WO2024055783A1 - 马铃薯产量的预测方法、装置、电子设备及存储介质 - Google Patents

马铃薯产量的预测方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2024055783A1
WO2024055783A1 PCT/CN2023/112004 CN2023112004W WO2024055783A1 WO 2024055783 A1 WO2024055783 A1 WO 2024055783A1 CN 2023112004 W CN2023112004 W CN 2023112004W WO 2024055783 A1 WO2024055783 A1 WO 2024055783A1
Authority
WO
WIPO (PCT)
Prior art keywords
potato
date
num
spadb
spadt
Prior art date
Application number
PCT/CN2023/112004
Other languages
English (en)
French (fr)
Other versions
WO2024055783A8 (zh
Inventor
李丹
方立刚
姜浩
贾凯
王重洋
苗宇新
陈水森
Original Assignee
苏州得墨忒耳科技有限公司
苏州市职业大学
广东省科学院广州地理研究所
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 苏州得墨忒耳科技有限公司, 苏州市职业大学, 广东省科学院广州地理研究所 filed Critical 苏州得墨忒耳科技有限公司
Publication of WO2024055783A1 publication Critical patent/WO2024055783A1/zh
Publication of WO2024055783A8 publication Critical patent/WO2024055783A8/zh

Links

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
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/55—Specular reflectivity
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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

Definitions

  • the invention relates to the field of agricultural technology, and in particular to a potato yield prediction method, device, electronic equipment and storage medium.
  • the object of the present invention is to provide a potato yield prediction method, device, electronic equipment and storage medium.
  • one embodiment of the present invention provides a method for predicting potato yield in potato farmland, including the following steps: obtaining potato crowns collected in Num different preset dates date i in the potato farmland.
  • ⁇ 1 -1.3473
  • An embodiment of the present invention also provides a potato yield prediction device for potato farmland, including the following modules:
  • the first process is used to standardize NIR i , R i , RE i , SPADB i , SPADM i and SPADT i corresponding to Num preset dates date i ; generate NIR corresponding to Num preset dates date i respectively. as well as
  • the second process is used to generate potato yield based on NDVI i , CCCI i , SPADB i , SPADM i and SPADT i respectively corresponding to Num preset dates date i .
  • An embodiment of the present invention also provides an electronic device, including: a memory for storing executable instructions; and a processor for implementing the above prediction method when executing the executable instructions stored in the memory.
  • Embodiments of the present invention also provide a storage medium that stores executable instructions for causing the processor to implement the above prediction method when executed.
  • embodiments of the present invention provide a potato yield prediction method, device, electronic device and storage medium.
  • the prediction method includes: taking potato farmland data on multiple different preset dates. collected horses The near-infrared reflectance value of the potato canopy, the red band reflectance value of the canopy, the red edge reflectance value, the chlorophyll value at the bottom of the canopy, the chlorophyll value in the middle of the canopy, and the chlorophyll value at the top of the canopy, based on the above information Generate potato yield.
  • this prediction method is able to predict potato yield.
  • Figure 1 is a schematic flow chart of a prediction method in an embodiment of the present invention
  • Figures 2 and 3 are experimental results of the prediction method in the embodiment of the present invention.
  • Embodiment 1 of the present invention provides a method for predicting potato yield for potato farmland.
  • the potato farmland is a farmland used for planting potatoes. Its area, soil type, etc. are all determined and are a determined quantity.
  • other variables of the potato farmland for example, environmental factors, potato growth conditions, etc.
  • the prediction method in this embodiment is to predict potato yield based on these variables.
  • some sensors can be used to obtain these variables, and then the obtained variables are input into the computer through the network, and the computer executes the potato yield prediction method.
  • a plurality of sensors can be provided in the potato field to detect NIR i , Ri , RE i , SPADB i , SPADM i and SPADT i , for example, active remote sensing sensors (in In the inventor's experiments, using The RapidSCAN CS-45 plant spectrometer), this active remote sensing sensor emits electromagnetic radiation waves of a certain frequency to the potato canopy, and then receives the radiation information returned from the potato canopy and analyzes it (for example, by analyzing the echo properties, characteristics and changes to achieve the purpose of identifying potato canopy), thereby obtaining NIR i , Ri , RE i , SPADB i , SPADM i and SPADT i , etc.
  • Step 102 Standardize NIR i , Ri , RE i , SPADB i , SPADM i and SPADT i corresponding to the Num preset dates date i ; generate NIR i , R i , RE i , SPADB i , SPADM i and SPADT i respectively; generate as well as
  • Step 103 Generate potato yield based on NDVI i , CCCI i , SPADB i , SPADM i and SPADT i respectively corresponding to Num preset dates date i .
  • the reflectance data ie NIR i , R i and RE i
  • the relative chlorophyll values measured by the chlorophyll meter ie SPADB i , SPADM i and SPADT i
  • SPADB i the relative chlorophyll values measured by the chlorophyll meter
  • date 3 and the potato planting day The number of days between -70
  • date 1 is about 45 days after the potato planting
  • date 2 is about 60 days after the potato planting
  • date 3 is about 70 days after the potato planting
  • date 4 is about 80 days after the potato planting. .
  • the "generating potato yield based on NDVI i , CCCI i , SPADB i , SPADM i and SPADT i respectively corresponding to Num preset dates date i" specifically includes:
  • the area, soil type, etc. of the potato farmland are all determined. These factors also affect the yield of the potato farmland. Here, these factors can be considered to be a certain quantity. Therefore, when y is larger, the potato yield will be greater. .
  • ⁇ 1 -1.3473
  • the "standardizing processing of NIR i , Ri , RE i , SPADB i , SPADM i and SPADT i corresponding to Num preset dates date i" specifically includes:
  • Figures 2 and 3 are experimental result diagrams obtained by the inventor when conducting experiments.
  • the full English spelling of RMSE is: root-mean-square error
  • the full Chinese name is: root-mean-square error
  • the full English spelling of R2 is: coefficient of determination
  • the full Chinese name is: coefficient of determination, coefficient of determination or goodness of fit, etc.
  • Embodiment 2 of the present invention provides a potato yield prediction device for potato farmland, including the following modules:
  • the first processing is used to standardize NIR i , R i , RE i , SPADB i , SPADM i and SPADT i corresponding to Num preset dates date i ; generate NIR corresponding to Num preset dates date i respectively. as well as
  • the second process is used to generate potato yield based on NDVI i , CCCI i , SPADB i , SPADM i and SPADT i respectively corresponding to Num preset dates date i .
  • Embodiment 3 of the present invention provides an electronic device, including: a memory for storing executable instructions;
  • the processor is configured to implement the prediction method in Embodiment 1 when executing executable instructions stored in the memory.
  • Embodiment 4 of the present invention provides a storage medium that stores executable instructions for causing a processor to implement the prediction method in Embodiment 1 when executed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Computational Mathematics (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Development Economics (AREA)
  • Primary Health Care (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Mining & Mineral Resources (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Animal Husbandry (AREA)
  • Agronomy & Crop Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Algebra (AREA)
  • Quality & Reliability (AREA)

Abstract

本发明提供一种马铃薯产量的预测方法、装置、电子设备及存储介质，该预测方法包括：取马铃薯农田在多个不同预设日期所采集到的马铃薯冠层的近红外反射率值、冠层的红波段反射率值、红边反射率值、冠层底部的叶绿素值、冠层中部的叶绿素值和冠层顶部的叶绿素值，基于上述信息生成马铃薯产量。综上所述，该预测方法能够预测马铃薯的产量。

Description

马铃薯产量的预测方法、装置、电子设备及存储介质
本申请要求了申请日为2022年09月13日，申请号为202211109460.9，发明名称为“马铃薯产量的预测方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及农业技术领域，尤其涉及一种马铃薯产量的预测方法、装置、电子设备及存储介质。
背景技术
2015年起，我国启动了马铃薯主粮化战略，马铃薯成为除了水稻、小麦、玉米之外的又一主粮。因此，需要一种有效的马铃薯产量的预测方法对马铃薯产量进行预测，根据预测的马铃薯产量，对马铃薯产业进行风险防控和战略性预见，有效且及时的对马铃薯生产进行防控和统筹，而现有技术中缺乏一种对马铃薯产量进行预测的方法。
发明内容
本发明的目的在于提供一种马铃薯产量的预测方法、装置、电子设备及存储介质。
为了实现上述发明目的之一，本发明一实施方式提供了一种用于马铃薯农田的马铃薯产量的预测方法，包括以下步骤：获取马铃薯农田在Num个不同预设日期datei所采集到的马铃薯冠层的近红外反射率值NIRi、马铃薯冠层的红波段反射率值Ri、马铃薯冠层的红边反射率值REi、马铃薯冠层底部的叶绿素值SPADBi、马铃薯冠层中部的叶绿素值SPADMi和马铃薯冠层顶部的叶绿素值SPADTi；其中，i＝1、2、...、Num，Num为自然数，Num≥2；对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理；生成Num个预设日期datei分别对应的以及基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量。
作为本发明一实施方式的进一步改进，Num＝4，date1早于date2，date2早于date3，date3早于date4。
作为本发明一实施方式的进一步改进，|date1与马铃薯种植日之间的间隔天数-45|≤error，|date2与马铃薯种植日之间的间隔天数-60|≤error，|date3与马铃薯种植日之间的间隔天数-70|≤error，|date4与马铃薯种植日之间的间隔天数-80|≤error，0≤error。
作为本发明一实施方式的进一步改进，所述“基于Num个预设日期datei分别对应的NDVIi、 CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量”具体包括：y＝α1NDVI1+α2CCCI2+α3SPADB3+α4NDVI4+α5AVG+α6NDVI3，其中，α1、α2、α3、α4、α5和α6均为常数，AVG＝(SPADB3+SPADM3+SPADT3)/3；当y越大时，马铃薯产量越大。
作为本发明一实施方式的进一步改进，α1＝-1.3473，α2＝0.2528，α3＝0.8161，α4＝-0.7368，α5＝-2.6969，α6＝-2.1364。
作为本发明一实施方式的进一步改进，所述“对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理”具体包括：NIR′ i＝F(NIR1,NIR2,...,NIRNum,i),R′i＝F(R1,R2,...,RNum,i),RE′i＝F(RE1,RE2,...,RENum,i),SPADB′i＝F(SPADB1,SPADB2,...,SPADBNum,i),SPADM′i＝F(SPADM1,SPADM2,...,SPADMNum,i),SPADT′i＝F(SPADT1,SPADT2,...,SPADTNum,i)；其中，函数NIRi＝NIR′i,Ri＝R′i,REi＝RE′i,SPADBi＝SPADB′i,SPADMi＝SPADM′i,SPADTi＝SPADT′i。
本发明实施例还提供了一种用于马铃薯农田的马铃薯产量预测装置，包括以下模块：
信息获取模块，用于获取马铃薯农田在Num个不同预设日期datei所采集到的马铃薯冠层的近红外反射率值NIRi、马铃薯冠层的红波段反射率值Ri、马铃薯冠层的红边反射率值REi、马铃薯冠层底部的叶绿素值SPADBi、马铃薯冠层中部的叶绿素值SPADMi和马铃薯冠层顶部的叶绿素值SPADTi；其中，i＝1、2、...、Num，Num为自然数，Num≥2；
第一处理，用于对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理；生成Num个预设日期datei分别对应的以及
第二处理，用于基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量。
作为本发明一实施方式的进一步改进，Num＝4，date1早于date2，date2早于date3，date3早于date4。
本发明实施例还提供了一种电子设备，包括：存储器，用于存储可执行指令；处理器，用于执行所述存储器中存储的可执行指令时，实现上述的预测方法。
本发明实施例还提供了一种存储介质，存储有可执行指令，用于引起处理器执行时，实现上述的预测方法。
相对于现有技术，本发明的技术效果在于：本发明实施例提供一种马铃薯产量的预测方法、装置、电子设备及存储介质，该预测方法包括：取马铃薯农田在多个不同预设日期所采集到的马 铃薯冠层的近红外反射率值、冠层的红波段反射率值、红边反射率值、冠层底部的叶绿素值、冠层中部的叶绿素值和冠层顶部的叶绿素值，基于上述信息生成马铃薯产量。综上所述，该预测方法能够预测马铃薯的产量。
附图说明
图1是本发明实施例中的预测方法的流程示意图；
图2和图3是本发明实施例中的预测方法的实验结果图。
具体实施方式
以下将结合附图所示的各实施方式对本发明进行详细描述。但这些实施方式并不限制本发明，本领域的普通技术人员根据这些实施方式所做出的结构、方法、或功能上的变换均包含在本发明的保护范围内。
本文使用的例如“上”、“上方”、“下”、“下方”等表示空间相对位置的术语是出于便于说明的目的来描述如附图中所示的一个单元或特征相对于另一个单元或特征的关系。空间相对位置的术语可以旨在包括设备在使用或工作中除了图中所示方位以外的不同方位。例如，如果将图中的设备翻转，则被描述为位于其他单元或特征“下方”或“之下”的单元将位于其他单元或特征“上方”。因此，示例性术语“下方”可以囊括上方和下方这两种方位。设备可以以其他方式被定向(旋转90度或其他朝向)，并相应地解释本文使用的与空间相关的描述语。
本发明实施例一提供了一种用于马铃薯农田的马铃薯产量的预测方法，这里，该马铃薯农田是一个用于种植马铃薯的农田，其面积，泥土类型等都是确定，是一个确定的量，但该马铃薯农田的其他变量(例如，环境因素，马铃薯的生长情况等)都会马铃薯产量的；本实施例中的预测方法就是基于这些变量来预测马铃薯的产量。在实际中，可以利用一些传感器来获取这些变量，然后，通过网络将所获取到的变量输入到计算机中，由计算机来执行该马铃薯产量的预测方法。
如图1所示，包括以下步骤：
步骤101：获取马铃薯农田在Num个不同预设日期datei所采集到的马铃薯冠层的近红外(NIR，Near Infrared)反射率值NIRi、马铃薯冠层的红波段(Red)反射率值Ri、马铃薯冠层的红边(Rededge)反射率值REi、马铃薯冠层底部的叶绿素值SPADBi、马铃薯冠层中部的叶绿素值SPADMi和马铃薯冠层顶部的叶绿素值SPADTi；其中，i＝1、2、...、Num，Num为自然数，Num≥2；
这里，在实际中，可以在马铃薯农田中设置有多个传感器，有这些传感器来探测NIRi、Ri、REi、SPADBi、SPADMi和SPADTi，例如，可以安装有主动遥感传感器(在发明人的实验中，使用 的是RapidSCAN CS-45植物光谱测量仪)，该主动遥感传感器会向马铃薯冠层发射一定频率的电磁辐射波，然后接收从马铃薯冠层返回的辐射信息并进行分析(例如，通过分析回波的性质、特征及其变化来达到识别马铃薯冠层的目的)，从而得到NIRi、Ri、REi、SPADBi、SPADMi和SPADTi等。
步骤102：对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理；生成Num个预设日期datei分别对应的以及
步骤103：基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量。
在本实施例的预测方法中，将反射率数据(即NIRi、Ri和REi)和叶绿素测定仪测量的叶绿素相对值(即SPADBi、SPADMi和SPADTi)，结合在一起，分析了马铃薯不同生育期，这两个设备测量的一些参数值，将不同生育期测量的植被信息结合在一起，建立了一个融合两种观测数据源，融合了不同生育期信息的估产模型。这种模型简单、易操作。
本实施例中，Num＝4，date1早于date2，date2早于date3，date3早于date4。
本实施例中，|date1与马铃薯种植日之间的间隔天数-45|≤error，|date2与马铃薯种植日之间的间隔天数-60|≤error，|date3与马铃薯种植日之间的间隔天数-70|≤error，|date4与马铃薯种植日之间的间隔天数-80|≤error，0≤error。这里，可以理解的是，date1在马铃薯种植后的45天左右，date2在马铃薯种植后的60天左右，date3在马铃薯种植后的70天左右，date4在马铃薯种植后的80天左右。
本实施例中，所述“基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量”具体包括：
y＝α1NDVI1+α2CCCI2+α3SPADB3+α4NDVI4+α5AVG+α6NDVI3，其中，α1、α2、α3、α4、α5和α6均为常数，AVG＝(SPADB3+SPADM3+SPADT3)/3；
当y越大时，马铃薯产量越大。
该马铃薯农田的面积、泥土类型等都是确定，这些因数也是影响该马铃薯农田的产量的，这里，可以认为这些因数都是一个确定量，于是，当y越大时，马铃薯的产量就越大。
本实施例中，α1＝-1.3473，α2＝0.2528，α3＝0.8161，α4＝-0.7368，α5＝-2.6969，α6＝-2.1364
本实施例中，所述“对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理”具体包括：
NIR′i＝F(NIR1,NIR2,...,NIRNum,i),R′i＝F(R1,R2,...,RNum,i),RE′i＝F(RE1,RE2,...,RENum,i),SPADB′i＝F(SPADB1,SPADB2,...,SPADBNum,i),SPADM′i＝F(SPADM1,SPADM2,...,SPADMNum,i),SPADT′i＝F(SPADT1,SPADT2,...,SPADTNum,i)；其中，函数
NIRi＝NIR′i,Ri＝R′i,REi＝RE′i,SPADBi＝SPADB′i,SPADMi＝SPADM′i,SPADTi＝SPADT′i。
图2和图3是发明人在进行实验时所得到的实验结果图，在图2和图3中，RMSE的英文全拼为：root-mean-square error，中文全称为：均方根误差；R2的英文全拼为：coefficient ofdetermination，中文全称为：决定系数、判定系数或拟合优度等。
本发明实施例二提供了一种用于马铃薯农田的马铃薯产量预测装置，包括以下模块：
信息获取模块，用于获取马铃薯农田在Num个不同预设日期datei所采集到的马铃薯冠层的近红外反射率值NIRi、马铃薯冠层的红波段反射率值Ri、马铃薯冠层的红边反射率值REi、马铃薯冠层底部的叶绿素值SPADBi、马铃薯冠层中部的叶绿素值SPADMi和马铃薯冠层顶部的叶绿素值SPADTi；其中，i＝1、2、...、Num，Num为自然数，Num≥2；
第一处理，用于对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理；生成Num个预设日期datei分别对应的以及
第二处理，用于基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量。
本实施例中，Num＝4，date1早于date2，date2早于date3，date3早于date4。
本发明实施例三提供了一种电子设备，包括：存储器，用于存储可执行指令；
处理器，用于执行所述存储器中存储的可执行指令时，实现实施例一中的预测方法。
本发明实施例四提供了一种存储介质，存储有可执行指令，用于引起处理器执行时，实现实施例一中的预测方法。
应当理解，虽然本说明书按照实施方式加以描述，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施方式中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。
上文所列出的一系列的详细说明仅仅是针对本发明的可行性实施方式的具体说明，它们并非用以限制本发明的保护范围，凡未脱离本发明技艺精神所作的等效实施方式或变更均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种用于马铃薯农田的马铃薯产量的预测方法，其特征在于，包括以下步骤：
    获取马铃薯农田在Num个不同预设日期datei所采集到的马铃薯冠层的近红外反射率值NIRi、马铃薯冠层的红波段反射率值Ri、马铃薯冠层的红边反射率值REi、马铃薯冠层底部的叶绿素值SPADBi、马铃薯冠层中部的叶绿素值SPADMi和马铃薯冠层顶部的叶绿素值SPADTi；其中，i＝1、2、...、Num，Num为自然数，Num≥2；
    对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理；生成Num个预设日期datei分别对应的以及
    基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量。
  2. 根据权利要求1所述的预测方法，其特征在于：
    Num＝4，date1早于date2，date2早于date3，date3早于date4。
  3. 根据权利要求2所述的预测方法，其特征在于：
    |date1与马铃薯种植日之间的间隔天数-45|≤error，|date2与马铃薯种植日之间的间隔天数-60|≤error，|date3与马铃薯种植日之间的间隔天数-70|≤error，|date4与马铃薯种植日之间的间隔天数-80|≤error，0≤error。
  4. 根据权利要求3所述的预测方法，其特征在于，所述“基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量”具体包括：
    y＝α1NDVI1+α2CCCI2+α3SPADB3+α4NDVI4+α5AVG+α6NDVI3，其中，α1、α2、α3、α4、α5和α6均为常数，AVG＝(SPADB3+SPADM3+SPADT3)/3；
    当y越大时，马铃薯产量越大。
  5. 根据权利要求3所述的预测方法，其特征在于：
    α1＝-1.3473，α2＝0.2528，α3＝0.8161，α4＝-0.7368，α5＝-2.6969，α6＝-2.1364。
  6. 根据权利要求1所述的预测方法，其特征在于，所述“对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理”具体包括：
    NIR′i＝F(NIR1,NIR2,...,NIRNum,i),R′i＝F(R1,R2,...,RNum,i),RE′i＝F(RE1,RE2,...,RENum,i),SPADB′i＝F(SPADB1,SPADB2,...,SPADBNum,i),SPADM′i＝F(SPADM1,SPADM2,...,SPADMNum,i),SPADT′i＝F(SPADT1,SPADT2,...,SPADTNum,i)；其中，函 数
    NIRi＝NIR′i,Ri＝R′i,REi＝RE′i,SPADBi＝SPADB′i,SPADMi＝SPADM′i,SPADTi＝SPADT′i。
  7. 一种用于马铃薯农田的马铃薯产量预测装置，其特征在于，包括以下模块：
    信息获取模块，用于获取马铃薯农田在Num个不同预设日期datei所采集到的马铃薯冠层的近红外反射率值NIRi、马铃薯冠层的红波段反射率值Ri、马铃薯冠层的红边反射率值REi、马铃薯冠层底部的叶绿素值SPADBi、马铃薯冠层中部的叶绿素值SPADMi和马铃薯冠层顶部的叶绿素值SPADTi；其中，i＝1、2、...、Num，Num为自然数，Num≥2；
    第一处理，用于对Num个预设日期datei所对应的NIRi、Ri、REi、SPADBi、SPADMi和SPADTi均进行标准化处理；生成Num个预设日期datei分别对应的以及
    第二处理，用于基于Num个预设日期datei分别对应的NDVIi、CCCIi、SPADBi、SPADMi和SPADTi，生成马铃薯产量。
  8. 根据权利要求7所述的预测装置，其特征在于：
    Num＝4，date1早于date2，date2早于date3，date3早于date4。
  9. 一种电子设备，其特征在于，包括：
    存储器，用于存储可执行指令；
    处理器，用于执行所述存储器中存储的可执行指令时，实现权利要求6所述的预测方法。
  10. 一种存储介质，其特征在于，存储有可执行指令，用于引起处理器执行时，实现权利要求6所述的预测方法。
PCT/CN2023/112004 2022-09-13 2023-08-09 马铃薯产量的预测方法、装置、电子设备及存储介质 WO2024055783A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211109460.9 2022-09-13
CN202211109460.9A CN115358482A (zh) 2022-09-13 2022-09-13 马铃薯产量的预测方法、装置、电子设备及存储介质

Publications (2)

Publication Number Publication Date
WO2024055783A1 true WO2024055783A1 (zh) 2024-03-21
WO2024055783A8 WO2024055783A8 (zh) 2024-04-18

Family

ID=84007049

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/112004 WO2024055783A1 (zh) 2022-09-13 2023-08-09 马铃薯产量的预测方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN115358482A (zh)
WO (1) WO2024055783A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115358482A (zh) * 2022-09-13 2022-11-18 苏州得墨忒耳科技有限公司 马铃薯产量的预测方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160180473A1 (en) * 2011-05-13 2016-06-23 Hydrobio, Inc. Systems to prescribe and deliver fertilizer over agricultural fields and related methods
JP2016146784A (ja) * 2015-02-12 2016-08-18 コニカミノルタ株式会社 植物育成指標測定装置および該方法
CN113884444A (zh) * 2020-07-03 2022-01-04 上海市农业科学院 模型建立方法、预测spad值的方法、装置及电子设备
CN114460015A (zh) * 2021-10-29 2022-05-10 东北农业大学 一种用于预测寒地水稻冠层叶绿素含量的方法及模型
CN114509403A (zh) * 2021-12-28 2022-05-17 广东省科学院广州地理研究所 马铃薯叶柄的硝酸盐预测方法、装置、设备及存储介质
CN115358482A (zh) * 2022-09-13 2022-11-18 苏州得墨忒耳科技有限公司 马铃薯产量的预测方法、装置、电子设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160180473A1 (en) * 2011-05-13 2016-06-23 Hydrobio, Inc. Systems to prescribe and deliver fertilizer over agricultural fields and related methods
JP2016146784A (ja) * 2015-02-12 2016-08-18 コニカミノルタ株式会社 植物育成指標測定装置および該方法
CN113884444A (zh) * 2020-07-03 2022-01-04 上海市农业科学院 模型建立方法、预测spad值的方法、装置及电子设备
CN114460015A (zh) * 2021-10-29 2022-05-10 东北农业大学 一种用于预测寒地水稻冠层叶绿素含量的方法及模型
CN114509403A (zh) * 2021-12-28 2022-05-17 广东省科学院广州地理研究所 马铃薯叶柄的硝酸盐预测方法、装置、设备及存储介质
CN115358482A (zh) * 2022-09-13 2022-11-18 苏州得墨忒耳科技有限公司 马铃薯产量的预测方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN115358482A (zh) 2022-11-18
WO2024055783A8 (zh) 2024-04-18

Similar Documents

Publication Publication Date Title
Muruganantham et al. A systematic literature review on crop yield prediction with deep learning and remote sensing
Terentev et al. Current state of hyperspectral remote sensing for early plant disease detection: A review
Pasqualotto et al. Multi-crop green LAI estimation with a new simple Sentinel-2 LAI Index (SeLI)
Toscano et al. A precision agriculture approach for durum wheat yield assessment using remote sensing data and yield mapping
Ahmad et al. A review of crop water stress assessment using remote sensing
Bellvert et al. Airborne thermal imagery to detect the seasonal evolution of crop water status in peach, nectarine and Saturn peach orchards
Nasrallah et al. A novel approach for mapping wheat areas using high resolution Sentinel-2 images
Chen et al. In-season diagnosis of winter wheat nitrogen status in smallholder farmer fields across a village using unmanned aerial vehicle-based remote sensing
Fu et al. Progress of hyperspectral data processing and modelling for cereal crop nitrogen monitoring
WO2024055783A1 (zh) 马铃薯产量的预测方法、装置、电子设备及存储介质
Roy Choudhury et al. Improving biomass and grain yield prediction of wheat genotypes on sodic soil using integrated high-resolution multispectral, hyperspectral, 3D point cloud, and machine learning techniques
Marino et al. Agronomic traits analysis of ten winter wheat cultivars clustered by UAV-derived vegetation indices
Masjedi et al. Multi-temporal predictive modelling of sorghum biomass using UAV-based hyperspectral and LiDAR data
Dado et al. High-resolution soybean yield mapping across the US Midwest using subfield harvester data
Kumar et al. Image based rapeseed-mustard disease expert system: An effective extension tool
Weksler et al. Detection of potassium deficiency and momentary transpiration rate estimation at early growth stages using proximal hyperspectral imaging and extreme gradient boosting
Wen et al. Thermal imaging: The digital eye facilitates high-throughput phenotyping traits of plant growth and stress responses
Bai et al. Estimation of soybean yield parameters under lodging conditions using RGB information from unmanned aerial vehicles
Nguyen et al. Early detection of wheat yellow rust disease and its impact on terminal yield with multi-spectral uav-imagery
Uribeetxebarria et al. A first approach to determine if it is possible to delineate in-season n fertilization maps for wheat using NDVI derived from sentinel-2
Sellami et al. Selection of hyperspectral vegetation indices for monitoring yield and physiological response in sweet maize under different water and nitrogen availability
Tedesco et al. Predicting on multi-target regression for the yield of sweet potato by the market class of its roots upon vegetation indices
Elmetwalli et al. Assessing the efficiency of remote sensing and machine learning algorithms to quantify wheat characteristics in the Nile Delta region of Egypt
Barbin et al. Influence of plant densities and fertilization on maize grains by near-infrared spectroscopy
Kandpal et al. Onsite age discrimination of an endangered medicinal and aromatic plant species Valeriana jatamansi using field hyperspectral remote sensing and machine learning techniques

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23864517

Country of ref document: EP

Kind code of ref document: A1