CN110750516A - Rainfall Analysis Model Construction Method, Construction System and Analysis Method Based on Radar Chart - Google Patents
Rainfall Analysis Model Construction Method, Construction System and Analysis Method Based on Radar Chart Download PDFInfo
- Publication number
- CN110750516A CN110750516A CN201910931683.5A CN201910931683A CN110750516A CN 110750516 A CN110750516 A CN 110750516A CN 201910931683 A CN201910931683 A CN 201910931683A CN 110750516 A CN110750516 A CN 110750516A
- Authority
- CN
- China
- Prior art keywords
- radar
- rainfall
- analysis model
- map
- echo data
- 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
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 114
- 238000010276 construction Methods 0.000 title claims abstract description 13
- 239000012634 fragment Substances 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims 2
- 238000000638 solvent extraction Methods 0.000 claims 1
- 230000000875 corresponding effect Effects 0.000 description 38
- 238000003908 quality control method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- 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
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Remote Sensing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
Description
技术领域technical field
本发明涉及降雨分析领域，具体地说是一种基于雷达图的降雨分析模型构建方法、构建系统及分析方法。The invention relates to the field of rainfall analysis, in particular to a method for building a rainfall analysis model, a building system and an analysis method based on a radar chart.
背景技术Background technique
自动雨量站资料向来都是能够准确反映实际降雨量的主要依据，然而我国自动雨量站布设密度目前尚无具体标准，对已设置的数以万计的雨量站的合理性也未进行过科学的论证，很多自动雨量站经历几次迁移后，地理位置信息已经不准确。另外，雨量的测量受风场影响很大，特别是翻斗式雨量计在大雨时，由于翻斗翻动的惯性，致使另一翻斗盛满水时还来不及翻转，造成雨量流失，使得测定的雨量有较大的误差，记录失真，以及翻斗上的沾水或泥沙的影响都会阻碍翻斗的翻动，都有可能造成雨量的测量误差。The data of automatic rainfall stations has always been the main basis for accurately reflecting the actual rainfall. However, there is currently no specific standard for the density of automatic rainfall stations in my country, and the rationality of the tens of thousands of rainfall stations that have been set up has not been scientifically studied. It is argued that after many automatic rainfall stations have undergone several migrations, the geographic location information has become inaccurate. In addition, the measurement of rainfall is greatly affected by the wind field, especially when the tipping bucket rain gauge is in heavy rain, due to the inertia of the tipping bucket, it is too late to turn over when the other tipping bucket is full of water, resulting in the loss of rainfall, which makes the measured rainfall more variable. Large errors, recording distortion, and the influence of water or sediment on the tipping bucket will prevent the tipping bucket from turning, and may cause errors in the measurement of rainfall.
近年来，国家在2004年出台了由气象站，到省级、国家级资料部门的地面自动站观测资料三级质量控制业务系统，其中各级质量控制方法仍以传统方法为主，如：格式检查-极值检查-内部一致性检查-时间一致性检查-空间一致性检查-人机交互检查。国外，尤其北欧各国在气象资料的质量控制规范化和技术上都处于世界先进行列，所用的空间质量控制方法主要有：Madsen-Allerup方法(丹麦)、DEC-WIM方法(挪威)、数值预报模式(HIRLAM)插值方法(挪威)、Kriging统计差值模式(芬兰)、MESAN方法(瑞典)等。但自然降雨具有时空分布不均匀、降水面积和强度变化大的特点，常规的质量控制方法并不能很好地对其进行判别。而雷达能实时探测云和降水结构及系统发生、发展演变情况，能迅速提供一定区域的实时降水情况。雷达站测的数据空间分布合理的优点，已经被广泛地应用于科研及业务应用各领域。In recent years, in 2004, the state introduced a three-level quality control business system for observation data from meteorological stations to provincial and national data departments from ground automatic stations. Among them, the quality control methods at all levels are still dominated by traditional methods, such as: Check - Extremum Check - Internal Consistency Check - Time Consistency Check - Spatial Consistency Check - Human-Computer Interaction Check. Foreign countries, especially the Nordic countries, are in the world's advanced ranks in the standardization and technology of meteorological data quality control. The main spatial quality control methods used are: Madsen-Allerup method (Denmark), DEC-WIM method (Norway), numerical prediction model ( HIRLAM) interpolation method (Norway), Kriging statistical difference model (Finland), MESAN method (Sweden), etc. However, natural rainfall has the characteristics of uneven spatial and temporal distribution, large variation of rainfall area and intensity, and conventional quality control methods cannot distinguish it well. Radar can detect cloud and precipitation structure and system occurrence, development and evolution in real time, and can quickly provide real-time precipitation in a certain area. The advantages of the reasonable spatial distribution of the data measured by the radar station have been widely used in various fields of scientific research and business applications.
多普勒天气雷达测量降雨一般使用Z＝ARb(Z-雷达反射率，R-降雨强度)，这是根据实测降雨强度和雨滴谱资料统计的结果得到的经验公式。但由于参数和降雨的类型以及季节、地域等关系很大，致使参数A、b在较大的范围内变动。新一代多普勒天气雷达采用单一的Z-R关系而忽略了这些降雨细节特征，造成局部区域降雨量测量值误差较大。Doppler weather radar generally uses Z=AR b (Z-radar reflectivity, R-rainfall intensity), which is an empirical formula obtained based on the results of measured rainfall intensity and raindrop spectral data. However, due to the great relationship between the parameters and the type of rainfall, season and region, the parameters A and b vary within a large range. The new generation of Doppler weather radar uses a single ZR relationship and ignores these detailed characteristics of rainfall, resulting in large errors in rainfall measurements in local areas.
可见，现有技术主要集中应用在雷达信息对雨量观测点数据的质量控制以及雷达信息预测降雨方向，在结合实测降雨和雷达信息率定参数的方面研究得极少。It can be seen that the existing technologies are mainly applied in the quality control of the data of the rainfall observation points by the radar information and the prediction of the rainfall direction by the radar information, and there is very little research in the aspect of combining the measured rainfall and the radar information to calibrate the parameters.
基于上述分析，如何结合实测降雨和雷达图精确的进行降雨分析，是需要解决的技术问题。Based on the above analysis, it is a technical problem that needs to be solved how to accurately analyze rainfall in combination with the measured rainfall and radar images.
发明内容SUMMARY OF THE INVENTION
本发明的技术任务是针对以上不足，提供一种基于雷达图的降雨分析模型构建方法、构建系统及分析方法，来解决如何结合实测降雨和雷达图精确的进行降雨分析的问题。The technical task of the present invention is to address the above deficiencies, and provide a method for building a rainfall analysis model, a building system and an analysis method based on radar charts, so as to solve the problem of how to accurately analyze rainfall in combination with measured rainfall and radar charts.
第一方面，本发明提供一种基于雷达图的降雨分析模型构建方法，包括：In a first aspect, the present invention provides a method for building a rainfall analysis model based on a radar chart, comprising:
获取不同时间的雷达图，对于每个雷达图，通过多点配准方法对雷达图和GIS地图进行地理位置配准，配准后雷达图中每个点的坐标与GIS地图坐标匹配；Obtain radar maps at different times, and for each radar map, perform geographic registration on the radar map and GIS map through the multi-point registration method. After registration, the coordinates of each point in the radar map match the coordinates of the GIS map;
将每个配准后雷达图网格划分为多个碎片雷达图，每个碎片雷达图匹配有至少一个雨量测量站；Divide each registered radar map grid into multiple fragment radar maps, and each fragment radar map is matched with at least one rainfall measuring station;
对于每个碎片雷达图，提取所述碎片雷达图的雷达回波数据，并采集所述碎片雷达图对应的所有雨量测量站测得的实际降雨量，分别按照时间顺序将所述碎片雷达图对应的雷达回波数据以及实际降雨量各存储为一组；For each debris radar map, extract the radar echo data of the debris radar map, collect the actual rainfall measured by all the rainfall measurement stations corresponding to the debris radar map, and map the debris radar maps corresponding to the time sequence respectively. The radar echo data and the actual rainfall are stored as a group;
构建降雨分析模型，所述降雨分析模型为Z-R关系模型，Z-R关系模型的表达式为：A rainfall analysis model is constructed, the rainfall analysis model is a Z-R relational model, and the expression of the Z-R relational model is:
Z＝ARb Z=AR b
其中，Z表示雷达回波数据，R为降雨量，A和b为待测参数；Among them, Z represents radar echo data, R is rainfall, A and b are parameters to be measured;
对于每个碎片雷达图，以所述碎片雷达图对应的不同时间的雷达回波数据以及实际降雨量为训练样本，训练所述降雨分析模型并优化参数A和b，得到所述区域的区域降雨分析模型；For each debris radar image, take the radar echo data at different times corresponding to the debris radar image and the actual rainfall as training samples, train the rainfall analysis model and optimize the parameters A and b to obtain the regional rainfall in the area Analytical model;
对于每个时间，以所述时间对应的各个碎片雷达图的雷达回波数据以及实实际降雨量际降雨量为训练样本，训练所述降雨分析模型并优化参数A和b，得到所述时段的时段降雨分析模型。For each time, take the radar echo data of each fragment radar image corresponding to the time and the actual rainfall as training samples, train the rainfall analysis model and optimize the parameters A and b to obtain the Time period rainfall analysis model.
作为优选，通过ArcGIS的clip工具对雷达图进行网格划分。Preferably, the radar map is meshed by the clip tool of ArcGIS.
作为优选，对于每个碎片雷达图，基于雷达图中颜色与雷达回波强度的不同，提取所述碎片雷达图的雷达回波数据，包括如下步骤：Preferably, for each radar image of debris, based on the difference between the color in the radar image and the intensity of the radar echo, extracting the radar echo data of the radar image of the debris includes the following steps:
通过opencv对碎片雷达图像进行图片色彩识别，将像素点的RGB值转换为Lab颜色模型表示值；Perform image color recognition on fragmented radar images through opencv, and convert the RGB values of pixels to the values represented by the Lab color model;
计算像素点的Lab颜色模型表示值与标准颜色值之间的差值，并选取差值最小的像素点的颜色作为所述碎片雷达图的标准色；Calculate the difference between the Lab color model representation value of the pixel and the standard color value, and select the color of the pixel with the smallest difference as the standard color of the fragment radar chart;
以所述标准色对应的雷达回波数据作为所述碎片雷达图像的雷达回波数据。The radar echo data corresponding to the standard color is used as the radar echo data of the debris radar image.
作为优选，上述每组雷达回波数据以及每组实际降雨量均存储于分布式存储系统；Preferably, each group of radar echo data and each group of actual rainfall are stored in a distributed storage system;
以上述雷达回波数据以及实际降雨量作为训练样本之前，通过分布式存储系统对所述每组雷达回波数据以及每组实际降雨量进行预处理，所述预处理包括：Before using the above-mentioned radar echo data and actual rainfall as training samples, each group of radar echo data and each group of actual rainfall is preprocessed through a distributed storage system, and the preprocessing includes:
设定雷达回波阈值范围，对于每组雷达回波数据中超出雷达回波阈值范围的异常数据，进行删除；Set the radar echo threshold range, and delete the abnormal data that exceeds the radar echo threshold range in each group of radar echo data;
设定降雨量阈值范围，对于每组实际降雨量中超出降雨量阈值范围的异常数据，进行删除。Set the rainfall threshold range, and delete the abnormal data that exceeds the rainfall threshold range in each group of actual rainfall.
第二方面，本发明提供一种基于雷达图的降雨分析模型构建系统，包括：In a second aspect, the present invention provides a system for building a rainfall analysis model based on a radar chart, comprising:
坐标匹配模块，所述坐标匹配模块用于通过多点配准方法对雷达图和GIS地图进行地理位置配准，配准后雷达图中每个点的坐标与GIS地图坐标匹配；a coordinate matching module, the coordinate matching module is used to perform geographic location registration on the radar map and the GIS map through a multi-point registration method, and the coordinates of each point in the radar map match the coordinates of the GIS map after registration;
区域划分模块，所述区域划分模块用于将每个配准后雷达图网格划分为多个碎片雷达图，每个碎片雷达图匹配有至少一个雨量测量站；an area division module, the area division module is used to divide each registered radar image grid into a plurality of fragment radar images, and each fragment radar image is matched with at least one rainfall measuring station;
数据采集模块，所述数据采集模块用于提取碎片雷达图的雷达回波数据，并采集碎片雷达图对应的所有雨量测量站测得的实际降雨量，分别按照时间顺序将碎片雷达图对应的雷达回波数据以及实际降雨量各存储为一组；A data acquisition module, the data acquisition module is used to extract radar echo data of the debris radar map, and collect the actual rainfall measured by all the rainfall measuring stations corresponding to the debris radar map, respectively, according to the time sequence of the radar corresponding to the debris radar map. The echo data and the actual rainfall are stored as a group;
存储模块，所述存储模块用于存储上述每组雷达回波数据以及每组实际降雨量；a storage module, the storage module is used to store each group of radar echo data and each group of actual rainfall;
模型构建模块，所述模型构建模块用于构建降雨分析模型，所述降雨分析模型为Z-R关系模型，Z-R关系模型的表达式为：A model building module, the model building module is used to build a rainfall analysis model, and the rainfall analysis model is a Z-R relational model, and the expression of the Z-R relational model is:
Z＝ARb Z=AR b
其中，Z表示雷达回波数据，R为降雨量，A和b为待测参数；Among them, Z represents radar echo data, R is rainfall, A and b are parameters to be measured;
模型训练模块，所述模型训练模块用于对于每个碎片雷达图，以所述碎片雷达图对应的不同时间的雷达回波数据以及实际降雨量为训练样本，训练所述降雨分析模型并优化参数A和b，得到所述区域的区域降雨分析模型；并用于对于每个时间，以所述时间对应的各个碎片雷达图的雷达回波数据以及实际降雨量为训练样本，训练所述降雨分析模型并优化参数A和b，得到所述时段的时段降雨分析模型。A model training module, which is used to train the rainfall analysis model and optimize parameters for each radar image of debris, using radar echo data at different times and actual rainfall corresponding to the radar image of the debris as training samples A and b, obtain the regional rainfall analysis model of the area; and for each time, use the radar echo data of each fragment radar image corresponding to the time and the actual rainfall as training samples to train the rainfall analysis model And optimize the parameters A and b to obtain the period rainfall analysis model of the period.
作为优选，区域划分模块通过ArcGIS的clip工具对雷达图进行网格划分。Preferably, the area division module performs grid division on the radar map through the clip tool of ArcGIS.
作为优选，数据采集模块用于基于雷达图中颜色与雷达回波强度的不同，提取所述碎片雷达图的雷达回波数据，包括如下步骤：Preferably, the data acquisition module is configured to extract the radar echo data of the debris radar image based on the difference between the color in the radar image and the intensity of the radar echo, including the following steps:
通过opencv对碎片雷达图像进行图片色彩识别，将像素点的RGB值转换为Lab颜色模型表示值；Perform image color recognition on fragmented radar images through opencv, and convert the RGB values of pixels to the values represented by the Lab color model;
计算像素点的Lab颜色模型表示值与标准颜色值之间的差值，并选取差值最小的像素点的颜色作为所述碎片雷达图的标准色；Calculate the difference between the Lab color model representation value of the pixel and the standard color value, and select the color of the pixel with the smallest difference as the standard color of the fragment radar chart;
以所述标准色对应的雷达回波数据作为所述碎片雷达图像的雷达回波数据。The radar echo data corresponding to the standard color is used as the radar echo data of the debris radar image.
作为优选，所述存储模块为分布式存储系统；Preferably, the storage module is a distributed storage system;
分布式存储系统用于对每组雷达回波数据以及每组实际降雨量进行预处理，所述预处理包括：The distributed storage system is used to preprocess each group of radar echo data and each group of actual rainfall, and the preprocessing includes:
设定雷达回波阈值范围，对于每组雷达回波数据中超出雷达回波阈值范围的异常数据，进行删除；Set the radar echo threshold range, and delete the abnormal data that exceeds the radar echo threshold range in each group of radar echo data;
设定降雨量阈值范围，对于每组实际降雨量中超出降雨量阈值范围的异常数据，进行删除。Set the rainfall threshold range, and delete the abnormal data that exceeds the rainfall threshold range in each group of actual rainfall.
第三方面，本发明提供一种基于雷达图的降雨分析方法，包括如下步骤：In a third aspect, the present invention provides a method for analyzing rainfall based on a radar chart, comprising the following steps:
通过如第一方面任一项所述的基于雷达图的降雨分析模型构建方法构建降雨分析模型，得到区域降雨分析模型和时段降雨分析模型；A rainfall analysis model is constructed by using the radar chart-based rainfall analysis model construction method according to any one of the first aspects, to obtain a regional rainfall analysis model and a period rainfall analysis model;
基于区域降雨分析模型，获取所述区域降雨分析模型对应的雷达回波数据和实际降雨量为测试样本，以所述测试样本输入对应的区域降雨分析模型，得到所述区域对应的降雨分析；Based on the regional rainfall analysis model, the radar echo data and actual rainfall corresponding to the regional rainfall analysis model are obtained as test samples, and the test samples are input into the corresponding regional rainfall analysis model to obtain the rainfall analysis corresponding to the region;
基于时段降雨分析模型，获取所述时段降雨分析模型对应的雷达回波数据和实际降雨量为测试样本，以所述测试样本输入对应的时段降雨分析模型，得到所述时段对应的降雨分析。Based on the period rainfall analysis model, the radar echo data and actual rainfall corresponding to the period rainfall analysis model are obtained as test samples, and the test samples are input into the corresponding period rainfall analysis model to obtain the rainfall analysis corresponding to the period.
本发明的基于雷达图的降雨分析模型构建方法、构建系统及分析方法具有以下优点：通过网格划分将雷达图划分为多个碎片雷达图，每个碎片雷达图对应至少一个雨量测量站，从而通过精细化区域切分定点划定测站点监测区域，同时可将该碎片雷达图对应的雷达回波数据以及相应的雨量测量站实时提取的实际降雨量进行全局性关联分析，实现Z-R关系模型在不同条件(区域及时段)下参数的有效率定，提高实测雨量数据的质量控制以及利用雷达资料对未来短时降雨预测的可靠性。The radar map-based rainfall analysis model construction method, construction system and analysis method of the present invention have the following advantages: the radar map is divided into a plurality of fragment radar maps by grid division, and each fragment radar map corresponds to at least one rainfall measurement station, thereby The monitoring area of the station is demarcated by the refined area segmentation and fixed point. At the same time, the radar echo data corresponding to the radar image of the debris and the actual rainfall extracted in real time by the corresponding rainfall measuring station can be globally correlated and analyzed, so as to realize the Z-R relationship model in the Effective determination of parameters under different conditions (regions and time periods) improves the quality control of measured rainfall data and the reliability of future short-term rainfall predictions using radar data.
附图说明Description of drawings
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例中描述中所需要使用的附图作简要介绍，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，对于本领域的普通技术人员来讲，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。In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.
下面结合附图对本发明进一步说明。The present invention will be further described below with reference to the accompanying drawings.
附图1为实施例1基于雷达图的降雨分析模型构建方法的流程框图。FIG. 1 is a flowchart of a method for constructing a rainfall analysis model based on a radar chart in Embodiment 1. FIG.
具体实施方式Detailed ways
下面结合附图和具体实施例对本发明作进一步说明，以使本领域的技术人员可以更好地理解本发明并能予以实施，但所举实施例不作为对本发明的限定，在不冲突的情况下，本发明实施例以及实施例中的技术特征可以相互结合。The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention, and in the case of no conflict Hereinafter, the embodiments of the present invention and the technical features in the embodiments may be combined with each other.
本发明实施例提供一种基于雷达图的降雨分析模型构建方法、构建系统及分析方法，用于解决如何结合实测降雨和雷达图精确的进行降雨分析的技术问题。Embodiments of the present invention provide a method for building a rainfall analysis model, a building system, and an analysis method based on radar charts, which are used to solve the technical problem of how to accurately perform rainfall analysis in combination with measured rainfall and radar charts.
实施例1：Example 1:
本发明的一种基于雷达图的降雨分析模型构建方法，包括如下步骤：A method for constructing a radar chart-based rainfall analysis model of the present invention includes the following steps:
S100、获取不同时间的雷达图，对于每个雷达图，通过多点配准方法对雷达图和GIS地图进行地理位置配准，配准后雷达图中每个点的坐标与GIS地图坐标匹配；S100 , obtaining radar maps at different times, and for each radar map, perform geographic registration on the radar map and the GIS map through a multi-point registration method, and after the registration, the coordinates of each point in the radar map match the coordinates of the GIS map;
S200、将每个配准后雷达图网格划分为多个碎片雷达图，每个碎片雷达图匹配有至少一个雨量测量站；S200. Divide each registered radar map grid into a plurality of fragment radar maps, and each fragment radar map is matched with at least one rainfall measuring station;
S300、对于每个碎片雷达图，提取所述碎片雷达图的雷达回波数据，并采集所述碎片雷达图对应的所有雨量测量站测得的实际降雨量，分别按照时间顺序将所述碎片雷达图对应的雷达回波数据以及实际降雨量各存储为一组；S300. For each debris radar map, extract radar echo data of the debris radar map, collect the actual rainfall measured by all the rainfall measuring stations corresponding to the debris radar map, and classify the debris radar images in chronological order. The radar echo data corresponding to the map and the actual rainfall are stored as a group;
S400、构建降雨分析模型，所述降雨分析模型为Z-R关系模型，Z-R关系模型的表达式为：S400, construct a rainfall analysis model, the rainfall analysis model is a Z-R relational model, and the expression of the Z-R relational model is:
Z＝ARb Z=AR b
其中，Z表示雷达回波数据，R为降雨量，A和b为待测参数；Among them, Z represents radar echo data, R is rainfall, A and b are parameters to be measured;
S500、对于每个碎片雷达图，以所述碎片雷达图对应的不同时间的雷达回波数据以及实际降雨量为训练样本，训练所述降雨分析模型并优化参数A和b，得到所述区域的区域降雨分析模型；S500. For each radar image of debris, take the radar echo data at different times corresponding to the radar image of the debris and the actual rainfall as training samples, train the rainfall analysis model and optimize parameters A and b to obtain the area of Regional rainfall analysis model;
对于每个时间，以所述时间对应的各个碎片雷达图的雷达回波数据以及实际降雨量为训练样本，训练所述降雨分析模型并优化参数A和b，得到所述时段的时段降雨分析模型。For each time, take the radar echo data and actual rainfall of each fragment radar image corresponding to the time as training samples, train the rainfall analysis model and optimize parameters A and b to obtain the time period rainfall analysis model for the period .
具体方法为在雷达图上选取多个点，然后进行X坐标和Y坐标确定，通过多个点与地图坐标进行匹配，选择的点越多，匹配的精度就越高。The specific method is to select multiple points on the radar map, then determine the X and Y coordinates, and match the multiple points with the map coordinates. The more points selected, the higher the matching accuracy.
其中，雷达图更新频率为6分钟一张，基于该频率，获取不同时间的雷达图，通过ArcGIS的clip工具对雷达图进行网格划分。Among them, the update frequency of the radar map is one every 6 minutes. Based on this frequency, the radar maps at different times are obtained, and the radar maps are divided into grids by the clip tool of ArcGIS.
雷达图中，从蓝色到紫色逐渐变化，代表回波强度有小到大变化，基于雷达图中颜色与雷达回波强度的不同，获取碎片雷达图的颜色以得到对应的雷达回波数据。基于上述原理，对于每个碎片雷达图，基于雷达图中颜色与雷达回波强度的不同，提取该碎片雷达图的雷达回波数据，具体包括如下步骤：In the radar chart, it gradually changes from blue to purple, indicating that the echo intensity changes from small to large. Based on the difference between the color in the radar chart and the radar echo intensity, the color of the debris radar chart is obtained to obtain the corresponding radar echo data. Based on the above principles, for each radar image of debris, based on the difference between the color in the radar image and the intensity of the radar echo, the radar echo data of the radar image of the fragment is extracted, which specifically includes the following steps:
(1)通过opencv对碎片雷达图像进行图片色彩识别，将像素点的RGB值转换为Lab颜色模型表示值；(1) Perform image color recognition on the fragment radar image through opencv, and convert the RGB value of the pixel point to the value represented by the Lab color model;
(2)计算像素点的Lab颜色模型表示值与标准颜色值之间的差值，并选取差值最小的像素点的颜色作为该碎片雷达图的标准色；(2) Calculate the difference between the Lab color model representation value of the pixel and the standard color value, and select the color of the pixel with the smallest difference as the standard color of the fragment radar map;
(3)以标准色对应的雷达回波数据作为该碎片雷达图像的雷达回波数据。(3) The radar echo data corresponding to the standard color is used as the radar echo data of the debris radar image.
步骤S300中，上述每组雷达回波数据以及每组实际降雨量均存储于分布式存储系统。In step S300, each group of radar echo data and each group of actual rainfall are stored in a distributed storage system.
上述雷达回波数据以及实际降雨量作为训练样本之前，通过分布式存储系统对每组雷达回波数据以及每组实际降雨量进行预处理，预处理包括如下步骤：Before the above-mentioned radar echo data and actual rainfall are used as training samples, each group of radar echo data and each group of actual rainfall is preprocessed through a distributed storage system. The preprocessing includes the following steps:
(1)设定雷达回波阈值范围，对于每组雷达回波数据中超出雷达回波阈值范围的异常数据，进行删除；(1) Set the radar echo threshold range, and delete the abnormal data that exceeds the radar echo threshold range in each group of radar echo data;
(2)设定降雨量阈值范围，对于每组实际降雨量中超出降雨量阈值范围的异常数据，进行删除。(2) Set the rainfall threshold range, and delete the abnormal data that exceeds the rainfall threshold range in each group of actual rainfall.
本发明公开的降雨分析模型构建方法，通过网格划分将雷达图划分为多个碎片雷达图，并将提取的雷达回波数据和实际降雨量按照时间和区域分布存储，并以上述数据为训练样本，得到区域降雨分析模型和时段降雨分析模型，通过区域降雨分析模型和时段降雨分析模型可对未来短时降雨进行可靠预测。The method for constructing a rainfall analysis model disclosed in the present invention divides a radar image into a plurality of fragmented radar images through grid division, stores the extracted radar echo data and actual rainfall according to time and regional distribution, and uses the above data as training The regional rainfall analysis model and the period rainfall analysis model are obtained, and the short-term rainfall in the future can be reliably predicted through the regional rainfall analysis model and the period rainfall analysis model.
实施例2：Example 2:
本发明提供一种基于雷达图的降雨分析模型构建系统，包括坐标匹配模块、区域划分模块、数据采集模块、存储模块、模型构建模块以及模型训练模块。The invention provides a rainfall analysis model construction system based on radar chart, which includes a coordinate matching module, an area division module, a data acquisition module, a storage module, a model construction module and a model training module.
坐标匹配模块用于通过多点配准方法对雷达图和GIS地图进行地理位置配准，配准后雷达图中每个点的坐标与GIS地图坐标匹配。The coordinate matching module is used to perform geographic registration on the radar map and the GIS map through the multi-point registration method. After the registration, the coordinates of each point in the radar map match the coordinates of the GIS map.
区域划分模块用于将每个配准后雷达图网格划分为多个碎片雷达图，每个碎片雷达图匹配有至少一个雨量测量站。区域划分模块通过ArcGIS的clip工具对雷达图进行网格划分。The area division module is used to divide each registered radar map grid into a plurality of fragment radar maps, and each fragment radar map is matched with at least one rainfall measuring station. The area division module uses the ArcGIS clip tool to mesh the radar map.
雷达图中，从蓝色到紫色逐渐变化，代表回波强度有小到大变化，基于雷达图中颜色与雷达回波强度的不同，获取碎片雷达图的颜色以得到对应的雷达回波数据。基于上述原理，对于每个碎片雷达图，基于雷达图中颜色与雷达回波强度的不同，提取该碎片雷达图的雷达回波数据，具体包括如下步骤：In the radar chart, it gradually changes from blue to purple, indicating that the echo intensity changes from small to large. Based on the difference between the color in the radar chart and the radar echo intensity, the color of the debris radar chart is obtained to obtain the corresponding radar echo data. Based on the above principles, for each radar image of debris, based on the difference between the color in the radar image and the intensity of the radar echo, the radar echo data of the radar image of the fragment is extracted, which specifically includes the following steps:
(1)通过opencv对碎片雷达图像进行图片色彩识别，将像素点的RGB值转换为Lab颜色模型表示值；(1) Perform image color recognition on the fragment radar image through opencv, and convert the RGB value of the pixel point to the value represented by the Lab color model;
(2)计算像素点的Lab颜色模型表示值与标准颜色值之间的差值，并选取差值最小的像素点的颜色作为该碎片雷达图的标准色；(2) Calculate the difference between the Lab color model representation value of the pixel and the standard color value, and select the color of the pixel with the smallest difference as the standard color of the fragment radar map;
(3)以标准色对应的雷达回波数据作为该碎片雷达图像的雷达回波数据。(3) The radar echo data corresponding to the standard color is used as the radar echo data of the debris radar image.
数据采集模块用于提取碎片雷达图的雷达回波数据，并采集碎片雷达图对应的所有雨量测量站测得的实际降雨量，分别按照时间顺序将碎片雷达图对应的雷达回波数据以及实际降雨量各存储为一组。The data acquisition module is used to extract the radar echo data of the debris radar map, and collect the actual rainfall measured by all the rainfall measurement stations corresponding to the debris radar map, and collect the radar echo data corresponding to the debris radar map and the actual rainfall in chronological order. Each quantity is stored as a group.
存储模块为分布式数据库，用于存储上述每组雷达回波数据以及每组实际降雨量。该存储模块用于对每组雷达回波数据以及每组实际降雨量进行预处理，预处理包括如下步骤：The storage module is a distributed database for storing each group of radar echo data and the actual rainfall of each group. The storage module is used to preprocess each group of radar echo data and each group of actual rainfall. The preprocessing includes the following steps:
(1)设定雷达回波阈值范围，对于每组雷达回波数据中超出雷达回波阈值范围的异常数据，进行删除；(1) Set the radar echo threshold range, and delete the abnormal data that exceeds the radar echo threshold range in each group of radar echo data;
(2)设定降雨量阈值范围，对于每组实际降雨量中超出降雨量阈值范围的异常数据，进行删除。(2) Set the rainfall threshold range, and delete the abnormal data that exceeds the rainfall threshold range in each group of actual rainfall.
模型构建模块用于构建降雨分析模型，该降雨分析模型为Z-R关系模型，Z-R关系模型的表达式为：The model building module is used to build a rainfall analysis model. The rainfall analysis model is a Z-R relational model. The expression of the Z-R relational model is:
Z＝ARb Z=AR b
其中，Z表示雷达回波数据，R为降雨量，A和b为待测参数；Among them, Z represents radar echo data, R is rainfall, A and b are parameters to be measured;
模型训练模块用于对于每个碎片雷达图，以碎片雷达图对应的不同时间的雷达回波数据以及实际降雨量为训练样本，训练降雨分析模型并优化参数A和b，得到该区域的区域降雨分析模型；并用于对于每个时间，以时间对应的各个碎片雷达图的雷达回波数据以及实际降雨量为训练样本，训练该降雨分析模型并优化参数A和b，得到该时段的时段降雨分析模型。The model training module is used to train the rainfall analysis model and optimize the parameters A and b to obtain the regional rainfall in the area by using the radar echo data at different times corresponding to the debris radar image and the actual rainfall as training samples for each debris radar image. Analysis model; and used to train the rainfall analysis model and optimize parameters A and b for each time, using the radar echo data and actual rainfall of each fragment radar map corresponding to the time as training samples, to obtain the period rainfall analysis of the period Model.
上述系统可实现实施例1公开的基于雷达图的降雨分析模型构建方法。The above-mentioned system can implement the method for constructing a rainfall analysis model based on a radar chart disclosed in Embodiment 1.
实施例3：Example 3:
本发明的一种基于雷达图的降雨分析方法，包括如下步骤：A radar-based rainfall analysis method of the present invention includes the following steps:
(1)通过实施例1公开的基于雷达图的降雨分析模型构建方法构建降雨分析模型，得到区域降雨分析模型和时段降雨分析模型；(1) Constructing a rainfall analysis model by the method for constructing a rainfall analysis model based on a radar chart disclosed in Embodiment 1 to obtain a regional rainfall analysis model and a time period rainfall analysis model;
(2)基于区域降雨分析模型，获取该区域降雨分析模型对应的雷达回波数据和实际降雨量为测试样本，以该测试样本输入对应的区域降雨分析模型，得到该区域对应的降雨分析；(2) Based on the regional rainfall analysis model, obtain the radar echo data and the actual rainfall corresponding to the regional rainfall analysis model as the test sample, input the corresponding regional rainfall analysis model with the test sample, and obtain the rainfall analysis corresponding to the region;
基于时段降雨分析模型，获取该时段降雨分析模型对应的雷达回波数据和实际降雨量为测试样本，以该测试样本输入对应的时段降雨分析模型，得到该时段对应的降雨分析。Based on the period rainfall analysis model, the radar echo data and actual rainfall corresponding to the period rainfall analysis model are obtained as test samples, and the test samples are input into the corresponding period rainfall analysis model to obtain the rainfall analysis corresponding to the period.
其中，上述获取雷达回波数据的方法同实施例1公开的方法一致。The above-mentioned method for acquiring radar echo data is the same as the method disclosed in Embodiment 1.
雷达图中，从蓝色到紫色逐渐变化，代表回波强度有小到大变化，基于雷达图中颜色与雷达回波强度的不同，获取碎片雷达图的颜色以得到对应的雷达回波数据。基于上述原理，对于每个碎片雷达图，基于雷达图中颜色与雷达回波强度的不同，提取该碎片雷达图的雷达回波数据，具体包括如下步骤：In the radar chart, it gradually changes from blue to purple, indicating that the echo intensity changes from small to large. Based on the difference between the color in the radar chart and the radar echo intensity, the color of the debris radar chart is obtained to obtain the corresponding radar echo data. Based on the above principles, for each radar image of debris, based on the difference between the color in the radar image and the intensity of the radar echo, the radar echo data of the radar image of the fragment is extracted, which specifically includes the following steps:
(1)通过opencv对碎片雷达图像进行图片色彩识别，将像素点的RGB值转换为Lab颜色模型表示值；(1) Perform image color recognition on the fragment radar image through opencv, and convert the RGB value of the pixel point to the value represented by the Lab color model;
(2)计算像素点的Lab颜色模型表示值与标准颜色值之间的差值，并选取差值最小的像素点的颜色作为该碎片雷达图的标准色；(2) Calculate the difference between the Lab color model representation value of the pixel and the standard color value, and select the color of the pixel with the smallest difference as the standard color of the fragment radar map;
(3)以标准色对应的雷达回波数据作为该碎片雷达图像的雷达回波数据。(3) The radar echo data corresponding to the standard color is used as the radar echo data of the debris radar image.
以上所述实施例仅是为充分说明本发明而所举的较佳的实施例，本发明的保护范围不限于此。本技术领域的技术人员在本发明基础上所作的等同替代或变换，均在本发明的保护范围之内。本发明的保护范围以权利要求书为准。The above-mentioned embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or transformations made by those skilled in the art on the basis of the present invention are all within the protection scope of the present invention. The protection scope of the present invention is subject to the claims.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910931683.5A CN110750516B (en) | 2019-09-29 | 2019-09-29 | Rainfall analysis model construction method, construction system and analysis method based on radar map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910931683.5A CN110750516B (en) | 2019-09-29 | 2019-09-29 | Rainfall analysis model construction method, construction system and analysis method based on radar map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110750516A true CN110750516A (en) | 2020-02-04 |
| CN110750516B CN110750516B (en) | 2023-10-31 |
Family
ID=69277352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910931683.5A Active CN110750516B (en) | 2019-09-29 | 2019-09-29 | Rainfall analysis model construction method, construction system and analysis method based on radar map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110750516B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111397686A (en) * | 2020-02-24 | 2020-07-10 | 广州风雨雷科技有限公司 | Urban waterlogging early warning method |
| CN111650572A (en) * | 2020-07-23 | 2020-09-11 | 浪潮云信息技术股份公司 | Method and system for reducing short-time rainfall estimation deviation |
| CN112364029A (en) * | 2021-01-12 | 2021-02-12 | 中国气象局气象探测中心 | Satellite-ground raindrop spectrum parameter matching and evaluating method and system |
| CN112731403A (en) * | 2021-03-17 | 2021-04-30 | 北京墨迹风云科技股份有限公司 | Precipitation prediction method and device |
| CN114488351A (en) * | 2022-02-10 | 2022-05-13 | 中国民用航空华东地区空中交通管理局 | An airport strong echo monitoring and early warning system and method |
| CN116468737A (en) * | 2023-04-10 | 2023-07-21 | 华能澜沧江水电股份有限公司 | Method and device for obtaining rainfall information |
| CN118859213A (en) * | 2024-09-23 | 2024-10-29 | 四创科技有限公司 | A method and system for regional precipitation prediction based on radar echo |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101533095A (en) * | 2009-04-16 | 2009-09-16 | 福州四创软件开发有限公司 | Early radar warning method based on GIS |
| JP2010197185A (en) * | 2009-02-25 | 2010-09-09 | National Research Institute For Earth Science & Disaster Provention | Estimating system of rainfall distribution, and estimation method of rainfall distribution |
| US20170357029A1 (en) * | 2016-06-14 | 2017-12-14 | The Climate Corporation | Supervised neural network to predict unlabeled rain rates |
-
2019
- 2019-09-29 CN CN201910931683.5A patent/CN110750516B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010197185A (en) * | 2009-02-25 | 2010-09-09 | National Research Institute For Earth Science & Disaster Provention | Estimating system of rainfall distribution, and estimation method of rainfall distribution |
| CN101533095A (en) * | 2009-04-16 | 2009-09-16 | 福州四创软件开发有限公司 | Early radar warning method based on GIS |
| US20170357029A1 (en) * | 2016-06-14 | 2017-12-14 | The Climate Corporation | Supervised neural network to predict unlabeled rain rates |
Non-Patent Citations (1)
| Title |
|---|
| 何健;王春林;毛夏;孙向明;: "利用雷达回波与GIS技术反演面雨量研究" * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111397686A (en) * | 2020-02-24 | 2020-07-10 | 广州风雨雷科技有限公司 | Urban waterlogging early warning method |
| CN111650572A (en) * | 2020-07-23 | 2020-09-11 | 浪潮云信息技术股份公司 | Method and system for reducing short-time rainfall estimation deviation |
| CN111650572B (en) * | 2020-07-23 | 2023-02-24 | 浪潮云信息技术股份公司 | Method and system for reducing short-time precipitation estimation deviation |
| CN112364029A (en) * | 2021-01-12 | 2021-02-12 | 中国气象局气象探测中心 | Satellite-ground raindrop spectrum parameter matching and evaluating method and system |
| CN112731403A (en) * | 2021-03-17 | 2021-04-30 | 北京墨迹风云科技股份有限公司 | Precipitation prediction method and device |
| CN114488351A (en) * | 2022-02-10 | 2022-05-13 | 中国民用航空华东地区空中交通管理局 | An airport strong echo monitoring and early warning system and method |
| CN116468737A (en) * | 2023-04-10 | 2023-07-21 | 华能澜沧江水电股份有限公司 | Method and device for obtaining rainfall information |
| CN116468737B (en) * | 2023-04-10 | 2024-07-26 | 华能澜沧江水电股份有限公司 | Rainfall information acquisition method and device |
| CN118859213A (en) * | 2024-09-23 | 2024-10-29 | 四创科技有限公司 | A method and system for regional precipitation prediction based on radar echo |
| CN118859213B (en) * | 2024-09-23 | 2024-12-03 | 四创科技有限公司 | Regional precipitation prediction method and system based on radar echo |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110750516B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110750516A (en) | Rainfall Analysis Model Construction Method, Construction System and Analysis Method Based on Radar Chart | |
| CN110363327B (en) | ConvLSTM and 3D-CNN-based short rainfall prediction method | |
| US20220043182A1 (en) | Spatial autocorrelation machine learning-based downscaling method and system of satellite precipitation data | |
| Kääb et al. | The new remote-sensing-derived Swiss glacier inventory: II. First results | |
| CN106780091B (en) | Remote sensing extraction method of agricultural disaster information based on spatiotemporal statistical characteristics of vegetation index | |
| CN110033132B (en) | Tropical cyclone forecasting method based on depth target detection and numerical weather forecast | |
| CN111665575B (en) | Medium-and-long-term rainfall grading coupling forecasting method and system based on statistical power | |
| CN103034858B (en) | A kind of secondary cluster segmentation method of satellite cloud picture | |
| Matasci et al. | Mapping tree canopies in urban environments using airborne laser scanning (ALS): A Vancouver case study | |
| CN118470550B (en) | A natural resource asset data collection method and platform | |
| CN110930048A (en) | Crop drought risk assessment system and method based on disaster mechanism process | |
| CN116486031B (en) | Urban renewal area identification method based on the fusion of time series remote sensing data and geographic big data | |
| CN114219847A (en) | Method and system for determining crop planting area based on phenological characteristics and storage medium | |
| CN116663764A (en) | Weather modification effect evaluation system | |
| Rich et al. | Detecting wind disturbance severity and canopy heterogeneity in boreal forest by coupling high-spatial resolution satellite imagery and field data | |
| CN108981616A (en) | A method of by unmanned plane laser radar inverting artificial forest effective leaf area index | |
| LU503276B1 (en) | Construction method of canopy interception model based on ground-based lidar point cloud data | |
| KR20230167856A (en) | Visibility Prediction Method using Tree-based Machine Learning Algorithm and Meteorological Forecasting Data | |
| CN117593657A (en) | Method and system for processing refined weather forecast data and readable storage medium | |
| CN118038289A (en) | Integrated estimation method and device for artificial surface | |
| CN118115333A (en) | A method for estimating regional carbon emissions based on multi-source heterogeneous data | |
| CN117523388A (en) | Urban different-stage identification method based on sub-pixel-level impervious surface change mode | |
| CN116416532A (en) | Disease strain diagnosis and strain shortage detection method, system, equipment and storage medium | |
| WO2023240509A1 (en) | Spatial probability analysis method and system based on correspondence between precipitation forecast and teleconnection | |
| CN115527108A (en) | A method for quickly identifying soil erosion and human-disturbed plots based on multi-temporal Sentinel-2 |
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 |