Search

It is still very challenging to enhance the accuracy and stability of daily runoff forecasts, especially several days ahead, owing to the non-linearity of the forecasted processes. Here, we hypothesize that short lag-time has a significant impact on forecasting results. Thus, we incorporate short previous time steps into long short-term memory (LSTM) and develop the Self-Attentive Long Short-Term Memory (SA-LSTM). In SA-LSTM, the self-attention mechanism is used to model interdependencies within short previous time steps. SA-LSTM is evaluated at eight runoff datasets. The experimental results demonstrate that, compared with state-of-art benchmark models, SA-LSTM achieves the best performance. The RMSEs of SA-LSTM are at least 2.3% smaller than that of the second best model at the seventh day. The NSEs and NSE_In of SA-LSTM are at least 4.6% and 6.4% higher than those of the second best model at the seventh day. Furthermore, SA-LSTM also surpasses the baseline methods for base, mean and peak flows. The superiority of SA-LSTM can be attributed to its exploitation of information in short lag-time.

Hybridly polarized beam is a new type of vector beam different from conventional cylindrical vector beam. In our work, we present a simple and effective method to generate hybridly polarized beams by using a cascade of a super structured polarization converter and a quarter-wave plate. The transformation of light field was analyzed by using Jones vector and Jones matrix, and the Stokes parameters of the generated vector beams were measured to verify the states of polarization. Various novel multiscale micro-/nanostructures were fabricated on surfaces of 4H-SiC by using the hybrid vector beams, which are different from that induced by linearly polarized beam or conventional cylindrical vector beam. Experimental results show that the multiscale characteristics can be adjusted with a high degree of freedom by designing states of polarization. This research provides a new idea for preparation of multiscale micro-/nanostructures that may be useful in the fields of nano-/micro-electromechanical systems, thermal photovoltaics, and thermal management.