Runoff modeling is one of the key challenges in the field of hydrology. Various approaches exist, ranging from physically based over conceptual to fully data driven models. In this paper, we propose a data driven approach using the state-of-the-art Long-Short-Term-Memory (LSTM) network. The proposed model was applied in the Poyang Lake Basin (PYLB) and its performance was compared with an Artificial Neural Network (ANN) and the Soil & Water Assessment Tool (SWAT). We first tested the impacts of the number of previous time step (window size) in simulation accuracy. Results showed that a window in improper large size will dramatically deteriorate the model performance. In terms of PYLB, a window size of 15 days might be appropriate for both accuracy and computational efficiency. We then trained the model with 2 different input datasets, namely, dataset with precipitation only and dataset with all available meteorological variables. Results demonstrate that although LSTM with precipitation data as the only input can achieve desirable results (where the NSE ranged from 0.60 to 0.92 for the test period), the performance can be improved simply by feeding the model with more meteorological variables (where NSE ranged from 0.74 to 0.94 for the test period). Moreover, the comparison results with the ANN and the SWAT showed that the ANN can get comparable performance with the SWAT in most cases whereas the performance of LSTM is much better. The results of this study underline the potential of the LSTM for runoff modeling especially for areas where detailed topographical data are not available.

a b s t r a c tFlotation has been used in industry for more than a half century as the primary technique for upgrading phosphate. While the flotation of phosphate was inefficient when oleic acid was used alone as a collector, therefore a mixed collector of oleic acid (HOl), linoleic acid (LA) and linolenic acid (LNA) was employed to improve the recovery of phosphate flotation. The batch flotation results showed that the optimal composition of the mixed collector was 54 wt.% HOl, 36 wt.% LA and 10 wt.% LNA. Additionally, the effect of pH on the mixed collector application was studied while considering the surface tension, contact angle and micro-flotation. The results showed that the mixed collector should be used at a pH of 9.5. Above a pH of 9.5, the adsorption of fatty acids dimers on the apatite surface hindered phosphate flotation. The influence of the mixed collector assembly on apatite flotation was also investigated. It was demonstrated that due to its low critical micelle concentration, a sufficiently hydrophobic apatite surface could be generated at a collector concentration of 60 mg/L. In addition, zeta potential experiments suggested that collector adsorption was governed by chemisorption. FTIR and XPS spectra studies further indicated that the chemical reaction involved the carboxyl groups of fatty acids and Ca species at the apatite surface for each fatty acid in the mixed collector.

No abstract