Runoff simulations are of great significance to the planning management of water resources. Here, we discussed the influence of the model component, model parameters and model input on runoff modeling, taking Hanjiang River Basin as the research area. Convolution kernel and attention mechanism were introduced into an LSTM network, and a new data-driven model Conv-TALSTM was developed. The model parameters were analyzed based on the Conv-TALSTM, and the results suggested that the optimal parameters were greatly affected by the correlation between the input data and output data. We compared the performance of Conv-TALSTM and variant models (TALSTM, Conv-LSTM, LSTM), and found that Conv-TALSTM can reproduce high flow more accurately. Moreover, the results were comparable when the model was trained with meteorological or hydrological variables, whereas the peak values with hydrological data were closer to the observations. When the two datasets were combined, the performance of the model was better. Additionally, Conv-TALSTM was also compared with an ANN (artificial neural network) and Wetspa (a distributed model for Water and Energy Transfer between Soil, Plants and Atmosphere), which verified the advantages of Conv-TALSTM in peak simulations. This study provides a direction for improving the accuracy, simplifying model structure and shortening calculation time in runoff simulations.

Urban roads in China, particularly low-lying areas such as underpasses, tunnels, and culverts, are highly vulnerable to the dangers of urban pluvial flooding. We used spatial interpolation methods and limited measured data to assign elevation values to the road surface. The road network was divided into tiny squares, enabling us to calculate each square’s elevation, slope, and curvature. Statistical analysis was then employed to evaluate the impact of terrain on flood characteristics in urban road systems. Our analysis reveals a strong spatial correspondence between the distribution of flood-prone points and the curvature parameters of the terrain. The spatial coincidence rate can reach 100% when an appropriate sampling scale is chosen. The presence of depressions is necessary but insufficient for forming flood-prone points. In lowland/gentle slope (LL/GS) areas with higher drainage pressure, we observe a significant negative correlation between flood-prone points and terrain curvature (Spearman’s r = 0.205, p < 0.01). However, in highland/steep slope (HL/SS) areas, we find no significant correlation between them. Notably, terrain matters, but effective drainage is more influential in flood-prone areas. The maximum flood depth (MFD), submerged area, and ponding volume during urban pluvial flooding are constrained by depression topography, while the characteristics of the upstream catchment area also play a role in determining the MFD and flood peak lag time(FPLT). Larger upstream catchment areas and longer flow paths normally result in greater MFD and longer emergency response times/FPLT. Additionally, a higher flow path gradient will directly contribute to an increased flood risk (greater MFD and shorter FPLT). These findings have important implications for flood risk identification and the development of effective flood mitigation strategies.

The concept of low impact development (LID) plays a crucial role in rainstorm management and non-point source pollution prevention and control. Sorting and summarizing related research through the knowledge map can objectively present the disciplinary structure, research focus, and research hotspots of the LID research. Based on 2103 LID pieces of literature in Chinese and English included in the web of science (WOS) database and China’s integrated knowledge resources system (CNKI) database from 2004 to 2021, this paper aims to perform statistical analysis from three aspects: bibliometrics, keyword hotspot co-occurrence and clustering, and literature co-citation clustering. The obtained results reveal that research on LID-based issues maintains a high degree of enthusiasm in China and abroad, but their corresponding focuses are dissimilar. Foreign research essentially focuses on the environmental field with frequent interdisciplinary phenomena, combining the triple goals of water quality improvement, runoff reduction, and multi-functional expansion, and is committed to solving the impact of uncertain factors on urban stormwater management in extreme climates. Chinese research is mostly aimed at unlocking practical engineering problems, which also leads to the majority of research works in the field of building science and engineering. This is mainly due to a series of water-related problems caused by the change in land use types in China. The researchers have determined the type, quantity, location, and combination of the optimal LID measures by establishing appropriate models, using optimization algorithms, and developing multi-level analysis methods. Although the multi-dimensional results of LID in recent years have greatly expanded the framework paradigm, most of the conducted research works are still biased towards the micro-scale. The present hotspot research considers how to make a macroscopic overall layout and efficiently cooperate with the pipelines network, rivers, and lakes systems to unlock the problems pertinent to urban rainwater and non-point source pollution.

Evapotranspiration (ET) is a critical component of the water and energy cycles in desert grassland ecosystems. However, modeling ET in arid grasslands faces significant challenges due to data scarcity, high spatiotemporal heterogeneity, and complex interactions among climatic drivers. To address these challenges, this study developed a Random Forest Regression (RF-R) model integrated with high-resolution PML-V2 ET data and CRU meteorological datasets (2001–2020) to simulate ET in China’s desert grasslands. The RF-R model achieved superior performance, with R² values of 0.953 (training) and 0.931 (testing), RMSE of 3.421 and 4.182 mm/month, and an average prediction bias of 11.815%. The comparative analysis between BPNN and SVR models confirms the robustness of RF-R estimates. Key climate factors were identified through multi-scale importance assessments: precipitation and wet-day frequency were the primary drivers, followed by cloud cover and diurnal temperature range. This study provides a reliable framework for ET simulation in data-scarce arid regions and supports targeted water management strategies for desert grassland restoration.

The Fen River Basin (FRB), an ecologically fragile region in China, exemplifies the intricate interplay between vegetation dynamics and both climatic and human-driven factors. This study leverages a 40-year (1982–2022) dataset, utilizing the kernel-based normalized difference vegetation index (kNDVI) alongside key climatic variables—rainfall (PRE), temperature (TMP), and solar radiation (SRAD)—to investigate vegetation variations and their drivers in the FRB, particularly in relation to the Grain for Green Program (GGP). Our analysis highlights significant greening across the FRB, with the kNDVI slope increasing by 0.0028 yr⁻¹ and green-covered areas expanding by 92.8% over the study period. The GGP facilitated the greening process, resulting in a notable increase in the kNDVI slope from 0.0005 yr⁻¹ to 0.0052 yr⁻¹ and a marked expansion in the area of significant greening from 24.6% to 95.8%. Regional climate shifts, characterized by increased warming, heightened humidity, and a slight rise in SRAD, have further driven vegetation growth, contributing 75%, 58.7%, and 23.6% to vegetation dynamics, respectively. Notably, the GGP has amplified vegetation’s sensitivity to climatic variables, with areas significantly impacted by multiple climate factors expanding from 4.8% to 37.5%. Specially, PRE is the primary climatic influence, impacting 71.3% of the pertinent regions, followed by TMP (60.1%) and SRAD (30%). The integrated effects of climatic and anthropogenic factors, accounting for 47.8% and 52.2% of kNDVI variations, respectively, collectively influence 96% of the region’s vegetation dynamics. These findings underscore the critical role of climate change and human interventions in shaping vegetation patterns and provide a robust foundation for refining ecological conservation strategies, particularly in the context of global warming and land-use policies.