porosity and permeability increases.Keywords: Effective porosity, permeability, model triangle, model LGA

Mathematical Modelling of Volatile Gas Using Lattice Boltzmann Method

This study investigates the behaviour of pyrolysis gas, generated by the thermal decomposing of biomass, in a pilot size reactor. The discreet mathematical model, Lattice Boltzmann, has adopted for mathematical simulation of flow of pyrolysis gas across a porous bed of biomass. The effect of permeability, pressure gradient, voidage of bed, density, temperature, and the dynamic viscosity on the mass flow rate of gas is examined by simulating the gas flow across the fixed bed of hardwood. The Darcy equation is used to estimate the flow rate of gas across the fixed bed of hardwood chips. The temperature in the reactor varies from 32 °C to 600 °C. The reactor has an external diameter of 220 mm and the vertical height of 320 mm. Rockwool insulation is used to prevent heat loss across the reactor. The external heating element of 2 kWe was provided to trigger the pyrolysis reaction. The properties of the system have been recorded by the pressure and temperature sensors, which are retrofitted along the periphery of the reactor. The temperature sensors are located at 80 mm apart from each other; whereas the pressure sensor, placed at the bottom circumference of the reactor. The effect of input parameters on the flow properties of gas is also examined to add up the qualitative assessment of the system to biomass pyrolysis. The polytropic equation of gas is found to be PV2.051 = C, whereas the compressibility of gas varies from 0.0025–0.042 m2·N–1.