CN109270124A - A kind of Soil salinity prediction technique based on machine learning regression algorithm - Google Patents

A kind of Soil salinity prediction technique based on machine learning regression algorithm Download PDF

Info

Publication number
CN109270124A
CN109270124A CN201811399327.5A CN201811399327A CN109270124A CN 109270124 A CN109270124 A CN 109270124A CN 201811399327 A CN201811399327 A CN 201811399327A CN 109270124 A CN109270124 A CN 109270124A
Authority
CN
China
Prior art keywords
soil
salinity
vegetation
machine learning
regression algorithm
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.)
Pending
Application number
CN201811399327.5A
Other languages
Chinese (zh)
Inventor
吴伟成
周晓亭
祝民强
刘光萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
East China Institute of Technology
Original Assignee
East China Institute of Technology
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 East China Institute of Technology filed Critical East China Institute of Technology
Priority to CN201811399327.5A priority Critical patent/CN109270124A/en
Publication of CN109270124A publication Critical patent/CN109270124A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • G01N27/02—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/80—Geometric correction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/188—Vegetation
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Electrochemistry (AREA)
  • Pathology (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Multimedia (AREA)
  • Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)

Abstract

The invention discloses a kind of Soil salinity prediction techniques based on machine learning regression algorithm, include the following steps: S1, using equilateral triangle as measuring point shape, using the actual measurement salinity of three angle points of EM38 the earth conductivity gauge acquisition triangle, when measurement, vertical reading EM is readVEM is read with levelH, it is averaged the salinity as delta-shaped region, measures the EM of several delta-shaped regionsHAnd EMVFor basic truth training set (TS)；S2, soil constitution is obtained using the removal vegetation contribution of L-band Radar backscattering coefficients；S3, it plot will be surveyed by direct rasterizing is converted to grid and create training set (TS)；S4, using above-mentioned training set (TS), (RFR) algorithm modelling application is returned using random forest and carries out salinity prediction in joint data set.

Description

A kind of Soil salinity prediction technique based on machine learning regression algorithm
Technical field
The present invention relates to Soil salinity detection fields, and in particular to a kind of Soil salinity based on machine learning regression algorithm Prediction technique.
Background technique
The soil salinization is suppressed one of the important soil obstruction factor of crop growthing development.The soil salinization influences Crop production and grain security.The spatial distribution and soil salinization severity for drawing salinity to agricultural management and are developed to It closes important.
Summary of the invention
To solve the above problems, the present invention provides a kind of Soil salinity prediction sides based on machine learning regression algorithm Method.
To achieve the above object, the technical scheme adopted by the invention is as follows:
A kind of Soil salinity prediction technique based on machine learning regression algorithm, includes the following steps:
S1, using equilateral triangle as measuring point shape, using EM38 the earth conductivity gauge acquisition triangle three angle points reality Salinity is surveyed, when measurement, reads vertical reading EMVEM is read with levelH, it is averaged the salinity as delta-shaped region, if measurement The EM of dry delta-shaped regionHAnd EMVFor basic truth training set (TS)；
S2, soil constitution is obtained using the removal vegetation contribution of L-band Radar backscattering coefficients；
S3, it plot will be surveyed by direct rasterizing is converted to grid and create training set (TS)；
S4, using above-mentioned training set (TS), using random forest return (RFR) algorithm modelling application in joint data set into The prediction of row salinity.
Further, in the step S1,15-20 meters of the side length of the equilateral triangle, it is ensured that triangle can be approximate Indicate a TM (thematic imager) pixel；Measure specification 1m × 1m of block.
Further, the step S2 specifically comprises the following steps:
S21, LANDSAT 5 (Landsat 5) the TM image obtained from European Space Agency is calibrated with Radio Measurement, and adopt Additional atmospheric effect is eliminated with scattering method model, each wave band of generated reflectivity is reset to 0-1；
S22, geometric correction is carried out to the 1.5 grades of radar results obtained from European Space Agency, and pixel is readjusted 12.5 meters of size, the digital quantization value (DN) for receiving HH and horizontal emission vertical reception HV to horizontal emission level carry out respectively Correction, according to formulaBe converted to backscattering coefficient (σ0 HH、σ0 Hv)；Then Spot or noise are removed using enhanced Lee filter (the Enhanced Lee size of filter3 × 3, Lee 1980), exports σ0 HH And σ0 Hv, lay equal stress on and be amplified to 30m pixel for matching TM data；
The water-cloud model that S23, building vegetation water content (VWC) influence Radar backscattering coefficients:
L2=exp (- 2BV2sec(θi))
Wherein, σ0It is total backscattering coefficient (σ from Vegetation canopy and soil0 HH、σ0 Hv)；σ0 vegIt is the backward of vegetation Contribution of scatters, σ0 soilIt is the contribution of scatters of soil；L2It is two-way vegetation decaying；θiThe incidence angle of radar beam, A and B are vegetation Parameter；V1And V2It is vegetation description, V1It is applicable in leaf area index LAI (m2m-2), V2It is applicable in volumetric water content of soil VWC (kgm-2)；
S24, it takes:
LAI=0.091exp (3.7579GDVI2) (R2=0.932)
VWC=192.64NDVI5-417.46NDVI4+347.96NDVI3-138.93NDVI2+30.699NDVI-2.822 (kg·m-2)(R2=0.990)；
A=0.0045, B=0.4179；
With 34.3 ° for θiiThe incidence angle of radar beam calculates vegetation and removes backscattering coefficient (σ0 HH、σ0 Hv)。
Further, the step S3 specifically comprises the following steps:
Using the point in ArcGIS to grid crossover tool, it is 30,60 that average field measurement figure, which is converted to raster unit, With 90 meters of sizes, then resets and arrive 30m pixel, composition data collection.
Further, the step S4 specifically comprises the following steps:
S41, it is modeled using random forest regression algorithm RFR, using all 12 wave bands as input variable, utilizes observation The preset value 100 of (training set (TS)) in EnMap-Box；
The square root of all features is chosen with the number of the randomly selected feature of each node or variable number；
Ending standard (be used for node split), wherein preset value is smallest sample number in node, 1, according to gini index meter The minimum impurity of calculation, 0；
EM will be rasterizedVOr EMHAfter (EM38 is vertically read or horizontal reading) is TS (training set) parametrization, by generation RFR model is applied to combined data set, to predict soil apparent salinity (Eca).
Further, further include the steps that soil apparent salinity Eca being converted to soil conductivity ece, wherein ECe- Relationship between EM38 reading and (Eca) is expressed as follows:
ECe(dSm-1)=0.0005EMV 2-0.0779EMV+12.655(R2=0.850)；
ECe(dSm-1)=0.0002EMH 2+0.0956EMH+0.0688(R2=0.791).
The invention has the following advantages:
The forecast analysis for realizing Soil salinity to agricultural management and develops significant, random forest regression algorithm RFR charts for Soil salinity, there is higher precision and lower normalization root-mean-square error.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field For personnel, without departing from the inventive concept of the premise, various modifications and improvements can be made.These belong to the present invention Protection scope.
A kind of Soil salinity prediction technique based on machine learning regression algorithm of the embodiment of the present invention, including walk as follows It is rapid:
S1, using equilateral triangle as measuring point shape, using EM38 the earth conductivity gauge acquisition triangle three angle points reality Survey salinity, 15-20 meters of the side length of the equilateral triangle, it is ensured that triangle can with one TM of approximate representation (thematic imager) as Element；Measure specification 1m × 1m of block；When measurement, vertical reading EM is readVEM is read with levelH, it is averaged as triangle The salinity in region measures the EM of several delta-shaped regionsHAnd EMVFor basic truth training set (TS)；
S2, soil constitution is obtained using the removal vegetation contribution of L-band Radar backscattering coefficients；
S21, it is calibrated with Radio Measurement from European Space Agency LANDSAT 5 (Landsat 5) TM image, and using scattering Method model eliminates additional atmospheric effect, and each wave band of generated reflectivity is reset to 0-1；
S22, geometric correction is carried out to from 1.5 grades of radar results of European Space Agency, and pixel is readjusted 12.5 meters Size, to horizontal emission level receive HH and horizontal emission vertical reception HV digital quantization value (DN) be corrected respectively, According to formulaBe converted to backscattering coefficient (σ0 HH、σ0 Hv)；Then it applies Enhanced Lee filter (3 × 3 size of Enhanced Lee filter, Lee 1980) removes spot or noise, exports σ0 HHWith σ0 Hv, lay equal stress on and be amplified to 30m pixel for matching TM data；
The water-cloud model that S23, building vegetation water content (VWC) influence Radar backscattering coefficients:
L2=exp (- 2BV2sec(θi))
Wherein, σ0It is total backscattering coefficient (σ from Vegetation canopy and soil0 HH、σ0 Hv)；σ0 vegIt is the backward of vegetation Contribution of scatters, σ0 soilIt is the contribution of scatters of soil；L2It is two-way vegetation decaying；θiThe incidence angle of radar beam, A and B are vegetation Parameter；V1And V2It is vegetation description, V1It is applicable in leaf area index LAI (m2m-2), V2It is applicable in volumetric water content of soil VWC (kgm-2)；
S24, it takes:
LAI=0.091exp (3.7579GDVI2) (R2=0.932)
VWC=192.64NDVI5-417.46NDVI4+347.96NDVI3-138.93NDVI2+30.699NDVI-2.822 (kg·m-2)(R2=0.990)；
A=0.0045, B=0.4179；
With 34.3 ° for θiThe incidence angle of radar beam calculates vegetation and removes backscattering coefficient (σ0 HH、σ0 Hv)。
S3, it plot will be surveyed by direct rasterizing is converted to grid and create training set (TS)；
Using the point in ArcGIS to grid crossover tool, it is 30,60 that average field measurement figure, which is converted to raster unit, With 90 meters of sizes, then resets and arrive 30m pixel, composition data collection；
S4, using above-mentioned training set (TS), using random forest return (RFR) algorithm modelling application in joint data set into The prediction of row salinity.
S41, it is modeled using random forest regression algorithm RFR, using all 12 wave bands as input variable, is seen using 24 Preset value 100 of the measured value (training set (TS)) in EnMap-Box；
The square root of all features is chosen with the number of the randomly selected feature of each node or variable number；
Ending standard (be used for node split), wherein preset value is smallest sample number in node, 1, according to gini index meter The minimum impurity of calculation, 0.
EM will be rasterizedVOr EMHAfter (EM38 is vertically read or horizontal reading) is TS (training set) parametrization, by generation RFR model is applied to combined data set, to predict soil apparent salinity (Eca).
S5, the step of soil apparent salinity Eca is converted into soil conductivity ece, wherein ECe-EM38 reading with (Eca) relationship between is expressed as follows:
ECe(dSm-1)=0.0005EMV 2-0.0779EMV+12.655(R2=0.850)；
ECe(dSm-1)=0.0002EMH 2+0.0956EMH+0.0688(R2=0.791).
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase Mutually combination.

Claims (6)

1. a kind of Soil salinity prediction technique based on machine learning regression algorithm, characterized by the following steps:
S1, using equilateral triangle as measuring point shape, using EM38 the earth conductivity gauge acquisition triangle three angle points actual measurement salt Degree when measurement, reads vertical reading EMVEM is read with levelH, it is averaged the salinity as delta-shaped region, measures several The EM of delta-shaped regionHAnd EMVFor basic truth training set (TS)；
S2, soil constitution is obtained using the removal vegetation contribution of L-band Radar backscattering coefficients；
S3, it plot will be surveyed by direct rasterizing is converted to grid and create training set (TS)；
S4, using above-mentioned training set (TS), (RFR) algorithm modelling application is returned using random forest and carries out salt in joint data set Degree prediction.
2. a kind of Soil salinity prediction technique based on machine learning regression algorithm as described in claim 1, it is characterised in that: In the step S1,15-20 meters of the side length of the equilateral triangle, it is ensured that triangle can be with one TM pixel of approximate representation；It surveys Measure specification 1m × 1m of block.
3. a kind of Soil salinity prediction technique based on machine learning regression algorithm as described in claim 1, it is characterised in that: The step S2 specifically comprises the following steps:
S21, the LANDSAT5TM image obtained from European Space Agency is calibrated with Radio Measurement, and eliminated using scattering method model The each wave band of generated reflectivity is reset to 0-1 by additional atmospheric effect；
S22, geometric correction is carried out to the 1.5 grades of radar results obtained from European Space Agency, and pixel is readjusted 12.5 The size of rice, the digital quantization value for receiving HH and horizontal emission vertical reception HV to horizontal emission level are corrected respectively, press According to formulaBe converted to backscattering coefficient (σ0 HH、σ0 Hv)；Then application enhancing Lee filter (the Enhanced Lee size of filter3 × 3, Lee 1980) removes spot or noise, exports σ0 HHAnd σ0 Hv, and 30m pixel is amplified to again to be used to match TM data；
The water-cloud model that S23, building vegetation water content (VWC) influence Radar backscattering coefficients:
L2=exp (- 2BV2sec(θi))
Wherein, σ0It is total backscattering coefficient (σ from Vegetation canopy and soil0 HH、σ0 Hv)；σ0 vegIt is the back scattering of vegetation Contribution, σ0 soilIt is the contribution of scatters of soil；L2It is two-way vegetation decaying；θiThe incidence angle of radar beam, A and B are vegetation parameters； V1And V2It is vegetation description, V1It is applicable in leaf area index LAI (m2m-2), V2It is applicable in volumetric water content of soil VWC (kgm-2)；
S24, it takes:
LAI=0.091exp (3.7579GDVI2) (R2=0.932)
VWC=192.64NDVI5-417.46NDVI4+347.96NDVI3-138.93NDVI2+30.699NDVI-2.822 (kg·m-2)(R2=0.990)；
A=0.0045, B=0.4179；
With 34.3 ° for θiThe incidence angle of radar beam calculates vegetation and removes backscattering coefficient (σ0 HH、σ0 Hv)。
4. a kind of Soil salinity prediction technique based on machine learning regression algorithm as described in claim 1, it is characterised in that: The step S3 specifically comprises the following steps:
Using the point in ArcGIS to grid crossover tool, it is 30,60 and 90 that average field measurement figure, which is converted to raster unit, Then meter great little resets and arrives 30m pixel, composition data collection.
5. a kind of Soil salinity prediction technique based on machine learning regression algorithm as described in claim 1, it is characterised in that: The step S4 specifically comprises the following steps:
S41, it is modeled using random forest regression algorithm RFR, using all 12 wave bands as input variable, is existed using observation Preset value 100 in EnMap-Box；The flat of all features is chosen with the number of the randomly selected feature of each node or variable number Root；Ending standard, be used for node split, wherein preset value be node in smallest sample number, 1, according to gini index calculate Minimum impurity, 0；
EM will be rasterizedVOr EMHAfter TS (training set) parametrization, the RFR model of generation is applied to combined data set, is come pre- It surveys soil apparent salinity (Eca).
6. a kind of Soil salinity prediction technique based on machine learning regression algorithm as described in claim 1, it is characterised in that: Further include the steps that soil apparent salinity Eca being converted to soil conductivity ece, wherein between ECe-EM38 reading and (Eca) Relationship be expressed as follows:
ECe(dSm-1)=0.0005EMV 2-0.0779EMV+12.655(R2=0.850)；
ECe(dSm-1)=0.0002EMH 2+0.0956EMH+0.0688(R2=0.791).
CN201811399327.5A 2018-11-22 2018-11-22 A kind of Soil salinity prediction technique based on machine learning regression algorithm Pending CN109270124A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811399327.5A CN109270124A (en) 2018-11-22 2018-11-22 A kind of Soil salinity prediction technique based on machine learning regression algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811399327.5A CN109270124A (en) 2018-11-22 2018-11-22 A kind of Soil salinity prediction technique based on machine learning regression algorithm

Publications (1)

Publication Number Publication Date
CN109270124A true CN109270124A (en) 2019-01-25

Family

ID=65189946

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811399327.5A Pending CN109270124A (en) 2018-11-22 2018-11-22 A kind of Soil salinity prediction technique based on machine learning regression algorithm

Country Status (1)

Country Link
CN (1) CN109270124A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582156A (en) * 2020-05-07 2020-08-25 武汉大势智慧科技有限公司 Oblique photography-based tall and big vegetation extraction method for urban three-dimensional model
CN111879915A (en) * 2020-08-04 2020-11-03 北京师范大学 High-resolution monthly soil salinity monitoring method and system for coastal wetland
CN112162016A (en) * 2020-09-15 2021-01-01 塔里木大学 Regional scale soil profile salinization detection method based on electromagnetic induction data

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105608414A (en) * 2015-12-11 2016-05-25 国网四川省电力公司电力应急中心 Surface water content distribution extracting method
CN106885827A (en) * 2017-02-17 2017-06-23 国家海洋局第海洋研究所 Seawater invasion and the monitoring and evaluation method of the soil salinization
CN107417311A (en) * 2017-08-31 2017-12-01 北京沃尔夫斯科技有限公司 A kind of method and system that changing food waste into resources is accurately controlled according to soil property present situation
CN208109744U (en) * 2018-05-17 2018-11-16 上海海洋大学 A kind of Soil salinity detection recorder

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105608414A (en) * 2015-12-11 2016-05-25 国网四川省电力公司电力应急中心 Surface water content distribution extracting method
CN106885827A (en) * 2017-02-17 2017-06-23 国家海洋局第海洋研究所 Seawater invasion and the monitoring and evaluation method of the soil salinization
CN107417311A (en) * 2017-08-31 2017-12-01 北京沃尔夫斯科技有限公司 A kind of method and system that changing food waste into resources is accurately controlled according to soil property present situation
CN208109744U (en) * 2018-05-17 2018-11-16 上海海洋大学 A kind of Soil salinity detection recorder

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WEICHENG WU等: "Soil salinity prediction and mapping by machine learning regression in Central Mesopotamia, Iraq", 《LAND DEGRADATION & DEVELOPMENT》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111582156A (en) * 2020-05-07 2020-08-25 武汉大势智慧科技有限公司 Oblique photography-based tall and big vegetation extraction method for urban three-dimensional model
CN111582156B (en) * 2020-05-07 2023-12-05 武汉大势智慧科技有限公司 High and large vegetation extraction method based on oblique photography urban three-dimensional model
CN111879915A (en) * 2020-08-04 2020-11-03 北京师范大学 High-resolution monthly soil salinity monitoring method and system for coastal wetland
CN112162016A (en) * 2020-09-15 2021-01-01 塔里木大学 Regional scale soil profile salinization detection method based on electromagnetic induction data

Similar Documents

Publication Publication Date Title
Ma et al. Estimation of daily evapotranspiration and irrigation water efficiency at a Landsat-like scale for an arid irrigation area using multi-source remote sensing data
Wang et al. Predicting grain yield and protein content in wheat by fusing multi-sensor and multi-temporal remote-sensing images
WO2023087630A1 (en) Method for estimating soil salinity of straw residue farmland by using remote sensing construction index
Zhou et al. Assessing the impacts of an ecological water diversion project on water consumption through high-resolution estimations of actual evapotranspiration in the downstream regions of the Heihe River Basin, China
CN103994976A (en) MODIS data-based agricultural drought remote sensing monitoring method
CN110927120B (en) Early warning method for vegetation coverage
CN109270124A (en) A kind of Soil salinity prediction technique based on machine learning regression algorithm
Bell et al. The application of dielectric retrieval algorithms for mapping soil salinity in a tropical coastal environment using airborne polarimetric SAR
CN107688776B (en) Urban water body extraction method
Wang et al. Fractional vegetation cover estimation method through dynamic Bayesian network combining radiative transfer model and crop growth model
Xiang et al. Integration of tillage indices and textural features of Sentinel-2A multispectral images for maize residue cover estimation
CN114819737B (en) Method, system and storage medium for estimating carbon reserves of highway road vegetation
Leng et al. Determination of all-sky surface soil moisture at fine spatial resolution synergistically using optical/thermal infrared and microwave measurements
CN113534083B (en) SAR-based corn stubble mode identification method, device and medium
Ajith et al. Rice yield prediction using MODIS-NDVI (MOD13Q1) and land based observations
Zhang et al. Estimation of rice yield from a C-band radar remote sensing image by integrating a physical scattering model and an optimization algorithm
CN112733445A (en) Large-area-scale soil moisture inversion method based on evapotranspiration vegetation index spatial characteristics
Yadav et al. Estimation of soil moisture through water cloud model using sentinel-1A SAR data
CN114611699A (en) Soil moisture downscaling method and device, electronic equipment and storage medium
RU2705549C1 (en) Method of agrochemical survey of agricultural lands
Bannari et al. Potential of WorldView-3 for soil salinity modeling and mapping in an arid environment
Joshi et al. Estimating above ground biomass of Pinus roxbhurghii using slope based vegetation index model
Hutengs et al. Downscaling land surface temperatures from MODIS data to mesoscale resolution with Random Forest regression
Girard-Ardhuin et al. Sea ice drift in the central Arctic combining QuikSCAT and SSM/I sea ice drift data
CN115797785B (en) Method and device for determining farmland irrigation frequency based on microwave remote sensing

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20190125

RJ01 Rejection of invention patent application after publication