CN118334525B - Reliability evaluation method for modern marine ranch site selection based on decision tree model - Google Patents
Reliability evaluation method for modern marine ranch site selection based on decision tree model Download PDFInfo
- Publication number
- CN118334525B CN118334525B CN202410725837.6A CN202410725837A CN118334525B CN 118334525 B CN118334525 B CN 118334525B CN 202410725837 A CN202410725837 A CN 202410725837A CN 118334525 B CN118334525 B CN 118334525B
- Authority
- CN
- China
- Prior art keywords
- sub
- boundary
- image
- decision tree
- water color
- 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.)
- Active
Links
- 238000003066 decision tree Methods 0.000 title claims abstract description 95
- 238000011156 evaluation Methods 0.000 title 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 123
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000012937 correction Methods 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 64
- 229930002875 chlorophyll Natural products 0.000 claims description 61
- 235000019804 chlorophyll Nutrition 0.000 claims description 61
- 238000010200 validation analysis Methods 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 4
- 238000009304 pastoral farming Methods 0.000 claims 7
- 238000012795 verification Methods 0.000 claims 5
- 238000012216 screening Methods 0.000 claims 2
- 238000001514 detection method Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 3
- 230000015654 memory Effects 0.000 description 14
- 238000004590 computer program Methods 0.000 description 8
- 241000251468 Actinopterygii Species 0.000 description 4
- 241000195493 Cryptophyta Species 0.000 description 4
- 101000779672 Homo sapiens Probable inactive allantoicase Proteins 0.000 description 4
- 102100033794 Probable inactive allantoicase Human genes 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 206010013496 Disturbance in attention Diseases 0.000 description 3
- 241001420622 Meris Species 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 229930002868 chlorophyll a Natural products 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 241001474374 Blennius Species 0.000 description 1
- 241000238557 Decapoda Species 0.000 description 1
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 1
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 1
- 101100012902 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) FIG2 gene Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/36—Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Marine Sciences & Fisheries (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Animal Husbandry (AREA)
- Nonlinear Science (AREA)
- Vascular Medicine (AREA)
- Agronomy & Crop Science (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
本发明公开了基于决策树模型的现代海洋牧场选址可靠性评估方法，通过获取待评估海域在历史时间段内的水色遥感图像；在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像；对各个子图像进行修正边界操作获得修正边界子图像；通过所有水色遥感图像中的修正边界子图像对决策树模型进行训练获得预训练的决策树模型；利用预训练的决策树模型对待评估海域中的海洋牧场选址区域识别是否是可靠性高的海洋牧场选址区域。对于遥感图像边界的修正，使得海洋牧场的边界避开了这些潜在风险，从而提高了后续决策树模型对于海洋牧场位置的识别精度、合理性与可靠性，本发明应用于地理信息数据处理技术领域。
The present invention discloses a modern marine ranch site selection reliability assessment method based on a decision tree model, which is performed by obtaining a water color remote sensing image of a sea area to be assessed within a historical period; marking multiple regions of interest in the water color remote sensing image and performing preprocessing to extract sub-images of the regions of interest; performing boundary correction operations on each sub-image to obtain a corrected boundary sub-image; training a decision tree model through the corrected boundary sub-images in all water color remote sensing images to obtain a pre-trained decision tree model; and using the pre-trained decision tree model to identify whether the marine ranch site selection area in the sea area to be assessed is a marine ranch site selection area with high reliability. The correction of the remote sensing image boundary allows the marine ranch boundary to avoid these potential risks, thereby improving the recognition accuracy, rationality and reliability of the subsequent decision tree model for the location of the marine ranch, and the present invention is applied to the field of geographic information data processing technology.
Description
技术领域Technical Field
本发明涉及地理信息数据处理技术领域，具体涉及基于决策树模型的现代海洋牧场选址可靠性评估方法。The invention relates to the technical field of geographic information data processing, and in particular to a modern ocean ranch site selection reliability assessment method based on a decision tree model.
背景技术Background Art
海洋牧场一般是采用投放混凝土制的人工鱼礁、或者利用深远海的礁石、鱼礁等自然条件海洋牧场建设的人工鱼礁和藻场建设，由于深远海的气象、水文、地理、暗流、藻类、水生物等生物环境与陆地的差异很大，海洋牧场的选址位置受到这些生物环境的影响，生产效率会受到选址位置的直接影响，因为深远海和陆地的较大环境差异，所以海洋牧场的选址和陆地上的建筑物选址方法不一样，现有的选址方法应用于海洋牧场选址的可靠性较低。Marine ranches generally use artificial fish reefs made of concrete, or artificial fish reefs and algae beds built by utilizing natural conditions such as reefs and fish reefs in the deep sea. Since the biological environment such as meteorology, hydrology, geography, undercurrents, algae, aquatic organisms in the deep sea is very different from that on land, the site selection of marine ranches is affected by these biological environments, and production efficiency will be directly affected by the site selection. Due to the large environmental differences between the deep sea and land, the site selection of marine ranches is different from the site selection method of buildings on land, and the reliability of existing site selection methods when applied to marine ranch site selection is low.
发明内容Summary of the invention
本发明的目的在于提出基于决策树模型的现代海洋牧场选址可靠性评估方法，以解决现有技术中所存在的一个或多个技术问题，至少提供一种有益的选择或创造条件。The purpose of the present invention is to propose a modern marine ranch site selection reliability assessment method based on a decision tree model to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.
为了实现上述目的，根据本发明的一方面，提供基于决策树模型的现代海洋牧场选址可靠性评估方法，所述方法包括以下步骤：In order to achieve the above object, according to one aspect of the present invention, a modern ocean ranch site selection reliability assessment method based on a decision tree model is provided, the method comprising the following steps:
S100，获取待评估海域在历史时间段内的水色遥感图像；S100, obtaining water color remote sensing images of the sea area to be evaluated within a historical period;
S200，在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像；S200, marking a plurality of regions of interest in a water color remote sensing image and performing preprocessing to extract sub-images of the regions of interest;
S300，对各个子图像进行修正边界操作获得修正边界子图像；S300, performing a boundary correction operation on each sub-image to obtain a boundary correction sub-image;
S400，通过所有水色遥感图像中的修正边界子图像对决策树模型进行训练获得预训练的决策树模型；S400, training a decision tree model through corrected boundary sub-images in all water color remote sensing images to obtain a pre-trained decision tree model;
S500，利用预训练的决策树模型对待评估海域中的海洋牧场选址区域识别是否是可靠性高的海洋牧场选址区域。S500, using a pre-trained decision tree model to identify whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability.
进一步地，还包括：S600，将可靠性高的海洋牧场选址区域的对应位置的选址地点输出到对应的GIS地图到客户端显示或者输出到数据库中存储。Furthermore, it also includes: S600, outputting the site selection location of the corresponding position of the high-reliability ocean ranch site selection area to the corresponding GIS map to display on the client or outputting it to the database for storage.
进一步地，在S100中，历史时间段为选取的5到40天的历史时长。Further, in S100, the historical time period is a selected historical time period of 5 to 40 days.
其中，水色遥感图像为选取水色数据中的叶绿素a浓度遥感图像产品作为水色遥感图像。Among them, the water color remote sensing image is the chlorophyll a concentration selected from the water color data Remote sensing image products are water color remote sensing images.
其中，水色遥感图像通过MERIS水色传感器、中分辨率成像光谱仪和/或MODIS中分辨率成像光谱仪的图像获取。Among them, water color remote sensing images are obtained through MERIS water color sensor, moderate resolution imaging spectrometer and/or MODIS moderate resolution imaging spectrometer. Image acquisition.
进一步地，在S200中，在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像的方法包括以下步骤：在水色遥感图像中的水色遥感图像中标记多个感兴趣区域；对各个感兴趣区域进行底帽变换并且以阈值分割提取感兴趣区域的图像作为子图像；Further, in S200, the method of marking a plurality of regions of interest in a water color remote sensing image and performing preprocessing to extract sub-images of the regions of interest includes the following steps: marking a plurality of regions of interest in a water color remote sensing image; performing a bottom-hat transformation on each region of interest and extracting an image of the region of interest as a sub-image by threshold segmentation;
对水色遥感图像进行反演获得水色遥感图像的叶绿素含量分布。The water color remote sensing image is inverted to obtain the chlorophyll content distribution of the water color remote sensing image.
由于在海洋牧场中即使水色遥感图像的水色（叶绿素a浓度）在各个子图像的边界之间的变换虽然会受到藻类、水生物的浓度差异的影响，但子图像之间出现的暗流、浪高、海流等因素的较大差异会导致海洋牧场的最终选址并不可靠，使得在对应位置选址的海洋牧场以后的产量由于这些因素在边缘位置形成的叶绿素浓度流失通路使得叶绿素浓度产生快速变化，最终使海洋牧场的产量低于预期。In marine ranches, even though the transformation of water color (chlorophyll a concentration) of remote sensing images at the boundaries of each sub-image will be affected by the concentration differences of algae and aquatic organisms, the large differences in undercurrents, wave heights, ocean currents and other factors between sub-images will make the final site selection of the marine ranch unreliable, resulting in the subsequent production of the marine ranch located at the corresponding location. Due to the chlorophyll concentration loss pathway formed at the edge by these factors, the chlorophyll concentration changes rapidly, and ultimately the production of the marine ranch is lower than expected.
进一步地，在S300中，对各个子图像进行修正边界操作获得修正边界子图像的方法包括以下步骤：Furthermore, in S300, the method of performing a boundary correction operation on each sub-image to obtain a boundary correction sub-image includes the following steps:
分别对各个子图像进行灰度化获得灰度子图像；Grayscale each sub-image to obtain a grayscale sub-image;
计算各个灰度子图像的水色通道程度；Calculate the degree of water color channel of each grayscale sub-image;
筛选出水色通道程度小于所有灰度子图像的平均水色通道程度的灰度子图像作为待修正边界子图像；Screen out the grayscale sub-image whose water color channel degree is less than the average water color channel degree of all grayscale sub-images as the boundary sub-image to be corrected;
对待修正边界子图像进行修正边界操作获得修正边界子图像。A boundary correction operation is performed on the boundary sub-image to be corrected to obtain a corrected boundary sub-image.
通过计算水色通道程度的大小能准确体现出子图像的边界上叶绿素在局部的范围内是否容易形成浓度流失通道，通过浓度流失通道大小的变化，判断整个子图像是否会对海洋选址区域的叶绿素的平衡造成影响，如果水色通道程度的值较大则需要进一步的进行边界扩展或缩减，从而减少在边界上叶绿素的浓度流向较为明显的区域，重新确定边界位置，保障海洋牧场选址的边界上的可靠性和准确性。By calculating the size of the water color channel, it can be accurately reflected whether the chlorophyll on the boundary of the sub-image is prone to form a concentration loss channel in the local range. By changing the size of the concentration loss channel, it can be judged whether the entire sub-image will affect the chlorophyll balance in the ocean site selection area. If the value of the water color channel is large, it is necessary to further expand or reduce the boundary, thereby reducing the area where the chlorophyll concentration flows to a more obvious direction on the boundary, redetermining the boundary position, and ensuring the reliability and accuracy of the boundary of the marine ranch site selection.
进一步地，计算各个灰度子图像的水色通道程度的方法为：Furthermore, the method for calculating the degree of the water color channel of each grayscale sub-image is as follows:
令灰度子图像构成的集合为Areas={Areasi}，以i作为灰度子图像的序号，i∈[1,N]，N为灰度子图像的数量；Areasi为第i个灰度子图像；对Areasi进行边缘检测，以检测得到的各个边缘线将Areasi划分为多个水色流向区域；Let the set of grayscale sub-images be Areas = {Areas i }, with i as the serial number of the grayscale sub-image, i∈[1,N], N is the number of grayscale sub-images; Areas i is the i-th grayscale sub-image; perform edge detection on Areas i , and divide Areas i into multiple water color flow areas based on the detected edge lines;
以Areasi的各个水色流向区域中的平均叶绿素含量值最大的平均叶绿素含量值为局部极限叶绿素PeakGreeni，以Areasi的所有水色流向区域中的平均叶绿素含量值的平均值为QMeanGreeni；The maximum average chlorophyll content value among the water color flow directions of Areas i is the local limit chlorophyll PeakGreen i , and the average of the average chlorophyll content values among all water color flow directions of Areas i is QMeanGreen i ;
以所有灰度子图像中的各个水色流向区域中平均叶绿素含量大于或等于PeakGreeni的所有的水色流向区域构成集合ALLCi, 以集合ALLCi中所有水色流向区域中的平均叶绿素含量值的平均值为HMeanGreeni；All water color flow direction areas in all grayscale sub-images whose average chlorophyll content is greater than or equal to PeakGreen i constitute a set ALLC i , and the average value of the average chlorophyll content values of all water color flow direction areas in the set ALLC i is HMeanGreen i ;
计算灰度子图像Areasi的水色通道程度Tunneli计算式为：The calculation formula for calculating the water color channel degree Tunnel i of the grayscale sub-image Areas i is:
Tunneli=PeakGreeni/(QMeanGreeni+HMeanGreeni)。Tunnel i =PeakGreen i /(QMeanGreen i +HMeanGreen i ).
计算水色通道程度是水色流向区域在叶绿素含量可能朝周边形成叶绿素扩散通道的趋势强弱值，是整个水色遥感图像中的灰度子图像的边界是否平衡的指数。The degree of water color channel calculation is the strength of the trend that the chlorophyll content in the water color flow area may form a chlorophyll diffusion channel toward the surrounding area. It is an index of whether the boundary of the gray sub-image in the entire water color remote sensing image is balanced.
进一步地，对待修正边界子图像进行修正边界操作获得修正边界子图像的方法包括：Furthermore, the method of performing a boundary correction operation on the boundary sub-image to be corrected to obtain a corrected boundary sub-image includes:
按照待修正边界子图像的水色通道程度的大小顺序将待修正边界子图像构成集合EdgeStre={EdgeStrej}，EdgeStrej表示EdgeStre中序号为j的待修正边界子图像；对EdgeStrej进行边缘检测，以检测得到的各个边缘线将EdgeStrej划分为多个水色流向区域；The boundary sub-images to be corrected are grouped into a set EdgeStre={EdgeStre j } according to the order of the water color channel degree of the boundary sub-images to be corrected, where EdgeStre j represents the boundary sub-image to be corrected with sequence number j in EdgeStre; edge detection is performed on EdgeStre j , and EdgeStre j is divided into a plurality of water color flow direction regions by using the detected edge lines;
从j=2开始，在j的取值范围内，依次对EdgeStrej进行修正边界操作，具体方法为：Starting from j=2, within the value range of j, the edge correction operation is performed on EdgeStre j in turn. The specific method is:
记EdgeStrej中各个水色流向区域中的叶绿素含量最大的水色流向区域的内接圆圆心为CycMaxP；记EdgeStrej中各个水色流向区域中的叶绿素含量最小的水色流向区域的内接圆圆心为CycMinP；以CycMaxP到CycMinP的方向为水色流方向；The center of the inscribed circle of the water color flow area with the largest chlorophyll content in each water color flow area in EdgeStre j is CycMaxP; the center of the inscribed circle of the water color flow area with the smallest chlorophyll content in each water color flow area in EdgeStre j is CycMinP; the direction from CycMaxP to CycMinP is the water color flow direction;
以EdgeStrej的边界线上叶绿素含量最大的点为EdgeMaxPj；以EdgeStrej的边界线上叶绿素含量最小的点为EdgeMinPj；以EdgeStrej的边界线上从EdgeMaxPj到EdgeMinPj的水色流方向之间的曲线记为待修正边界；The point with the maximum chlorophyll content on the boundary line of EdgeStre j is EdgeMaxP j ; the point with the minimum chlorophyll content on the boundary line of EdgeStre j is EdgeMinP j ; the curve between the water color flow directions from EdgeMaxP j to EdgeMinP j on the boundary line of EdgeStre j is recorded as the boundary to be corrected;
在序号小于j的所有待修正边界子图像中搜索边界线上叶绿素含量最大的点的叶绿素含量与EdgeStrej的边界线上叶绿素含量最大的点的叶绿素含量之间差值最小的待修正边界子图像记为稳定边界子图像EdgeStable；Search all the boundary sub-images with serial numbers less than j for the boundary sub-images to be corrected, and the boundary sub-image to be corrected has the smallest difference between the chlorophyll content of the point with the largest chlorophyll content on the boundary line and the chlorophyll content of the point with the largest chlorophyll content on the boundary line of EdgeStre j , and record it as the stable boundary sub-image EdgeStable;
以EdgeStable的边界线上叶绿素含量最大的点为StabMaxP；以EdgeStable的边界线上叶绿素含量最小的点为StabMinP；以EdgeStable的边界线上从StabMaxP到StabMinP的水色流方向之间的曲线记为修正边界曲线FixLine；The point with the largest chlorophyll content on the boundary line of EdgeStable is StabMaxP; the point with the smallest chlorophyll content on the boundary line of EdgeStable is StabMinP; the curve between the water color flow directions from StabMaxP to StabMinP on the boundary line of EdgeStable is recorded as the corrected boundary curve FixLine;
删除EdgeStrej的边界线上的待修正边界，将EdgeStrej的边界线上的EdgeMaxPj点记为A端点、将EdgeStrej的边界线上的EdgeMinPj点记为B端点，Delete the boundary to be corrected on the boundary line of EdgeStre j , record the EdgeMaxP j point on the boundary line of EdgeStre j as the A endpoint, and record the EdgeMinP j point on the boundary line of EdgeStre j as the B endpoint.
将复制的修正边界曲线FixLine的StabMaxP点记为C端点、复制的修正边界曲线的StabMinP点记为D端点；The StabMaxP point of the copied correction boundary curve FixLine is recorded as the C endpoint, and the StabMinP point of the copied correction boundary curve is recorded as the D endpoint;
将曲线FixLine等比例缩放到C端点和D端点之间的距离与A端点和B端点之间的距离相等大小记为曲线UpFixLine；Scale the curve FixLine to the same size that the distance between endpoints C and D is equal to the distance between endpoints A and B, and record it as the curve UpFixLine;
将曲线UpFixLine整体移动到C端点与A端点重合、D端点与B端点重合重新构成修正后的边界EdgeStrej；Move the entire curve UpFixLine to the point where the C endpoint coincides with the A endpoint, and the D endpoint coincides with the B endpoint to reconstruct the corrected boundary EdgeStre j ;
将修正后的边界EdgeStrej的待修正边界子图像作为修正边界子图像。The to-be-corrected boundary sub-image of the corrected boundary EdgeStre j is used as the corrected boundary sub-image.
其有益效果为：待修正边界是叶绿素流速最异常的区域边界，如果海洋牧场的选址边界上存在这种待修正边界，则有可能边界上存在着气象、热流、藻类、水生物、暗流、浪高、海流等因素导致的水色流方向异常的问题，叶绿素流向异常直接意味着该海域存在着这些异常因素，会使海洋牧场出现不稳定因素，使得在海洋牧场中的鱼虾养殖业与海藻、海生蔬菜等农产品减产或者流失，因而会直接导致海洋牧场选址的不可靠；通过对于边界的修正，使得海洋牧场的边界避开了这些潜在风险，从而提高了后续决策树模型的识别精度与可靠性。The beneficial effects are as follows: the boundary to be corrected is the boundary of the area with the most abnormal chlorophyll flow velocity. If such a boundary to be corrected exists on the boundary of the marine ranch site selection, it is possible that there are abnormal water color flow direction problems caused by meteorological, thermal current, algae, aquatic organisms, undercurrent, wave height, ocean current and other factors on the boundary. The abnormal chlorophyll flow direction directly means that these abnormal factors exist in the sea area, which will cause instability in the marine ranch, resulting in reduced production or loss of fish and shrimp farming and agricultural products such as seaweed and marine vegetables in the marine ranch, which will directly lead to unreliable site selection for the marine ranch. By correcting the boundary, the boundary of the marine ranch avoids these potential risks, thereby improving the recognition accuracy and reliability of the subsequent decision tree model.
进一步地，在S400中，决策树模型为XGBoost模型。Further, in S400, the decision tree model is an XGBoost model.
其中，通过所有水色遥感图像中的修正边界子图像对决策树模型进行训练获得预训练的决策树模型的方法为：将所有水色遥感图像中各个子图像划分为训练集和验证集，具体为：将修正边界子图像作为正样本标注为1，筛选出水色通道程度大于所有灰度子图像的平均水色通道程度的灰度子图像作为负样本标注为0，从而完成样本的标注；由标注后的正样本和负样本构成将训练样本集；将训练样本集按照4:1的比例划分为训练集和验证集，训练集用于训练决策树模型，验证集用于验证训练后的决策树模型的预测性能。Among them, the method for obtaining a pre-trained decision tree model by training the decision tree model through the corrected boundary sub-images in all water color remote sensing images is: each sub-image in all water color remote sensing images is divided into a training set and a validation set, specifically: the corrected boundary sub-image is marked as 1 as a positive sample, and the grayscale sub-image whose water color channel degree is greater than the average water color channel degree of all grayscale sub-images is screened out as a negative sample and marked as 0, thereby completing the labeling of the samples; the training sample set is composed of the labeled positive samples and negative samples; the training sample set is divided into a training set and a validation set in a ratio of 4:1, the training set is used to train the decision tree model, and the validation set is used to verify the prediction performance of the trained decision tree model.
使用训练集和验证集对决策树模型进行训练获得预训练的决策树模型。The decision tree model is trained using the training set and the validation set to obtain a pre-trained decision tree model.
其中，使用训练集和验证集对决策树模型进行训练的方法为：Among them, the method of training the decision tree model using the training set and the validation set is:
提取训练集的特征并输入决策树模型，采用网格搜索方法对决策树模型中超参数进行优化，按照优化后的超参数对决策树模型进行重新训练，获得训练好的预训练的决策树模型。The features of the training set are extracted and input into the decision tree model. The hyperparameters in the decision tree model are optimized using the grid search method. The decision tree model is retrained according to the optimized hyperparameters to obtain a trained pre-trained decision tree model.
进一步地，在S500中，利用预训练的决策树模型对待评估海域中的海洋牧场选址区域识别是否是可靠性高的海洋牧场选址区域的方法具体为：Further, in S500, the method of using the pre-trained decision tree model to identify whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability is specifically as follows:
通过MERIS水色传感器、中分辨率成像光谱仪和/或MODIS中分辨率成像光谱仪的图像获取待评估海域中的海洋牧场选址区域的水色遥感图像；The MERIS ocean color sensor, the Moderate Resolution Imaging Spectroradiometer and/or the MODIS Moderate Resolution Imaging Spectroradiometer Image acquisition: remote sensing images of water color in the marine ranch site selection area in the sea area to be evaluated;
对水色遥感图像进行反演获得水色遥感图像的叶绿素含量分布；Invert the water color remote sensing image to obtain the chlorophyll content distribution of the water color remote sensing image;
在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像并灰度化；Mark multiple regions of interest in the water color remote sensing image and perform preprocessing to extract sub-images of the regions of interest and grayscale them;
使用预训练的决策树模型对灰度化的子图像中的正样本区域进行筛选，如果能够筛选得到正样本区域，则判断待评估海域中的海洋牧场选址区域是可靠性高的海洋牧场选址区域。A pre-trained decision tree model is used to screen the positive sample areas in the grayscale sub-image. If the positive sample areas can be screened out, it is judged that the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability.
本发明还提供了基于决策树模型的现代海洋牧场选址可靠性评估系统，所述系统包括：存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序运行在以下系统的单元中：The present invention also provides a modern marine ranch site selection reliability assessment system based on a decision tree model, the system comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program running in the following system units:
遥感图像采集单元，用于获取待评估海域在历史时间段内的水色遥感图像；A remote sensing image acquisition unit, used to obtain water color remote sensing images of the sea area to be assessed within a historical period of time;
预处理单元，用于在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像；A preprocessing unit, used for marking a plurality of regions of interest in the water color remote sensing image and performing preprocessing to extract sub-images of the regions of interest;
边界修正单元，用于对各个子图像进行修正边界操作获得修正边界子图像；A boundary correction unit, used for performing boundary correction operation on each sub-image to obtain a boundary-corrected sub-image;
决策树训练单元，用于通过所有水色遥感图像中的修正边界子图像对决策树模型进行训练获得预训练的决策树模型；A decision tree training unit, used for training a decision tree model through corrected boundary sub-images in all water color remote sensing images to obtain a pre-trained decision tree model;
决策树识别单元，用于利用预训练的决策树模型对待评估海域中的海洋牧场选址区域识别是否是可靠性高的海洋牧场选址区域。The decision tree recognition unit is used to use a pre-trained decision tree model to identify whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability.
本发明的有益效果为：本发明提供基于决策树模型的现代海洋牧场选址可靠性评估方法，对于遥感图像边界的修正，使得海洋牧场的边界避开了这些潜在风险，从而提高了后续决策树模型对于海洋牧场位置的识别精度、合理性与可靠性。The beneficial effects of the present invention are as follows: the present invention provides a modern marine ranch site selection reliability assessment method based on a decision tree model, and the correction of the remote sensing image boundary allows the marine ranch boundary to avoid these potential risks, thereby improving the subsequent decision tree model's recognition accuracy, rationality and reliability for the marine ranch location.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
通过对结合附图所示出的实施方式进行详细说明，本发明的上述以及其他特征将更加明显，本发明附图中相同的参考标号表示相同或相似的元素，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图，在附图中：The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings:
图1所示为基于决策树模型的现代海洋牧场选址可靠性评估方法的流程图；FIG1 is a flow chart showing a reliability assessment method for modern marine ranch site selection based on a decision tree model;
图2所示为基于决策树模型的现代海洋牧场选址可靠性评估系统结构图。Figure 2 shows the structure diagram of the modern ocean ranch site selection reliability assessment system based on the decision tree model.
具体实施方式DETAILED DESCRIPTION
以下将结合实施例和附图对本发明的构思、具体结构及产生的技术效果进行清楚、完整的描述，以充分地理解本发明的目的、方案和效果。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.
如图1所示为根据本发明的基于决策树模型的现代海洋牧场选址可靠性评估方法的流程图，下面结合图1来阐述根据本发明的实施方式的基于决策树模型的现代海洋牧场选址可靠性评估方法。As shown in Figure 1, it is a flow chart of the modern ocean ranch site selection reliability assessment method based on the decision tree model according to the present invention. The modern ocean ranch site selection reliability assessment method based on the decision tree model according to an implementation mode of the present invention will be explained in conjunction with Figure 1 below.
本发明的实施例提供一种基于决策树模型的现代海洋牧场选址可靠性评估方法，具体包括以下步骤：An embodiment of the present invention provides a modern ocean ranch site selection reliability assessment method based on a decision tree model, which specifically includes the following steps:
S100，获取待评估海域在历史时间段内的水色遥感图像；S100, obtaining water color remote sensing images of the sea area to be evaluated within a historical period;
S200，在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像；S200, marking a plurality of regions of interest in a water color remote sensing image and performing preprocessing to extract sub-images of the regions of interest;
S300，对各个子图像进行修正边界操作获得修正边界子图像；S300, performing a boundary correction operation on each sub-image to obtain a boundary correction sub-image;
S400，通过所有水色遥感图像中的修正边界子图像对决策树模型进行训练获得预训练的决策树模型；S400, training a decision tree model through corrected boundary sub-images in all water color remote sensing images to obtain a pre-trained decision tree model;
S500，利用预训练的决策树模型对待评估海域中的海洋牧场选址区域识别是否是可靠性高的海洋牧场选址区域。S500, using a pre-trained decision tree model to identify whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability.
进一步地，还包括：S600，将可靠性高的海洋牧场选址区域的对应位置的选址地点输出到对应的GIS地图到客户端显示。Furthermore, it also includes: S600, outputting the site selection location of the corresponding position of the marine ranch site selection area with high reliability to the corresponding GIS map to display on the client.
进一步地，在S100中，历史时间段为选取的40天的历史时长。Further, in S100, the historical time period is a selected historical period of 40 days.
其中，水色遥感图像为选取水色数据中的叶绿素a浓度遥感图像产品作为水色遥感图像。Among them, the water color remote sensing image is the chlorophyll a concentration selected from the water color data Remote sensing image products are water color remote sensing images.
进一步地，在S200中，在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像的方法包括以下步骤：在水色遥感图像中的水色遥感图像中标记多个感兴趣区域；对各个感兴趣区域进行底帽变换并且以阈值分割提取感兴趣区域的图像作为子图像；Further, in S200, the method of marking a plurality of regions of interest in a water color remote sensing image and performing preprocessing to extract sub-images of the regions of interest includes the following steps: marking a plurality of regions of interest in a water color remote sensing image; performing a bottom-hat transformation on each region of interest and extracting an image of the region of interest as a sub-image by threshold segmentation;
对水色遥感图像进行反演获得水色遥感图像的叶绿素含量分布。The water color remote sensing image is inverted to obtain the chlorophyll content distribution of the water color remote sensing image.
进一步地，在S300中，对各个子图像进行修正边界操作获得修正边界子图像的方法包括以下步骤：Furthermore, in S300, the method of performing a boundary correction operation on each sub-image to obtain a boundary correction sub-image includes the following steps:
分别对各个子图像进行灰度化获得灰度子图像；Grayscale each sub-image to obtain a grayscale sub-image;
计算各个灰度子图像的水色通道程度；Calculate the degree of water color channel of each grayscale sub-image;
筛选出水色通道程度小于所有灰度子图像的平均水色通道程度的灰度子图像作为待修正边界子图像；Screen out the grayscale sub-image whose water color channel degree is less than the average water color channel degree of all grayscale sub-images as the boundary sub-image to be corrected;
对待修正边界子图像进行修正边界操作获得修正边界子图像。A boundary correction operation is performed on the boundary sub-image to be corrected to obtain a corrected boundary sub-image.
进一步地，计算各个灰度子图像的水色通道程度的方法为：Furthermore, the method for calculating the degree of the water color channel of each grayscale sub-image is as follows:
令灰度子图像构成的集合为Areas={Areasi}，以i作为灰度子图像的序号，i∈[1,N]，N为灰度子图像的数量；Areasi为第i个灰度子图像；对Areasi进行边缘检测，以检测得到的各个边缘线将Areasi划分为多个水色流向区域；Let the set of grayscale sub-images be Areas = {Areas i }, with i as the serial number of the grayscale sub-image, i∈[1,N], N is the number of grayscale sub-images; Areas i is the i-th grayscale sub-image; perform edge detection on Areas i , and divide Areas i into multiple water color flow areas based on the detected edge lines;
以Areasi的各个水色流向区域中的平均叶绿素含量值最大的平均叶绿素含量值为局部极限叶绿素PeakGreeni，以Areasi的所有水色流向区域中的平均叶绿素含量值的平均值为QMeanGreeni；The maximum average chlorophyll content value among the water color flow directions of Areas i is the local limit chlorophyll PeakGreen i , and the average of the average chlorophyll content values among all water color flow directions of Areas i is QMeanGreen i ;
以所有灰度子图像中的各个水色流向区域中平均叶绿素含量大于或等于PeakGreeni的所有的水色流向区域构成集合ALLCi, 以集合ALLCi中所有水色流向区域中的平均叶绿素含量值的平均值为HMeanGreeni；All water color flow direction areas in all grayscale sub-images whose average chlorophyll content is greater than or equal to PeakGreen i constitute a set ALLC i , and the average value of the average chlorophyll content values of all water color flow direction areas in the set ALLC i is HMeanGreen i ;
计算灰度子图像Areasi的水色通道程度Tunneli计算式为：The calculation formula for calculating the water color channel degree Tunnel i of the grayscale sub-image Areas i is:
Tunneli=PeakGreeni/(QMeanGreeni+HMeanGreeni)。Tunnel i =PeakGreen i /(QMeanGreen i +HMeanGreen i ).
计算水色通道程度是水色流向区域在叶绿素含量可能朝周边形成叶绿素扩散通道的趋势强弱值，是整个水色遥感图像中的灰度子图像的边界是否平衡的指数。The degree of water color channel calculation is the strength of the trend that the chlorophyll content in the water color flow area may form a chlorophyll diffusion channel toward the surrounding area. It is an index of whether the boundary of the gray sub-image in the entire water color remote sensing image is balanced.
进一步地，对待修正边界子图像进行修正边界操作获得修正边界子图像的方法包括：Furthermore, the method of performing a boundary correction operation on the boundary sub-image to be corrected to obtain a corrected boundary sub-image includes:
按照待修正边界子图像的水色通道程度的大小顺序将待修正边界子图像构成集合EdgeStre={EdgeStrej}，EdgeStrej表示EdgeStre中序号为j的待修正边界子图像；对EdgeStrej进行边缘检测，以检测得到的各个边缘线将EdgeStrej划分为多个水色流向区域；The boundary sub-images to be corrected are grouped into a set EdgeStre={EdgeStre j } according to the order of the water color channel degree of the boundary sub-images to be corrected, where EdgeStre j represents the boundary sub-image to be corrected with sequence number j in EdgeStre; edge detection is performed on EdgeStre j , and EdgeStre j is divided into a plurality of water color flow direction regions by using the detected edge lines;
从j=2开始，在j的取值范围内，依次对EdgeStrej进行修正边界操作，具体方法为：Starting from j=2, within the value range of j, the edge correction operation is performed on EdgeStre j in turn. The specific method is:
记EdgeStrej中各个水色流向区域中的叶绿素含量最大的水色流向区域的内接圆圆心为CycMaxP；记EdgeStrej中各个水色流向区域中的叶绿素含量最小的水色流向区域的内接圆圆心为CycMinP；以CycMaxP到CycMinP的方向为水色流方向；The center of the inscribed circle of the water color flow area with the largest chlorophyll content in each water color flow area in EdgeStre j is CycMaxP; the center of the inscribed circle of the water color flow area with the smallest chlorophyll content in each water color flow area in EdgeStre j is CycMinP; the direction from CycMaxP to CycMinP is the water color flow direction;
以EdgeStrej的边界线上叶绿素含量最大的点为EdgeMaxPj；以EdgeStrej的边界线上叶绿素含量最小的点为EdgeMinPj；以EdgeStrej的边界线上从EdgeMaxPj到EdgeMinPj的水色流方向之间的曲线记为待修正边界；The point with the maximum chlorophyll content on the boundary line of EdgeStre j is EdgeMaxP j ; the point with the minimum chlorophyll content on the boundary line of EdgeStre j is EdgeMinP j ; the curve between the water color flow directions from EdgeMaxP j to EdgeMinP j on the boundary line of EdgeStre j is recorded as the boundary to be corrected;
在序号小于j的所有待修正边界子图像中搜索边界线上叶绿素含量最大的点的叶绿素含量与EdgeStrej的边界线上叶绿素含量最大的点的叶绿素含量之间差值最小的待修正边界子图像记为稳定边界子图像EdgeStable；Search all the boundary sub-images with serial numbers less than j for the boundary sub-images to be corrected, and the boundary sub-image to be corrected has the smallest difference between the chlorophyll content of the point with the largest chlorophyll content on the boundary line and the chlorophyll content of the point with the largest chlorophyll content on the boundary line of EdgeStre j , and record it as the stable boundary sub-image EdgeStable;
以EdgeStable的边界线上叶绿素含量最大的点为StabMaxP；以EdgeStable的边界线上叶绿素含量最小的点为StabMinP；以EdgeStable的边界线上从StabMaxP到StabMinP的水色流方向之间的曲线记为修正边界曲线FixLine；The point with the largest chlorophyll content on the boundary line of EdgeStable is StabMaxP; the point with the smallest chlorophyll content on the boundary line of EdgeStable is StabMinP; the curve between the water color flow directions from StabMaxP to StabMinP on the boundary line of EdgeStable is recorded as the corrected boundary curve FixLine;
删除EdgeStrej的边界线上的待修正边界，将EdgeStrej的边界线上的EdgeMaxPj点记为A端点、将EdgeStrej的边界线上的EdgeMinPj点记为B端点，Delete the boundary to be corrected on the boundary line of EdgeStre j , record the EdgeMaxP j point on the boundary line of EdgeStre j as the A endpoint, and record the EdgeMinP j point on the boundary line of EdgeStre j as the B endpoint.
将复制的修正边界曲线FixLine的StabMaxP点记为C端点、复制的修正边界曲线的StabMinP点记为D端点；The StabMaxP point of the copied correction boundary curve FixLine is recorded as the C endpoint, and the StabMinP point of the copied correction boundary curve is recorded as the D endpoint;
将曲线FixLine等比例缩放到C端点和D端点之间的距离与A端点和B端点之间的距离相等大小记为曲线UpFixLine；Scale the curve FixLine to the same size that the distance between endpoints C and D is equal to the distance between endpoints A and B, and record it as the curve UpFixLine;
将曲线UpFixLine整体移动到C端点与A端点重合、D端点与B端点重合重新构成修正后的边界EdgeStrej；Move the entire curve UpFixLine to the point where the C endpoint coincides with the A endpoint, and the D endpoint coincides with the B endpoint to reconstruct the corrected boundary EdgeStre j ;
将修正后的边界EdgeStrej的待修正边界子图像作为修正边界子图像。The to-be-corrected boundary sub-image of the corrected boundary EdgeStre j is used as the corrected boundary sub-image.
进一步地，在S400中，决策树模型为XGBoost模型。Further, in S400, the decision tree model is an XGBoost model.
其中，通过所有水色遥感图像中的修正边界子图像对决策树模型进行训练获得预训练的决策树模型的方法为：将所有水色遥感图像中各个子图像划分为训练集和验证集，具体为：将修正边界子图像作为正样本标注为1，筛选出水色通道程度大于所有灰度子图像的平均水色通道程度的灰度子图像作为负样本标注为0，从而完成样本的标注；由标注后的正样本和负样本构成将训练样本集；将训练样本集按照4:1的比例划分为训练集和验证集，训练集用于训练决策树模型，验证集用于验证训练后的决策树模型的预测性能。Among them, the method for obtaining a pre-trained decision tree model by training the decision tree model through the corrected boundary sub-images in all water color remote sensing images is: each sub-image in all water color remote sensing images is divided into a training set and a validation set, specifically: the corrected boundary sub-image is marked as 1 as a positive sample, and the grayscale sub-image whose water color channel degree is greater than the average water color channel degree of all grayscale sub-images is screened out as a negative sample and marked as 0, thereby completing the labeling of the samples; the training sample set is composed of the labeled positive samples and negative samples; the training sample set is divided into a training set and a validation set in a ratio of 4:1, the training set is used to train the decision tree model, and the validation set is used to verify the prediction performance of the trained decision tree model.
使用训练集和验证集对决策树模型进行训练获得预训练的决策树模型。The decision tree model is trained using the training set and the validation set to obtain a pre-trained decision tree model.
其中，使用训练集和验证集对决策树模型进行训练的方法为：Among them, the method of training the decision tree model using the training set and the validation set is:
提取训练集的特征并输入决策树模型，采用网格搜索方法对决策树模型中超参数进行优化，按照优化后的超参数对决策树模型进行重新训练，获得训练好的预训练的决策树模型。The features of the training set are extracted and input into the decision tree model. The hyperparameters in the decision tree model are optimized using the grid search method. The decision tree model is retrained according to the optimized hyperparameters to obtain a trained pre-trained decision tree model.
进一步地，在S500中，利用预训练的决策树模型对待评估海域中的海洋牧场选址区域识别是否是可靠性高的海洋牧场选址区域的方法具体为：Further, in S500, the method of using the pre-trained decision tree model to identify whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability is specifically as follows:
通过MERIS水色传感器获取待评估海域中的海洋牧场选址区域的水色遥感图像；Use the MERIS water color sensor to obtain water color remote sensing images of the marine ranch site selection area in the sea area to be evaluated;
对水色遥感图像进行反演获得水色遥感图像的叶绿素含量分布；Invert the water color remote sensing image to obtain the chlorophyll content distribution of the water color remote sensing image;
在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像并灰度化；Mark multiple regions of interest in the water color remote sensing image and perform preprocessing to extract sub-images of the regions of interest and grayscale them;
使用预训练的决策树模型对灰度化的子图像中的正样本区域进行筛选，如果能够筛选得到正样本区域，则判断待评估海域中的海洋牧场选址区域是可靠性高的海洋牧场选址区域。A pre-trained decision tree model is used to screen the positive sample areas in the grayscale sub-image. If the positive sample areas can be screened out, it is judged that the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability.
本发明的实施例提供的基于决策树模型的现代海洋牧场选址可靠性评估系统，如图2所示为本发明的基于决策树模型的现代海洋牧场选址可靠性评估系统结构图，该实施例的基于决策树模型的现代海洋牧场选址可靠性评估系统包括：处理器、存储器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述基于决策树模型的现代海洋牧场选址可靠性评估系统实施例中的步骤。An embodiment of the present invention provides a modern ocean ranch site selection reliability assessment system based on a decision tree model. FIG2 is a structural diagram of the modern ocean ranch site selection reliability assessment system based on a decision tree model of the present invention. The modern ocean ranch site selection reliability assessment system based on a decision tree model of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiment of the modern ocean ranch site selection reliability assessment system based on a decision tree model are implemented.
所述系统包括：存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序运行在以下系统的单元中：The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system:
遥感图像采集单元，用于获取待评估海域在历史时间段内的水色遥感图像；A remote sensing image acquisition unit, used to obtain water color remote sensing images of the sea area to be assessed within a historical period of time;
预处理单元，用于在水色遥感图像标记多个感兴趣区域并且进行预处理提取感兴趣区域的子图像；A preprocessing unit, used for marking a plurality of regions of interest in the water color remote sensing image and performing preprocessing to extract sub-images of the regions of interest;
边界修正单元，用于对各个子图像进行修正边界操作获得修正边界子图像；A boundary correction unit, used for performing boundary correction operation on each sub-image to obtain a boundary-corrected sub-image;
决策树训练单元，用于通过所有水色遥感图像中的修正边界子图像对决策树模型进行训练获得预训练的决策树模型；A decision tree training unit, used for training a decision tree model through corrected boundary sub-images in all water color remote sensing images to obtain a pre-trained decision tree model;
决策树识别单元，用于利用预训练的决策树模型对待评估海域中的海洋牧场选址区域识别是否是可靠性高的海洋牧场选址区域。The decision tree recognition unit is used to use a pre-trained decision tree model to identify whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability.
所述基于决策树模型的现代海洋牧场选址可靠性评估系统可以运行于桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备中。所述基于决策树模型的现代海洋牧场选址可靠性评估系统，可运行的系统可包括，但不仅限于，处理器、存储器。本领域技术人员可以理解，所述例子仅仅是基于决策树模型的现代海洋牧场选址可靠性评估系统的示例，并不构成对基于决策树模型的现代海洋牧场选址可靠性评估系统的限定，可以包括比例子更多或更少的部件，或者组合某些部件，或者不同的部件，例如所述基于决策树模型的现代海洋牧场选址可靠性评估系统还可以包括输入输出设备、网络接入设备、总线等。The modern ocean ranch site selection reliability assessment system based on the decision tree model can be run on computing devices such as desktop computers, notebooks, PDAs and cloud servers. The modern ocean ranch site selection reliability assessment system based on the decision tree model, the executable system may include, but is not limited to, processors and memories. Those skilled in the art will understand that the example is only an example of the modern ocean ranch site selection reliability assessment system based on the decision tree model, and does not constitute a limitation on the modern ocean ranch site selection reliability assessment system based on the decision tree model, and may include more or fewer components than the example, or a combination of certain components, or different components, for example, the modern ocean ranch site selection reliability assessment system based on the decision tree model may also include input and output devices, network access devices, buses, etc.
所称处理器可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器 (Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列 (Field-Programmable Gate Array，FPGA) 或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等，所述处理器是所述基于决策树模型的现代海洋牧场选址可靠性评估系统运行系统的控制中心，利用各种接口和线路连接整个基于决策树模型的现代海洋牧场选址可靠性评估系统可运行系统的各个部分。The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the operation system of the modern ocean ranch site selection reliability assessment system based on the decision tree model, and uses various interfaces and lines to connect various parts of the entire operation system of the modern ocean ranch site selection reliability assessment system based on the decision tree model.
所述存储器可用于存储所述计算机程序和/或模块，所述处理器通过运行或执行存储在所述存储器内的计算机程序和/或模块，以及调用存储在存储器内的数据，实现所述基于决策树模型的现代海洋牧场选址可靠性评估系统的各种功能。所述存储器可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序（比如声音播放功能、图像播放功能等）等；存储数据区可存储根据手机的使用所创建的数据（比如音频数据、电话本等）等。此外，存储器可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡（Smart Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。The memory can be used to store the computer program and/or module, and the processor realizes various functions of the modern marine ranch site selection reliability assessment system based on the decision tree model by running or executing the computer program and/or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
尽管本发明的描述已经相当详尽且特别对几个所述实施例进行了描述，但其并非旨在局限于任何这些细节或实施例或任何特殊实施例，从而有效地涵盖本发明的预定范围。此外，上文以发明人可预见的实施例对本发明进行描述，其目的是为了提供有用的描述，而那些目前尚未预见的对本发明的非实质性改动仍可代表本发明的等效改动。Although the description of the present invention has been quite detailed and has been described in particular with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present invention. In addition, the present invention is described above with the embodiments foreseeable by the inventors, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that are not currently foreseen may still represent equivalent changes of the present invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410725837.6A CN118334525B (en) | 2024-06-06 | 2024-06-06 | Reliability evaluation method for modern marine ranch site selection based on decision tree model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410725837.6A CN118334525B (en) | 2024-06-06 | 2024-06-06 | Reliability evaluation method for modern marine ranch site selection based on decision tree model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118334525A CN118334525A (en) | 2024-07-12 |
| CN118334525B true CN118334525B (en) | 2024-08-16 |
Family
ID=91777242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410725837.6A Active CN118334525B (en) | 2024-06-06 | 2024-06-06 | Reliability evaluation method for modern marine ranch site selection based on decision tree model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118334525B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119338082A (en) * | 2024-12-20 | 2025-01-21 | 自然资源部第一海洋研究所 | Marine pasture site selection evaluation method based on machine learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001641A (en) * | 2020-08-27 | 2020-11-27 | 中国海洋大学 | Scallop culture area suitability remote sensing evaluation system |
| CN116313145A (en) * | 2023-05-10 | 2023-06-23 | 江西省农业科学院畜牧兽医研究所 | Intelligent epidemiological investigation system for animals |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10628756B1 (en) * | 2019-09-12 | 2020-04-21 | Performance Livestock Analytics, Inc. | Livestock and feedlot data collection and processing using UHF-band interrogation of radio frequency identification tags |
| CN116502903A (en) * | 2023-03-22 | 2023-07-28 | 中国科学院海洋研究所 | Method for evaluating suitability of bottom-sowing scallop breeding area site selection based on analytic hierarchy process |
| CN116739817B (en) * | 2023-08-08 | 2024-01-19 | 广州桓乐生态环境科技有限公司 | Marine organism diversity monitoring system and data processing method |
| CN118134678A (en) * | 2024-03-20 | 2024-06-04 | 广东海洋大学 | A modern marine ranch site selection method |
-
2024
- 2024-06-06 CN CN202410725837.6A patent/CN118334525B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001641A (en) * | 2020-08-27 | 2020-11-27 | 中国海洋大学 | Scallop culture area suitability remote sensing evaluation system |
| CN116313145A (en) * | 2023-05-10 | 2023-06-23 | 江西省农业科学院畜牧兽医研究所 | Intelligent epidemiological investigation system for animals |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118334525A (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112580439B (en) | Large-format remote sensing image ship target detection method and system under small sample condition | |
| CN113269257A (en) | Image classification method and device, terminal equipment and storage medium | |
| CN116994140A (en) | Cultivated land extraction method, device, equipment and medium based on remote sensing image | |
| CN105551036A (en) | Training method and device for deep learning network | |
| CN118334525B (en) | Reliability evaluation method for modern marine ranch site selection based on decision tree model | |
| US20220067336A1 (en) | System and process for integrative computational soil mapping | |
| Rasmussen et al. | Automatic detection and classification of baleen whale social calls using convolutional neural networks | |
| CN112669323A (en) | Image processing method and related equipment | |
| CN114324336B (en) | Nondestructive measurement method for biomass of soybean in whole growth period | |
| CN114677589B (en) | Method, device, equipment and medium for identifying urban functional areas based on remote sensing interpretation | |
| CN114943696B (en) | Marine environment change monitoring method, device and medium based on remote sensing image | |
| CN115953577A (en) | A Semantic Segmentation Method of Remote Sensing Image Based on Supervised Long-range Correlation | |
| CN110705535A (en) | Method for automatically detecting test paper layout character line | |
| CN114429577A (en) | A flag detection method, system and device based on high-confidence labeling strategy | |
| CN114241470A (en) | Natural scene character detection method based on attention mechanism | |
| CN116824274B (en) | Small sample fine granularity image classification method and system | |
| CN117197048A (en) | Ship water gauge reading detection method, device and equipment | |
| CN116843946A (en) | A method and device for identifying the main structural planes of tunnel rock mass based on image recognition | |
| CN113408595B (en) | Pathological image processing method and device, electronic equipment and readable storage medium | |
| CN116129320A (en) | Target detection method, system and equipment based on video SAR | |
| CN115240198A (en) | High-precision water level enhancement identification multi-mode measuring method for hydraulic engineering | |
| Musara et al. | Statistical modeling of annual highest monthly rainfall in Zimbabwe | |
| CN116363498A (en) | Loess plateau terrace automatic identification method based on deep migration learning | |
| CN113936103A (en) | Construction method and equipment of laser point cloud image model | |
| CN113920377A (en) | Method of classifying image, computer device, and storage medium |
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 |