Maritime search and rescue is a crucial component of the national emergency response system, which mainly relies on unmanned aerial vehicles (UAVs) to detect objects. Most traditional object detection methods focus on boosting the detection accuracy while neglecting the detection speed of the heavy model. However, improving the detection speed is essential, which can provide timely maritime search and rescue. To address the issues, we propose a lightweight object detector named Shuffle-GhostNet-based detector (SG-Det). First, we construct a lightweight backbone named Shuffle-GhostNet, which enhances the information flow between channel groups by redesigning the correlation group convolution and introducing the channel shuffle operation. Second, we propose an improved feature pyramid model, namely BiFPN-tiny, which has a lighter structure capable of reinforcing small object features. Furthermore, we incorporate the Atrous Spatial Pyramid Pooling module (ASPP) into the network, which employs atrous convolution with different sampling rates to obtain multi-scale information. Finally, we generate three sets of bounding boxes at different scales—large, medium, and small—to detect objects of different sizes. Compared with other lightweight detectors, SG-Det achieves better tradeoffs across performance metrics and enables real-time detection with an accuracy rate of over 90% for maritime objects, showing that it can better meet the actual requirements of maritime search and rescue.

Water resources carrying capacity (WRCC) is an important component of the carrying capacity of regional natural resources. It is a restrictive index indicating whether a region can support the coordinated development of its population, economy, and environment. In order to solve the problem that WRCC varies with the supporting capacity of, load on, and capacity for regulation of the water resources, this study establishes the relationship between WRCC and the level of socio-economic development (carrying level) and then develops a WRCC evaluation model by analyzing the connotations, characteristics and influencing factors of WRCC. The model is applied to calculate the population and economic scales supportable by water resources in Jiangsu Province under different carrying levels. Predictions are made of the effects of varying water consumption quotas and the industrial structure so as to explore methods of regulating and controlling WRCC in the region. The evaluation, prediction, and control results provide an important reference for the rational allocation of water resources in Jiangsu Province so as to further improve the regional WRCC and achieve sustainable development of regional water resources. The regional WRCC evaluation model has strong applicability and good application effects.

Reliable simulation of seawater intrusion (SI) is necessary for sustainable groundwater utilization. As a powerful tool, feedforward neural network (FNN) was applied to study seawater intrusion area (SIA) fluctuations in Longkou, China. In the present study, changes of groundwater level (GWL) were modeled by FNN Model 1. Then, FNN Model 2 was developed for fitting the relationship between GWL and SIA. Finally, two models were integrated to simulate SIA changes in response to climatic and artificial factors. The sensitivity analysis of each impact factor was conducted by the “stepwise” method to quantify the relative importance for SIA and GWL. The results from the integrated model indicated that this method could accurately reproduce SIA fluctuations when the Nash–Sutcliffe efficiency coefficient was 0.964, the root mean square error was 1.052 km², the correlation coefficient was 0.983, and the mean absolute error was 0.782 km². The results of sensitivity analysis prove that precipitation and groundwater pumping for agriculture mainly affect fluctuations of SIA in the study area. It can be concluded that FNN is effectively used for modeling SI fluctuations together with GWL, which can provide enough support for the sustainable management of groundwater resources with consideration of crucial impact factors of seawater intrusion (SI).

Runoff is greatly influenced by changes in climate conditions. Predicting runoff and analyzing its variations under future climates are crucial for ensuring water security, managing water resources effectively, and promoting sustainable development within the catchment area. As the key step in runoff modeling, the calibration of hydrological model parameters plays an important role in models’ performance. Identifying an efficient and reliable optimization algorithm and objective function continues to be a significant challenge in applying hydrological models. This study selected new algorithms, including the strategic random search (SRS) and sparrow search algorithm (SSA) used in hydrology, gold rush optimizer (GRO) and snow ablation optimizer (SAO) not used in hydrology, and classical algorithms, i.e., shuffling complex evolution (SCE-UA) and particle swarm optimization (PSO), to calibrate the two-parameter monthly water balance model (TWBM), abcd, and HYMOD model under the four objective functions of the Kling–Gupta efficiency (KGE) variant based on knowable moments (KMoments) and considering the high and low flows (HiLo) for monthly runoff simulation and future runoff prediction in Tunxi basin, China. Furthermore, the identified algorithm and objective function scenario with the best performance were applied for runoff prediction under climate change projections. The results show that the abcd model has the best performance, followed by the HYMOD and TWBM models, and the rank of model stability is abcd > TWBM > HYMOD with the change of algorithms, objective functions, and contributing calibration years in the history period. The KMoments based on KGE can play a positive role in the model calibration, while the effect of adding the HiLo is unstable. The SRS algorithm exhibits a faster, more stable, and more efficient search than the others in hydrological model calibration. The runoff obtained from the optimal model showed a decrease in the future monthly runoff compared to the reference period under all SSP scenarios. In addition, the distribution of monthly runoff changed, with the monthly maximum runoff changing from June to May. Decreases in the monthly simulated runoff mainly occurred from February to July (10.9–56.1%). These findings may be helpful for the determination of model parameter calibration strategies, thus improving the accuracy and efficiency of hydrological modeling for runoff prediction.

Base flow, as an important component of runoff, is the main recharge source of runoff during the dry period, especially in the Yellow River Basin located in a semiarid area. However, the process of obtaining base flow has great uncertainty when considering hydrological simulations. Thus, in this study, a three-step framework is proposed, i.e., the particle swarm optimization (PSO) algorithm is used to calibrate model parameters under different subbasin partitioning schemes; then, the hydrograph separation (HYSEP), Improved United Kingdom Institute of Hydrology (IUKIH) and Lyne and Hollick filter (Lyne-Hollick) methods are used to separate the baseflow from the total runoff process, thereby exploring the uncertainty impacts of baseflow segmentation methods on the hydrological simulation process. The subsample-variance-decomposition method is used to quantify the independent and interactive uncertainty in the hydrological simulation process. The results show that the Topmodel model can be better applied to the source area of the Yellow River (the KGE values in the Sub5, Sub13, Sub21, Sub29, Sub37 and Sub13 scenarios were 0.91 and 0.65, 0.94 and 0.86, 0.94 and 0.88, 0.92 and 0.82, 0.95 and 0.89, and 0.92 and 0.83, respectively). The subbasin division uncertainty had less impact on simulated streamflow during the dry season and had a significant impact in the wet season, such as, the subbasin division uncertainty caused the difference between the median of the simulated streamflow to be as high as 213.09 m³/s in August but only 107.19 m³/s in January; Meanwhile, the baseflow segmentation method uncertainty has a significant impact on the annual mean streamflow values under different subbasin segmentation schemes. In addition, the baseflow values estimated by the Lyne-Hollick and HYSEP methods were obviously higher than those estimated by the IUKIH method during the wet season. The uncertainty influence of subbasin partitioning schemes and baseflow segmentation methods had significant differences on hydrological processes in different periods. The uncertainty influence of subbasin partitioning schemes was dominant in the dry season, accounting for 86%, and the baseflow segmentation methods took second place, accounting for approximately 12%. In the wet season, the uncertainty influence of the baseflow segmentation methods was gradually weakened, which may have been due to the uncertainty influence of the hydrological model. These results provide a reference for the calibration and validation of hydrological model parameters using baseflow components.