Waterlogging risk detection method and device

Abstract

The invention provides a waterlogging risk detection method and device. The method comprises the following steps: determining each risk rainfall event which causes waterlogging to occur in a to-be-detected area from each historical rainfall event corresponding to a rainfall level; according to an initial ponding amount interval in which the predicted ponding amount of the future rainfall event at the initial moment is located, determining each target rainfall event of which the ponding amount at the initial moment is smaller than or in the initial ponding amount interval from the risk rainfall events; according to each target rainfall event corresponding to the rainfall level and each historical rainfall event corresponding to the rainfall level, determining a waterlogging risk probability of the rainfall level in the to-be-detected area; and according to the waterlogging risk probability of each rainfall level, determining a target risk probability of each predicted rainfall level of a future rainfall event of the to-be-detected area, so as to determine a waterlogging risk detection result of the to-be-detected area in the future rainfall event according to the target risk probability of each predicted rainfall level.

Description

Technical Field

[0001] The present application relates to the technical field of risk detection, and in particular to a method and device for detecting urban flooding risk. Background Art

[0002] In urban flood prevention and control, detecting areas at risk of waterlogging is an important basis for planning and designing flood control and drainage facilities and formulating emergency plans. At present, the detection of areas at risk of waterlogging is based on the current rainfall in a certain area to determine whether the area is a risk area for waterlogging. However, this method has a serious lag, and it is easy for a certain area to be identified as a risk area when waterlogging has already occurred, resulting in the inability to issue early warnings to the risk area in a timely manner, affecting the safety of urban drainage. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems existing in the related art. To this end, the present application proposes a waterlogging risk detection method, which can timely warn the risk areas of waterlogging and improve the safety of urban drainage.

[0004] The present application also proposes a waterlogging risk detection device.

[0005] The application also provides an electronic device.

[0006] The present application also proposes a computer-readable storage medium.

[0007] According to the first aspect of the present application, the method for detecting waterlogging risk includes:

[0008] Determine the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested;

[0009] Determining, from the historical rainfall events corresponding to the rainfall levels, the risk rainfall events that may cause waterlogging in the tested area;

[0010] According to the starting water volume interval of the predicted water volume of the future rainfall event at the starting time, determine from each of the risky rainfall events each target rainfall event whose water volume at the starting time is less than or within the starting water volume interval;

[0011] Determine, according to each of the target rainfall events corresponding to the rainfall level and each of the historical rainfall events corresponding to the rainfall level, a waterlogging risk probability of the rainfall level in the test area;

[0012] Determine the target risk probability of each predicted rainfall level of future rainfall events in the tested area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the tested area in the future rainfall events according to the target risk probability of each predicted rainfall level;

[0013] The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

[0014] By determining the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested, and determining the risk rainfall events that may cause waterlogging in the area to be tested from the historical rainfall events corresponding to the rainfall level, and determining the target rainfall events whose waterlogging at the starting time is less than or in the starting waterlogging range according to the predicted waterlogging at the starting time of the future rainfall event from the risk rainfall events, the waterlogging risk probability of the rainfall level in the area to be tested is determined according to the target rainfall events corresponding to the rainfall level and the historical rainfall events corresponding to the rainfall level, and the target risk probability of each predicted rainfall level of future rainfall events in the area to be tested is determined according to the waterlogging risk probability of each rainfall level, and the waterlogging risk detection result of the area to be tested in the future rainfall event is determined according to the target risk probability of each predicted rainfall level. Therefore, before the occurrence of future rainfall events, the target rainfall events that will cause urban waterlogging can be determined by the predicted water accumulation at the starting time of future rainfall events. The target rainfall events of various levels in the tested area and historical rainfall events can be combined to predict whether the tested area will face the risk of urban waterlogging in future rainfall events. This can provide timely warnings to areas at risk of urban waterlogging, improve the accuracy of prediction results, and thereby improve the safety of urban drainage.

[0015] According to an embodiment of the present application, determining the waterlogging risk probability of the rainfall level in the test area according to each target rainfall event corresponding to the rainfall level and each historical rainfall event corresponding to the rainfall level includes:

[0016] Generate an event sequence by chronologically sequencing each of the target rainfall events in each of the historical rainfall events corresponding to the rainfall level and each of the non-target rainfall events in each of the historical rainfall events;

[0017] Inputting the event sequence into a trained long short-term memory network to obtain a predicted probability that a future event is the target rainfall event;

[0018] Determining the waterlogging risk probability of the rainfall level in the test area according to the predicted probability;

[0019] The long short-term memory network is trained based on historical event samples of any level.

[0020] According to one embodiment of the present application, it also includes:

[0021] The predicted amount of water accumulation is determined according to the amount of water accumulation in the area to be measured at the current moment, the drainage rate of the area to be measured and the starting moment of the future rainfall event.

[0022] According to an embodiment of the present application, determining the target risk probability of each predicted rainfall level of the tested area in future rainfall events according to the waterlogging risk probability of each rainfall level includes:

[0023] Determining the initial risk probability of each predicted rainfall level in the tested area in future rainfall events according to the waterlogging risk probability of each rainfall level;

[0024] Obtaining a target risk probability of the predicted rainfall level according to the predicted probability of the predicted rainfall level and the initial risk probability of the predicted rainfall level;

[0025] The predicted probability is the probability that the predicted rainfall of the future rainfall event reaches the predicted rainfall level.

[0026] According to an embodiment of the present application, determining the waterlogging risk detection result of the tested area in the future rainfall event according to the target risk probability of each predicted rainfall level includes:

[0027] Superimposing the target risk probabilities of the predicted rainfall levels, to obtain the probability of waterlogging in the tested area in the future rainfall event;

[0028] According to the waterlogging probability, a waterlogging risk detection result of the tested area in the future rainfall event is determined.

[0029] According to one embodiment of the present application, it also includes:

[0030] Determine that the waterlogging risk detection result indicates that the tested area has a waterlogging risk in the future rainfall event, and generate prompt information for modifying the drainage network in the tested area.

[0031] According to one embodiment of the present application, the rainfall amount is positively correlated with the rainfall level.

[0032] According to the second aspect of the present application, the waterlogging risk detection device includes:

[0033] A rainfall event acquisition module, used to determine each historical rainfall event corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested;

[0034] A first event determination module is used to determine each risk rainfall event that causes waterlogging in the test area from each of the historical rainfall events corresponding to the rainfall level;

[0035] The second event determination module is used to determine, from the risky rainfall events, each target rainfall event whose water accumulation amount at the starting time is less than or equal to the predicted water accumulation amount according to the predicted water accumulation amount of the future rainfall event at the starting time;

[0036] A risk probability determination module, used to determine the waterlogging risk probability of the rainfall level in the test area according to each target rainfall event corresponding to the rainfall level and each historical rainfall event corresponding to the rainfall level;

[0037] A waterlogging risk detection module, for determining the target risk probability of each predicted rainfall level of future rainfall events in the tested area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the tested area in the future rainfall events according to the target risk probability of each predicted rainfall level;

[0038] The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

[0039] According to an electronic device of an embodiment of the third aspect of the present application, the electronic device includes a processor and a memory storing a computer program, and when the processor executes the computer program, the method for detecting waterlogging risk described in any of the above embodiments is implemented.

[0040] According to the computer-readable storage medium of the fourth aspect of the present application, a computer program is stored thereon, and when the computer program is executed by a processor, the method for detecting waterlogging risk described in any of the above embodiments is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 A first flow chart of a method for detecting waterlogging risk according to some embodiments of the present application;

[0043] Figure 2 A second flow chart of a waterlogging risk detection method according to some embodiments of the present application;

[0044] Figure 3 A schematic diagram of the structure of a waterlogging risk detection device provided in some embodiments of the present application;

[0045] Figure 4 A schematic diagram of the structure of an electronic device provided for some embodiments of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] Below, the waterlogging risk detection method and device provided in the embodiments of the present application will be introduced and explained in detail through several specific embodiments.

[0048] In one embodiment, a method for detecting waterlogging risk is provided, which is applied to a terminal device and is used to predict the risk of waterlogging in a detected area. The terminal device may be any terminal device such as a mobile terminal, a desktop terminal or a server, wherein the server may be an independent server or a server cluster composed of multiple servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud message databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and large message data and artificial intelligence sampling point devices.

[0049] like Figure 1 As shown, a waterlogging risk detection method provided in this embodiment includes:

[0050] Determine the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested;

[0051] Determining, from the historical rainfall events corresponding to the rainfall levels, the risk rainfall events that may cause waterlogging in the tested area;

[0052] According to the predicted water accumulation volume of future rainfall events at the starting time, from each of the risky rainfall events, each target rainfall event whose water accumulation volume at the starting time is less than or equal to the predicted water accumulation volume is determined;

[0053] Determine, in the test area, a waterlogging risk probability of the rainfall level according to each of the target rainfall events corresponding to the rainfall level and each of the historical rainfall events corresponding to the rainfall level;

[0054] Determine the target risk probability of each predicted rainfall level of future rainfall events in the tested area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the tested area in the future rainfall events according to the target risk probability of each predicted rainfall level;

[0055] The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

[0056] In some embodiments, the area to be tested may be any area of ​​a city. For example, a city map may be gridded, and one of the grids after the gridding is determined as the area to be tested.

[0057] For a certain area to be tested, the rainfall level of each historical rainfall event can be determined according to the rainfall range of each historical rainfall event in the certain area to be tested. Among them, a rainfall event refers to a rainfall, and the rainfall event can include the starting time, the ending time and the rainfall of this rainfall. The rainfall range is positively correlated with the rainfall level. For example, the rainfall ranges are light rain (total rainfall in 24 hours is less than 10mm), moderate rain (total rainfall in 24 hours is 10-25mm), heavy rain (total rainfall in 24 hours is 25-50mm), rainstorm (total rainfall in 24 hours is 50-100mm), heavy rainstorm (total rainfall in 24 hours is 100-250mm) and extremely heavy rainstorm (total rainfall in 24 hours is greater than or equal to 250mm), and the corresponding rainfall levels are 1-6.

[0058] After obtaining the rainfall level of the historical rainfall event, the historical rainfall events corresponding to any rainfall level can be determined. After obtaining the historical rainfall events corresponding to a certain rainfall level k, the water accumulation at the starting time of each historical rainfall event corresponding to the rainfall level k, that is, the time when the rainfall event is triggered, is divided into the corresponding starting water accumulation interval r. i In which, i represents the i-th starting water volume interval r.

[0059] If it is assumed that the historical rainfall event set consisting of each historical rainfall event s corresponding to rainfall level k is S = {s1, s2, s3, s4, s5}, then the water accumulation of each historical rainfall event s1-s5 at the starting time can be obtained. If the rainfall time of historical rainfall event s1 is 8:00-9:00 on xx / xx / xx, then 8:00 on xx / xx / xx is the starting time of the historical rainfall event s1. At this time, the water accumulation of the test area at 8:00 on xx / xx / xx can be obtained as the water accumulation at the starting time of historical rainfall event s1.

[0060] After obtaining the water accumulation volume of each historical rainfall event at the starting time, the water accumulation volume of each historical rainfall event at the starting time can be divided into corresponding starting water accumulation volume intervals according to the water accumulation volume of each historical rainfall event at the starting time. Among them, each starting water accumulation volume interval can be set according to actual conditions, such as each starting water accumulation volume interval r i From low to high, they can be <10cm, 10-20cm, 20-30cm, and >30cm.

[0061] After obtaining the starting water volume interval of each historical rainfall event at the starting time, the number of historical rainfall events corresponding to each starting water volume interval can be determined, so as to determine the starting water volume interval r of the test area at the starting time according to the number of historical rainfall events corresponding to each starting water volume interval. i The corresponding probability of waterlogging. For example, the initial waterlogging interval r i From low to high, they are r1: <10cm, r2: 10-20cm, r3: 20-30cm, r4: >30cm. The total number of historical rainfall events corresponding to rainfall level k is C, and the starting water volume interval r i The corresponding historical rainfall events are C1, C2, C3, C4, C1+C2+C3+C4=C, then the starting water volume interval r of the measured area at the starting time is i The corresponding probabilities of waterlogging are: C1 / C, C1+C2 / C, C1+C2+C3 / C, C1+C2+C3+C4 / C.

[0062] For future rainfall events, the predicted water accumulation at the starting time of the future rainfall event can be predicted through weather forecasts.

[0063] To further improve the accuracy of the prediction results, in some embodiments, the predicted water accumulation volume can be determined based on the water accumulation volume in the measured area at the current moment, the drainage rate of the measured area, and the starting time of the future rainfall event.

[0064] For example, water volume detection can be used to detect the amount of water accumulation R in the test area at the current time t1. t1and the drainage rate v of the area to be tested. At the same time, according to the weather forecast, the starting time t2 of the next rainfall event in the area to be tested can be predicted, and the water accumulation R at the current time t1 and the current time t1 can be calculated. t1 , the drainage rate v of the area to be tested and the starting time t2, the predicted water volume of the area to be tested at the starting time of the future rainfall event is obtained as:

[0065] R'=R t1 -v×(t2-t1).

[0066] After obtaining the predicted water volume at the starting moment of the future rainfall event, all risk rainfall events whose water volume at the starting moment is less than or within the starting water volume interval can be determined from the risk rainfall events as target rainfall events according to the starting water volume interval in which the predicted water volume is located. The probability of waterlogging risk corresponding to the rainfall level in the test area can be determined according to the number of target rainfall events and the number of historical rainfall events corresponding to the rainfall level.

[0067] For example, if the predicted water accumulation volume is in the starting water accumulation volume interval r3, the total number of historical rainfall events corresponding to rainfall level k is C, and the starting water accumulation volume interval r i The corresponding number of historical rainfall events are r1:C1, r2:C2, r3:C3, r4:C4, and since r1 and r2 are less than r3, the number of target rainfall events can be determined as C1+C2+C3, and the probability of waterlogging corresponding to the initial waterlogging interval r3 is C1+C2+C3 / C, which can be determined as the probability of waterlogging risk corresponding to rainfall level k in the test area. In this way, the probability of waterlogging risk corresponding to each rainfall level can be obtained.

[0068] In some embodiments, future rainfall events in the area to be tested, that is, all possible predicted rainfall amounts of the most recent rainfall event in the future, are determined through weather forecasts, so that the predicted rainfall levels of future rainfall events can be determined based on the rainfall range in which each predicted rainfall amount lies and from the correspondence between the rainfall range and the rainfall level.

[0069] Exemplarily, assuming that the rainfall intervals are light rain (total rainfall in 24 hours is less than 10 mm), moderate rain (total rainfall in 24 hours is 10-25 mm), heavy rain (total rainfall in 24 hours is 25-50 mm), rainstorm (total rainfall in 24 hours is 50-100 mm), heavy rainstorm (total rainfall in 24 hours is 100-250 mm) and extremely heavy rainstorm (total rainfall in 24 hours is greater than or equal to 250 mm), and the corresponding rainfall levels are 1-6. Through weather forecast, it is determined that the rainfall intervals corresponding to each predicted rainfall of future rainfall events are moderate rain and heavy rain, respectively, that is, future rainfall events may be moderate rain or heavy rain, then it can be determined that the predicted rainfall levels of future rainfall events are 2 and 3, respectively.

[0070] After obtaining the predicted rainfall levels of future rainfall events, the target risk probabilities of each predicted rainfall level can be determined according to the corresponding relationship between rainfall level and waterlogging risk probability. For example, assuming that the corresponding relationship between rainfall level and waterlogging risk probability is: rainfall level 1, the corresponding waterlogging risk probability is P1; rainfall level 2, the corresponding waterlogging risk probability is P2; rainfall level 3, the corresponding waterlogging risk probability is P3; rainfall level 4, the corresponding waterlogging risk probability is P4; rainfall level 5, the corresponding waterlogging risk probability is P5; rainfall level 6, the corresponding waterlogging risk probability is P6. The predicted rainfall levels of future rainfall events are 2 and 3, and the target risk probabilities of each predicted rainfall level are determined to be P2 and P3.

[0071] After obtaining the target risk probability of each predicted rainfall level, if the target risk probability of one of the predicted rainfall levels is greater than the preset probability, such as greater than 50%, it means that there is a high probability of waterlogging in the tested area in future rainfall events. At this time, it can be determined that the waterlogging risk detection result is that there is a waterlogging risk, and the tested area is a risk area in future rainfall events; otherwise, it can be determined that the waterlogging risk detection result is that there is no waterlogging risk, and the tested area is a non-risk area in future rainfall events.

[0072] By determining the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested, and determining the risk rainfall events that may cause waterlogging in the area to be tested from the historical rainfall events corresponding to the rainfall level, and determining the target rainfall events whose waterlogging at the starting time is less than or in the starting waterlogging range according to the predicted waterlogging at the starting time of the future rainfall event from the risk rainfall events, the waterlogging risk probability of the rainfall level in the area to be tested is determined according to the target rainfall events corresponding to the rainfall level and the historical rainfall events corresponding to the rainfall level, and the target risk probability of each predicted rainfall level of future rainfall events in the area to be tested is determined according to the waterlogging risk probability of each rainfall level, and the waterlogging risk detection result of the area to be tested in the future rainfall event is determined according to the target risk probability of each predicted rainfall level. Therefore, before the occurrence of future rainfall events, the target rainfall events that will cause urban waterlogging can be determined by the predicted water accumulation at the starting time of future rainfall events. The target rainfall events of various levels in the tested area and historical rainfall events can be combined to predict whether the tested area will face the risk of urban waterlogging in future rainfall events. This can provide timely warnings to areas at risk of urban waterlogging, improve the accuracy of prediction results, and thereby improve the safety of urban drainage.

[0073] To further improve the accuracy of the detection results, in some embodiments, Figure 2 As shown, according to each of the target rainfall events corresponding to the rainfall level and each of the historical rainfall events corresponding to the rainfall level, determining the waterlogging risk probability of the rainfall level in the test area includes:

[0074] Step 201, generating an event sequence by chronologically arranging each of the target rainfall events in the historical rainfall events corresponding to the rainfall level and each of the non-target rainfall events in the historical rainfall events;

[0075] Step 202, inputting the event sequence into the trained long short-term memory network to obtain the predicted probability that the future event is the target rainfall event;

[0076] Step 203, determining the waterlogging risk probability of the rainfall level in the test area according to the predicted probability;

[0077] The long short-term memory network is trained based on historical event samples of any level.

[0078] In some embodiments, for the training of the long short-term memory network, historical rainfall events of any level can be obtained as historical event samples, and each historical event sample is labeled, such as risk samples that cause waterlogging in the test area, and non-risk samples that do not cause waterlogging in the test area.

[0079] Then, the marked historical time samples are sorted from early to late according to the time of the event, and a historical event sample sequence is obtained. After obtaining the historical event sample sequence, each historical event sample in the historical event sample sequence is input into the long short-term memory network to be trained for multiple trainings. In each training, the first n historical event samples in the historical event sample sequence are input into the long short-term memory network to obtain the predicted probability that the n+1th historical event sample output by the long short-term memory network is a risk sample, and then the predicted probability is matched with the actual probability that the n+1th historical event sample is a risk sample, the loss of the long short-term memory network is calculated and back-propagated, and after adjusting the network parameters of the long short-term memory network, the first n+1 historical event samples in the historical event sample sequence are input into the long short-term memory network for the next training, and so on. Until the predicted probability obtained after each input of the first n historical event samples in the historical event sample sequence into the long short-term memory network matches the actual probability that the n+1th historical event sample is a risk sample, the training of the long short-term memory network is completed.

[0080] After obtaining the trained long short-term memory network, the target rainfall events in the historical rainfall events corresponding to the rainfall level and the non-target rainfall events in the historical rainfall events can be sorted in chronological order from early to late to generate an event sequence. Among them, the non-target rainfall events are events other than the target rainfall events in the historical rainfall events. Then, the event sequence is input into the trained long short-term memory network to obtain the predicted probability that the future event is the target rainfall event, and the predicted probability is used as the probability of waterlogging risk for the rainfall level in the test area. Therefore, the probability of waterlogging risk for the rainfall level can be accurately predicted through the changing trend of the historical rainfall events corresponding to the rainfall level, thereby improving the accuracy of the subsequent use of the waterlogging risk probability of the rainfall level to determine the accuracy of the waterlogging risk detection results of the test area in future rainfall events.

[0081] Considering that the occurrence probabilities of each predicted rainfall level in future rainfall events are not the same, in order to further improve the accuracy of the detection result, in some embodiments, according to the waterlogging risk probability of each rainfall level, the target risk probability of each predicted rainfall level in the tested area in future rainfall events is determined, including:

[0082] Determining the initial risk probability of each predicted rainfall level in the tested area in future rainfall events according to the waterlogging risk probability of each rainfall level;

[0083] Obtaining a target risk probability of the predicted rainfall level according to the predicted probability of the predicted rainfall level and the initial risk probability of the predicted rainfall level;

[0084] The predicted probability is the probability that the predicted rainfall of the future rainfall event reaches the predicted rainfall level.

[0085] In some embodiments, the probability Pi of the predicted rainfall of future rainfall events in the test area being in different rainfall intervals can be determined based on the weather forecast. After obtaining the probability Pi of the predicted rainfall of future rainfall events being in different rainfall intervals, the predicted probability Pi of the future rainfall events in the test area being in different predicted rainfall levels can be determined based on the corresponding relationship between the rainfall intervals and the predicted rainfall levels. For example, the probability Pi of a certain rainfall interval is determined as the predicted probability Pi of the predicted rainfall level corresponding to the rainfall interval.

[0086] For example, assuming that according to the weather forecast, the predicted rainfall of future rainfall events in the test area is determined to be light rain (total rainfall in 24 hours is less than 10 mm) with a probability of 10%, moderate rain (total rainfall in 24 hours is 10-25 mm) with a probability of 40%, and heavy rain (total rainfall in 24 hours is 25-50 mm) with a probability of 40%, then it can be determined that the predicted rainfall level of future rainfall events is 1 with a predicted probability of 10%, 2 with a predicted probability of 40%, and 3 with a predicted probability of 40%.

[0087] At the same time, after obtaining the waterlogging risk probability of each rainfall level, the waterlogging risk probability corresponding to each predicted rainfall level of future rainfall events can be obtained according to the corresponding relationship between each rainfall level and each waterlogging risk probability, as the initial risk probability Pi' of each predicted rainfall level. For example, if each rainfall level is 1-6, the corresponding waterlogging risk probability is P1'-P6', and each predicted rainfall level of future rainfall events is 1-3, then the waterlogging risk probability P1' can be determined as the initial risk probability of predicted rainfall level 1, the waterlogging risk probability P2' can be determined as the initial risk probability of predicted rainfall level 2, and the waterlogging risk probability P3' can be determined as the initial risk probability of predicted rainfall level 3.

[0088] After obtaining the initial risk probability Pi' and the predicted probability Pi of each predicted rainfall level, for any predicted rainfall level k, the target risk probability P(k) can be obtained as P(k)=Pi'×Pi according to its initial risk probability Pi' and the predicted probability Pi.

[0089] By determining the initial risk probability of each predicted rainfall level in the tested area in future rainfall events based on the waterlogging risk probability of each rainfall level, and obtaining the target risk probability of the predicted rainfall level based on the predicted probability of the predicted rainfall level and the initial risk probability of the predicted rainfall level, the obtained target risk probability of the predicted rainfall level is combined with the occurrence probability of the predicted rainfall level, making the obtained target risk probability of the predicted rainfall level more accurate, thereby further improving the accuracy of the subsequent waterlogging risk detection results obtained using the target risk probability of the predicted rainfall level.

[0090] After obtaining the target risk probability of each predicted rainfall level, it can be detected whether there is a target risk probability greater than a preset probability, such as greater than 50%. If so, it can be determined that the waterlogging risk detection result is that the tested area has a waterlogging risk in future rainfall events, and the tested area is a risk area in future rainfall events. Otherwise, it can be determined that the waterlogging risk detection result is that the tested area does not have a waterlogging risk in future rainfall events.

[0091] To further improve the accuracy of the waterlogging risk detection result, in some embodiments, the waterlogging risk detection result of the tested area in the future rainfall event is determined according to the target risk probability of each predicted rainfall level, including:

[0092] Superimposing the target risk probabilities of the predicted rainfall levels, to obtain the probability of waterlogging in the tested area in the future rainfall event;

[0093] According to the waterlogging probability, a waterlogging risk detection result of the tested area in the future rainfall event is determined.

[0094] In some embodiments, after obtaining the target risk probability P(k) of each predicted rainfall level, the target risk probability of each predicted rainfall level can be superimposed, that is, the target risk probability P(k) of each predicted rainfall level is added together to obtain the probability of waterlogging in the tested area in the future rainfall event. For example, assuming that each predicted rainfall level is 1-3, the probability of waterlogging in the tested area in the future rainfall event is

[0095] After obtaining the probability of waterlogging in the test area in future rainfall events, it can be detected whether the probability of waterlogging is greater than a preset probability, such as 50%; if so, it can be determined that the test area is prone to waterlogging in future rainfall events. At this time, the waterlogging risk detection result can be determined that the test area has a risk of waterlogging in future rainfall events, the test area is a risk area, and an alarm message is generated.

[0096] By superimposing the target risk probability of each predicted rainfall level, the probability of waterlogging in the tested area in future rainfall events is obtained. Based on the waterlogging probability, the waterlogging risk detection result of the tested area in future rainfall events is determined. Therefore, the waterlogging risk detection of the tested area takes into account the risk of the tested area under different predicted rainfall levels, thereby further improving the accuracy of waterlogging risk detection in the tested area.

[0097] To further improve the safety of drainage, in some embodiments, the method further includes:

[0098] Determine that the waterlogging risk detection result indicates that the tested area has a waterlogging risk in the future rainfall event, and generate prompt information for modifying the drainage network in the tested area.

[0099] In some embodiments, the waterlogging risk detection result of the tested area in future rainfall events is determined, and if the tested area is at risk of waterlogging in the future rainfall events, then the pipe model of the drainage network located in the tested area can be obtained based on the location information of the tested area, and prompt information for modifying the drainage network in the tested area is generated, and the pipe model of the drainage network is marked to prompt fine-tuning of the drainage network.

[0100] The waterlogging risk detection device provided in the present application is described below. The waterlogging risk detection device described below and the waterlogging risk detection method described above can be referenced to each other.

[0101] In one embodiment, if Figure 3 As shown, a waterlogging risk detection device is provided, comprising:

[0102] A rainfall event acquisition module 210 is used to determine each historical rainfall event corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested;

[0103] A first event determination module 220 is used to determine each risk rainfall event that causes waterlogging in the test area from each of the historical rainfall events corresponding to the rainfall level;

[0104] The second event determination module 230 is used to determine, from the risky rainfall events, each target rainfall event whose water accumulation amount at the starting time is less than or equal to the predicted water accumulation amount according to the predicted water accumulation amount of the future rainfall event at the starting time;

[0105] A risk probability determination module 240, configured to determine the waterlogging risk probability of the rainfall level in the test area according to each of the target rainfall events corresponding to the rainfall level and each of the historical rainfall events corresponding to the rainfall level;

[0106] The waterlogging risk detection module 250 is used to determine the target risk probability of each predicted rainfall level of the future rainfall event in the test area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the test area in the future rainfall event according to the target risk probability of each predicted rainfall level;

[0107] The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

[0108] By determining the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested, and determining the risk rainfall events that may cause waterlogging in the area to be tested from the historical rainfall events corresponding to the rainfall level, and determining the target rainfall events whose waterlogging at the starting time is less than or in the starting waterlogging range according to the predicted waterlogging at the starting time of the future rainfall event from the risk rainfall events, the waterlogging risk probability of the rainfall level in the area to be tested is determined according to the target rainfall events corresponding to the rainfall level and the historical rainfall events corresponding to the rainfall level, and the target risk probability of each predicted rainfall level of future rainfall events in the area to be tested is determined according to the waterlogging risk probability of each rainfall level, and the waterlogging risk detection result of the area to be tested in the future rainfall event is determined according to the target risk probability of each predicted rainfall level. Therefore, before the occurrence of future rainfall events, the target rainfall events that will cause urban waterlogging can be determined by the predicted water accumulation at the starting time of future rainfall events. The target rainfall events of various levels in the tested area and historical rainfall events can be combined to predict whether the tested area will face the risk of urban waterlogging in future rainfall events. This can provide timely warnings to areas at risk of urban waterlogging, improve the accuracy of prediction results, and thereby improve the safety of urban drainage.

[0109] In one embodiment, the risk probability determination module 240 is specifically used to:

[0110] Generate an event sequence by chronologically sequencing each of the target rainfall events in each of the historical rainfall events corresponding to the rainfall level and each of the non-target rainfall events in each of the historical rainfall events;

[0111] Inputting the event sequence into a trained long short-term memory network to obtain a predicted probability that a future event is the target rainfall event;

[0112] Determining the waterlogging risk probability of the rainfall level in the test area according to the predicted probability;

[0113] The long short-term memory network is trained based on historical event samples of any level.

[0114] In one embodiment, the second event determination module 230 is further configured to:

[0115] The predicted amount of water accumulation is determined according to the amount of water accumulation in the area to be measured at the current moment, the drainage rate of the area to be measured and the starting moment of the future rainfall event.

[0116] In one embodiment, the waterlogging risk detection module 250 is specifically used to:

[0117] Determining the initial risk probability of each predicted rainfall level in the tested area in future rainfall events according to the waterlogging risk probability of each rainfall level;

[0118] Obtaining a target risk probability of the predicted rainfall level according to the predicted probability of the predicted rainfall level and the initial risk probability of the predicted rainfall level;

[0119] The predicted probability is the probability that the predicted rainfall of the future rainfall event reaches the predicted rainfall level.

[0120] In one embodiment, the waterlogging risk detection module 250 is specifically used to:

[0121] Superimposing the target risk probabilities of the predicted rainfall levels, to obtain the probability of waterlogging in the tested area in the future rainfall event;

[0122] According to the waterlogging probability, a waterlogging risk detection result of the tested area in the future rainfall event is determined.

[0123] In one embodiment, the waterlogging risk detection module 250 is further configured to:

[0124] Determine that the waterlogging risk detection result indicates that the tested area has a waterlogging risk in the future rainfall event, and generate prompt information for modifying the drainage network in the tested area.

[0125] In one embodiment, the rainfall amount is positively correlated with the rainfall level.

[0126] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call a computer program in the memory 830 to execute a waterlogging risk detection method, for example, including:

[0127] Determine the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested;

[0128] Determining, from the historical rainfall events corresponding to the rainfall levels, the risk rainfall events that may cause waterlogging in the tested area;

[0129] According to the starting water volume interval of the predicted water volume of the future rainfall event at the starting time, determine from each of the risky rainfall events each target rainfall event whose water volume at the starting time is less than or within the starting water volume interval;

[0130] Determine, according to each of the target rainfall events corresponding to the rainfall level and each of the historical rainfall events corresponding to the rainfall level, a waterlogging risk probability of the rainfall level in the test area;

[0131] Determine the target risk probability of each predicted rainfall level of future rainfall events in the tested area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the tested area in the future rainfall events according to the target risk probability of each predicted rainfall level;

[0132] The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

[0133] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0134] On the other hand, an embodiment of the present application further provides a storage medium, the storage medium includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the waterlogging risk detection method provided by the above embodiments, for example, including:

[0135] Determine the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested;

[0136] Determining, from the historical rainfall events corresponding to the rainfall levels, the risk rainfall events that may cause waterlogging in the tested area;

[0137] According to the starting water volume interval of the predicted water volume of the future rainfall event at the starting time, determine from each of the risky rainfall events each target rainfall event whose water volume at the starting time is less than or within the starting water volume interval;

[0138] Determine, in the test area, a waterlogging risk probability of the rainfall level according to each of the target rainfall events corresponding to the rainfall level and each of the historical rainfall events corresponding to the rainfall level;

[0139] Determine the target risk probability of each predicted rainfall level of future rainfall events in the tested area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the tested area in the future rainfall events according to the target risk probability of each predicted rainfall level;

[0140] The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

[0141] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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. However, 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 embodiments of the present application.

Claims

1. A method for detecting waterlogging risk, characterized in that: include: Determine the historical rainfall events corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested; Determining, from the historical rainfall events corresponding to the rainfall levels, the risk rainfall events that may cause waterlogging in the tested area; According to the starting water volume interval of the predicted water volume of the future rainfall event at the starting time, determine from each of the risky rainfall events each target rainfall event whose water volume at the starting time is less than or within the starting water volume interval; Determine, in the test area, a waterlogging risk probability of the rainfall level according to each of the target rainfall events corresponding to the rainfall level and each of the historical rainfall events corresponding to the rainfall level; Determine the target risk probability of each predicted rainfall level of future rainfall events in the tested area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the tested area in the future rainfall events according to the target risk probability of each predicted rainfall level; The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

2. The method for detecting waterlogging risk according to claim 1, characterized in that: Determining the waterlogging risk probability of the rainfall level in the test area according to the target rainfall events corresponding to the rainfall level and the historical rainfall events corresponding to the rainfall level includes: Generate an event sequence by chronologically sequencing each of the target rainfall events in each of the historical rainfall events corresponding to the rainfall level and each of the non-target rainfall events in each of the historical rainfall events; Inputting the event sequence into a trained long short-term memory network to obtain a predicted probability that a future event is the target rainfall event; Determining the waterlogging risk probability of the rainfall level in the test area according to the predicted probability; The long short-term memory network is trained based on historical event samples of any level.

3. The method for detecting waterlogging risk according to claim 1, characterized in that: Also includes: The predicted amount of water accumulation is determined according to the amount of water accumulation in the area to be measured at the current moment, the drainage rate of the area to be measured and the starting moment of the future rainfall event.

4. The method for detecting waterlogging risk according to any one of claims 1 to 3, characterized in that: Determining the target risk probability of each predicted rainfall level of the tested area in future rainfall events according to the waterlogging risk probability of each rainfall level, including: Determining the initial risk probability of each predicted rainfall level in the tested area in future rainfall events according to the waterlogging risk probability of each rainfall level; Obtaining a target risk probability of the predicted rainfall level according to the predicted probability of the predicted rainfall level and the initial risk probability of the predicted rainfall level; The predicted probability is the probability that the predicted rainfall of the future rainfall event reaches the predicted rainfall level.

5. The method for detecting waterlogging risk according to claim 1, characterized in that: According to the target risk probability of each predicted rainfall level, the waterlogging risk detection result of the tested area in the future rainfall event is determined, including: Superimposing the target risk probabilities of the predicted rainfall levels, to obtain the probability of waterlogging in the tested area in the future rainfall event; According to the waterlogging probability, a waterlogging risk detection result of the tested area in the future rainfall event is determined.

6. The method for detecting waterlogging risk according to claim 1 or 5, characterized in that: Also includes: Determine that the waterlogging risk detection result indicates that the tested area has a waterlogging risk in the future rainfall event, and generate prompt information for modifying the drainage network in the tested area.

7. The method for detecting waterlogging risk according to claim 1, characterized in that: The rainfall amount is positively correlated with the rainfall level.

8. A waterlogging risk detection device, characterized in that: include: A rainfall event acquisition module, used to determine each historical rainfall event corresponding to any rainfall level according to the rainfall of each historical rainfall event in the area to be tested; A first event determination module is used to determine each risk rainfall event that causes waterlogging in the test area from each of the historical rainfall events corresponding to the rainfall level; The second event determination module is used to determine, from the risky rainfall events, each target rainfall event whose water accumulation amount at the starting time is less than or equal to the predicted water accumulation amount according to the predicted water accumulation amount of the future rainfall event at the starting time; A risk probability determination module, used to determine the waterlogging risk probability of the rainfall level in the test area according to each target rainfall event corresponding to the rainfall level and each historical rainfall event corresponding to the rainfall level; A waterlogging risk detection module, for determining the target risk probability of each predicted rainfall level of future rainfall events in the tested area according to the waterlogging risk probability of each rainfall level, so as to determine the waterlogging risk detection result of the tested area in the future rainfall events according to the target risk probability of each predicted rainfall level; The future rainfall event is the first rainfall event in the test area in the future, and the predicted rainfall level is the predicted rainfall level of the future rainfall event.

9. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the waterlogging risk detection method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the waterlogging risk detection method according to any one of claims 1 to 7 is implemented.

Images