+

CN119274076A - A hydrological forecasting method and system - Google Patents

A hydrological forecasting method and system Download PDF

Info

Publication number
CN119274076A
CN119274076A CN202411423898.3A CN202411423898A CN119274076A CN 119274076 A CN119274076 A CN 119274076A CN 202411423898 A CN202411423898 A CN 202411423898A CN 119274076 A CN119274076 A CN 119274076A
Authority
CN
China
Prior art keywords
data
image
terrain model
hydrological
area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202411423898.3A
Other languages
Chinese (zh)
Other versions
CN119274076B (en
Inventor
杨会刚
谢文洁
胡威
郑昊
宋雯雯
邢文月
夏达忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Meteorological Service Center Sichuan Professional Meteorological Observatory Sichuan Meteorological Film And Television Center
Datang Sichuan Power Generation Co ltd
Hohai University HHU
Original Assignee
Sichuan Meteorological Service Center Sichuan Professional Meteorological Observatory Sichuan Meteorological Film And Television Center
Datang Sichuan Power Generation Co ltd
Hohai University HHU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sichuan Meteorological Service Center Sichuan Professional Meteorological Observatory Sichuan Meteorological Film And Television Center, Datang Sichuan Power Generation Co ltd, Hohai University HHU filed Critical Sichuan Meteorological Service Center Sichuan Professional Meteorological Observatory Sichuan Meteorological Film And Television Center
Priority to CN202411423898.3A priority Critical patent/CN119274076B/en
Publication of CN119274076A publication Critical patent/CN119274076A/en
Application granted granted Critical
Publication of CN119274076B publication Critical patent/CN119274076B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

The application discloses a hydrologic forecasting method and system, which relate to hydrologic forecasting and artificial intelligence technology and comprise the steps of acquiring remote sensing data of a target river basin in advance, establishing a rough terrain model of the target river basin based on the acquired remote sensing data, acquiring image data of set positions of a plurality of target river basins according to set time intervals, constructing a global image containing the set positions of the target river basins according to an overlapping area, reconstructing at least part of positions of a dam contained in the global image, extracting features under a uniform visual angle, inputting the extracted features into an LSTM (local area network), encoding the output of the LSTM by a Decoder, extracting hydrologic data in a forecasting image, mapping the extracted hydrologic data to the rough terrain model, and executing hydrologic forecasting according to the extracted hydrologic data and the mapped rough terrain model. The application can reduce runoff hysteresis of the dimension existing at the upstream and the downstream and improve the instantaneity and the accuracy of hydrologic forecasting.

Description

Hydrologic forecasting method and system
Technical Field
The application relates to the technical field of hydrologic forecasting and artificial intelligence, in particular to a hydrologic forecasting method and system.
Background
The hydrological data and meteorological data of the large-scale river basin are limited by conditions such as topography, regional economy and the like, measured data are scarce, and only data are difficult to support and construct hydrological simulation of the river basin, and particularly effective forecasting of flood under future conditions is difficult. The effective runoff simulation and flood forecasting technology provides important technological support for water resource utilization, ecological system protection, agricultural development and urban planning of the area.
Hydrologic models are classical methods of runoff simulation and flood forecast, and currently the main methods are a physical mechanism model and a data driving model based on a process. The physical mechanism models such as VIC (Varia ble InfiltrationCapacity) and SWAT (Soil AND WATERASSESSMENT Tool) based on the process have strong practicability based on physical theory and a large amount of actual measurement data in water circulation, but the creation of the models widely adopts inductive reasoning, provides reliable explanation for the hydrologic process, but the existing theory is incomplete and the models are not comprehensive compared with the actually-occurring complex process, and meanwhile, a large amount of complex parameters need to be repeatedly calibrated, so that more time is needed to construct the regional model.
Disclosure of Invention
The embodiment of the application provides a hydrologic forecasting method and a hydrologic forecasting system, which are combined with a coarse geographic model and a local fine model, and realize hydrologic forecasting based on the local fine model through a long-short-term memory network LSTM, so that runoff hysteresis of the dimension existing at the upstream and the downstream is reduced, and the real-time performance and the accuracy of forecasting are improved.
The embodiment of the application provides a hydrologic forecasting method, which comprises the following steps:
acquiring remote sensing data of a target river basin in advance, and establishing a rough terrain model of the target river basin based on the acquired remote sensing data;
collecting image data of a plurality of target watershed set positions according to a set time interval, wherein the plurality of image data at least have partial overlapping areas and comprise water area data;
identifying an overlapping region in the plurality of pieces of image data, and constructing a global image containing the target river basin setting position according to the overlapping region;
reconstructing at least part of the locations of the included dams based on the global image to obtain a local fine model;
extracting features of the local fine model at continuous moments by utilizing Encoder under a unified view angle, inputting the extracted features into a long-short-time memory network LSTM, and encoding the output of the LSTM by utilizing a Decoder to obtain a predicted image under the unified view angle;
extracting hydrologic data in the predicted image, and mapping the extracted hydrologic data to the coarse terrain model;
And performing hydrologic forecasting according to the extracted hydrologic data in the mapped rough terrain model.
Optionally, identifying the overlapping region in the plurality of pieces of image data includes:
dividing a plurality of pieces of image data, and calculating the similarity between the image divisions between two pieces of image data;
dividing an image with similarity larger than a preset similarity threshold value, and taking a local area between boundaries of two pieces of image data as a possible overlapping area;
and carrying out edge detection on the possible overlapping areas of the two pieces of image data so as to determine the overlapping areas according to the edge detection result.
Optionally, performing edge detection on a possible overlapping region of the two pieces of image data, so as to determine the overlapping region according to an edge detection result includes:
According to the edge detection result, overlapping two pieces of image data based on the image segmentation with the maximum calculated similarity;
Changing the transparency of the possible overlapping area of one piece of the image data, and calculating the definition of the possible overlapping area of the two pieces of the superimposed image data;
if the calculated definition of the possible overlapping area is smaller than a preset definition threshold, selecting image segmentation according to the periphery of the image segmentation with the maximum similarity;
determining pixel deviation between the same boundaries according to edge detection results of selected image segmentation;
And adjusting the two superimposed image data according to the direction and the distance of the pixel deviation until the calculated definition of the possible overlapping area meets the requirement.
Optionally, constructing a global image including the target river basin setting position according to the overlapping region includes:
a plurality of reference points are set according to the determined overlapping area to construct a global image containing the target basin set position based on the reference points.
Optionally, extracting the hydrologic data in the predicted image and mapping the extracted hydrologic data to the coarse terrain model includes:
identifying a water area boundary of a set position in the predicted image;
Extracting a representative boundary of a set pixel width based on the water boundary, and identifying the water boundary at the representative boundary;
Under the unified view angle, searching in the coarse terrain model by utilizing the representative boundary to select the position with the highest matching degree as a mapping boundary;
And mapping the water area boundary to the mapping boundary according to the position of the water area boundary in the representative boundary so as to map water level data to the corresponding set position in the coarse terrain model.
Optionally, extracting the hydrologic data in the predicted image and mapping the extracted hydrologic data to the coarse terrain model further includes:
And filling water level data according to the hydraulic gradient relation of the target river basin based on the water level data of the set position map in the rough terrain model so as to refresh partial runoff data of the target river basin based on the mapped water level data in the rough terrain model.
Optionally, performing the hydrologic forecast with the mapped coarse terrain model according to the extracted hydrologic data includes:
acquiring rainfall data of the target river basin;
Determining a rainfall influence area based on the rough terrain model, and estimating runoff data of the rest part according to the rainfall influence area and the rainfall data;
According to the basic runoff information, filling the estimated runoff data to corresponding runoffs of the coarse terrain model along the water flow direction;
And splicing the estimated filled runoff data with partial runoff data refreshed based on the mapped water level data in the coarse terrain model to obtain combined runoff.
Optionally, executing the hydrologic forecast according to the extracted hydrologic data with the mapped rough terrain model further comprises:
performing hydrologic forecasting based on the water level data, rainfall data, and combined runoff, and
Identifying a water level change area in the coarse terrain model in any refreshing process;
and highlighting the water level change area on the terrain model.
The embodiment of the application provides a hydrological forecasting system, which comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program realizes the steps of the hydrological forecasting method when being executed by the processor.
The hydrologic forecasting method combines the coarse geographic model and the local fine model, and realizes hydrologic forecasting based on the local fine model through the long-short memory network LSTM, thereby reducing runoff hysteresis of the dimension existing at the upstream and the downstream and improving the real-time performance and the accuracy of forecasting.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 is a basic flow chart of the hydrologic forecasting method of the present embodiment.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the application provides a hydrologic forecasting method, which is shown in fig. 1 and comprises the following steps:
In step S101, remote sensing data of a target river basin is acquired in advance, and a rough terrain model of the target river basin is established based on the acquired remote sensing data. In some examples, the accuracy of the coarse terrain model may be determined according to actual needs, for example, a simplified model may be constructed for areas where the target river basin is not reachable during flood periods, in particular examples the terrain model may initially give a basic basin water level, and the coarse terrain model containing the basic water level may be applied to a subsequent water level refresh process.
In step S102, image data of a set position of a plurality of target watershed is acquired at set time intervals, wherein the plurality of image data has at least a partial overlapping area and includes water area data. For example, the set time interval can be set according to the actual flood conditions of the target river basin, and the user hopes that the user pays more attention to the flood conditions, and the interval can be set to be shorter. At the same time, for example, the plurality of pieces of image data arranged at the acquisition setting position are monitored, for example, the plurality of pieces of image data can be acquired by rotating the monitoring device by a certain angle, and images acquired under adjacent angles have a certain area overlapping.
In step S103, an overlapping area in the plurality of pieces of image data is identified, and a global image including the target basin setting position is constructed according to the overlapping area. The identification of the overlapping area is performed based on the aforementioned images acquired at the same time to, after identifying the overlapping portion, construct a global image with a set position at that time, which in some examples may be, for example, a dam area, or a monitoring site with monitoring set.
In step S104, at least part of the locations of the included dams are reconstructed based on the global image to obtain a local fine model. In some embodiments, for example, the reconstruction may be performed based on the global image through the readiness Capture, so as to obtain a fine model, and specifically, the key points included in the identified overlapping area may be input into readiness Capture software together, so as to improve the reconstruction effect, so as to adapt to the reconstruction of the fine model under various ambient illumination conditions.
In step S105, feature extraction is performed on the local fine model at successive time instants using Encoder at a unified view angle, the extracted features are input into a long-short-time memory network LSTM, and the output of the LSTM is encoded using a Decoder to obtain a predicted image at the unified view angle. The embodiment of the application predicts the hydrological data (such as water level data) at the later moment in the fine model based on the local fine model at the continuous moment by utilizing the memory capacity of the LSTM, thereby realizing the prediction of the local water condition at the set position.
In step S106, the hydrologic data in the predicted image is extracted, and the extracted hydrologic data is mapped to the coarse terrain model. According to the embodiment of the application, the predicted water regime data is further mapped to the coarse terrain model, so that the water regime data of the target river basin is comprehensively covered and analyzed, and the hydrological prediction of the target river basin is realized.
In step S107, a hydrologic forecast is performed with the mapped coarse terrain model based on the extracted hydrologic data.
The hydrologic forecasting method combines the coarse geographic model and the local fine model, and realizes hydrologic forecasting based on the local fine model through the long-short memory network LSTM, thereby reducing runoff hysteresis of the dimension existing at the upstream and the downstream and improving the real-time performance and the accuracy of forecasting.
In some embodiments, identifying overlapping areas in the plurality of pieces of image data includes:
the plurality of pieces of image data are divided, and the similarity between the image divisions between the two pieces of image data is calculated. The specific image data with the overlapping region can be determined according to the change rule of the calculated similarity, and the segmentation similarity of the overlapping region is larger than that of the non-overlapping region.
And dividing the image with the similarity larger than a preset similarity threshold value and taking a local area between boundaries of two pieces of image data as a possible overlapping area. For example, if the preset similarity threshold is set to 80%, the image area of the overlapping area appears to be gradually greater than 80% in similarity from outside to inside.
And carrying out edge detection on the possible overlapping areas of the two pieces of image data so as to determine the overlapping areas according to the edge detection result.
In some embodiments, edge detecting a possible overlapping region of the two pieces of image data to determine the overlapping region according to an edge detection result includes:
And according to the edge detection result, overlapping the two pieces of image data based on the image segmentation with the maximum calculated similarity. In some specific examples, according to the identified possible overlapping areas, the image area with the greatest similarity is selected for superposition.
The transparency of the possible overlapping area of one piece of the image data is changed, and the sharpness of the possible overlapping area of the two pieces of the image data after the superimposition is calculated.
And if the calculated definition of the possible overlapping area is smaller than a preset definition threshold, selecting image segmentation according to the periphery of the image segmentation with the maximum similarity.
And determining pixel deviation between the same boundaries according to the edge detection result of the selected image segmentation, in a specific example, overlapping the image areas with the maximum similarity according to the edge detection result, and performing fine adjustment, and calculating pixel deviation (offset) of the selected image segmentation around the segmentation with the maximum similarity, thereby determining the fine adjustment direction and the fine adjustment pixel quantity.
And adjusting the two superimposed image data according to the direction and the distance of the pixel deviation until the calculated definition of the possible overlapping area meets the requirement.
In some embodiments, constructing a global image containing the target basin set position from the overlapping region comprises:
A plurality of reference points are set according to the determined overlapping area to construct a global image containing the target basin set position based on the reference points. In a specific example, a plurality of reference points may be set according to the edge detection result of the overlapping region to construct a global image of the loving setting position at that time.
In some embodiments, extracting the hydrologic data in the predicted image and mapping the extracted hydrologic data to the coarse terrain model comprises:
And identifying the water area boundary of the set position in the predicted image. In some examples, the boundary of the water area can also be determined by edge detection, and the boundary recognition accuracy is not high because the boundary of the water area is covered with the influence of a river bank area and a dam area.
In the embodiment of the application, a representative boundary with a set pixel width is further extracted based on the water boundary, and the water boundary is marked on the representative boundary. A representative boundary including the water boundary is extracted and identified by setting a certain pixel width based on the water boundary.
And under the unified view angle, searching in the coarse terrain model by utilizing the representative boundary to select the position with the highest matching degree as a mapping boundary. In a specific example, if the water area boundary is directly used for searching, the problem that the accurate position cannot be matched is likely to be caused due to factors such as the influence of the river bank area and the dam area, insufficient fineness of the coarse model and the like. According to the embodiment of the application, the representative boundary of the pixel width is set, so that the matching accuracy of the fine model to the coarse model can be greatly improved.
And mapping the water area boundary to the mapping boundary according to the position of the water area boundary in the representative boundary so as to map the water level data to the corresponding set position in the coarse terrain model, for example, the set position is a dam area, and mapping the water area boundary to the mapping boundary of the coarse terrain model according to the position relation between the identification of the water area boundary and the pixel width.
In some embodiments, extracting the hydrologic data in the predicted image and mapping the extracted hydrologic data to the coarse terrain model further comprises filling water level data according to the hydraulic gradient relation of a target river basin based on the water level data of the set position mapping in the coarse terrain model so as to refresh partial runoff data of the target river basin based on the mapped water level data in the coarse terrain model. According to the scheme, the association and mapping filling are carried out through the refined local model and the rough terrain model of the target river basin, and the hydrologic condition of the whole target river basin can be reflected through the rough model, so that the effect of point determination is achieved.
In some embodiments, performing the hydrologic forecast based on the extracted hydrologic data with the mapped coarse terrain model includes:
acquiring rainfall data of the target river basin;
And determining a rainfall influence area based on the rough terrain model, and estimating runoff data of the rest part according to the rainfall influence area and the rainfall data. In some examples, the flow rate of incoming runoff may be estimated from empirical data or fitting a relationship of rainfall to the rainfall impact area.
And filling the estimated runoff data to the corresponding runoffs of the coarse terrain model along the water flow direction according to the basic runoff information.
And splicing the estimated filled runoff data with partial runoff data refreshed based on the mapped water level data in the coarse terrain model to obtain combined runoff. Based on the previous example, filling is carried out on the rough terrain model according to the estimated runoff data and the basic runoff information, so that partial runoffs which are not covered by filling water level data according to the hydraulic gradient relation of the target river basin in the previous example are filled and flow is connected in parallel, and the combined runoffs of the target river basin are formed.
In some embodiments, performing the hydrologic forecast based on the extracted hydrologic data with the mapped coarse terrain model further comprises:
performing hydrologic forecasting based on the water level data, rainfall data, and combined runoff, and
Identifying a water level change area in the coarse terrain model in any refreshing process;
The water level change area is highlighted in the terrain model, and the water level change area is highlighted in the terrain model, so that a user can pay more attention to the change area, and particularly, a predicted subsequent flood inundation area can be determined after refreshing according to the water level rising condition, thereby reducing runoff hysteresis of the dimension existing at the upstream and downstream, improving the real-time performance and accuracy of forecasting, and improving the auxiliary effect on flood control scheduling.
The embodiment of the application provides a hydrological forecasting system, which comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program realizes the steps of the hydrological forecasting method when being executed by the processor.
Furthermore, although exemplary embodiments have been described herein, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of the various embodiments across schemes), adaptations or alterations based on the present disclosure. And are not limited to the examples described in this specification or during the practice of the application, which examples are to be construed as non-exclusive.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description.
The above embodiments are merely exemplary embodiments of the present disclosure, and those skilled in the art may make various modifications or equivalents to the present invention within the spirit and scope of the present disclosure, and such modifications or equivalents should also be construed as falling within the scope of the present invention.

Claims (9)

1.一种水文预报方法，其特征在于，包括：1. A hydrological forecasting method, comprising: 预先获取目标流域的遥感数据，并基于所获取的遥感数据建立所述目标流域的粗地形模型；Pre-acquire remote sensing data of a target watershed, and establish a rough terrain model of the target watershed based on the acquired remote sensing data; 按照设定的时间间隔采集多张目标流域设定位置的图像数据，其中多张图像数据至少存在部分重叠区域且包含水域数据；Collecting a plurality of image data of a set location of a target watershed at a set time interval, wherein the plurality of image data at least partially overlap and contain water area data; 识别出多张图像数据中的重叠区域，并根据所述重叠区域，构建包含所述目标流域设定位置的全局图像；Identify overlapping areas in the plurality of image data, and construct a global image including the set location of the target watershed based on the overlapping areas; 基于所述全局图像对所包含的大坝的至少部分位置进行重构，以获得局部精细模型；Reconstructing at least a portion of the location of the included dam based on the global image to obtain a local fine model; 对连续时刻的局部精细模型、在统一视角下利用Encoder进行特征提取，并将提取的特征输入长短时记忆网络LSTM中，以及利用Decoder对LSTM的输出进行编码，以获得所述统一视角下的预测图像；Extract features from the local fine model at continuous moments using an Encoder under a unified perspective, input the extracted features into a long short-term memory network LSTM, and encode the output of the LSTM using a Decoder to obtain a predicted image under the unified perspective; 提取所述预测图像中的水文数据，并将所提取的水文数据映射至所述粗地形模型；Extracting hydrological data from the predicted image, and mapping the extracted hydrological data to the rough terrain model; 根据所提取的水文数据以映射的粗地形模型，执行水文预报。Hydrological forecasting is performed based on the extracted hydrological data and the mapped coarse terrain model. 2.如权利要求1所述的水文预报方法，其特征在于，识别出多张图像数据中的重叠区域包括：2. The hydrological forecasting method according to claim 1, wherein identifying overlapping areas in the plurality of image data comprises: 对多张图像数据进行分割，并计算两张图像数据之间的图像分割之间的相似度；Segmenting multiple image data and calculating the similarity between image segmentations of two image data; 按照相似度的大于预设相似度阈值的图像分割以及两张所述图像数据的边界之间的局部区域作为可能重叠区域；Segment the images with similarity greater than a preset similarity threshold and use the local area between the boundaries of the two image data as a possible overlapping area; 对两张所述图像数据的可能重叠区域进行边缘检测，以根据边缘检测结果确定重叠区域。Edge detection is performed on possible overlapping areas of the two image data to determine the overlapping area according to the edge detection result. 3.如权利要求2所述的水文预报方法，其特征在于，对两张所述图像数据的可能重叠区域进行边缘检测，以根据边缘检测结果确定重叠区域包括：3. The hydrological forecasting method according to claim 2, wherein edge detection is performed on possible overlapping areas of the two image data to determine the overlapping area according to the edge detection result, comprising: 根据所述边缘检测结果，将两张所述图像数据基于计算的相似度最大的图像分割进行叠加；According to the edge detection result, the two pieces of image data are superimposed based on the image segmentation with the largest calculated similarity; 改变一张所述图像数据的可能重叠区域的透明度，并计算叠加后的两张所述图像数据的可能重叠区域的清晰度；Changing the transparency of a possible overlapping area of one of the image data, and calculating the clarity of the possible overlapping areas of the two superimposed image data; 若计算的可能重叠区域的清晰度小于预设清晰度阈值，则根据在相似度最大图像分割周围选取图像分割；If the calculated clarity of the possible overlapping area is less than the preset clarity threshold, then an image segmentation is selected based on the image segmentation around the image segmentation with the maximum similarity; 根据选取图像分割的边缘检测结果确定同一边界之间的像素偏差；Determine the pixel deviation between the same boundaries according to the edge detection result of the selected image segmentation; 将叠加的两张所述图像数据按照所述像素偏差的方向和距离进行调整，直至计算的可能重叠区域的清晰度满足要求。The two superimposed image data are adjusted according to the direction and distance of the pixel deviation until the clarity of the calculated possible overlapping area meets the requirement. 4.如权利要求3所述的水文预报方法，其特征在于，根据所述重叠区域，构建包含所述目标流域设定位置的全局图像包括：4. The hydrological forecasting method according to claim 3, wherein constructing a global image including the set position of the target watershed according to the overlapping area comprises: 根据所确定重叠区域设置数个参考点，以基于所述参考点构建包含所述目标流域设定位置的全局图像。A plurality of reference points are set according to the determined overlapping area, so as to construct a global image including the set position of the target watershed based on the reference points. 5.如权利要求3所述的水文预报方法，其特征在于，提取所述预测图像中的水文数据，并将所提取的水文数据映射至所述粗地形模型包括：5. The hydrological forecasting method according to claim 3, wherein extracting the hydrological data in the predicted image and mapping the extracted hydrological data to the rough terrain model comprises: 识别所述预测图像中设定位置的水域边界；Identifying a water area boundary at a set location in the predicted image; 基于所述水域边界提取出设定像素宽度的代表边界，以及，在所述代表边界标识所述水域边界；Extracting a representative boundary of a set pixel width based on the water area boundary, and marking the water area boundary on the representative boundary; 在所述统一视角下，利用所述代表边界在所述粗地形模型进行查找，以选取匹配度最高的位置作为映射边界；Under the unified perspective, searching the coarse terrain model using the representative boundary to select the position with the highest matching degree as the mapping boundary; 根据代表边界中所述水域边界的位置，将所述水域边界映射至所述映射边界，以将水位数据映射至所述粗地形模型中对应的设定位置。According to the position of the water area boundary in the representative boundary, the water area boundary is mapped to the mapping boundary, so as to map the water level data to the corresponding set position in the rough terrain model. 6.如权利要求5所述的水文预报方法，其特征在于，提取所述预测图像中的水文数据，并将所提取的水文数据映射至所述粗地形模型还包括：6. The hydrological forecasting method according to claim 5, wherein extracting the hydrological data in the predicted image and mapping the extracted hydrological data to the rough terrain model further comprises: 基于所述粗地形模型中设定位置映射的水位数据，根据目标流域的水力坡度关系进行水位数据填充，以在所述粗地形模型基于映射的水位数据刷新所述目标流域的部分径流数据。Based on the water level data mapped at the set position in the rough terrain model, the water level data is filled according to the hydraulic gradient relationship of the target basin, so as to refresh part of the runoff data of the target basin based on the mapped water level data in the rough terrain model. 7.如权利要求6所述的水文预报方法，其特征在于，根据所提取的水文数据以映射的粗地形模型，执行水文预报包括：7. The hydrological forecasting method according to claim 6, wherein performing hydrological forecasting based on the extracted hydrological data and the mapped rough terrain model comprises: 获取所述目标流域的降雨数据；Acquiring rainfall data of the target watershed; 基于所述粗地形模型，确定降雨影响区域，并根据所述降雨影响区域以及所述降雨数据估算剩余部分的径流数据；Based on the rough terrain model, determine the rainfall impact area, and estimate the runoff data of the remaining part according to the rainfall impact area and the rainfall data; 根据基础径流信息，将估算的径流数据沿水流方向填充至所述粗地形模型的相应径流；According to the basic runoff information, the estimated runoff data is filled into the corresponding runoff of the rough terrain model along the water flow direction; 将估算填充的径流数据与基于映射的水位数据刷新的部分径流数据，在所述粗地形模型进行拼接，获得组合径流。The estimated and filled runoff data and the partial runoff data updated based on the mapped water level data are spliced in the coarse terrain model to obtain the combined runoff. 8.如权利要求6所述的水文预报方法，其特征在于，根据所提取的水文数据以映射的粗地形模型，执行水文预报还包括：8. The hydrological forecasting method according to claim 6, wherein the step of performing hydrological forecasting based on the extracted hydrological data and the mapped rough terrain model further comprises: 基于所述水位数据、降雨数据以及组合径流执行水文预报；以及，Performing hydrological forecasting based on the water level data, rainfall data, and combined runoff; and, 识别任一次刷新过程中所述粗地形模型中的水位变化区域；Identifying areas of water level change in the coarse terrain model during any refresh process; 将所述水位变化区域在所述地形模型进行突出呈现。The water level change area is highlighted in the terrain model. 9.一种水文预报系统，其特征在于，包括处理器和存储器，所述存储器上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1至8中任一项所述的水文预报方法的步骤。9. A hydrological forecasting system, comprising a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the hydrological forecasting method according to any one of claims 1 to 8 are implemented.
CN202411423898.3A 2024-10-12 2024-10-12 Hydrologic forecasting method and system Active CN119274076B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411423898.3A CN119274076B (en) 2024-10-12 2024-10-12 Hydrologic forecasting method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411423898.3A CN119274076B (en) 2024-10-12 2024-10-12 Hydrologic forecasting method and system

Publications (2)

Publication Number Publication Date
CN119274076A true CN119274076A (en) 2025-01-07
CN119274076B CN119274076B (en) 2025-05-16

Family

ID=94118288

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411423898.3A Active CN119274076B (en) 2024-10-12 2024-10-12 Hydrologic forecasting method and system

Country Status (1)

Country Link
CN (1) CN119274076B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1610156A1 (en) * 2004-03-31 2005-12-28 Centre National Du Machinisme Agricole, Du Genie Rural, Des Eaux Et Des Forets (Cemagref) Alerting Device for Meteorological Phenomena such as Rain or High Water of Rivers in a Geographical Region
US20190354873A1 (en) * 2018-02-16 2019-11-21 Lucas Pescarmona Analysis system and hydrology management for basin rivers
CN115829163A (en) * 2023-01-16 2023-03-21 河海大学 Multi-mode integration-based runoff prediction method and system for middle and lower reaches of Yangtze river
CN115860231A (en) * 2022-12-08 2023-03-28 河海大学 MCR _ BilSTM-based intelligent flood forecasting method
CN116609860A (en) * 2023-07-18 2023-08-18 水利部交通运输部国家能源局南京水利科学研究院 Method and system for real-time correction of hydrological model based on integrated learning algorithm
CN117348108A (en) * 2023-08-31 2024-01-05 南京南瑞水利水电科技有限公司 Watershed meteorological forecast method and system based on meteorological big data
CN117909905A (en) * 2024-02-08 2024-04-19 中国长江电力股份有限公司 Method and device for identifying anomalies in multidimensional time series of hydrological stations considering hydrological connections
CN118230155A (en) * 2024-03-13 2024-06-21 西安建材地质工程勘察院有限公司 Natural resource investigation monitoring method and system based on artificial intelligence
KR102710812B1 (en) * 2023-09-12 2024-09-27 주식회사 이시스비젼 Apparatus for predicting risk of inundation

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1610156A1 (en) * 2004-03-31 2005-12-28 Centre National Du Machinisme Agricole, Du Genie Rural, Des Eaux Et Des Forets (Cemagref) Alerting Device for Meteorological Phenomena such as Rain or High Water of Rivers in a Geographical Region
US20190354873A1 (en) * 2018-02-16 2019-11-21 Lucas Pescarmona Analysis system and hydrology management for basin rivers
CN115860231A (en) * 2022-12-08 2023-03-28 河海大学 MCR _ BilSTM-based intelligent flood forecasting method
CN115829163A (en) * 2023-01-16 2023-03-21 河海大学 Multi-mode integration-based runoff prediction method and system for middle and lower reaches of Yangtze river
CN116609860A (en) * 2023-07-18 2023-08-18 水利部交通运输部国家能源局南京水利科学研究院 Method and system for real-time correction of hydrological model based on integrated learning algorithm
CN117348108A (en) * 2023-08-31 2024-01-05 南京南瑞水利水电科技有限公司 Watershed meteorological forecast method and system based on meteorological big data
KR102710812B1 (en) * 2023-09-12 2024-09-27 주식회사 이시스비젼 Apparatus for predicting risk of inundation
CN117909905A (en) * 2024-02-08 2024-04-19 中国长江电力股份有限公司 Method and device for identifying anomalies in multidimensional time series of hydrological stations considering hydrological connections
CN118230155A (en) * 2024-03-13 2024-06-21 西安建材地质工程勘察院有限公司 Natural resource investigation monitoring method and system based on artificial intelligence

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
江德文;: "水文预报方法分析", 商业故事, no. 12, 25 April 2016 (2016-04-25) *

Also Published As

Publication number Publication date
CN119274076B (en) 2025-05-16

Similar Documents

Publication Publication Date Title
Overton Modelling floodplain inundation on a regulated river: integrating GIS, remote sensing and hydrological models
Wu et al. Estimating the probability of compound floods in estuarine regions
Sun et al. Estimating daily time series of streamflow using hydrological model calibrated based on satellite observations of river water surface width: Toward real world applications
Heimhuber et al. Modeling 25 years of spatio-temporal surface water and inundation dynamics on large river basin scale using time series of Earth observation data
CN112800379A (en) A MODIS remote sensing snow information processing method and device
CN110517575A (en) Method and device for surface water system mapping
Zhu et al. Loess terrain segmentation from digital elevation models based on the region growth method
Herzog et al. Measuring zero water level in stream reaches: A comparison of an image‐based versus a conventional method
CN111222679A (en) Remote sensing-based river water amount estimation method
Tesfaye et al. Reservoir sedimentation evaluation using remote sensing and GIS approaches for the reservoirs in the upper Blue Nile Basin
Anand et al. Dynamic change analysis of water spread region and its impact assessment using spectral indices of remotely sensed data
Manaouch et al. Integrating GIS-based FAHP and WaTEM/SEDEM for identifying potential RWH areas in semi-arid areas
Singh et al. Sedimentation analysis for a reservoir using remote sensing and GIS techniques
CN117764317A (en) Hydropower station safe operation prediction method and system considering environmental disasters
CN119378269B (en) Method for extracting submerged range of accumulated water around subway station and emergency disposal method
Darji et al. Hydrodynamic modeling of dam breach floods for predicting downstream inundation scenarios using integrated approach of satellite data, unmanned aerial vehicles (UAVs), and Google Earth Engine (GEE)
CN119274076B (en) Hydrologic forecasting method and system
CN110852232A (en) River bank vegetation coverage extraction method based on mountain river classification
CN116883651B (en) A watershed division method based on deep learning semantic segmentation
Santos et al. Designing a deep learning-based framework for the prediction of lake surface closed curves
Vishwakarma et al. Assessment of reservoir sedimentation using remote sensing technique with GIS model-A review
Das Goolge earth engine-based rainfall-runoff modelling for hydrological assessment in Rasulpur River basin
CN112926416A (en) Vegetation partitioning method, system and device based on ecological hydrological features
Singh et al. Evaluating reservoir capacity and sedimentation rates using geospatial technique: a case study of Chohal dam reservoir
Opiyo Modeling the impacts of land use and land cover changes on streamflow and sediment yield with the SWAT Model in Migori River Watershed, Lake Victoria Basin Region, Kenya

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载