Predictive Soil Mapping Using Thermal Response Curves
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current predictive soil mapping methods in flat areas are inaccurate and inefficient, with high costs and limited applicability due to weak vegetation-soil correlations and the inability to effectively capture soil spatial variation using remote-sensing technologies.
Innovation Solution
A method utilizing solar radiation data captured by a moderate-resolution imaging spectrometer to create dynamic response curves of earth's surface heat, which are then parameterized and used as environmental covariates in a machine learning model, specifically a random forest algorithm, to predict soil attributes and generate spatial distribution maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If remote-sensing interpretation and classification technology is used to generate soil distribution maps in flat areas, then mapping efficiency is improved, but mapping accuracy deteriorates due to low image separability and weak vegetation-soil correlations
Solution Approach 1:
The patent transforms the remote sensing approach from using vegetation indices to using surface temperature dynamic response parameters. By capturing temperature changes at multiple time points and extracting parameters like maximum temperature, minimum temperature, temperature range, and heating/cooling rates, the method changes the measured parameters to ones that directly reflect soil thermal properties, thereby improving both accuracy and efficiency
Solution Approach 2:
The patent replaces the traditional optical remote sensing system with a thermal remote sensing system. Instead of using visible-infrared spectral images that rely on vegetation reflectance, the system uses thermal infrared imagery to capture surface temperature dynamics, substituting one physical measurement domain for another that is more sensitive to soil properties in flat areas
2Productivity
If soil spectral inversion technology is used to estimate soil attributes, then mapping speed is improved, but application scope deteriorates as it is limited to bare soil areas and shallow depths
Solution Approach 1:
The patent changes from using spectral reflectance parameters to using thermal temperature dynamics parameters. By measuring surface temperature at multiple time points and calculating thermal response parameters, the method captures deeper soil thermal properties that are not limited to the shallow 3-5mm depth detectable by spectral inversion, thereby expanding application scope while maintaining speed
Solution Approach 2:
The patent employs periodic thermal imaging captures at multiple time points throughout the day to track surface temperature dynamics. This periodic measurement approach allows the system to capture the heating and cooling cycles of the surface, providing information about subsurface thermal properties that extends beyond shallow depth limitations
3Measurement precision
If a large amount of field survey samples are collected for spatial interpolation, then mapping accuracy is improved, but cost and time consumption deteriorate
Solution Approach 1:
The patent replaces extensive field sampling with thermal remote sensing measurements. By using satellite or aerial thermal infrared imagery to capture surface temperature dynamics across the entire study area, the system obtains spatially continuous data without the need for numerous physical soil samples, thereby maintaining accuracy while dramatically reducing sample quantity requirements
Solution Approach 2:
The patent creates a thermal signature copy of the soil properties through remote sensing. Instead of physically collecting and analyzing soil samples, the system captures thermal radiation patterns that replicate soil thermal characteristics, providing a non-contact, non-invasive method to estimate soil attributes across large areas
4Adaptability or versatility
If conventional polygon-based soil mapping is used, then expert knowledge utilization is improved, but mapping efficiency and update capability deteriorate
Solution Approach 1:
The patent replaces manual polygon delineation with automated thermal remote sensing analysis. By using algorithms to process temperature time series data and generate continuous soil attribute maps, the system eliminates time-consuming manual mapping while incorporating expert knowledge into the model parameters and interpretation frameworks
Solution Approach 2:
The patent transitions from static polygon-based maps to dynamic continuous surface maps. The thermal remote sensing approach generates smooth, continuous spatial distributions that can be easily updated as new thermal data becomes available, replacing the rigid polygon boundaries with flexible, continuously updatable surfaces
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 significantly improves the accuracy and efficiency of soil mapping in flat areas, reducing the need for extensive field surveys and lowering costs, while providing detailed spatial information that meets industry requirements.
Implementation Method 1
A method utilizing solar radiation data captured by a moderate-resolution imaging spectrometer to create dynamic response curves of earth's surface heat
Implementation Method 2
capturing the response process of the earth's surface heat: after an observation day or an observation period is selected, a curve graph depicting a dynamic response of the surface heat to solar radiation captured by using a remote sensor of a moderate-resolution imaging spectrometer
Data Source
AI summary
The disclosure provides a method for predictive soil mapping based on solar radiation in large flat area, comprising: Step 1, capturing the response process of the earth's surface heat: after an observation day or an observation period is selected, a curve graph depicting a dynamic response of the surface heat to solar radiation captured by using a remote sensor of a moderate-resolution imaging spectrometer; Step 2, constructing environmental covariates: quantitative analysis is performed for the dynamic response curve graph obtained in Step 1 by a mathematical method, and characteristic parameters are extracted and taken as environmental covariates; and Step 3: a machine learning model is established for the predictive soil attribute mapping. This method solves the challenge of effective soil mapping in flat areas, significantly improves the accuracy and efficiency of predictive soil mapping in flat areas, reduces the cost in time and economy of soil survey mapping.