Aerial Yield Data Aggregation for Offline Farm Connectivity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Agricultural data transfer and processing challenges arise due to poor network connectivity in rural areas, leading to unreliable data collection and loss, which hampers real-time decision-making and accurate yield determination in precision agriculture, especially in areas with limited infrastructure and multiple device deployments.
Innovation Solution
A data-centric computing platform enabling edge and cloud computing for reliable data transfer and processing, standardizing IoT data ingestion, and simplifying AI/ML inferencing functions, using aerial drones or similar technology to collect and process data in areas with little to no network connectivity, and enabling two-way communication between data delivery vehicles and compute nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If USB sticks are used to store data on farm machinery, then data can be collected offline in areas with poor network connectivity, but data loss occurs due to lost, erased, stolen, or misplaced USB sticks
Solution Approach 1:
Aerial data delivery vehicles (drones) act as intermediaries between ground-based farm machinery and cloud computing systems. The drones collect data from multiple sources including USB sticks, onboard sensors, and direct machine connections, then transport this data to areas with network connectivity for upload to the cloud, eliminating the risk of USB stick loss while maintaining offline data collection capability
Solution Approach 2:
The aerial data delivery vehicle serves multiple functions: it acts as a mobile data collection point, a data transport aircraft, and a communication relay. It can collect data from various sources (USB sticks, sensors, direct machine interfaces), store data onboard, and deliver data to multiple destinations, making the system more reliable than single-function USB stick storage
2Quantity of substance
If data is collected from multiple harvesters using different yield monitors, then comprehensive harvest data is obtained, but data inconsistency occurs due to lack of calibration between devices
Solution Approach 1:
The system applies calibration factors and normalization parameters to data from different yield monitors. By adjusting measurement parameters and applying correction algorithms, data from multiple uncalibrated devices can be standardized to a common reference frame, enabling accurate aggregation of harvest data across multiple harvesters
Solution Approach 2:
The system implements calibration feedback loops where data from reference-grade sensors and historical data are used to continuously adjust and refine calibration parameters for each yield monitor. This ongoing calibration process ensures that measurements from multiple devices remain consistent and accurate over time
3Measurement precision
If cloud analytics systems are used for sophisticated data processing, then accurate yield determination is achieved, but network connectivity requirements cannot be met in rural areas
Solution Approach 1:
The system moves data processing from a single location (cloud) to multiple dimensions by implementing edge computing capabilities on aerial vehicles and ground equipment. This distributed computing architecture brings analytics closer to the data source, enabling sophisticated processing in rural areas without requiring continuous cloud connectivity
Solution Approach 2:
The computing architecture is segmented into multiple layers: onboard machine computing, aerial vehicle edge computing, and cloud computing. Each layer handles appropriate processing tasks, with critical analytics performed at the edge where data is collected, reducing dependency on continuous cloud connectivity while maintaining analytical capability
Data Source
AI summary
The present invention is for an autonomous aerial vehicle that enables near real-time computation of harvest yield data. Generally, the autonomous aerial vehicle receives combine harvest data from a harvesting vehicle, generates high-resolution yield data based on sensor suite that is on-board the autonomous vehicle, obtains edge compute data from an edge computing device at the edge of the network, and segments the received combine harvest data, the generated high-resolution yield data, and the obtained edge compute data. The aerial vehicle applies data normalization models to the segmented data and computes a normalized harvest yield for at least a portion a land tract. In this manner, the data delivery vehicles computes normalized data that otherwise can by noisy and unreliable.