Remote Sensor Data Correction via Local Ground Truth
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current remote sensor data used in agricultural fields, such as satellite images, is limited by availability and quality, leading to inaccuracies due to atmospheric distortions and lack of field-specific microclimatic data, which affects the accuracy of plant and pest models, and requires additional in-situ measurements for precise farming practices.
Innovation Solution
A method that corrects remote sensor data by using a correction model based on local sensor data from in-situ measurements, which includes weather, soil, and crop conditions, to enhance data quality and accuracy, allowing for real-time validation or amendment of satellite data to reflect field-specific conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If remote sensor data from satellites is used to cover the entirety of an agricultural field, then spatial coverage is improved, but measurement precision deteriorates due to atmospheric distortions and distance
Solution Approach 1:
The patent combines remote sensor data from satellites with local sensor data from ground-based sensors to create a hybrid dataset that leverages the spatial coverage of remote sensing while correcting for its precision limitations using ground truth measurements
Solution Approach 2:
Local sensor data acts as an intermediary to correct and validate remote sensor data, bridging the gap between satellite observations and actual field conditions by serving as a reference for atmospheric distortion correction
2Measurement precision
If local sensors are installed for in-situ measurements to improve measurement precision, then data quality is improved, but device complexity and maintenance effort increase
Solution Approach 1:
The system is designed to work with multiple types of sensors (remote and local) that can measure various parameters (temperature, humidity, vegetation indices), making the correction framework universally applicable to different sensor configurations and farming scenarios
Solution Approach 2:
The system automatically processes and corrects remote sensor data using local sensor data without requiring manual intervention, reducing maintenance burden on farmers while improving data quality
3Measurement precision
If multiple satellite products and post-processing steps are used to mitigate image availability and quality issues, then data quality is improved, but cost increases
Solution Approach 1:
Local sensor data serves as a cost-effective intermediary that corrects remote sensor data without requiring expensive multiple satellite products or complex post-processing, achieving similar quality improvements at lower cost
4Measurement precision
If farmers focus on installing and maintaining IoT devices to improve data availability, then measurement precision is improved, but productivity decreases due to time consumption
Solution Approach 1:
The system automatically collects, processes, and corrects data from multiple sensors without requiring farmer intervention, eliminating maintenance burdens while improving data availability and quality
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
A method for correcting remote sensor data of an agricultural field, the method comprising the following steps: receiving remote sensor data (DR) for the agricultural field from a remote sensor, wherein the remote sensor data (DR) comprises at least one remote measurement value corresponding to at least one location that is measured by the remote sensor at at least one point in time of obtaining the remote measurement value; receiving local sensor data (DL) for the agricultural field from at least one local sensor, wherein the at least one local sensor data (DL) comprises at least one local measurement value corresponding to at least one location of the at least one local sensor and corresponding to at least one point in time of obtaining the local measurement value correlating to the location and point of time of obtaining the remote measurement value; determining a correction model based on the previously received local sensor data (DL) and the previously received remote sensor data (DR); and determining corrected current remote sensor data (DRP, DRPR) by applying the correction model to current remote sensor data.