scholarly journals Improving the regional model forecasting of persistent severe rainfall over the Yangtze River Valley using the spectral nudging and update cycle methods: a case study

2017 ◽  
Vol 18 (2) ◽  
pp. 96-102 ◽  
Author(s):  
Yanfeng Zhao ◽  
Donghai Wang ◽  
Jianjun Xu
Water ◽  
2021 ◽  
Vol 13 (22) ◽  
pp. 3294
Author(s):  
Chentao He ◽  
Jiangfeng Wei ◽  
Yuanyuan Song ◽  
Jing-Jia Luo

The middle and lower reaches of the Yangtze River valley (YRV), which are among the most densely populated regions in China, are subject to frequent flooding. In this study, the predictor importance analysis model was used to sort and select predictors, and five methods (multiple linear regression (MLR), decision tree (DT), random forest (RF), backpropagation neural network (BPNN), and convolutional neural network (CNN)) were used to predict the interannual variation of summer precipitation over the middle and lower reaches of the YRV. Predictions from eight climate models were used for comparison. Of the five tested methods, RF demonstrated the best predictive skill. Starting the RF prediction in December, when its prediction skill was highest, the 70-year correlation coefficient from cross validation of average predictions was 0.473. Using the same five predictors in December 2019, the RF model successfully predicted the YRV wet anomaly in summer 2020, although it had weaker amplitude. It was found that the enhanced warm pool area in the Indian Ocean was the most important causal factor. The BPNN and CNN methods demonstrated the poorest performance. The RF, DT, and climate models all showed higher prediction skills when the predictions start in winter than in early spring, and the RF, DT, and MLR methods all showed better prediction skills than the numerical climate models. Lack of training data was a factor that limited the performance of the machine learning methods. Future studies should use deep learning methods to take full advantage of the potential of ocean, land, sea ice, and other factors for more accurate climate predictions.


2021 ◽  
Vol 35 (4) ◽  
pp. 557-570
Author(s):  
Licheng Wang ◽  
Xuguang Sun ◽  
Xiuqun Yang ◽  
Lingfeng Tao ◽  
Zhiqi Zhang

2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Xinghu SONG ◽  
Ying HUANG ◽  
Yuan YUAN ◽  
Atta Tung SHAHBAZ ◽  
Souliyanonh BIANGKHAM ◽  
...  

Abstract Background An optimal N rate is one of the basic determinants for high cotton yield. The purpose of this study was to determine the optimal N rate on a new cotton cropping pattern with late-sowing, high density and one-time fertilization at the first flower period in Yangtze River Valley, China. A 2-year experiment was conducted in 2015 and 2016 with a randomized complete block design. The cotton growth process, yield, and biomass accumulation were examined. Results The results showed that N rates had no effect on cotton growing progress or periods. Cotton yield was increased with N rates increasing from 120 to 180 kg·hm−2, while the yield was not increased when the N rate was beyond 180 kg·hm−2, or even decreased (9∼29%). Cotton had the highest biomass at the N rate of 180 kg·hm−2 is due to its highest accumulation speed during the fast accumulation period. Conclusions The result suggests that the N rate for cotton could be reduced further to be 180 kg·hm− 2 under the new cropping pattern in the Yangtze River Valley, China.


Sign in / Sign up

Export Citation Format

Share Document