Search

Recent research has shown that deep learning (DL) faces physical realism challenges in predicting runoff responses under climate change, mainly due to DL’s data dependence and lack of process understanding. In this study, a physics-encoded neural network model (dNN) was developed to adress this. dNN enables a fully process-based way to training and prediction by encoding process-based modeling knowledge into the DL architecture, including the water balance principle and causal linkages of catchment hydrological processes. To examine whether dNN can produce reliable runoff responses under warming scenarios, we first conducted regional training for dNN on daily runoff in 29 catchment in California. Two process-based models, EXP-HYDRO and HBV, were then developed as benchmarks. Both dNN and a pure data-driven LSTM were forced under warming scenarios, and the monthly hydrographs and total runoff ratios metrics were evaluated relative to the benchmarks. The results demonstrated: (1) For monthly hydrographs, dNN exhibited advantages in capturing cold-season runoff increase and warm-season recession than LSTM, effectively predicting the changes and trends in monthly runoff under warming scenarios; (2) For total runoff ratios, dNN predicted fewer catchments with increased runoff, indicating it can better maintain the total water budget under warming scenarios; (3) Through the synergy with physics, dNN was able to reasonably infer unobserved snowpack dynamics under warming scenarios. These results highlight the credibility and necessity of considering physics for DL in predicting runoff responses under climate change. Overall, this study provides a promising solution for considering physics in DL to further improve the process understanding in changing environments.

Investigating the effects of climate and land-use changes on surface runoff is critical for water resources management. The majority of studies focused on projected climate change effects on surface runoff, while neglecting future land-use change. Therefore, the main aim of this article is to discriminate the impacts of projected climate and land-use changes on surface runoff using the Soil and Water Assessment Tool (SWAT) through the lens of the Upper Indus Basin, Pakistan. Future scenarios of the land-use and climate changes are predicted using cellular automata artificial neural network and four bias-corrected general circulation models, respectively. The historical record (2000–2013) was divided into the calibration period (2000–2008) and the validation period (2009–2013). The simulated results demonstrated that the SWAT model performed well. The results obtained from 2000 to 2013 show that climate change (61.61%) has a higher influence on river runoff than land-use change (38.39%). Both climate and land-use changes are predicted to increase future runoff depth in this basin. The influence of climate change (12.76–25.92%) is greater than land-use change (0.37–1.1%). Global weather data has good applicability for simulating hydrological responses in the region where conventional gauges are unavailable. The study discusses that both climate and land-use changes impact runoff depth and concludes with some suggestions for water resources managers to bring water environment sustainability. HIGHLIGHTS The SWAT model was used to isolate the climate and land-use change impacts on streamflow.; The general circulation model was used to assess climate change impacts on streamflow.; The CA-ANN model was used to predict future land use.; Multiple climate and land-use scenarios were set to isolate climate and land-use change impacts on streamflow.; Climate change effects overweigh the land-use change effects on streamflow.;

In this study, runoff responses of typical urban surfaces were investigated by scale models under artificial rainfall simulation, and the Soil Conservation Service (SCS) model was used to assess the impacts of land use changes and green infrastructures implementation on surface runoff of Beijing urban areas. The results showed that: Runoff coefficient of the impervious surface was about 2.1 times than that of the grassland. Time to runoff of the grassland was about 22.0 times that of the impervious surface. The concaved grassland, compared with the impervious surface, can significantly delay by 6.2 minutes the time to runoff, while the porous pavement significantly reduces 28.1% of the runoff coefficient. The runoff coefficient of Beijing urban areas increased from 0.68 in 2002 to 0.72 in 2012, due to the substantially increased impervious surfaces. The runoff coefficient decreased by 2.7%, 15.3% and 22.2% respectively under three green infrastructure scenarios. [ABSTRACT FROM AUTHOR]

Climate and land use/cover (LUC) are the two most significant factors that directly affect the runoff process. However, most research on runoff response has focused mainly on projected climate variation, while future LUC variability has been neglected. Therefore, the objective of this study is to examine the impacts of projected climate and LUC changes on runoff. Future climate scenarios are projected using the Quantile Mapping (QM) method, and future LUC scenarios are predicted with the Cellular Automaton-Markov (CA-Markov) model. Three different scenarios are simulated and compared to evaluate their impacts: Scenario 1 (LUC of 2010 and climate during the 2011–2050 period, abbreviated S1), Scenario 2 (LUC of 2010, 2020, 2030, 2040 and 2050 and climate of the historical wet year, normal year and dry year, abbreviated S2) and Scenario 3 (LUC of 2010, 2020, 2030, 2040 and 2050 and corresponding climate projections of 2011–2020, 2021–2030, 2031–2040 and 2041–2050 period, abbreviated S3). These three scenarios are then input into the Soil and Water Assessment Tool (SWAT) model to assess runoff responses. Beijiang River Basin, located in southern China, is used in this case study. The results obtained from S1, S2 and S3 show that runoff change in this basin is mainly caused by climate change; warmer temperatures and greater precipitation increase runoff. LUC change has little influence on runoff at the whole-basin scale, but changes in runoff components are more notable in the urban area than in the natural region at the sub-watershed level. The impact of LUC change in urbanized region on runoff components differ obviously among the wet, normal and dry years, and surface runoff and groundwater are found to be more sensitive to urbanization. Runoff depth is predicted to increase in this basin under the impacts of both climate and LUC changes in the future. Climate change brings greater increase in water yield and surface runoff, whereas LUC change leads to changes in allocation between surface runoff and groundwater in the urban region. [ABSTRACT FROM AUTHOR]

Summary: We examined the effect of forest thinning on runoff generation at plot and catchment scales in headwater basins draining a Japanese cypress (Chamaecyparis obtusa) forest. We removed 58.3% of the stems (corresponding to 43.2% of the basal area) in the treated headwater basin (catchment M5), and left the control catchment (M4) untreated. In both catchments, we monitored overland flow from hillslope plots and stream runoff from catchments at basin outlets over a 2-year pre-thinning period and a 2-year post-thinning period. Paired catchment analysis revealed that annual catchment runoff increased 240.7mm after thinning. Delayed runoff increased significantly, while quick runoff followed similar patterns in the pre- and post-thinning periods. Flow duration in the ephemeral channel in catchment M5 increased from 56.9% in the pre-thinning period to 73.3% in the post-thinning period. Despite the changes in hydrological responses at the catchment scale, increases in overland flow were not significant. The increased availability of water in the soil matrix, caused by decreased interception loss and evapotranspiration, increased base flow after thinning. Based on the summarized data of previous studies together with this study, the effects of forest thinning on increases in runoff were less than partial harvesting in which the managed areas were concentrated within a watershed. We demonstrated that the effect of forest thinning was strongly scale dependent, an important finding for optimizing water and forest management in forested watersheds. [Copyright &y& Elsevier]