Sidong Zeng

Prof. Dr. Sidong Zeng

Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing 400714, China
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 August 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JWJian Wu
Jian Wu
Sidong ZengSidong Zeng
Sidong Zeng
LYLinhan Yang
Linhan Yang
YRYuanxin Ren
Yuanxin Ren
JXJun Xia
Jun Xia
The spatiotemporal characteristics of river water quality are the key indicators for ecosystem health evaluation in basins. Land use patterns, as one of the main driving forces of water quality change, affect stream water quality differently with the variations in the spatiotemporal scales. Thus, quantitative analysis of the relationship between different land cover types and river water quality contributes to a better understanding of the effects of land cover on water quality, the landscape planning of water quality protection, and integrated water resources management. Based on water quality data of 2006–2018 at 18 typical water quality stations in the Yangtze River basin, this study analyzed the spatial and temporal variation characteristics of water quality by using the single-factor water quality identification index through statistical analysis. Furthermore, the Spearman correlation analysis method was adopted to quantify the spatial-scale and temporal-scale effects of various land uses, including agricultural land (AL), forest land (FL), grassland (GL), water area (WA), and construction land (CL), on the stream water quality of dissolved oxygen (DO), chemical oxygen demand (CODMn), and ammonia (NH3-N). The results showed that (1) in terms of temporal variation, the water quality of the river has improved significantly and the tributaries have improved more than the main rivers; (2) in the spatial variation respect, the water quality pollutants in the tributaries are significantly higher than those in the main stream, and the concentration of pollutants increases with the decrease of the distance from the estuary; and (3) the correlation between DO and land use is low, while that between NH3-N, CODMn, and land use is high. CL and AL have a negative effect on water quality, while FL and GL have a purifying effect on water quality. In particular, AL and CL have a significant positive correlation with pollutants in water. Compared with NH3-N, CODMn has a higher correlation with land use at a larger scale. The results highlight the spatial scale and seasonal dependence of land use on water quality, which can provide a scientific basis for land management and seasonal pollution control.

25 May 2022 in Water
Verified
Journal Article
Open access
PDF file
YRYuanxin Ren
Yuanxin Ren
Sidong ZengSidong Zeng
Sidong Zeng
JLJianwei Liu
Jianwei Liu
ZTZhengyang Tang
Zhengyang Tang
XHXiaojun Hua
Xiaojun Hua
JXJun Xia
Jun Xia
Deep learning models are essential tools for mid- to long-term runoff prediction. However, the influence of the input time lag and output lead time on the prediction results in deep learning models has been less studied. Based on 290 schemas, this study specified different time lags by sliding windows and predicted the runoff process by RNN (Recurrent Neural Network), LSTM (Long–short-term Memory), and GRU (Gated Recurrent Unit) models at five hydrological stations in the upper Yangtze River during 1980–2018 at daily, ten-day, and monthly scales. Different models have different optimal time lags; therefore, multiple time lags were analyzed in this paper to find out the relationship between the time intervals and the accuracy of different river runoff predictions. The results show that the optimal time-lag settings for the RNN, LSTM, and GRU models in the daily, ten-day, and monthly scales were 7 days, 24 ten days, 27 ten days, 24 ten days, 24 months, 27 months, and 21 months, respectively. Furthermore, with the increase of time lags, the simulation accuracy would stabilize after a specific time lag at multiple time scales of runoff prediction. Increased lead time was linearly related to decreased NSE at daily and ten-day runoff prediction. However, there was no significant linear relationship between NSE and lead time at monthly runoff prediction. Choosing the smallest lead time could have the best prediction results at different time scales. Further, the RMSE of the three models revealed that RNN was inferior to LSTM and GRU in runoff prediction. In addition, RNN, LSTM, and GRU models could not accurately predict extreme runoff events at different time scales. This study highlights the influence of time-lag setting and lead-time selection in the mid- to long-term runoff prediction results for the upper Yangtze River basin. It is recommended that researchers should evaluate the effect of time lag before using deep learning models for runoff prediction, and to obtain the best prediction, the shortest lead-time length can be chosen as the best output for different time scales.

6 September 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
XLXiao Li
Xiao Li
Liping ZhangLiping Zhang
Liping Zhang
Sidong ZengSidong Zeng
Sidong Zeng
ZTZhenyu Tang
Zhenyu Tang
LLLina Liu
Lina Liu
XHXiaojun Hua
Xiaojun Hua
Accurate monthly runoff prediction is significant to extreme flood control and water resources management. However, traditional statistical models without multi-variable input may fail to capture runoff changes effectively due to the dual effect of climate change and human activities. Here, we used five multi-input machine learning (ML) models to predict monthly runoff, where multiple global circulation indexes and surface meteorological indexes were selected as explanatory variables by the stepwise regression or copula entropy methods. Moreover, four univariate models were adopted as benchmarks. The multi-input ML models were tested at two typical hydrological stations (i.e., Gaochang and Cuntan) in the Upper Yangtze River. The results indicate that the LSTM_Copula (long short-term memory model combined with copula entropy method) model outperformed other models in both hydrological stations, while the GRU_Step (gate recurrent unit model combined with stepwise regression method) model and the RF_Copula (random forest model combined with copula entropy method) model also showed satisfactory performances. In addition, the ML models with multi-variable input provided better predictability compared with four univariate statistical models, and the MAPE (mean absolute percentage error), RMSE (root mean square error), NSE (Nash–Sutcliffe efficiency coefficient), and R (Pearson’s correlation coefficient) values were improved by 5.10, 4.16, 5.34, and 0.43% for the Gaochang Station, and 10.84, 17.28, 13.68, and 3.55% for the Cuntan Station, suggesting the proposed ML approaches are practically applicable to monthly runoff forecasting in large rivers.

2 May 2023 in Journal of Geographical Sciences
Verified
Journal Article
Closed access
PDF file
Sidong ZengSidong Zeng
Sidong Zeng
XLXin Liu
Xin Liu
JXJun Xia
Jun Xia
HDHong Du
Hong Du
MCMinghao Chen
Minghao Chen
RHRenyong Huang
Renyong Huang

14 May 2024 in Environmental Research
Verified
Journal Article
Closed access
YJYongyue Ji
Yongyue Ji
Sidong ZengSidong Zeng
Sidong Zeng
XLXin Liu
Xin Liu
JXJun Xia
Jun Xia

9 January 2024 in Water Research
Verified
Journal Article
Closed access
XTXun Tan
Xun Tan
Sidong ZengSidong Zeng
Sidong Zeng
ZCZhong Chen
Zhong Chen
MLMingquan Lv
Mingquan Lv
XTXiaoya Tang
Xiaoya Tang
JZJingping Zhang
Jingping Zhang