WO2020063529A1 - 基于随机森林算法的降水数据检测方法、装置及电子设备 - Google Patents

基于随机森林算法的降水数据检测方法、装置及电子设备 Download PDF

Info

Publication number
WO2020063529A1
WO2020063529A1 PCT/CN2019/107267 CN2019107267W WO2020063529A1 WO 2020063529 A1 WO2020063529 A1 WO 2020063529A1 CN 2019107267 W CN2019107267 W CN 2019107267W WO 2020063529 A1 WO2020063529 A1 WO 2020063529A1
Authority
WO
WIPO (PCT)
Prior art keywords
surface temperature
daytime
nighttime
precipitation data
sample area
Prior art date
Application number
PCT/CN2019/107267
Other languages
English (en)
French (fr)
Inventor
荆文龙
周成虎
姚凌
杨骥
Original Assignee
广州地理研究所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州地理研究所 filed Critical 广州地理研究所
Publication of WO2020063529A1 publication Critical patent/WO2020063529A1/zh

Links

Images

Classifications

    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]

Definitions

  • the invention relates to the field of meteorological information technology, in particular to a method, device and electronic equipment for detecting precipitation data based on a random forest algorithm.
  • Satellite microwave remote sensing technology can overcome this limitation and achieve precipitation observation on a global scale. / Visible light can only reflect information such as cloud thickness and cloud height. For satellite microwaves, they can penetrate cloud bodies, and use the interaction of precipitation particles and cloud particles with microwaves to detect clouds and rain more directly and realize precipitation data.
  • the existing satellite microwave remote sensing technology in areas covered by snow and ice, water bodies and desert areas, where the vegetation index (NDVI) is usually less than zero, is affected by anomalies such as water bodies, ice and snow, and the precipitation data monitoring is usually very error Big.
  • the object of the present invention is to provide a method for detecting precipitation data based on a random forest algorithm, which can detect precipitation data in areas where the vegetation index (NDVI) such as snow-covered areas, water bodies, and desert areas is generally less than zero.
  • NDVI vegetation index
  • a method for detecting precipitation data based on a random forest algorithm includes the following steps:
  • An optimal random forest algorithm model is established and trained according to the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index of the sample area, and satellite remote sensing precipitation data of the sample area.
  • the daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index of the sample area are used as input samples for the training optimal random forest algorithm model, and satellite remote sensing precipitation data of the sample area is used as the training.
  • Output samples of the optimal random forest algorithm model
  • the daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index of the area to be monitored are input into the optimal random forest algorithm model to obtain precipitation data of the area to be monitored.
  • the method for detecting precipitation data based on a random forest algorithm utilizes daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index, and remote sensing precipitation in a sample area of a sample area with satellite remote sensing precipitation data. Data, establish the optimal random forest algorithm model, and use this model to calculate the precipitation data in the data missing area, which can make up for the shortcomings of satellite remote sensing monitoring and improve the precipitation data.
  • an optimal random is established and trained according to the daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index of the sample area, and satellite remote sensing precipitation data of the sample area.
  • the forest algorithm model the following steps are also included:
  • Resampling the daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index of the first resolution of the sample area to the same second resolution as the satellite remote sensing precipitation data of the sample area Rate, wherein the second resolution is greater than the first resolution.
  • the daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model and vegetation index of the sample area are resampled to the same resolution as the satellite remote sensing precipitation data of the sample area. Rate, including the following steps:
  • the sample area is an area with a vegetation index greater than zero.
  • the present invention also provides a precipitation data detection device based on a random forest algorithm, including:
  • a first data acquisition module configured to obtain a daytime surface temperature and a nighttime surface temperature of the sample area, and obtain a day and night surface temperature difference of the sample area according to the daytime and nighttime surface temperature, and obtain a digital elevation model and sample of the sample area Regional vegetation index;
  • Random forest training module for establishing and training optimal random based on daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index of the sample area, and satellite remote sensing precipitation data of the sample area.
  • Forest algorithm model wherein daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index of the sample area are used as input samples for training the optimal random forest algorithm model, and satellites of the sample area Remote sensing precipitation data as output samples of the trained optimal random forest algorithm model;
  • the second data acquisition module is used to obtain the daytime surface temperature and nighttime surface temperature of the area to be monitored, and obtain the daytime and nighttime surface temperature difference of the area to be monitored according to the daytime surface temperature and nighttime surface temperature to be monitored, and obtain the area to be monitored Digital elevation model and vegetation index of the area to be monitored;
  • the precipitation data prediction module is configured to input daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the area to be monitored into the optimal random forest algorithm model to obtain the area to be monitored. Precipitation data.
  • the precipitation data detection device based on the random forest algorithm according to the present invention utilizes daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model and vegetation index, and remote sensing precipitation in the sample area of the sample area with satellite remote sensing precipitation data. Data, establish the optimal random forest algorithm model, and use this model to calculate the precipitation data in the data missing area, which can make up for the shortcomings of satellite remote sensing monitoring and improve the precipitation data.
  • the method further includes a resampling module for resampling the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the first resolution of the sample area, to The second resolution is the same as the satellite remote sensing precipitation data of the sample area, wherein the second resolution is greater than the first resolution.
  • the resampling module includes a resolution calculation unit, configured to calculate an average value of all the first resolution pixels in the range of the second resolution pixels.
  • the present invention also provides a computer-readable medium having stored thereon a computer program that, when executed by a processor, implements any of the above-mentioned methods for detecting precipitation data based on a random forest algorithm.
  • the present invention further provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable by the processor.
  • the processor executes the computer program, the processor implements the above-mentioned Any one of the precipitation data detection methods based on the random forest algorithm.
  • FIG. 1 is a schematic flowchart of a precipitation data detection method based on a random forest algorithm in an embodiment
  • FIG. 2 is a schematic flowchart of a method for detecting precipitation data based on a random forest algorithm in another embodiment
  • FIG. 3 is a schematic structural diagram of a precipitation data detection device based on a random forest algorithm in an embodiment
  • FIG. 4 is a schematic structural diagram of an electronic device in an embodiment.
  • a method for detecting precipitation data based on a random forest algorithm includes the following steps:
  • Step S10 Acquire the daytime surface temperature and the nighttime surface temperature of the sample area, and acquire the day and night surface temperature difference of the sample area according to the daytime surface temperature and the nighttime surface temperature.
  • the sample area is an area having satellite remote sensing precipitation data, and the size of the sample area is an integer multiple of the resolution of the satellite remote sensing data.
  • the daytime surface temperature is an average value of the surface temperature throughout the day
  • the nighttime surface temperature is the average value of the surface temperature throughout the night.
  • the daytime surface temperature and the nighttime surface temperature pass Acquired by a satellite sensor modis (moderate-resolution imaging spectroradiometer), the day and night temperature difference of the sample area is the difference between the daytime surface temperature and the nighttime surface temperature.
  • Step S20 Obtain the digital elevation model of the sample area and the vegetation index of the sample area.
  • the Digital Elevation Model (DEM), referred to as DEM, is a digital simulation of the ground terrain through limited terrain elevation data, that is, a digital representation of the terrain surface shape, which is a set of ordered numerical arrays that represent the ground elevation.
  • the vegetation index is a combination of satellite visible light and near-infrared bands based on the spectral characteristics of vegetation to form a vegetation coverage index for qualitative and quantitative evaluation of vegetation coverage and its growth vitality.
  • the value of the vegetation index is usually -1 to 1. In snow and ice, water bodies, and desert areas, the vegetation index is usually a constant less than zero. In one embodiment, the sample area is an area where the vegetation index is greater than zero.
  • Step S30 establishing and training an optimal random forest algorithm model according to the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index of the sample area, and satellite remote sensing precipitation data of the sample area,
  • the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the sample area are used as input samples for the training optimal random forest algorithm model, and satellite remote sensing precipitation data of the sample area is used as Output samples of the trained optimal random forest algorithm model.
  • the satellite remote sensing precipitation data in the sample area is the precipitation data monitored by satellite remote sensing in the sample area.
  • the optimal random forest algorithm model is a random forest where the error of the rainfall data calculation reaches the minimum after repeated training. Algorithm model.
  • Step S40 Acquire the daytime surface temperature and the nighttime surface temperature of the area to be monitored, and obtain the day and night surface temperature difference of the area to be monitored according to the daytime surface temperature and the nighttime surface temperature to be monitored.
  • the daytime surface temperature and the nighttime surface temperature of the area to be monitored are obtained by a satellite sensor modis (moderate-resolution imaging spectrometer).
  • Step S50 Obtain a digital elevation model of the area to be monitored and a vegetation index of the area to be monitored.
  • the area to be monitored is an area where satellite remote sensing precipitation data is missing, and in this embodiment, an area where the vegetation index is less than zero.
  • Step S60 The daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the area to be monitored are input into the optimal random forest algorithm model to obtain precipitation data of the area to be monitored.
  • the method for detecting precipitation data based on a random forest algorithm utilizes daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index, and remote sensing precipitation in a sample area of a sample area with satellite remote sensing precipitation data Data, establish the optimal random forest algorithm model, and use this model to calculate the precipitation data in the data missing area, which can make up for the shortcomings of satellite remote sensing monitoring and improve the precipitation data.
  • step S30 the method further includes the following steps:
  • Step S2A re-sampling the first resolution daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index of the first resolution of the sample area to the same as the satellite remote sensing precipitation data of the sample area A second resolution, wherein the second resolution is greater than the first resolution.
  • the first resolution of the daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model and vegetation index is usually 1km * 1km
  • the second resolution of satellite remote sensing precipitation data is usually 25km * 25km. Therefore, it is necessary to resample the daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index to the second resolution at the first resolution.
  • resampling the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index to the second resolution at the first resolution by calculating the second resolution pixel range
  • the average value of all first-resolution pixels is realized, that is, the average value of each 1km * 1km within a range of 25km * 25km is calculated.
  • Step S201 Acquire the daytime surface temperature and the nighttime surface temperature of the sample area, and calculate the day and night surface temperature difference.
  • Step S202 Obtain a digital elevation model of the sample area and a vegetation index of the sample area.
  • Step S203 Resampling the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the first resolution of the sample area.
  • Step S204 Establish the original sample set S according to the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the sample area.
  • Step S205 Extract k training sample sets from the original sample set S by the Bootstrap method.
  • Step S206 learning the k training sets to generate k decision tree models.
  • the decision tree generation process there are a total of 4 input variables, and n variables are randomly selected from the four variables. Each internal node is split using the optimal splitting method on the n characteristic variables, and the value of n is in a random forest. The formation of the model is a constant constant.
  • Step S207 Combine the results of the k decision trees, and repeat training to form an optimal random forest algorithm model.
  • Step S208 Acquire the daytime surface temperature and the nighttime surface temperature of the area to be monitored, and calculate the day and night surface temperature difference of the area to be monitored.
  • Step S209 Obtain a digital elevation model of the area to be monitored and a vegetation index of the area to be monitored.
  • Step S210 Resampling the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index of the first resolution of the area to be monitored to the second resolution.
  • Step S211 input the first resolution daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the resampled region to be monitored into the optimal random forest algorithm model to obtain the detection of the region to be detected Precipitation data.
  • the method for detecting precipitation data based on a random forest algorithm utilizes daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index, and remote sensing precipitation in a sample area of a sample area with satellite remote sensing precipitation data.
  • Data establish the optimal random forest algorithm model, and use this model to calculate the precipitation data in the missing areas of the data, which can make up for the shortcomings of satellite remote sensing monitoring, improve the precipitation data, and resample the parameters to obtain the most accurate Optimal random forest algorithm model, so as to more accurately detect precipitation in unknown areas.
  • the precipitation data detection device 30 based on the random forest algorithm of the present invention includes:
  • the first data acquisition module 31 is configured to obtain a daytime surface temperature and a nighttime surface temperature of the sample area, and obtain a day and night surface temperature difference of the sample area according to the daytime and nighttime surface temperature, and obtain a digital elevation model of the sample area and Vegetation index of the sample area;
  • the random forest training module 32 is configured to establish and train the optimal according to the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model and vegetation index of the sample area, and satellite remote sensing precipitation data of the sample area.
  • the random forest algorithm model wherein daytime surface temperature, nighttime surface temperature, day and night surface temperature difference, digital elevation model, and vegetation index of the sample area are used as input samples for training the optimal random forest algorithm model, and Satellite remote sensing precipitation data as output samples of the trained optimal random forest algorithm model;
  • the second data acquisition module 33 is configured to obtain the daytime surface temperature and the nighttime surface temperature of the area to be monitored, and obtain the daytime and nighttime surface temperature difference of the area to be monitored according to the daytime surface temperature and nighttime surface temperature to be monitored, and to obtain the area to be monitored Digital elevation model of the area and vegetation index of the area to be monitored;
  • the precipitation data prediction module 34 is configured to input the daytime surface temperature, nighttime surface temperature, nighttime surface temperature difference, digital elevation model, and vegetation index of the area to be monitored into the optimal random forest algorithm model to obtain the area to be monitored Precipitation data.
  • the method further includes a resampling module 35 for resampling the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the first resolution of the sample area.
  • a resampling module 35 for resampling the daytime surface temperature, nighttime surface temperature, daytime and nighttime surface temperature difference, digital elevation model, and vegetation index of the first resolution of the sample area. To the same second resolution as the satellite remote sensing precipitation data of the sample area, wherein the second resolution is greater than the first resolution.
  • the resampling module 35 includes a resolution calculation unit 351, configured to calculate an average value of all the first resolution pixels in the range of the second resolution pixels.
  • the present invention also provides a computer-readable medium on which a computer program is stored, and when the computer program is executed by a processor, the method for detecting precipitation data based on a random forest algorithm in any of the foregoing embodiments is implemented.
  • the electronic device 40 of the present invention includes a memory 41 and a processor 42, and a computer program stored in the memory 41 and executable by the processor 42.
  • the processor 42 When the computer program is executed, a method for detecting precipitation data based on a random forest algorithm in any of the foregoing embodiments is implemented.
  • the controller 42 may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programmable Gate array (FPGA), controller, microcontroller, microprocessor, or other electronic component.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable Gate array
  • controller microcontroller, microprocessor, or other electronic component.
  • the storage medium 41 may take the form of a computer program product implemented on one or more storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing program code.
  • Computer-readable storage media includes permanent and non-permanent, removable and non-removable media, and information can be stored by any method or technology.
  • Information may be computer-readable instructions, data structures, modules of a program, or other data.
  • Examples of computer storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media may be used to store information that can be accessed by computing devices.
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash memory or other memory technologies
  • CD-ROM compact disc read-only memory
  • DVD digital versatile disc
  • Magnetic tape cartridges magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media may be used to store information that can be accessed
  • the disclosed apparatus and method may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, which may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objective of the solution of this embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Development Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Game Theory and Decision Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Image Processing (AREA)

Abstract

基于随机森林算法的降水数据检测方法、装置及电子设备。所述的基于随机森林算法的降水数据检测方法包括如下步骤：根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型（S30）；将所述待监测区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入所述最优随机森林算法模型，获取所述待监测区域的降水数据（S60）。能够检测出冰雪覆盖区域、水体和沙漠区域等植被指数(NDVI)通常小于零的区域的降水数据。

Description

基于随机森林算法的降水数据检测方法、装置及电子设备 技术领域
本发明涉及气象信息技术领域，特别是涉及一种基于随机森林算法的降水数据检测方法、装置及电子设备。
背景技术
降水强烈的时空变化常使得常规地基台站的降水观测不能准确把握降水的空间分布和强度变化，而卫星微波遥感技术可以克服此局限，实现在全球范围内实现对降水的观测，而且相对于红外/可见光只能反映云厚、云高等信息而言，卫星微波能够穿透云体，利用云内降水粒子和云粒子与微波的相互作用对云、雨进行更为直接的探测，实现对降水数据的监测，然而，现有的卫星微波遥感技术，在冰雪覆盖区域、水体和沙漠区域等植被指数(NDVI)通常小于零的区域，受水体、冰雪等异常的影响，其降水数据监测通常误差很大。
发明内容
基于此，本发明的目的在于，提供一种基于随机森林算法的降水数据检测方法，其能够检测出冰雪覆盖区域、水体和沙漠区域等植被指数(NDVI)通常小于零的区域的降水数据。
本发明是通过如下方案实现的：
一种基于随机森林算法的降水数据检测方法，包括如下步骤：
获取样本区域的白天地表温度和夜间地表温度，并根据所述白天地表温度和夜间地表温度获取样本区域的昼夜地表温度差；
获取样本区域的数字高程模型和样本区域的植被指数；
根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型，其中，所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数作为所述训练最优随机森林算法模 型的输入样本，所述样本区域的卫星遥感降水数据作为所述训练最优随机森林算法模型的输出样本；
获取待监测区域的白天地表温度和夜间地表温度，并根据所述待监测的白天地表温度和夜间地表温度获取待监测区域的昼夜地表温度差；
获取待监测区域的数字高程模型和待监测区域的植被指数；
将所述待监测区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入所述最优随机森林算法模型，获取所述待监测区域的降水数据。
本发明所述的基于随机森林算法的降水数据检测方法，利用有卫星遥感降水数据的样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数以及样本区域的遥感降水数据，建立最优的随机森林算法模型，利用该模型，计算出数据缺失区域的降水数据，可以弥补卫星遥感监测的缺陷，完善降水数据。
在一种实施例中，根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型前，还包括如下步骤：
将所述样本区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样，至与所述样本区域的卫星遥感降水数据相同的第二分辨率，其中，第二分辨率大于第一分辨率。
在一种实施例中，将所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样，至与所述样本区域的卫星遥感降水数据相同的分辨率，包括如下步骤：
计算第二分辨率像元范围内，所有第一分辨率像元的平均值。
在一种实施例中，所述样本区域为植被指数大于零的区域。
进一步地，本发明还提供一种基于随机森林算法的降水数据检测装置，包括：
第一数据采集模块，用于获取样本区域的白天地表温度和夜间地表温度， 并根据所述白天地表温度和夜间地表温度获取样本区域的昼夜地表温度差，以及获取样本区域的数字高程模型和样本区域的植被指数；
随机森林训练模块，用于根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型，其中，所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数作为所述训练最优随机森林算法模型的输入样本，所述样本区域的卫星遥感降水数据作为所述训练最优随机森林算法模型的输出样本；
第二数据采集模块，用于获取待监测区域的白天地表温度和夜间地表温度，并根据所述待监测的白天地表温度和夜间地表温度获取待监测区域的昼夜地表温度差，以及获取待监测区域的数字高程模型和待监测区域的植被指数；
降水数据预测模块，用于将所述待监测区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入所述最优随机森林算法模型，获取所述待监测区域的降水数据。
本发明所述的基于随机森林算法的降水数据检测装置，利用有卫星遥感降水数据的样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数以及样本区域的遥感降水数据，建立最优的随机森林算法模型，利用该模型，计算出数据缺失区域的降水数据，可以弥补卫星遥感监测的缺陷，完善降水数据。
在一种实施例中，还包括重采样模块，用于将所述样本区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样，至与所述样本区域的卫星遥感降水数据相同的第二分辨率，其中，第二分辨率大于第一分辨率。
在一种实施例中，所述重采样模块包括分辨率计算单元，用于计算第二分辨率像元范围内，所有第一分辨率像元的平均值。
进一步地，本发明还提供一种计算机可读介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如上述任意一项基于随机森林算法的降水数 据检测方法。
进一步地，本发明还提供一种电子设备，包括存储器、处理器以及储存在所述存储器并可被所述处理器执行的计算机程序，所述处理器执行所述计算机程序时，实现如上述的任意一项基于随机森林算法的降水数据检测方法。
为了更好地理解和实施，下面结合附图详细说明本发明。
附图说明
图1为一种实施例中基于随机森林算法的降水数据检测方法流程示意图；
图2为另一种实施例中基于随机森林算法的降水数据检测方法流程示意图；
图3为一种实施例中基于随机森林算法的降水数据检测装置结构示意图；
图4为一种实施例中电子设备结构示意图。
具体实施方式
请参阅图1，在一种实施例中，基于随机森林算法的降水数据检测方法包括如下步骤：
步骤S10：获取样本区域的白天地表温度和夜间地表温度，并根据所述白天地表温度和夜间地表温度获取样本区域的昼夜地表温度差。
所述样本区域为有卫星遥感降水数据的区域，所述样本区域的大小为所述卫星遥感数据的分辨率大小的整数倍。所述白天地表温度为地表温度在整个白天内的平均值，所述夜间地表温度为地表温度在整个夜间的平均值，在一种实施例中，所述白天地表温度和所述夜间地表温度通过卫星传感器modis(中分辨率成像光谱仪moderate-resolution imaging spectroradiometer)获取，所述样本区域的昼夜温度差为所述白天地表温度和所述夜间地表温度之间的差值。
步骤S20：获取样本区域的数字高程模型和样本区域的植被指数。
所述数字高程模型(Digital Elevation Model)，简称DEM，是通过有限的地形高程数据实现对地面地形的数字化模拟，即地形表面形态的数字化表达，为一组有序数值阵列形式表示地面高程的一种实体地面模型，所述植被指数为 根据植被的光谱特性，将卫星可见光和近红外波段进行组合，形成的植被覆盖指标，定性和定量评价植被覆盖及其生长活力。植被指数的值通常为-1至1，在冰雪覆盖、水体及沙漠区域，植被指数通常为小于零的常数，在一种实施例中，所述样本区域为植被指数大于零的区域。
步骤S30：根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型，其中，所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数作为所述训练最优随机森林算法模型的输入样本，所述样本区域的卫星遥感降水数据作为所述训练最优随机森林算法模型的输出样本。
所述样本区域的卫星遥感降水数据，为所述样本区域内，通过卫星遥感所监测到的降水数据，所述最优随机森林算法模型为经反复训练后，降水数据计算误差达到最小的随机森林算法模型。
步骤S40：获取待监测区域的白天地表温度和夜间地表温度，并根据所述待监测的白天地表温度和夜间地表温度获取待监测区域的昼夜地表温度差。
在本实施例中，所述待监测区域的白天地表温度和所述夜间地表温度通过卫星传感器modis(中分辨率成像光谱仪moderate-resolution imaging spectroradiometer)获取。
步骤S50：获取待监测区域的数字高程模型和待监测区域的植被指数。
所述待监测区域为卫星遥感降水数据缺失区域，在本实施例中，为植被指数小于零的区域。
步骤S60：将所述待监测区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入所述最优随机森林算法模型，获取所述待监测区域的降水数据。
本发明所述的基于随机森林算法的降水数据检测方法，利用有卫星遥感降水数据的样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数以及样本区域的遥感降水数据，建立最优的随机森林算法模 型，利用该模型，计算出数据缺失区域的降水数据，可以弥补卫星遥感监测的缺陷，完善降水数据。
在一种实施例中，步骤S30前，还包括如下步骤：
步骤S2A：将所述样本区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样，至与所述样本区域的卫星遥感降水数据相同的第二分辨率，其中，第二分辨率大于第一分辨率。
其中，所述白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数的第一分辨率通常为1km*1km，而卫星遥感降水数据的第二分辨率通常为25km*25km，因此，需要将第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数重采样为第二分辨率。
在一种实施例中，将第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数重采样为第二分辨率，是通过计算第二分辨率像元范围内，所有第一分辨率像元的平均值来实现的，即计算25km*25km范围内，每个1km*1km的平均值。
请参阅图2，在一个具体的实施例中，包括如下步骤：
步骤S201：获取样本区域的白天地表温度和夜间地表温度，计算昼夜地表温度差。
步骤S202：获取样本区域的数字高程模型和样本区域的植被指数。
步骤S203：将所述样本区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样。
步骤S204：根据样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数建立原始样本集S。
步骤S205：通过Bootstrap方法在原始样本集S中抽取k个训练样本集。
步骤S206：对k个训练集进行学习，以此生成k个决策树模型。在决策树生成过程中，共有4个输入变量，从4个变量中随机抽取n个变量，各个内部节点均是利用这n个特征变量上最优的分裂方式来分裂，且n值在随机森林模型的形成过程中为恒定常数。
步骤S207：将k个决策树的结果进行组合，经反复训练，形成最优随机森林算法模型。
步骤S208：获取待监测区域的白天地表温度和夜间地表温度，计算待监测区域的昼夜地表温度差。
步骤S209：获取待监测区域的数字高程模型和待监测区域的植被指数。
步骤S210：将所述待监测区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样至第二分辨率。
步骤S211：将重采样的待监测区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入最优随机森林算法模型，获取该待检测区域的检测降水数据。
本发明所述的基于随机森林算法的降水数据检测方法，利用有卫星遥感降水数据的样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数以及样本区域的遥感降水数据，建立最优的随机森林算法模型，利用该模型，计算出数据缺失区域的降水数据，可以弥补卫星遥感监测的缺陷，完善降水数据，通过对各参数进行重采样，能更准确的获得最优随机森林算法模型，从而更准确的检测未知区域的降水量。
请参阅图3，在一个实施例中，本发明基于随机森林算法的降水数据检测装置30包括：
第一数据采集模块31，用于获取样本区域的白天地表温度和夜间地表温度，并根据所述白天地表温度和夜间地表温度获取样本区域的昼夜地表温度差，以及获取样本区域的数字高程模型和样本区域的植被指数；
随机森林训练模块32，用于根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型，其中，所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数作为所述训练最优随机森林算法模型的输入样本，所述样本区域的卫星遥感降水数据作为所述训练最优随机森林算法模型的输出样本；
第二数据采集模块33，用于获取待监测区域的白天地表温度和夜间地表温度，并根据所述待监测的白天地表温度和夜间地表温度获取待监测区域的昼夜地表温度差，以及获取待监测区域的数字高程模型和待监测区域的植被指数；
降水数据预测模块34，用于将所述待监测区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入所述最优随机森林算法模型，获取所述待监测区域的降水数据。
在一种实施例中，还包括重采样模块35，用于将所述样本区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样，至与所述样本区域的卫星遥感降水数据相同的第二分辨率，其中，第二分辨率大于第一分辨率。
在一种实施例中，所述重采样模块35包括分辨率计算单元351，用于计算第二分辨率像元范围内，所有第一分辨率像元的平均值。
本发明还提供一种计算机可读介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述任意一项实施例中的基于随机森林算法的降水数据检测方法。
请参阅图4，在一种实施例中，本发明的电子设备40包括存储器41和处理器42，以及储存在所述存储器41并可被所述处理器42执行的计算机程序，所述处理器42执行所述计算机程序时，实现如上述任意一项实施例中的基于随机森林算法的降水数据检测方法。
在本实施例中，控制器42可以是一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件。存储介质41可采用在一个或多个其中包含有程序代码的存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。计算机可读储存介质包括永久性和非永久性、可移动和非可移动媒体，可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括但不限于：相变内存(PRAM)、静 态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所披露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。

Claims (9)

  1. 一种基于随机森林算法的降水数据检测方法，其特征在于，包括如下步骤：
    获取样本区域的白天地表温度和夜间地表温度，并根据所述白天地表温度和夜间地表温度获取样本区域的昼夜地表温度差；
    获取样本区域的数字高程模型和样本区域的植被指数；
    根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型，其中，所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数作为所述训练最优随机森林算法模型的输入样本，所述样本区域的卫星遥感降水数据作为所述训练最优随机森林算法模型的输出样本；
    获取待监测区域的白天地表温度和夜间地表温度，并根据所述待监测的白天地表温度和夜间地表温度获取待监测区域的昼夜地表温度差；
    获取待监测区域的数字高程模型和待监测区域的植被指数；
    将所述待监测区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入所述最优随机森林算法模型，获取所述待监测区域的降水数据。
  2. 根据权利要求1所述的基于随机森林算法的降水数据检测方法，其特征在于，根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型前，还包括如下步骤：
    将所述样本区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样至与所述样本区域的卫星遥感降水数据相同的第二分辨率，其中，第二分辨率大于第一分辨率。
  3. 根据权利要求2所述的基于随机森林算法的降水数据检测方法，其特征在于，将所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数 字高程模型和植被指数进行重采样至与所述样本区域的卫星遥感降水数据相同的分辨率，包括如下步骤：
    计算第二分辨率像元范围内，所有第一分辨率像元的平均值。
  4. 根据权利要求1所述的基于随机森林算法的降水数据检测方法，其特征在于：
    所述样本区域为植被指数大于零的区域。
  5. 一种基于随机森林算法的降水数据检测装置，其特征在于，包括：
    第一数据采集模块，用于获取样本区域的白天地表温度和夜间地表温度，并根据所述白天地表温度和夜间地表温度获取样本区域的昼夜地表温度差，以及获取样本区域的数字高程模型和样本区域的植被指数；
    随机森林训练模块，用于根据所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数，以及所述样本区域的卫星遥感降水数据，建立并训练最优随机森林算法模型，其中，所述样本区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数作为所述训练最优随机森林算法模型的输入样本，所述样本区域的卫星遥感降水数据作为所述训练最优随机森林算法模型的输出样本；
    第二数据采集模块，用于获取待监测区域的白天地表温度和夜间地表温度，并根据所述待监测的白天地表温度和夜间地表温度获取待监测区域的昼夜地表温度差，以及获取待监测区域的数字高程模型和待监测区域的植被指数；
    降水数据预测模块，用于将所述待监测区域的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数输入所述最优随机森林算法模型，获取所述待监测区域的降水数据。
  6. 根据权利要求5所述的一种基于随机森林算法的降水数据检测装置，其特征在于：
    还包括重采样模块，用于将所述样本区域的第一分辨率的白天地表温度、夜间地表温度、昼夜地表温度差、数字高程模型和植被指数进行重采样，至与所述样本区域的卫星遥感降水数据相同的第二分辨率，其中，第二分辨率大于 第一分辨率。
  7. 根据权利要求6所述的一种基于随机森林算法的降水数据检测装置，其特征在于：
    所述重采样模块包括分辨率计算单元，用于计算第二分辨率像元范围内，所有第一分辨率像元的平均值。
  8. 一种计算机可读介质，其上存储有计算机程序，其特征在于：
    该计算机程序被处理器执行时实现如权利要求1至7任意一项基于随机森林算法的降水数据检测方法。
  9. 一种电子设备，包括存储器、处理器以及储存在所述存储器并可被所述处理器执行的计算机程序，其特征在于：
    所述处理器执行所述计算机程序时，实现如权利要求1至7所述的任意一项基于随机森林算法的降水数据检测方法。
PCT/CN2019/107267 2018-09-30 2019-09-23 基于随机森林算法的降水数据检测方法、装置及电子设备 WO2020063529A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811159069.3 2018-09-30
CN201811159069.3A CN109447325A (zh) 2018-09-30 2018-09-30 基于随机森林算法的降水数据检测方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2020063529A1 true WO2020063529A1 (zh) 2020-04-02

Family

ID=65544665

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/107267 WO2020063529A1 (zh) 2018-09-30 2019-09-23 基于随机森林算法的降水数据检测方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN109447325A (zh)
WO (1) WO2020063529A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109447325A (zh) * 2018-09-30 2019-03-08 广州地理研究所 基于随机森林算法的降水数据检测方法、装置及电子设备
CN110852149B (zh) * 2019-09-24 2022-10-04 广州地理研究所 基于分类和回归树算法的植被指数预测方法、系统及设备
CN110826764B (zh) * 2019-09-24 2020-11-24 广州地理研究所 基于随机森林算法的植被指数预测方法、系统及设备
CN110824586B (zh) * 2019-10-23 2021-11-19 上海理工大学 基于改进决策树算法的降水预测方法
CN111652404B (zh) * 2020-02-06 2023-04-28 北京师范大学 一种全天气地表温度反演方法和系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105760814A (zh) * 2016-01-25 2016-07-13 中国水利水电科学研究院 一种基于数据挖掘的干旱监测方法
CN106019408A (zh) * 2016-05-10 2016-10-12 浙江大学 一种基于多源遥感数据的高分辨率卫星遥感估算方法
CN106021868A (zh) * 2016-05-10 2016-10-12 浙江大学 一种基于多规则算法的遥感数据降尺度方法
US20160307073A1 (en) * 2015-04-20 2016-10-20 Los Alamos National Security, Llc Change detection and change monitoring of natural and man-made features in multispectral and hyperspectral satellite imagery
US20170161584A1 (en) * 2015-12-07 2017-06-08 The Climate Corporation Cloud detection on remote sensing imagery
CN109447325A (zh) * 2018-09-30 2019-03-08 广州地理研究所 基于随机森林算法的降水数据检测方法、装置及电子设备

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106021872A (zh) * 2016-05-10 2016-10-12 浙江大学 一种基于低分辨率卫星遥感数据的环境变量动态筛选建模降尺度方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160307073A1 (en) * 2015-04-20 2016-10-20 Los Alamos National Security, Llc Change detection and change monitoring of natural and man-made features in multispectral and hyperspectral satellite imagery
US20170161584A1 (en) * 2015-12-07 2017-06-08 The Climate Corporation Cloud detection on remote sensing imagery
CN105760814A (zh) * 2016-01-25 2016-07-13 中国水利水电科学研究院 一种基于数据挖掘的干旱监测方法
CN106019408A (zh) * 2016-05-10 2016-10-12 浙江大学 一种基于多源遥感数据的高分辨率卫星遥感估算方法
CN106021868A (zh) * 2016-05-10 2016-10-12 浙江大学 一种基于多规则算法的遥感数据降尺度方法
CN109447325A (zh) * 2018-09-30 2019-03-08 广州地理研究所 基于随机森林算法的降水数据检测方法、装置及电子设备

Also Published As

Publication number Publication date
CN109447325A (zh) 2019-03-08

Similar Documents

Publication Publication Date Title
WO2020063458A1 (zh) 空间降尺度降水数据检测方法、装置及电子设备
WO2020063529A1 (zh) 基于随机森林算法的降水数据检测方法、装置及电子设备
WO2020063461A1 (zh) 基于随机森林分类算法的城市范围提取方法、装置及电子设备
CN109522516B (zh) 基于随机森林回归算法的土壤湿度检测方法、装置及电子设备
Lehnert et al. Retrieval of grassland plant coverage on the Tibetan Plateau based on a multi-scale, multi-sensor and multi-method approach
CN110287457B (zh) 基于卫星雷达遥感数据的玉米生物量反演测算方法
Zhu et al. Mapping forest height using photon-counting LiDAR data and Landsat 8 OLI data: A case study in Virginia and North Carolina, USA
Huang et al. Mapping vegetation heights in China using slope correction ICESat data, SRTM, MODIS-derived and climate data
CN112434617B (zh) 一种基于多源遥感数据的森林生物量变化监测方法及系统
Yeom et al. Mapping rice area and yield in northeastern Asia by incorporating a crop model with dense vegetation index profiles from a geostationary satellite
CN115077656B (zh) 水库水储量反演方法和装置
Liu et al. Estimation of surface and near-surface air temperatures in arid northwest china using landsat satellite images
Zhang et al. Development of the direct-estimation albedo algorithm for snow-free Landsat TM albedo retrievals using field flux measurements
WO2022140836A1 (en) Method and system for producing a digital terrain model
Chelotti et al. Space-Temporal analysis of suspended sediment in low concentration reservoir by remote sensing
CN117075138A (zh) 一种区域30米森林冠层高度遥感测算方法、系统及介质
Zhu et al. High-precision sugarcane yield prediction by integrating 10-m Sentinel-1 VOD and Sentinel-2 GRVI indexes
Hartl et al. Small-scale spatial variability in bare-ice reflectance at Jamtalferner, Austria
Sobrino et al. Time series corrections and analyses in thermal remote sensing
Santi et al. A prototype ann based algorithm for the soil moisture retrieval from l-band in view of the incoming SMAP mission
Chandrasekar et al. Rainfall estimation from spaceborne and ground based radars using neural networks
Julien et al. TISSBERT: A benchmark for the validation and comparison of NDVI time series reconstruction methods
Tsheko et al. Sorghum yield and associated satellite-derived meteorological parameters in semi-arid Botswana
Liu et al. Comparison of three modeling methods for estimating forest biomass using TM, GLAS and field measurement data
Chen Using nighttime lights data as a proxy in social scientific research

Legal Events

Date Code Title Description
DPE2 Request for preliminary examination filed before expiration of 19th month from priority date (pct application filed from 20040101)
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19865680

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19865680

Country of ref document: EP

Kind code of ref document: A1