The change of spatial and temporal distribution of precipitation has an important impact on urban water security. The effect of land cover land use change (LCLUC) on the spatial and temporal distribution of precipitation needs to be further studied. In this study, transfer matrix, standard deviation ellipse and spatial autocorrelation analysis techniques were used. Based on the data of land cover land use and precipitation, this paper analyzed the land cover land use change and its influence on the spatial and temporal distribution pattern of precipitation in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA). The results showed that from 2001 to 2019, the area of cropland, water, barren, forest/grassland in the GBA decreased by 44.03%, 8.05%, 50.22%, 0.43%, respectively, and the area of construction land increased by 20.05%. The precipitation in the GBA was mainly concentrated in spring and summer, and the precipitation in spring tended to increase gradually, while the precipitation in summer tended to decrease gradually, while the precipitation in autumn and winter has no obvious change. It was found that with the change of land cover land use, the spatial distribution of precipitation also changed. Especially in the areas where the change of construction land was concentrated, the spatial distribution of precipitation changed most obviously.

In unmanned aerial vehicle based urban observation and monitoring, the performance of computer vision algorithms is inevitably limited by the low illumination and light pollution caused degradation, therefore, the application image enhancement is a considerable prerequisite for the performance of subsequent image processing algorithms. Therefore, we proposed a deep learning and generative adversarial network based model for UAV low illumination image enhancement, named LighterGAN. The design of LighterGAN refers to the CycleGAN model with two improvements—attention mechanism and semantic consistency loss—having been proposed to the original structure. Additionally, an unpaired dataset that was captured by urban UAV aerial photography has been used to train this unsupervised learning model. Furthermore, in order to explore the advantages of the improvements, both the performance in the illumination enhancement task and the generalization ability improvement of LighterGAN were proven in the comparative experiments combining subjective and objective evaluations. In the experiments with five cutting edge image enhancement algorithms, in the test set, LighterGAN achieved the best results in both visual perception and PIQE (perception based image quality evaluator, a MATLAB build-in function, the lower the score, the higher the image quality) score of enhanced images, scores were 4.91 and 11.75 respectively, better than EnlightenGAN the state-of-the-art. In the enhancement of low illumination sub-dataset $Y$ (containing 2000 images), LighterGAN also achieved the lowest PIQE score of 12.37, 2.85 points lower than second place. Moreover, compared with the CycleGAN, the improvement of generalization ability was also demonstrated. In the test set generated images, LighterGAN was 6.66 percent higher than CycleGAN in subjective authenticity assessment and 3.84 lower in PIQE score, meanwhile, in the whole dataset generated images, the PIQE score of LighterGAN is 11.67, 4.86 lower than CycleGAN.

Waterlogging simulation is a key technology for solving urban waterlogging problems. The current waterlogging modeling process is relatively complex and requires high basic data, which is not conducive to rapid modeling and popularization. In this study, we evaluated the correlation between rainfall and waterlogging water using the following factors: terrain, evaporation, infiltration, pipe drainage capacity, and river flood water level. By quantifying the influence value of each factor on rainfall, we established a simplified model for fast calculation of waterlogging depth through input rainfall. Waterlogging data was collected from Guangzhou, China to set up the multi-factor correlation model, and verify the simulation results of the model. After the original rainfall is added/deducted, the added/loss value, the relationship between net rainfall, and maximum water depth is better than that between original rainfall and maximum water depth. Establishing a stable multi-factor correlation model for a waterlogging point requires at least three historical waterlogging event data for parameter calibration by sensitivity analysis. Comparing the simulation of four waterlogging points, the multi-factor correlation model (error = −13%) presented the least error in simulating the maximum water volume, followed by the Mike Urban model (error = −19%), and finally the SWMM model (error = 20%). Furthermore, the multi-factor correlation model and SWMM model required the least calculation time (less than 1 s), followed by the Mike Urban model (About half a minute). By analyzing the waterlogging data of Guangzhou, 42 waterlogging points with modeling conditions were screened out to further validate the multi-factor correlation model. Each waterlogging point was modeled based on the historical field, and the last rainstorm was used for model verification. The mean error of the comparison between the simulated maximum waterlogging and the measured maximum waterlogging was 3%, and the R² value was 0.718. In summary, the multi-factor correlation model requires fewer basic data, has a simple modeling process and wide applicability, and makes it easy to realize the intelligent parameter adjustment, which is more suitable for the urgent requirements of current urban waterlogging prediction. The model results may prove accurate and provide scientific decision support for the prevention and control of urban waterlogging.

As an effective heuristic method, three-way decision theory gives a new semantic interpretation to the three fields of the rough set, which has a huge application space. To classify the information of agricultural products more accurately under certain thresholds, this paper first makes a comprehensive evaluation of the decision, particularly the influence of the attributes of the event itself on the results and their interactions. By using fuzzy sets corresponding to membership and non-membership degree, this paper analyzes and puts forward two cases of proportional correlation coefficients in the transformation of a delayed decision domain, and selects the corresponding coefficients to compare the results directly. Finally, consumers can conveniently grasp product attribute information to make decisions. On this basis, this paper analyzed the standard data to verify the accuracy of the model. After that, the proposed algorithm, based on three decision-making agricultural product information classification processing, is applied to the relevant data of agricultural products. The experimental results showed that the algorithm can obtain more accurate results through a more straightforward calculation process. It can be concluded that the algorithm proposed in this paper can enable people to make more convenient and accurate decisions based on product attribute information.