Time-Series Remote Sensing for Soil Profile Salinity Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current remote sensing technologies are limited in accurately estimating soil salinity beyond the topsoil, failing to provide comprehensive assessments of salt content in the soil profile, especially at depths relevant to crop health, due to their limited depth of characterization and inability to monitor salt movement over time.
Innovation Solution
A method using time-series Sentinel-2 satellite remote sensing data combined with ground survey data, involving multi-depth conductivity measurements and EM38-MK2 conductivity data, to construct linear regression and spatiotemporal regression models for estimating salt content at 1-meter depth, enabling a comprehensive and spatially resolved assessment of soil profile salinity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If optical remote sensing satellites are used to monitor soil salinity, then spatial coverage and observation resolution are improved, but the depth of soil salinity characterization is limited to topsoil only
Solution Approach 1:
The patent transitions from monitoring only surface soil salinity (2D spatial mapping) to estimating vertical profile salinity (3D spatial mapping) by integrating time-series remote sensing data with ground-based electromagnetic induction measurements, adding the depth dimension to remote sensing soil salinity characterization
Solution Approach 2:
The patent performs preliminary data processing including atmospheric correction, quality filtering, and feature extraction on remote sensing images before integration with ground data, preparing the data in advance to enable accurate depth profile estimation when combined with electromagnetic induction measurements
2Productivity
If single-period remote sensing images are used for soil salinity monitoring, then time efficiency is improved, but comprehensive assessment of soil profile salt content is lost
Solution Approach 1:
The patent uses continuous time-series remote sensing images spanning multiple growing seasons to continuously monitor vegetation growth and soil salinity changes, maintaining uninterrupted observation to capture seasonal variations in soil moisture and salt content that affect root zone salinity
Solution Approach 2:
The patent leverages periodic seasonal cycles of vegetation growth and soil moisture variation to infer deep soil salinity patterns, using recurring annual patterns in remote sensing data combined with periodic ground-based electromagnetic induction measurements to characterize temporal dynamics of soil profile salinity
3Measurement precision
If ground survey methods are used to measure soil salt content, then measurement precision at sample points is improved, but spatial coverage and rapid survey capability are lost
Solution Approach 1:
The patent merges satellite remote sensing data (providing broad spatial coverage) with ground-based electromagnetic induction measurements (providing precise salt content data) to create a hybrid estimation system that achieves both wide-area monitoring capability and accurate soil profile salinity characterization
Solution Approach 2:
The patent uses electromagnetic induction measurements as an intermediary to bridge remote sensing observations and actual soil salinity conditions, employing ground-based electrical conductivity measurements at multiple depths to calibrate and validate the remote sensing-based soil profile salinity estimation model
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for high-resolution, high-quality estimation of soil profile salinity, breaking the limitations of remote sensing data and providing a new method for large-scale soil salinity management and policy formulation, with significant theoretical and practical implications.
Implementation Method 1
EM38-MK2 conductivity data comprises the multi-mode conductivity data of each soil sample point in a second soil sample point set. The multi-mode conductivity data comprises multiple conductivities measured at locations of the soil sample points at different depths and according to different modes.
Implementation Method 2
Linear regression is performed on the segmented conductivity data and the multi-mode conductivity data corresponding to each soil sample point in the first soil sample point set, so that a linear regression model may estimate the segmented conductivity data of the same soil sample point based on the multi-mode conductivity data.
Implementation Method 3
For each soil sample point in the second soil sample point set, each conductivity of five soil layer depths corresponding to each soil sample point is estimated by using the linear regression model, and conversion is performed according to the conductivities to obtain salt contents of different soil layer depths of the soil profile.
Data Source
AI summary
A method for jointly estimating soil profile salinity by using time-series remote sensing image is provided. The method includes following. First, soil profile sample (1 meter), EM38-MK2 soil conductivity data, and a long time series monthly average Sentinel-2 satellite remote sensing image data for describing the same object is obtained. Secondly, the salt content of the soil profile with a depth of 1 meter is obtained according to linear regression equation and profile salt content calculation formula. Then, indices based on the time-series monthly average Sentinel-2 images are obtained to serve as independent variables of modeling by using a random forest to screen the independent variables. Finally, the salt contents of soil profile at 1 meter of the sample points are used as dependent variables, a temporal convolution network regression model is used for estimating, and a distribution map of the salt contents of the soil profile of large-space-scale is obtained.