Pest Forecasting Model Using Historical Pesticide Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional pest forecasting methods are time-consuming, costly, and require extensive manpower to collect surveillance data, making it difficult to generate reliable field-specific models.
Innovation Solution
A processor-implemented method that uses historical pesticide application data and agronomic information to estimate pest affecting stages and inoculation times, generating a pest forecasting model based on weather conducive lag, which can be validated and adapted using participatory sensing and crowd sourcing inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If surveillance data collection method is used to gather pest infestation data, then forecasting model reliability is improved, but time consumption and cost increase significantly
Solution Approach 1:
The patent applies preliminary action by using historical pesticide application data that has already been collected and stored, rather than collecting new surveillance data from scratch. The system retrospectively analyzes past pesticide usage records to infer pest infestation patterns, thereby avoiding the time-consuming process of forward-looking surveillance data collection while maintaining model training capability
Solution Approach 2:
The patent uses copying by creating a proxy representation of pest infestation data through pesticide application records. Instead of directly observing and collecting pest incidence data through field surveillance, the system copies indirect information from pesticide usage patterns, which correlate with pest pressure, thereby obtaining training data without direct surveillance effort
2Reliability
If surveillance data collection method is used to gather pest infestation data, then forecasting model reliability is improved, but manpower requirements increase significantly
Solution Approach 1:
The patent applies self-service by enabling the system to automatically retrieve and process pesticide application data from existing digital records without requiring human investigators to physically visit fields. The data extraction and initial processing are performed automatically by the computing system, eliminating the need for manual data collection teams
Solution Approach 2:
The patent uses an intermediary approach by introducing pesticide application records as a mediator between the goal of obtaining pest infestation data and the actual data collection process. Instead of directly measuring pest populations, the system uses pesticide usage information as an intermediate proxy that indirectly reflects pest pressure, thereby avoiding direct field surveillance manpower requirements
3Measurement precision
If field-specific surveillance data collection is performed, then forecasting model accuracy for specific locations is improved, but data collection difficulty increases
Solution Approach 1:
The patent applies universality by using a single pesticide application database that serves multiple purposes: it provides both location-specific data for field-specific models and aggregated data for regional models. The same digital pesticide usage records can be queried with different spatial filters to generate forecasts at multiple scales, eliminating the need for separate data collection systems for different geographic granularities
Data Source
AI summary
Traditionally, forecasting models were developed using pest or disease instances collected through pest or disease surveillance. The present disclosure relates to pest forecasting using historical pesticide usage information thereby obviating need for voluminous and time consuming effort of collecting site specific data. Firstly forecasting models for different pests or diseases of different crops are generated based on historical data on pesticide usage and historical weather data collected for a geo-location under consideration. The model is validated and adapted with the current scenario of pests. Current scenario is captured using image samples sent from the field or farm through participatory sensing platform. The images are then analyzed to extract information like actual pest infestation in the field, severity, if there was infestation and the like. This analyses helps to derive the actual pest infestation instances in the field.