No abstract

No abstract

No abstract

Abstract Central Asia, the pioneering place of the ‘Belt and Road’, is under the threat of prominent water issues. Based on the Gini coefficient model and the matching index, the amount of the total renewable water resources and the cultivated land area were introduced to evaluate the matching pattern between the water and land resources in Central Asia. The water problem of Kazakhstan, being the most prominent, shows low water resources per unit area with the highest reclamation rate. The matching degree for the upstream countries of the Aral Sea (Kyrgyzstan, Tajikistan) was better than those of the downstream countries (Turkmenistan, Uzbekistan, Kazakhstan). The Gini coefficient in Central Asia was 0.32, smaller than that of the global average value (0.59). The overall water available for use and the matching cultivated land resources was reasonable. Large differences exist in the matching degree in water distribution and utilization among Central Asian countries. The matching index of water and land resources in Central Asia was 1.25, similar to the matching degree estimated from the Gini coefficient model. Moreover, rational measures are suggested to alleviate the issue of water and land resources matching in Central Asia.

ABSTRACT:Although traditional artificial neural networks have been an attractive topic in modeling membrane filtration, lower efficiency by trial-and-error constructing and random initializing methods often accompanies neural networks. To improve traditional neural networks, the present research used the wavelet network, a special feedforward neural network with a single hidden layer supported by the wavelet theory. Prediction performance and efficiency of the proposed network were examined with a published experimental dataset of cross-flow membrane filtration. The dataset was divided into two parts: 62 samples for training data and 329 samples for testing data. Various combinations of transmembrane pressure, filtration time, ionic strength and zeta potential were used as inputs of the wavelet network so as to predict the permeate flux. Through the orthogonal least square alogorithm, an initial network with 12 hidden neurons was obtained which offered a normalized square root of mean square of 0.103 for the training data. The initial network led to a wavelet network model after training procedures with fast convergence within 30 epochs. Futher the wavelet network model accurately depicted the positive effects of either transmembrane pressure or zeta potential on permeate flux. The wavelet network also offered accurate predictions for the testing data, 96.4 % of which deviated the measured data within the ± 10 % relative error range. Moreover, comparisons indicated the wavelet network model produced better predictability than the back-forward backpropagation neural network and the multiple regression models. Thus the wavelet network approach could be employed successfully in modeling dynamic permeate flux in cross-flow membrane filtration.