Considering the high random and non-static property of the rainfall-runoff process, lots of models are being developed in order to learn about such a complex phenomenon. Recently, Machine learning techniques such as the Artificial Neural Network (ANN) and other networks have been extensively used by hydrologists for rainfall-runoff modelling as well as for other fields of hydrology. However, deep learning methods such as the state-of-the-art for LSTM networks are little studied in hydrological sequence time-series predictions. We deployed ANN and LSTM network models for simulating the rainfall-runoff process based on flood events from 1971 to 2013 in Fen River basin monitored through 14 rainfall stations and one hydrologic station in the catchment. The experimental data were from 98 rainfall-runoff events in this period. In between 86 rainfall-runoff events were used as training set, and the rest were used as test set. The results show that the two networks are all suitable for rainfall-runoff models and better than conceptual and physical based models. LSTM models outperform the ANN models with the values of $R^2$ and $NSE$ beyond 0.9, respectively. Considering different lead time modelling the LSTM model is also more stable than ANN model holding better simulation performance. The special units of forget gate makes LSTM model better simulation and more intelligent than ANN model. In this study, we want to propose new data-driven methods for flood forecasting.

Runoff reduction in most river basins in China has become a hotpot in recent years. The Gushanchuan river, a primary tributary of the middle Yellow river, Northern China, showed a significant downward trend in the last century. Little is known regarding the relative contributions of changing environment to the observed hydrological trends and response on the runoff generation process in its watershed. On the basis of observed hydrological and meteorological data from 1965–2010, the Mann-Kendall trend test and climate elasticity method were used to distinguish the effects of climate change and human activities on runoff in the Gushanchuan basin. The results indicate that the runoff in the Gushanchuan Basin has experienced significant declines as large as 77% from 1965 to 2010, and a mutation point occurred around 1997; the contribution rate of climate change to runoff change is 12.9–15.1%, and the contribution rate of human activities to runoff change is 84.9–87.1%. Then we divided long-term data sequence into two stages around the mutation point, and analyzed runoff generation mechanisms based on land use and cover changes (LUCC). We found that the floods in the Gushanchuan Basin were still dominated by Excess-infiltration runoff, but the proportion in 1965–1997 and 1998–2010 decreased gradually (68.46% and 45.83% in turn). The proportion of Excess-storage runoff and Mixed runoff has increased, which means that the runoff is made up of more runoff components. The variation law of the LUCC indicates that the forest area increased by 49.61%, the confluence time increased by 50.42%, and the water storage capacity of the watershed increased by 30.35%.

In 1999, the Yellow River Basin (YRB) launched the Grain for Green Program (GGP), which has had a huge impact on the Yellow River Basin vegetation. Research regarding the causes of vegetation changes can provide beneficial information for the management and construction of the ecological environment in the Yellow River Basin. In this study, after reconstructing the relationship between vegetation and climate change under natural conditions, topographic factors were introduced to understand vegetation change in the Yellow River Basin before and after the initiation of the Grain for Green Program, and the contribution rates of the driving factors of change were analyzed. Results show that human activities have had a great impact on the vegetation cover in the Yellow River Basin. We found that after the start of the Grain for Green Program, the vegetation recovery rate was more than six times (slope = 0.0067) that before its start (slope = 0.0011); high NDVI levels moved to lower altitudes, while low NDVI levels moved to high altitudes; and most vegetation types turned to gentle slopes. Human activities and climate change are the dominant factors influencing vegetation coverage, and the contribution rate of human activities had reached 59.3% after 2000, with a tendency to gradually dominate.

Rainfall pulses can significantly drive the evolution of the structure and function of semiarid ecosystems, and understanding the mechanisms that underlie the response of semiarid plants to rainfall is the key to understanding the responses of semi–arid ecosystems to global climatic change. We measured sap flow in the branches and stems of shrubs (Caragana korshinskii Kom. and Hippophae rhamnoides Linn.) using sap flow gauges, and studied the response of sap flow density to rainfall pulses using the “threshold–delay” model in the Chinese Loess Plateau. The results showed that the sap flow began about 1 h earlier, and increased twofold after rainfall, compared to its pre-rainfall value. The sap flow increased significantly with increasing rainfall classes, then gradually decreased. The response of sap flow was different among rainfall, species, position (branch and stem) during the pulse period, and the interactive effects also differed significantly (P < 0.0001). The response pattern followed the threshold–delay model, with lower rainfall thresholds of 5.2, 5.5 mm and 0.7, 0.8 mm of stem and branch for C. korshinskii and H. rhamnoides, demonstrating the importance of small rainfall events for plant growth and survival in semi–arid regions.