Rainwater runoff non-point source pollution load prediction method and device based on watershed

Abstract

The present invention is applicable to the field of pollution control technology and provides a method and device for predicting rainwater runoff non-point source pollution load based on a watershed. The method comprises: obtaining satellite remote sensing image data of each catchment area of ​​a target watershed section, as well as rainfall forecast information for each catchment area during a future rainfall period; dividing each catchment area into multiple functional areas; determining underlying surface distribution information for each functional area based on the satellite remote sensing image data; and predicting a rainwater runoff non-point source pollution load curve for each functional area during the future rainfall period based on the functional type, rainfall forecast information, and underlying surface distribution information of each functional area, ultimately determining a prediction result for the rainwater runoff non-point source pollution load for the target watershed section during the future rainfall period. The present invention can accurately predict the rainwater runoff non-point source pollution load.

Description

Technical Field

[0001] The present invention belongs to the technical field of pollution control, and in particular relates to a method and device for predicting rainwater runoff non-point source pollution load based on a watershed. Background Art

[0002] Urban non-point source pollution refers to the water pollution caused by various pollutants on the urban surface entering the receiving water bodies of urban rainfall runoff in the form of runoff or surface flow, under the scouring and leaching of rainwater. With my country's rapid urbanization, urban stormwater runoff carries a large amount of pollutants into water bodies, which has become a major cause of deteriorating urban water quality.

[0003] Preventing and controlling rainwater runoff pollution is a key priority for improving water quality, both now and in the future. To further mitigate the impact of initial rainfall on meeting water quality standards at assessed sections and ensure long-term river water quality, it is necessary to predict urban non-point source pollution emissions and implement appropriate regulatory and treatment measures. However, the numerous factors influencing urban non-point source pollution and the complex causes make accurate prediction difficult. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a method and apparatus for predicting rainwater runoff non-point source pollution load based on a watershed, so as to accurately predict rainwater runoff non-point source pollution load.

[0005] A first aspect of an embodiment of the present invention provides a method for predicting rainwater runoff non-point source pollution load based on a watershed, comprising:

[0006] Obtain satellite remote sensing image data of each watershed subarea in the target watershed section, as well as rainfall forecast information for each watershed subarea during future rainfall periods;

[0007] Each watershed area is divided into multiple functional areas;

[0008] Determining underlying surface distribution information of each functional area based on the satellite remote sensing image data;

[0009] Based on the functional type, rainfall forecast information and underlying surface distribution information of each functional area, the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period is predicted;

[0010] Based on the rainwater runoff non-point source pollution load curve of each functional area during the future rainfall period, the rainwater runoff non-point source pollution load prediction result of the target watershed section during the future rainfall period is determined.

[0011] In combination with the first aspect, in a possible implementation of the first aspect, the rainfall forecast information includes rainfall levels, and the underlying surface distribution information includes an area ratio of each type of underlying surface;

[0012] The method of predicting the rainwater runoff non-point source pollution load curve for each functional area during a future rainfall period based on the functional type, rainfall forecast information, and underlying surface distribution information of each functional area includes:

[0013] The functional type, rainfall level and area proportion of each underlying surface of each functional area are input into a pre-trained non-point source pollution prediction model to obtain the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period; wherein, the non-point source pollution prediction model is a deep learning model.

[0014] In combination with the first aspect, in a possible implementation of the first aspect, the method further includes: pre-training the non-point source pollution prediction model;

[0015] The pre-training of the non-point source pollution prediction model includes:

[0016] Obtain pollutant concentration time series and runoff discharge series monitored in multiple functional areas under different rainfall levels;

[0017] Determining, based on the pollutant concentration time series and the runoff discharge volume series, a rainwater runoff non-point source pollution load curve for each functional area under different rainfall levels;

[0018] The functional type, rainfall level and area proportion of each underlying surface of each functional area are used as the input of the initial model, and the corresponding rainwater runoff non-point source pollution load curve is used as the output of the initial model. The connection weights of the initial model are trained to obtain the non-point source pollution prediction model.

[0019] In conjunction with the first aspect, in a possible implementation of the first aspect, determining, based on the rainwater runoff non-point source pollution load curve for each functional area in the future rainfall period, a predicted result of the rainwater runoff non-point source pollution load for the target watershed section in the future rainfall period includes:

[0020] The rainwater runoff non-point source pollution load curves of each functional area in each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of each catchment area;

[0021] The rainwater runoff non-point source pollution load curves of each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of the target watershed section;

[0022] Based on the rainwater runoff non-point source pollution load curve of the target watershed section, a prediction result of the rainwater runoff non-point source pollution load of the target watershed section in a future rainfall period is determined.

[0023] In conjunction with the first aspect, in a possible implementation of the first aspect, before fusing the rainwater runoff non-point source pollution load curves of each functional area in each catchment zone, the method further includes:

[0024] Obtain air pollution data and / or pipeline pollutant deposition data for each functional area;

[0025] Determine the pollution load adjustment curve for each functional area during future rainfall periods based on the atmospheric pollution data and / or pipeline pollutant deposition data for each functional area;

[0026] According to the pollution load adjustment curve of each functional area, the rainwater runoff surface source pollution load curve of each functional area is adjusted.

[0027] In conjunction with the first aspect, in a possible implementation of the first aspect, after determining the prediction result of the rainwater runoff non-point source pollution load of the target watershed section in the future rainfall period, the method further includes:

[0028] Determining the maximum pollution load of the target watershed section based on the rainwater runoff non-point source pollution load curve of the target watershed section;

[0029] Obtaining the pollution absorption rate and water environment capacity of the target watershed section;

[0030] Determining the recovery time of the target watershed section based on the maximum pollution load, the water environment capacity, and the pollution absorption rate;

[0031] If the recovery time is greater than a preset time threshold, it is determined that a preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period.

[0032] In conjunction with the first aspect, in a possible implementation of the first aspect, after determining that a preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period, the method further includes:

[0033] Determine, based on the rainwater runoff non-point source pollution load curve of the target watershed section, a target period within the future rainfall period in which the slope is greater than a preset threshold;

[0034] The target period is determined as the period for implementing the non-point source pollution reduction strategy.

[0035] A second aspect of an embodiment of the present invention provides a basin-based rainwater runoff non-point source pollution load prediction device, comprising:

[0036] An acquisition module is used to obtain satellite remote sensing image data of each watershed subarea of ​​the target watershed section, as well as rainfall forecast information of each watershed subarea during future rainfall periods;

[0037] The division module is used to divide each catchment area into multiple functional areas;

[0038] a processing module, configured to determine underlying surface distribution information of each functional area based on the satellite remote sensing image data;

[0039] A prediction module is used to predict the rainwater runoff non-point source pollution load curve of each functional area during the future rainfall period based on the functional type, rainfall forecast information and underlying surface distribution information of each functional area;

[0040] The calculation module is used to determine the rainwater runoff non-point source pollution load prediction result of the target basin section in the future rainfall period based on the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period.

[0041] In conjunction with the second aspect, in a possible implementation of the second aspect, the rainfall forecast information includes rainfall levels, and the underlying surface distribution information includes an area ratio of each type of underlying surface;

[0042] The prediction module is used to:

[0043] The functional type, rainfall level and area proportion of each underlying surface of each functional area are input into a pre-trained non-point source pollution prediction model to obtain the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period; wherein, the non-point source pollution prediction model is a deep learning model.

[0044] In conjunction with the second aspect, in a possible implementation of the second aspect, the prediction module is further used to: pre-train the non-point source pollution prediction model;

[0045] The pre-training of the non-point source pollution prediction model includes:

[0046] Obtain pollutant concentration time series and runoff discharge series monitored in multiple functional areas under different rainfall levels;

[0047] Determining, based on the pollutant concentration time series and the runoff discharge volume series, a rainwater runoff non-point source pollution load curve for each functional area under different rainfall levels;

[0048] The functional type, rainfall level and area proportion of each underlying surface of each functional area are used as the input of the initial model, and the corresponding rainwater runoff non-point source pollution load curve is used as the output of the initial model. The connection weights of the initial model are trained to obtain the non-point source pollution prediction model.

[0049] In conjunction with the second aspect, in a possible implementation of the second aspect, the calculation module is configured to:

[0050] The rainwater runoff non-point source pollution load curves of each functional area in each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of each catchment area;

[0051] The rainwater runoff non-point source pollution load curves of each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of the target watershed section;

[0052] Based on the rainwater runoff non-point source pollution load curve of the target watershed section, a prediction result of the rainwater runoff non-point source pollution load of the target watershed section in a future rainfall period is determined.

[0053] In conjunction with the second aspect, in a possible implementation of the second aspect, before fusing the rainwater runoff non-point source pollution load curves of each functional area in each catchment zone, the calculation module is further configured to:

[0054] Obtain air pollution data and / or pipeline pollutant deposition data for each functional area;

[0055] Determine the pollution load adjustment curve for each functional area during future rainfall periods based on the atmospheric pollution data and / or pipeline pollutant deposition data for each functional area;

[0056] According to the pollution load adjustment curve of each functional area, the rainwater runoff surface source pollution load curve of each functional area is adjusted.

[0057] In conjunction with the second aspect, in a possible implementation of the second aspect, after determining the prediction result of the rainwater runoff non-point source pollution load of the target watershed section in the future rainfall period, the calculation module is further configured to:

[0058] Determining the maximum pollution load of the target watershed section based on the rainwater runoff non-point source pollution load curve of the target watershed section;

[0059] Obtaining the pollution absorption rate and water environment capacity of the target watershed section;

[0060] Determining the recovery time of the target watershed section based on the maximum pollution load, the water environment capacity, and the pollution absorption rate;

[0061] If the recovery time is greater than a preset time threshold, it is determined that a preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period.

[0062] In conjunction with the second aspect, in a possible implementation of the second aspect, after determining that a preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period, the calculation module is further configured to:

[0063] Determine, based on the rainwater runoff non-point source pollution load curve of the target watershed section, a target period within the future rainfall period in which the slope is greater than a preset threshold;

[0064] The target period is determined as the period for implementing the non-point source pollution reduction strategy.

[0065] A third aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the computer program, the steps of the method in the first aspect or any one of the implementations of the first aspect are implemented.

[0066] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method in the first aspect or any one of the implementations of the first aspect.

[0067] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0068] The embodiment of the present invention takes into account that urban non-point source pollution is mainly affected by the coupling effect of the functional type, rainfall forecast information and underlying surface distribution information of the region. Therefore, the functional areas are divided by the watershed area of ​​the target basin section, and the underlying surface distribution information of the functional areas is determined according to the satellite remote sensing image data. Then, according to the functional type, rainfall forecast information and underlying surface distribution information of each functional area, the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period is predicted. The curve can reflect the change of non-point source pollution load over time. Finally, according to the rainwater runoff non-point source pollution load curve of each functional area, the rainwater runoff non-point source pollution load prediction result of the target basin section is obtained, which can help relevant personnel predict the non-point source pollution load and formulate corresponding non-point source pollution reduction strategies in advance, which helps to weaken the impact of initial rain on the water quality of the assessment section and ensure the long-term clean water quality of the river. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0070] Figure 1 Schematic diagram of an application scenario of a method for predicting rainwater runoff non-point source pollution load based on a watershed provided by an embodiment of the present invention;

[0071] Figure 21 is a schematic diagram of the implementation flow of a method for predicting rainwater runoff non-point source pollution load based on a watershed provided by an embodiment of the present invention;

[0072] Figure 3 1 is a schematic structural diagram of a device for predicting rainwater runoff non-point source pollution load based on a watershed, provided by an embodiment of the present invention;

[0073] Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0074] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0075] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0076] Figure 1 It is a schematic diagram of an application scenario of the watershed-based rainwater runoff non-point source pollution load prediction method provided by an embodiment of the present invention.

[0077] See also Figure 1 As shown in Figure 1, urban nonpoint sources are formed and discharged into the natural environment as urban runoff forms and transfers. Urban ground is composed of various underlying surfaces. Urban runoff first forms on these surfaces and then, through erosion, forms urban nonpoint sources. Within a given confluence area, runoff from these various underlying surfaces eventually converges and enters the river basin.

[0078] Urban non-point source pollution is affected by many factors such as rainfall, underlying surface, and land use. Rainfall is highly random, and the urban underlying surface and its land use have high spatial heterogeneity, resulting in a complex formation mechanism of urban non-point source pollution, high randomness, high uncertainty, and great difficulty in prediction and control.

[0079] To this end, the present invention proposes a method for predicting rainwater runoff non-point source pollution load based on a watershed. Figure 2 Shown, including:

[0080] Step S201 : obtaining satellite remote sensing image data of each watershed subarea of ​​the target watershed section, as well as rainfall forecast information of each watershed subarea in the future rainfall period.

[0081] Urban catchment zoning can be done by combining regional topographic data and drainage network data. For example, the catchment boundaries of major streams within a basin can be first delineated based on the basin boundaries. Then, based on the main streams, the boundaries of major tributaries can be further refined. Finally, based on the division of the major tributary catchment units, the drainage network characteristics of each area can be further refined to determine the final catchment zones.

[0082] See also Figure 1 As shown in the figure, for a watershed, the target watershed section to be studied is set by controlling the section. Based on the confluence of the divided watershed sections, the watershed subsections flowing into the target watershed section are determined as the watershed subsections corresponding to the target watershed section.

[0083] Satellite remote sensing images should be able to reflect the current status of the underlying surface of each catchment area as closely as possible. First, the spatial resolution of the remote sensing data should be as high as possible, and second, the remote sensing data should be as cloud-free as possible.

[0084] Rainfall forecast information includes duration and rainfall level. For example, rainfall levels can be categorized as light rain, moderate rain, heavy rain, torrential rain, heavy rainstorm, and extremely heavy rainstorm, generally measured by daily rainfall. Light rain refers to daily rainfall of less than 10 mm; moderate rain refers to daily rainfall of 10 to 24.9 mm; heavy rain refers to daily rainfall of 25 to 49.9 mm; torrential rain refers to daily rainfall of 50 to 99.9 mm; torrential rain refers to daily rainfall of 100 to 250 mm; and extremely heavy rain refers to daily rainfall of more than 250 mm.

[0085] Step S201: Divide each water catchment area into multiple functional areas.

[0086] With the rapid development of urbanization, resources and factors continue to converge into cities. Urbanization and human socio-economic activities have significantly changed the composition, form, and structural pattern of urban landscapes, forming different types of functional areas (such as commercial areas, residential areas, industrial areas, etc.).

[0087] A large water catchment unit is often composed of several different functional areas, and the pollution load characteristics of different functional areas are significantly different. In this embodiment, a land planning map of the city can be obtained, and the functional area composition of each water catchment unit can be determined based on the land planning map.

[0088] Step S203: determining the underlying surface distribution information of each functional area based on the satellite remote sensing image data.

[0089] The underlying surface is the interface between the atmosphere and the solid ground or liquid water below it. Preprocessing satellite remote sensing images, including geometric correction, atmospheric correction, and image fusion, is combined with professional remote sensing interpretation software and manual interpretation to conduct a refined classification of remote sensing land use. Based on the underlying surface composition, land cover types can be divided into water bodies (reservoirs, canals, rivers, lakes), roofs, roads, and green spaces (woodlands, grasslands, etc.).

[0090] Step S204 , predicting the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period according to the functional type, rainfall forecast information and underlying surface distribution information of each functional area.

[0091] This embodiment pre-trains a deep learning non-point source pollution prediction model. By inputting the functional type, rainfall level and area proportion of each underlying surface of each functional area into the non-point source pollution prediction model, the rainwater runoff non-point source pollution load curve in the future rainfall period can be obtained.

[0092] There are obvious differences in pollution loads on different underlying surfaces, so the underlying surface distribution information can be the area ratio of different underlying surfaces.

[0093] Rainfall forecast information can be rainfall levels. For example, during a light rain event, although the early runoff volume is small and the scouring capacity is limited, the pollutant concentration is very high during the light rain event. In a moderate rain event, the pollutant concentration decreases due to the dilution effect of water. The larger the rainfall type, the greater the runoff volume, which has a greater scouring capacity for surface pollutants. The scouring effect on the road surface is greater than the dilution effect of water. Therefore, the concentration level is the highest during the entire heavy rain process.

[0094] At the same time, usually 20% to 30% of the runoff carries more than 50% to 80% of the pollution load, and the initial scouring effect is obvious.

[0095] Through the non-point source pollution prediction model, the coupling effect of functional type, rainfall prediction information and underlying surface distribution information on pollution load can be considered to achieve the prediction of pollution load changes.

[0096] Here, the nonpoint source pollution prediction model can be pre-trained in the following ways:

[0097] Obtain pollutant concentration time series and runoff discharge series monitored in multiple functional areas under different rainfall levels;

[0098] Based on the pollutant concentration time series and runoff discharge series, the pollutant concentration at the same moment multiplied by the runoff discharge is the generated pollution load, which can determine the rainwater runoff non-point source pollution load curve for each functional area under different rainfall levels;

[0099] The functional type, rainfall level and area proportion of each underlying surface of each functional area are used as the input of the initial model, and the corresponding rainwater runoff non-point source pollution load curve is used as the output of the initial model. The connection weights of the initial model are trained to obtain the non-point source pollution prediction model.

[0100] Step S205 , determining the prediction result of the rainwater runoff non-point source pollution load of the target watershed section in the future rainfall period according to the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period.

[0101] Here, the rainwater runoff non-point source pollution load curves for each functional area of ​​each catchment area can be fused to obtain the rainwater runoff non-point source pollution load curve for each catchment area; the rainwater runoff non-point source pollution load curves for each catchment area can be fused to obtain the rainwater runoff non-point source pollution load curve for the target watershed section; based on the rainwater runoff non-point source pollution load curve for the target watershed section, the rainwater runoff non-point source pollution load prediction results for the target watershed section during the future rainfall period can be determined. Curve fusion refers to the addition of the load values ​​of multiple curves at the same time.

[0102] As a possible implementation method, before merging the rainwater runoff non-point source pollution load curves of each functional area in each catchment area, the following may also be included:

[0103] Obtain air pollution data and / or pipeline pollutant deposition data for each functional area;

[0104] Determine the pollution load adjustment curve for each functional area during future rainfall periods based on the atmospheric pollution data and / or pipeline pollutant deposition data for each functional area;

[0105] According to the pollution load adjustment curve of each functional area, the rainwater runoff surface source pollution load curve of each functional area is adjusted.

[0106] In this embodiment, atmospheric pollution and pipeline pollutant deposition are taken into account. Atmospheric pollution causes pollutants to be carried in rainwater, and pollutants deposited in pipelines will also flow into the river under the scouring of rainwater. Both will have a significant impact on the non-point source pollution load of rainwater runoff. Therefore, here, atmospheric pollution data for future time periods can be obtained through weather forecast data. By sampling sediments in some typical sampling pipe sections, pipeline pollutant deposition data for future time periods can be obtained. Based on these two types of data, the pollution load adjustment curve for each functional area in the future rainfall period is determined through an intelligent algorithm model. Finally, according to the pollution load adjustment curve, the rainwater runoff non-point source pollution load curve is adjusted to improve accuracy.

[0107] The final rainwater runoff non-point source pollution load curve of the target watershed section can not only analyze the amount of rainwater runoff non-point source pollution load of the target watershed section after rain, but also analyze the changes in the rainwater runoff non-point source pollution load during the rain, helping managers to formulate appropriate load reduction strategies.

[0108] The embodiment of the present invention takes into account that urban non-point source pollution is mainly affected by the coupling effect of the functional type, rainfall forecast information and underlying surface distribution information of the region. Therefore, the functional areas are divided by the watershed area of ​​the target basin section, and the underlying surface distribution information of the functional areas is determined according to the satellite remote sensing image data. Then, according to the functional type, rainfall forecast information and underlying surface distribution information of each functional area, the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period is predicted. The curve can reflect the change of non-point source pollution load over time. Finally, according to the rainwater runoff non-point source pollution load curve of each functional area, the rainwater runoff non-point source pollution load prediction result of the target basin section is obtained, which can help relevant personnel predict the non-point source pollution load and formulate corresponding non-point source pollution reduction strategies in advance, which helps to weaken the impact of initial rain on the water quality of the assessment section and ensure the long-term clean water quality of the river.

[0109] The above examples describe how to predict the non-point source pollution load of rainwater runoff at a target watershed section during future rainfall periods. In the following example, based on the rainwater runoff non-point source pollution load prediction results, namely, the rainwater runoff non-point source pollution load curve for the target watershed section, a non-point source pollution reduction strategy for the target watershed section is analyzed. This is described in detail below:

[0110] After determining the prediction results of rainwater runoff non-point source pollution load of the target watershed section during the future rainfall period, the following can also be included:

[0111] Determine the maximum pollution load of the target watershed section based on the rainwater runoff non-point source pollution load curve of the target watershed section;

[0112] Obtain the pollution absorption rate and water environment capacity of the target watershed section;

[0113] Determine the recovery time of the target watershed section based on the maximum pollution load, water environment capacity and pollution absorption rate;

[0114] If the recovery time is greater than the preset time threshold, it is determined that the preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period.

[0115] Water environmental capacity refers to the maximum load of pollutants a water body can accommodate while still meeting water quality requirements. It's also called water load or pollution absorption capacity. The maximum value of the non-point source pollution load curve for rainwater runoff represents the maximum pollution load for the target watershed section. The recovery time for the target watershed section is calculated by subtracting the water environmental capacity from this maximum pollution load and dividing the result by the pollution absorption rate.

[0116] For example, if pollutants in the target watershed section can be restored to a level within the water environment capacity within 48 hours, then there is no need to implement non-point source pollution reduction strategies, and the river will absorb the pollutants on its own. Otherwise, non-point source pollution reduction strategies are required.

[0117] As a possible implementation method, the non-point source pollution load curve for rainwater runoff at the target watershed section can be used to identify target periods during future rainfall periods when the slope exceeds a preset threshold. This target period is then designated as the time period for implementing non-point source pollution reduction strategies. Non-point source pollution reduction strategies can include intercepting rainwater runoff and transferring it to a sewage treatment plant for treatment, temporarily storing it in rainwater regulation facilities, and then feeding it into the sewage system on sunny days or undergoing other targeted treatment. By implementing non-point source pollution reduction strategies during target periods when pollution loads are increasing rapidly, pollution loads can be effectively reduced and sewage system overloads can be avoided.

[0118] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0119] Figure 3 : is a schematic structural diagram of a watershed-based rainwater runoff non-point source pollution load prediction device provided by an embodiment of the present invention, comprising:

[0120] The acquisition module 31 is used to obtain satellite remote sensing image data of each watershed subarea of ​​the target watershed section, as well as rainfall forecast information of each watershed subarea in the future rainfall period.

[0121] The division module 32 is used to divide each water catchment area into multiple functional areas.

[0122] The processing module 33 is used to determine the underlying surface distribution information of each functional area based on the satellite remote sensing image data.

[0123] The prediction module 34 is used to predict the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period according to the functional type, rainfall prediction information and underlying surface distribution information of each functional area.

[0124] The calculation module 35 is used to determine the prediction result of the rainwater runoff non-point source pollution load of the target watershed section in the future rainfall period according to the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period.

[0125] As a possible implementation method, the rainfall forecast information includes rainfall levels, and the underlying surface distribution information includes the area proportion of each type of underlying surface;

[0126] The prediction module 34 is used to:

[0127] The functional type, rainfall level and area proportion of each underlying surface of each functional area are input into the pre-trained non-point source pollution prediction model to obtain the rainwater runoff non-point source pollution load curve of each functional area during the future rainfall period; among them, the non-point source pollution prediction model is a deep learning model.

[0128] As a possible implementation method, the prediction module 34 is further used to: pre-train a non-point source pollution prediction model;

[0129] Pre-trained nonpoint source pollution prediction models include:

[0130] Obtain pollutant concentration time series and runoff discharge series monitored in multiple functional areas under different rainfall levels;

[0131] Based on the pollutant concentration time series and runoff discharge series, determine the rainwater runoff non-point source pollution load curve for each functional area under different rainfall levels;

[0132] The functional type, rainfall level and area proportion of each underlying surface of each functional area are used as the input of the initial model, and the corresponding rainwater runoff non-point source pollution load curve is used as the output of the initial model. The connection weights of the initial model are trained to obtain the non-point source pollution prediction model.

[0133] As a possible implementation, the calculation module 35 is configured to:

[0134] The rainwater runoff non-point source pollution load curves of each functional area in each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of each catchment area;

[0135] The rainwater runoff non-point source pollution load curves of each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of the target watershed section;

[0136] Based on the rainwater runoff non-point source pollution load curve of the target watershed section, the prediction results of the rainwater runoff non-point source pollution load of the target watershed section during the future rainfall period are determined.

[0137] As a possible implementation, before fusing the rainwater runoff non-point source pollution load curves of each functional area in each catchment zone, the calculation module 35 is further configured to:

[0138] Obtain air pollution data and / or pipeline pollutant deposition data for each functional area;

[0139] Determine the pollution load adjustment curve for each functional area during future rainfall periods based on the atmospheric pollution data and / or pipeline pollutant deposition data for each functional area;

[0140] According to the pollution load adjustment curve of each functional area, the rainwater runoff surface source pollution load curve of each functional area is adjusted.

[0141] As a possible implementation method, after determining the prediction result of the rainwater runoff non-point source pollution load of the target watershed section in the future rainfall period, the calculation module 35 is further used to:

[0142] Determine the maximum pollution load of the target watershed section based on the rainwater runoff non-point source pollution load curve of the target watershed section;

[0143] Obtain the pollution absorption rate and water environment capacity of the target watershed section;

[0144] Determine the recovery time of the target watershed section based on the maximum pollution load, water environment capacity and pollution absorption rate;

[0145] If the recovery time is greater than the preset time threshold, it is determined that the preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period.

[0146] As a possible implementation, after determining that a preset non-point source pollution reduction strategy needs to be implemented during a future rainfall period, the calculation module 35 is further configured to:

[0147] Based on the rainwater runoff non-point source pollution load curve of the target watershed section, determine the target period during future rainfall periods when the slope is greater than the preset threshold;

[0148] The target period is determined as the period for implementing the non-point source pollution reduction strategy.

[0149] The embodiment of the present invention takes into account that urban non-point source pollution is mainly affected by the coupling effect of the functional type, rainfall forecast information and underlying surface distribution information of the region. Therefore, the functional areas are divided by the watershed area of ​​the target basin section, and the underlying surface distribution information of the functional areas is determined according to the satellite remote sensing image data. Then, according to the functional type, rainfall forecast information and underlying surface distribution information of each functional area, the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period is predicted. The curve can reflect the change of non-point source pollution load over time. Finally, according to the rainwater runoff non-point source pollution load curve of each functional area, the rainwater runoff non-point source pollution load prediction result of the target basin section is obtained, which can help relevant personnel predict the non-point source pollution load and formulate corresponding non-point source pollution reduction strategies in advance, which helps to weaken the impact of initial rain on the water quality of the assessment section and ensure the long-term clean water quality of the river.

[0150] Figure 4 FIG is a schematic diagram of an electronic device 40 provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 40 of this embodiment includes: a processor 41, a memory 42, and a computer program 43 stored in the memory 42 and executable on the processor 41, such as a program for predicting the non-point source pollution load of rainwater runoff based on a watershed. When the processor 41 executes the computer program 43, the steps of the above-mentioned embodiments of the method for predicting the non-point source pollution load of rainwater runoff based on a watershed are implemented, such as Figure 2 Alternatively, when the processor 41 executes the computer program 43, the functions of the modules in the above-mentioned device embodiments are realized, for example, Figure 3 The functions of the modules 31 to 35 are shown.

[0151] Exemplarily, the computer program 43 may be divided into one or more modules / units, which are stored in the memory 42 and executed by the processor 41 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 43 in the electronic device 40.

[0152] The electronic device 40 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 40 may include, but is not limited to, a processor 41 and a memory 42. Those skilled in the art will understand that Figure 4 It is only an example of the electronic device 40 and does not constitute a limitation of the electronic device 40. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 40 may also include input and output devices, network access devices, buses, etc.

[0153] The processor 41 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0154] The memory 42 may be an internal storage unit of the electronic device 40, such as a hard disk or memory of the electronic device 40. The memory 42 may also be an external storage device of the electronic device 40, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 40. Furthermore, the memory 42 may include both an internal storage unit of the electronic device 40 and an external storage device. The memory 42 is used to store the computer program and other programs and data required by the electronic device 40. The memory 42 may also be used to temporarily store data that has been output or is about to be output.

[0155] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0156] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0157] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0158] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0160] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0161] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0162] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for predicting rainwater runoff non-point source pollution load based on a watershed, characterized in that: include: Obtain satellite remote sensing image data of each watershed subarea in the target watershed section, as well as rainfall forecast information for each watershed subarea during future rainfall periods; Each watershed area is divided into multiple functional areas; Determining underlying surface distribution information of each functional area based on the satellite remote sensing image data; Based on the functional type, rainfall forecast information and underlying surface distribution information of each functional area, the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period is predicted; Determine the predicted results of the rainwater runoff non-point source pollution load of the target watershed section during the future rainfall period based on the rainwater runoff non-point source pollution load curve of each functional area during the future rainfall period; The rainfall forecast information includes rainfall levels, and the underlying surface distribution information includes the area ratio of each type of underlying surface; The method of predicting the rainwater runoff non-point source pollution load curve for each functional area during a future rainfall period based on the functional type, rainfall forecast information, and underlying surface distribution information of each functional area includes: The functional type, rainfall level, and area proportion of each underlying surface of each functional area are input into a pre-trained non-point source pollution prediction model to obtain a rainwater runoff non-point source pollution load curve for each functional area during the future rainfall period; wherein the non-point source pollution prediction model is a deep learning model; Determining the rainwater runoff non-point source pollution load prediction result of the target watershed section in the future rainfall period based on the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period includes: The rainwater runoff non-point source pollution load curves of each functional area in each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of each catchment area; The rainwater runoff non-point source pollution load curves of each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of the target watershed section; Based on the rainwater runoff non-point source pollution load curve of the target watershed section, a prediction result of the rainwater runoff non-point source pollution load of the target watershed section in a future rainfall period is determined.

2. The method for predicting rainwater runoff non-point source pollution load based on a watershed as claimed in claim 1, characterized in that: The method further includes: pre-training the non-point source pollution prediction model; The pre-training of the non-point source pollution prediction model includes: Obtain pollutant concentration time series and runoff discharge series monitored in multiple functional areas under different rainfall levels; Determining, based on the pollutant concentration time series and the runoff discharge volume series, a rainwater runoff non-point source pollution load curve for each functional area under different rainfall levels; The functional type, rainfall level and area proportion of each underlying surface of each functional area are used as the input of the initial model, and the corresponding rainwater runoff non-point source pollution load curve is used as the output of the initial model. The connection weights of the initial model are trained to obtain the non-point source pollution prediction model.

3. The method for predicting rainwater runoff non-point source pollution load based on a watershed as claimed in claim 1, characterized in that: Before fusing the rainwater runoff non-point source pollution load curves of each functional area in each catchment zone, the method further includes: Obtain air pollution data and / or pipeline pollutant deposition data for each functional area; Determine the pollution load adjustment curve for each functional area during future rainfall periods based on the atmospheric pollution data and / or pipeline pollutant deposition data for each functional area; According to the pollution load adjustment curve of each functional area, the rainwater runoff surface source pollution load curve of each functional area is adjusted.

4. The method for predicting rainwater runoff non-point source pollution load based on a watershed as claimed in claim 1, characterized in that: After determining the prediction result of the rainwater runoff non-point source pollution load of the target watershed section in the future rainfall period, the method further includes: Determining the maximum pollution load of the target watershed section based on the rainwater runoff non-point source pollution load curve of the target watershed section; Obtaining the pollution absorption rate and water environment capacity of the target watershed section; Determining the recovery time of the target watershed section based on the maximum pollution load, the water environment capacity, and the pollution absorption rate; If the recovery time is greater than a preset time threshold, it is determined that a preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period.

5. The method for predicting rainwater runoff non-point source pollution load based on a watershed as claimed in claim 4, characterized in that: After determining that a preset non-point source pollution reduction strategy needs to be implemented during the future rainfall period, the method further includes: Determine, based on the rainwater runoff non-point source pollution load curve of the target watershed section, a target period within the future rainfall period in which the slope is greater than a preset threshold; The target period is determined as the period for implementing the non-point source pollution reduction strategy.

6. A device for predicting rainwater runoff non-point source pollution load based on a watershed, characterized in that: include: An acquisition module is used to obtain satellite remote sensing image data of each watershed subarea of ​​the target watershed section, as well as rainfall forecast information of each watershed subarea during future rainfall periods; The division module is used to divide each catchment area into multiple functional areas; a processing module, configured to determine underlying surface distribution information of each functional area based on the satellite remote sensing image data; A prediction module is used to predict the rainwater runoff non-point source pollution load curve of each functional area during the future rainfall period based on the functional type, rainfall forecast information and underlying surface distribution information of each functional area; a calculation module for determining a prediction result of the rainwater runoff non-point source pollution load of the target watershed section within the future rainfall period based on a rainwater runoff non-point source pollution load curve for each functional area within the future rainfall period; The rainfall forecast information includes rainfall levels, and the underlying surface distribution information includes the area ratio of each type of underlying surface; The method of predicting the rainwater runoff non-point source pollution load curve for each functional area during a future rainfall period based on the functional type, rainfall forecast information, and underlying surface distribution information of each functional area includes: The functional type, rainfall level, and area proportion of each underlying surface of each functional area are input into a pre-trained non-point source pollution prediction model to obtain a rainwater runoff non-point source pollution load curve for each functional area during the future rainfall period; wherein the non-point source pollution prediction model is a deep learning model; Determining the rainwater runoff non-point source pollution load prediction result of the target watershed section in the future rainfall period based on the rainwater runoff non-point source pollution load curve of each functional area in the future rainfall period includes: The rainwater runoff non-point source pollution load curves of each functional area in each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of each catchment area; The rainwater runoff non-point source pollution load curves of each catchment area are merged to obtain the rainwater runoff non-point source pollution load curve of the target watershed section; Based on the rainwater runoff non-point source pollution load curve of the target watershed section, a prediction result of the rainwater runoff non-point source pollution load of the target watershed section in a future rainfall period is determined.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images