179 results about "Surface runoff" patented technology

The invention discloses an intelligent discharge port dynamic regulation and control system and method based on multi-source time sequence fusion, and relates to the technical field of intelligent water affairs, and the system comprises a data collection module which is used for obtaining the multi-source data of a target area in real time; the space-time fusion module is used for mapping the meteorological radar data to the topological space of the drainage pipe network through a space-time alignment encoder, dynamically fusing the meteorological radar data, the surface runoff sensor data and the historical drainage data by adopting a multi-head attention mechanism, and generating a space-time fusion tensor; the prediction model module is used for constructing a TCN-LSTM hybrid model, taking the space-time fusion tensor as input and taking future drainage flow as output; and the dynamic regulation and control module is used for optimizing the gate opening degree and the pump station power control sequence in a rolling manner based on a model predictive control algorithm, and performing dual-target optimization by combining real-time electricity price data and overflow risks. According to the system, the prediction precision of the drainage flow can be improved, and double-target balance of the overflow risk and the energy consumption cost can be achieved.

The invention relates to the field of hydrology and water resource management and karst hydrodynamics, and discloses a karst basin coupling hydrology model prediction method, which comprises the following steps: S1, collecting and standardizing multi-source heterogeneous monitoring data of a karst basin; s2, constructing a hydrological model for dynamic coupling of surface runoff, fracture seepage and a pipeline network; s3, performing global optimization on the multi-dimensional hydrological parameters by adopting a hybrid intelligent optimization method; s4, performing iterative correction on the model based on a multi-level verification system; and S5, outputting a hydrological prediction result and generating disaster early warning information. By adopting a dynamic adjusting technology of karst area underground river and surface water flow network joint modeling, multi-karst water-containing medium characteristic analysis and integration of underground river and surface water system response characteristics, the problems that a traditional method cannot accurately predict underground water flow and flow velocity, and is difficult to deal with complexity of a karst water system, lack of data and the like are solved.

The invention discloses an urban inland inundation simulation method based on an SWMM and SIMWE coupling model. The method comprises the steps that basic data and historical heavy rainfall data of a research area are collected and processed; rainstorm events in different recurrence periods are designed; an SWMM-SIMWE coupling model is constructed and verified; and simulating the urban inland inundation condition in a certain period of time in the future based on the designed rainstorm. According to the method, the SWMM model and the SIMWE model are combined and used for simulating an underground drainage system and surface runoff respectively, and water flow movement and accumulated water distribution under the complex urban terrain can be reflected more accurately and efficiently. According to the method, through a reasonable coupling mechanism, the problem that in the prior art, the urban drainage system and the surface runoff dynamic state are difficult to accurately and efficiently simulate is solved, and the water exchange efficiency and precision between the underground drainage system and the surface water flow are remarkably improved. The simulation result provides a scientific basis for urban inland inundation risk assessment and flood control and drainage system optimization, and is helpful for improving the disaster defense capability of cities.

The invention discloses a flood detention area emergency evacuation early warning method based on environmental perception and intelligent analysis, and relates to the technical field of flood control and disaster mitigation, and the method comprises the steps: collecting the original data of a flood detention area site, and forming a monitoring array; a monitoring array is divided into a plurality of monitoring units according to geographic grids, a rainfall permeation model is established according to rainfall data and soil humidity data, a surface runoff field is constructed in combination with terrain elevation data, and the confluence direction of the runoff field is calibrated through water level data; based on a rainfall penetration model and a surface runoff field, generating a flood detention area inundation evolution sequence, segmenting into an inundation grade map according to a time step length, planning a flood detention area emergency evacuation path, matching with a road network in a geographic information system, generating an optimal evacuation path, and issuing graded early warning information to an early warning area. And sending a withdrawal instruction to residents in the flood detention area through the emergency broadcasting system. According to the invention, by establishing a partition early warning mechanism and a differential early warning strategy, accurate delivery and efficient transmission of early warning information are realized.

The invention relates to the technical field of data integration, and particularly discloses a perfluoro / polyfluoroalkyl substance multi-source exposure data integration risk assessment system, which is characterized in that environmental exposure data of perfluoro / polyfluoroalkyl substances is acquired through a multi-source environmental sensor array, and a PFAS multi-mode exposure feature database is established; carrying out pollution source isotope fingerprint analysis, and obtaining source contribution rate distribution maps of three pollution sources of industrial emission, surface runoff and atmospheric settlement through a nonlinear source analysis algorithm; constructing a three-dimensional geographic information dynamic migration model according to the source contribution rate distribution map, and generating a multi-medium dynamic migration flux matrix; a composite risk assessment model is established based on the multi-medium dynamic migration flux matrix, probability risk assessment is executed in combination with an ecological toxicity threshold database, and a space gridding risk grade map is output; the method not only fills the blank of the prior art in the aspects of multi-medium dynamic modeling and nonlinear source analysis, but also provides powerful technical support for environmental pollution control and ecological risk prevention and control.

The invention relates to an urban rainfall flood process forecasting method based on data assimilation and multi-mode coupling, and the method comprises the following steps: (1) collecting historical meteorological data, hydrological data, topographic data, soil texture data, vegetation data and urban infrastructure data in a region; performing quality control and format standardization on all the data, and inputting the data to a GIS technology-based visual analysis and decision-making platform; (2) establishing a parameter transfer rule among the WRF, the SHUD and the two-dimensional hydrodynamic model; (3) operating WRF, obtaining regional high-resolution rainfall forecast data, performing EnKF dynamic updating, and inputting the data to the platform; (4) driving the SHUD to obtain regional surface runoff and groundwater prediction data, performing EnKF dynamic updating and inputting the data to the platform; (5) driving the two-dimensional hydrodynamic model to obtain a flood propagation path and spatio-temporal release data of a submerged area, and inputting the data to the platform; and (6) forming risk level assessment by using an automatic threshold identification technology, and inputting the risk level assessment to the platform. The method is high in practicability and can realize accurate forecasting.

The present application relates to the technical field of heavy-metal pollution remediation, and relates in particular to a soil heavy‐metal accumulation predicting method employing an emission inventory and a receptor model. The method comprises: using atmospheric dust deposition, irrigation water, chemical fertilizers and pesticides as input flux sources of heavy metals to farmland soil, using surface runoff and crops as output fluxes, and constructing an input-output flux inventory of heavy-metal pollutants to clarify a dynamic balance relationship of soil heavy-metal accumulation; and continuously collecting and monitoring of soil samples. The invention provides crucial assistance in determining the transport balance of heavy metals in farmland areas impacted by non-ferrous metal smelting and beneficiation slag sites and in identifying sources of soil heavy-metal pollution, and offers theoretical guidance for subsequent soil heavy-metal remediation and targeted control.

The invention discloses a surface runoff cause identification method and device based on deep learning and interpretability analysis, and is used for solving the technical problem of low identification precision caused by the existing surface runoff cause identification method. The method comprises the following steps: acquiring meteorological and hydrological factor time series data, and inputting the meteorological and hydrological factor time series data into a surface runoff cause identification model based on deep learning; the surface runoff cause identification model based on deep learning comprises a one-dimensional convolution module, a bidirectional long short-term memory network and an identification module based on a multi-head attention mechanism. A one-dimensional convolution module is adopted to carry out convolution operation on the meteorological and hydrological factor time sequence data, and a local response feature sequence is output; performing bidirectional processing operation on the local response feature sequence through a bidirectional long-short-term memory network to generate a target comprehensive feature sequence; and inputting the target comprehensive feature sequence into an identification module based on a multi-head attention mechanism for identification, and outputting a target surface runoff cause identification result.

The invention discloses a source network, plant, river and lake integrated model simulation method and device, a medium and equipment in the technical field of regional water environment pollution treatment. The method comprises the following steps: inputting a boundary condition and an initial condition of a first model into a pre-constructed surface runoff production and convergence model of a target area, and outputting a flow rate of surface runoff and a water quality index time sequence; inputting the boundary condition and the initial condition of the second model into a pre-constructed pipe network model of a target area, and outputting a flow and water quality index time sequence of key nodes in a pipe network system; and inputting the boundary condition and the initial condition of the third model into a pre-constructed riverway and lake grid model of a target area, and simulating the river and lake hydrodynamics and water quality change process of the target area. According to the invention, coupling simulation of surface runoff, pipe networks, rivers and lakes is realized, and a propagation path and an influence mechanism of pollutants are comprehensively reflected; and high precision and reliability of the model are ensured through parameter calibration.

The invention provides an agricultural non-point source load simulation calculation method, and relates to the field of agricultural non-point source pollution calculation, and the method comprises the steps: constructing an agricultural non-point source load calculation model, reading surface runoff time sequence data of each hydrological response unit in a drainage basin, and setting corresponding model parameters; setting a time step length, sequentially calculating the thickness of soil capable of being scoured in the current time step length, the amount of pollutants capable of being scoured in unit area and the amount of pollutants actually scoured in unit area by utilizing surface runoff time sequence data and model parameters, and finally obtaining the updating amount of the concentration of the soil pollutants in the current time step length. All hydrological response units are respectively subjected to the above calculation in the simulation time period to obtain a time sequence of the soil pollutant concentration updating amount, and the agricultural non-point source load of the drainage basin in the simulation time period is calculated in combination with the surface runoff time sequence data. According to the method, the natural process in the agricultural non-point source scouring process is fused into the model, and the obtained agricultural non-point source load is more accurate and more interpretable.

The invention discloses a stepped layered soil fixation and slope protection structure based on plant root system bionics, and belongs to the technical field of ecological slope protection, the stepped layered soil fixation and slope protection structure comprises a stepped frame, a soil fixation module and a water circulation module, the stepped frame is composed of a plurality of slope protection units, the slope protection units are arranged in a stepped mode along a slope surface to form a multi-layer stepped platform, and the water circulation module is connected with the soil fixation module. The adjacent step platforms are connected through anchor rods, the slope protection units are hollow, and root system imitating grooves are formed in the slope protection units. The soil fixation module is arranged in the slope protection unit and is divided into a base layer module, a middle module and a surface layer module from bottom to top; the water circulation module is connected with the step platforms of all the layers and supplies water to vegetation. According to the layered plant root system bionic structure, the anti-sliding and anti-scouring capacity is improved, the stepped structure is adopted, slope runoff is dispersed through the stepped platform, meanwhile, the growth space of plants is provided, engineering materials and the plants are combined, the efficient, ecological and lasting soil fixation and slope protection structure is formed, construction is convenient and fast, and the structure can adapt to complex terrains.

The present application relates to the technical field of the treatment of heavy metal pollution, and in particular, to a method for predicting heavy metal accumulation in soil based on an emission inventory and a receptor model. Atmospheric dust fall, irrigation water, a fertilizer, and a pesticide are used as heavy metal input flux sources of farmland soil, and surface runoff and a crop are used as output fluxes. A heavy metal pollutant input-output flux inventory is established to specify a dynamic equilibrium relationship of heavy metal accumulation in soil, and soil samples are collected and monitored continuously, which provides important help for determining a migration equilibrium of heavy metals in a farmland region affected by a nonferrous metal dressing and smelting slag yard and a source of soil heavy metal pollution, thereby providing theoretical guidance for subsequent prevention and accurate control of heavy metals in soil.

The invention discloses an ecological maintenance structure for the geological environment of a slope in a high-altitude freeze-thaw area, and belongs to the field of ecological restoration and water and soil conservation of slopes in high-altitude frozen soil areas. Comprising a side slope platform, a slope surface is integrally formed on the rear surface of the side slope platform, a plurality of drainage channels are integrally formed in the front surface of the slope surface, a plurality of sedimentation tanks are formed in the position, located in front of the slope surface, of the upper surface of the side slope platform, and the drainage channels communicate with the sedimentation tanks correspondingly; the two adjacent sedimentation tanks are communicated with each other; a water pumping mechanism is arranged on the right side of the side slope platform; an irrigation mechanism is arranged on the upper surface of the slope surface; the irrigation mechanism comprises a mounting box; the water flow speed is slowed down through the interval variable angle design of the drainage channel; the surface runoff can be rapidly guided through the 30-degree slope section, and frost heaving caused by accumulated water permeation is avoided; the 5-degree gentle slope section promotes natural sedimentation of silt by reducing the water flow speed, reduces water and soil loss and disperses hydraulic scouring.

The invention discloses a hydrological forecasting method, medium and equipment for correcting surface runoff simulation precision, and relates to the technical field of hydrological forecasting. The method comprises the following steps: acquiring hydrological driving data, and establishing a hydrological model; constructing a machine learning model to calculate the dynamic contribution weight and contribution water volume of the surface runoff simulation value to the sub-basin outlet flow simulation value; calculating a proportion correction coefficient K by applying a proportion correction method according to the observed value and the simulated value of the outlet flow of the sub-basin; according to the grid surface runoff simulation value and the contribution water volume of the grid surface runoff simulation value to the sub-basin outlet flow simulation value, a reverse correction coefficient C is calculated; an error correction factor alpha is introduced, the grid surface runoff simulation value is corrected through the proportion correction coefficient K, the reverse correction coefficient C and the error correction factor alpha, the corrected grid surface runoff simulation value is used for correcting the hydrological model, and the corrected hydrological model is used for hydrological prediction. The simulation precision of the drainage basin outlet flow can be improved.

This invention discloses a non-uniform fertilization method for controlling non-point source pollution in sloping farmland, comprising: determining the type of cultivated crop and fertilization spacing based on the slope of the target treatment area; dividing the target treatment area into several plots of the same size, determining the slope length based on the slope of each plot, and dividing each plot into three slope positions: the foot, the middle, and the top; determining the fertilization amount at the top of the corresponding plot based on the soil nutrient background value; fertilizing each plot in the target treatment area, with the fertilization amount decreasing proportionally at the top, middle, and foot of the slope; collecting surface runoff samples generated after rainfall at the lower part of each plot, measuring pollutant indicators in the collected water samples to obtain non-point source pollution results; and after the crops on the sloping farmland are harvested, measuring and calculating the crop's fertilizer absorption and utilization efficiency, and obtaining the crop output under non-uniform fertilization. This invention can effectively reduce non-point source pollution in sloping farmland while ensuring crop yield, and has the advantage of low cost.

The invention discloses an intelligent irrigation dynamic regulation and control method and system based on multi-source data. The method comprises the steps that the daily total water demand volume is calculated; acquiring the volume moisture content of the soil of the surface layer and the main root system layer in real time through an array sensor, and calculating the real-time infiltration gradient between the surface layer and the main root system layer; and executing a pulse irrigation process formed by alternation of irrigation pulses and infiltration waiting pulses, stopping water supply when the volumetric water content of the surface layer reaches a first preset threshold value, starting next water supply when the real-time infiltration gradient is lower than a second preset threshold value, and stopping water supply until the accumulated irrigation amount reaches the daily total required water volume or deep layer leakage is monitored. The system is used for executing the method. According to the method, the soil internal infiltration gradient serves as the physical basis of pulse start and stop, efficient conveying of water to deep soil is achieved, the contradiction that surface runoff and deep root system water shortage coexist is solved, and the water utilization rate is increased.

The invention discloses a rice irrigation area nitrogen and phosphorus reduction process simulation method and system. The method comprises the following steps: respectively calculating irrigation nitrogen and phosphorus concentration and field surface water nitrogen concentration of a current round of a rice irrigation area according to meteorological data, field management data and water quality monitoring data; determining the concentration of pollutants carried by surface runoff and underground leaching load according to the nitrogen concentration of the field surface water; calculating the migration attenuation of the nitrogen and phosphorus concentration in the ditch based on preset ditch parameters and the concentration of pollutants carried by the surface runoff to obtain the ditch outlet concentration; calculating the pond purification concentration based on preset pond parameters and the ditch outlet concentration; and calculating the recharge water phosphorus concentration according to the pond purification concentration and the recharge proportion, and updating the irrigation water phosphorus concentration of the next round in the rice irrigation area according to the recharge water phosphorus concentration to finish the reduction process simulation of nitrogen and phosphorus in the rice irrigation area. The method can be used for quickly and accurately simulating the nitrogen and phosphorus reduction process and discharge load of each part of the paddy irrigation area from field to ditch to pond.

The invention provides a mountainous area railway drainage facility site selection method based on a hydrological space site selection analysis model, and relates to the technical field of runoff pollution control, and the method comprises the steps: carrying out the preprocessing of collected data, and obtaining the environment data of a mountainous area railway; a terrain factor analysis layer, a runoff calculation layer, a dumping point screening layer, a spatial clustering analysis layer, a geometric recognition classification layer and a drainage facility recommendation layer are utilized to construct a three-dimensional hydrological space site selection analysis model; and carrying out spatial clustering dimension reduction analysis and surface runoff calculation on the mountainous area railway environment data by utilizing the three-dimensional hydrological space site selection analysis model to obtain a site selection result of the mountainous area railway drainage facility so as to finish site selection of the mountainous area railway drainage facility. The method solves the problem that accurate site selection of drainage facilities of mountainous railways is difficult.

The invention discloses a CA-LSTM-RF soil heavy metal accumulation space-time prediction algorithm under a deep learning framework, and belongs to the technical field of soil heavy metal accumulation space-time prediction algorithms, and the algorithm comprises the steps: obtaining soil heavy metal content data of each sampling point in a plurality of historical periods in a target region and an environment variable data set affecting soil heavy metal accumulation; the method comprises the following steps: performing abnormal value detection, missing data supplementation, alignment processing, quantification processing, normalization processing and time sequence coding on data, performing cellular water flow direction judgment by improving a CA model and designing diffusion process simulation of adaptive time, and calculating heavy metal surface runoff diffusion by using a Manning formula. And taking the diffusion value of the heavy metal along with the surface runoff and the environment variable data as input, extracting a historical data relationship through LSTM, outputting a soil heavy metal accumulation prediction value at the current moment, and taking the output of the LSTM as input to construct an RF model to predict the spatial characteristics of the soil heavy metal.

The invention relates to the technical field of urban drainage modeling simulation, in particular to a hybrid drive modeling method and device for an urban drainage pipe network, and the method comprises the steps: constructing a control equation of an earth surface runoff generation stage and a control equation of a pipe network conveying stage, and constructing a hybrid drive model based on the control equation of the earth surface runoff generation stage and the control equation of the pipe network conveying stage; constructing a mechanism driving model, and obtaining a prediction result error of the mechanism driving model; and establishing a data driving model, inputting the error into the data driving model to calculate a residual error correction value of the data driving model, determining a dynamic compensation value, fusing the dynamic compensation value and a prediction result based on a corresponding weight, and constructing a hybrid driving model of the urban drainage network. Therefore, the problem that the simulation precision and robustness of a complex drainage system cannot be effectively guaranteed due to the fact that the related technology still has obvious weaknesses in the aspects of complex working condition adaptability, multi-facility cooperative regulation and control supporting capacity, atypical rainfall scene prediction precision and the like is solved.

The invention provides a plant-network-river integrated dispatching simulation calculation method and system based on parallel calculation, and the method comprises the steps: obtaining drainage facility attributes, canal plane distribution and section topography, regional digital elevation and land utilization distribution of a dispatching region, and building an SWMM model; collecting rainfall, surface runoff, and water level, flow and water quality monitoring data in the pipe duct confluence and transmission process of different sessions, and performing parameter calibration on the SWMM model to obtain a calibrated SWMM model; constructing a joint optimization scheduling algorithm model by utilizing a particle swarm algorithm, outputting a drainage facility joint regulation and control rule, inputting the joint regulation and control rule into the calibrated SWMM model, and obtaining a simulation calculation result by adopting a parallel calculation mode; and setting a scheduling rule evaluation index to evaluate the simulation calculation result, and outputting an optimal drainage facility joint regulation and control rule. According to the invention, a CPU parallel computing mode is adopted to realize analog computation of factory-network-river integrated operation scheduling, computer performance is fully exerted, and scheduling decision efficiency is improved.

The invention relates to the field of intelligent scheduling of drainage systems, in particular to an intelligent scheduling method and system for a tunnel drainage system based on multi-source data fusion, and the method comprises the steps: obtaining a final rainfall model after space-time calibration through obtaining data and carrying out space-time alignment; acquiring a seepage field and a surface runoff field of the tunnel to obtain a nonlinear mapping relation between rainfall intensity and tunnel catchment flow; obtaining tunnel predicted catchment flow through a nonlinear mapping relation, collecting water-collecting well liquid level data of a tunnel drainage system and operation output data of a drainage pump group, and generating drainage pump group control reference parameters; and when it is detected that the difference between the predicted catchment flow and the actually measured drainage flow of the adjacent tunnel is smaller than a preset difference threshold value, a frequency adjustment instruction and a start-stop control sequence are output in combination with the drainage pump set control reference parameters. The space-time precision of rainfall prediction is improved, the interference influence of catchment flow among tunnels is fully considered, and the accurate scheduling of a tunnel drainage system is improved.

The present invention provides a method for simulating and calculating agricultural non-point source loads, which relates to the field of agricultural non-point source pollution calculation. The method comprises: constructing an agricultural non-point source load calculation model, reading surface runoff time series data of each hydrological response unit in a watershed, and setting corresponding model parameters; setting a time step, and using the surface runoff time series data and the model parameters, sequentially calculating the soil thickness that can be washed within the current time step, the amount of pollutants that can be washed per unit area, and the amount of pollutants actually washed per unit area, ultimately obtaining an updated amount of soil pollutant concentration for the current time step; performing the above calculations for all hydrological response units within a simulation period, obtaining a time series of the updated amount of soil pollutant concentration, and calculating the agricultural non-point source load of the watershed within the simulation period in combination with the surface runoff time series data. The present invention incorporates the natural processes of agricultural non-point source washout into the model, resulting in a more accurate and interpretable agricultural non-point source load.

The invention discloses a camellia oleifera forest water and soil conservation method suitable for a hilly land, which comprises the following steps: carrying out partitioned soil preparation on the hilly land forest land, and arranging an intermittent ladder belt and an undisturbed soil belt in a slope cultivation area along a contour line; constructing a soil stabilizing structure and a water seepage buffer layer on the upstream side of the ladder belt to reduce corrosion and promote seepage; water collection slow-release ditches are arranged on the inner sides of the ladder belts for retaining and storing runoff; arranging a soil and water retention composite layer in the camellia oleifera planting pit; a desilting basin is arranged in the slope toe water collecting area to recover runoff; according to the method, the hilly land forest land is subjected to partitioned soil preparation, and the intermittent ladder belts and the undisturbed soil belts are arranged in the slope surface cultivation areas along the contour lines, so that slope surface runoff scouring can be weakened; a soil stabilizing structure, a water seepage buffer layer and a water collection slow release ditch are combined, so that runoff corrosion reduction and water retention are realized; the soil and water retention composite layers in the camellia oleifera planting pits are matched, so that the stability and the water retention capacity of the root zone can be enhanced, water and soil loss is effectively controlled under the condition that large-scale hard engineering is not needed, and the water utilization efficiency is improved.

The invention discloses a regional groundwater supply simulation method based on a rainfall intensity dynamic response mechanism. The method comprises the following steps: firstly, collecting and preprocessing data of a research area; then simulating a rainfall redistribution process; calculating surface runoff production and initial infiltration; calculating dynamic infiltration response based on rainfall intensity; calculating actual evapotranspiration; and finally outputting the groundwater replenishment amount. According to the method, the key technical problem that underground water supply under high-intensity rainfall is systematically underestimated due to the fact that an existing regional underground water supply simulation method is insufficient in rainfall intensity dynamic response and ignores a rapid deep seepage mechanism induced by high-intensity rainfall is solved.

The application discloses a method for measuring the influence of vegetation on runoff by combining a physical mechanism and an LSTM model, and comprises the following steps: step 1, collecting basic data of a research area; step 2, data processing; step 3, analyzing the influence mechanism among meteorology, vegetation, soil and runoff based on a SEM model; and step 4, simulating a runoff process based on an LSTM model to evaluate the influence of vegetation change on runoff. The method provided by the application analyzes the path of the influence of mountainous vegetation change on runoff and quantifies the influence amount, solves the problem of analyzing the influence of vegetation restoration on surface runoff attenuation, and provides a scientific reference for formulating a reasonable vegetation restoration plan in the next step.

The invention discloses an evaluation method of a hydrodynamic lifting technology based on terrain height difference. The evaluation method comprises the following steps: setting a threshold value based on a connected target to screen a target water body region to be connected; combining geographical, economic and humanistic factors to select resistance factors influencing water system communication, and determining the weight of each resistance factor to construct a water system communication comprehensive resistance surface; identifying potential water system communication galleries in the target water body area based on the target water body area and the water system communication comprehensive resistance surface; optimizing and adjusting a water system communication path according to the construction difficulty of the water system communication gallery and the current situation of regional surface runoff; and evaluating the regional hydrodynamic force lifting effect before and after the communication of the optimized and adjusted water system communication path. According to the method, the problems that a traditional numerical simulation method is complex in application, inconvenient to operate and the like in regional hydrodynamic evaluation are solved, and more convenient and efficient hydrodynamic evaluation is achieved.

The invention relates to the technical field of urban flood simulation, in particular to an urban flood simulation method based on a physical information neural network and multi-GPU calculation. The method comprises the following steps that a computational domain in urban flood simulation is divided into triangular grids, a data matrix is established, a solving process is divided into reconstruction calculation, flux calculation, bottom slope and friction source item calculation and flux updating, and then a two-dimensional shallow water equation finite volume solving process is constructed; a physical information neural network is used for replacing a numerical calculation step in a finite volume solving process of a two-dimensional shallow water equation, a simulation prediction model is obtained through training of the physical information neural network, and the simulation prediction model is used for rapid calculation of a surface runoff process; simulation coupling is carried out on the urban pipe network drainage process and the surface runoff process in urban flood simulation, and a drainage calculation model is constructed. According to the invention, rapid, stable and extensible simulation of large-scale urban flood is realized through an urban flood simulation technology.

The invention belongs to the technical field of pollutant traceability, and relates to a surface runoff particulate matter quantitative traceability method and system and a readable medium, and the method comprises the following steps: collecting element composition data of surface runoff particulate matters; classifying the particulate matters through a clustering algorithm according to the element composition data of the particulate matters; determining the average value of the element composition of each type of particulate matters; and comparing the average value of the elemental composition with the elemental composition characteristic spectrum, and determining the source type corresponding to each type of particulate matter. According to the method, source identification is carried out according to the characteristic that different sources have different element compositions, the source of the surface runoff particulate matter can be accurately identified, quantitative analysis of contribution of each source is realized, a scientific and accurate basis is provided for surface runoff pollution source prevention and control, targeted pollution control measures can be formulated, and pollution prevention and control efficiency can be improved.

The soil collecting device comprises a sample storage pipe and an outer sleeve arranged on the sample storage pipe in a sleeving mode, the upper end of the outer sleeve is open, the lower end of the outer sleeve is provided with a conical part, a supporting disc is arranged on the outer sleeve, a rotating disc located on the upper side of the supporting disc is movably arranged on the outer sleeve through a bearing, and at least one clamping hole is formed in the circumferential direction of the rotating disc. The bottom end of the sample storage pipe is closed, the upper end of the sample storage pipe is open, the sample storage pipe is provided with a mounting disc located on the upper side of the rotating disc, the bottom of the mounting disc is provided with a first mounting ring capable of being arranged on the rotating disc in a sleeving mode, the first mounting ring is provided with a first positioning structure matched with the clamping hole, and the circumferential wall of the sample storage pipe is provided with at least one feeding port; a material guiding opening matched with the feeding opening is formed in the outer sleeve, and a second positioning structure used for aligning the feeding opening and the material guiding opening is arranged between the mounting disc and the supporting disc, so that the problems of inconvenience in use and difficulty in operation in the prior art are solved, and the efficiency and convenience of soil sampling are improved.