Hybrid neural network—finite element river flow model

Results obtained from a hybrid neural network—finite element model are reported in this paper. The hybrid model incorporates artificial neural network (ANN) nodes into a numerical scheme, which solves the two-dimensional shallow water equations using finite elements (FE). First, numerical computations are carried out on the entire numerical model, using a larger mesh. The results from this computation are then used to train several preselected ANN nodes. The ANN nodes model the response for a part of the entire numerical model by transferring the system reaction to the location where both models are connected in real time. This allows a smaller mesh to be used in the hybrid ANN-FE model, resulting in savings in computation time. The hybrid model was developed for a river application, using the computational nodes located at the open boundaries to be the ANN nodes for the ANN-FE hybrid model. Real-time coupling between the ANN and FE models was achieved, and a reduction is CPU time of more than 25% was obtained.

Sustainable farming practices of the Chinese mitten crab (Eriocheir sinensis) around Hongze Lake, lower Yangtze River Basin, China.

Results of a survey of 156 Chinese mitten crab (Eriocheir sinensis) grow-out farms around Hongze Lake (118.48-118.72°E; 33.36-33.38°N) are reported. Area farmed has remained relatively unchanged but production (59 932 t in 2012) increased steadily over the last 7 years, indicative of the viability and sustainability of the farming system that has gradually replaced intensive Chinese major carp polyculture around Hongze Lake. Results showed that production range was 135-2400 kg ha(-1) cycle(-1) (mean 1144 ± 34). Crab yields correlated linearly to stocking density and conformed to a normal distribution curve, with 66.7 % of farms yielding 900 kg ha(-1) cycle(-1) or more. Yield was negatively correlated to pond size and capture size (p < 0.01), and farms with macrophyte coverage rate lower than 30 % of water surface were significantly (p < 0.05) lower than those exceeding 30 %.