Monthly streamflow forecasting is vital for managing water resources. Recently, numerous studies have explored and evidenced the potential of artificial intelligence (AI) models in hydrological forecasting. In this study, the feasibility of the convolutional neural network (CNN), a deep learning method, is explored for monthly streamflow forecasting. CNN can automatically extract critical features from numerous inputs with its convolution–pooling mechanism, which is a distinct advantage compared with other AI models. Hydrological and large-scale atmospheric circulation variables, including rainfall, streamflow, and atmospheric circulation factors are used to establish models and forecast streamflow for Huanren Reservoir and Xiangjiaba Hydropower Station, China. The artificial neural network (ANN) and extreme learning machine (ELM) with inputs identified based on cross-correlation and mutual information analyses are established for comparative analyses. The performances of these models are assessed with several statistical metrics and graphical evaluation methods. The results show that CNN outperforms ANN and ELM in all statistical measures. Moreover, CNN shows better stability in forecasting accuracy.
We report on the static and dynamic performance of high-power and high-modulation-speed 1060-nm distributed Bragg reflector (DBR) lasers for green-light emission by second-harmonic generation. Single-wavelength power of 387 mW at 1060-nm wavelength and green power as high as 99.5 mW were achieved. A thermally induced wavelength tuning of 2.4 nm and a carrier-induced wavelength tuning of -0.85 nm were obtained by injecting current into the DBR section. Measured rise-fall times of 0.2 ns for direct intensity modulation and 0.6 ns for wavelength modulation make the lasers suitable for >50-MHz green-light modulation applications. 相似文献
