At Cervantes Agritech our mission is to develop and deliver high-quality, affordable information tools to help manage insect and disease pests of plants. We have developed an integrated platform for turning pest surveillance, environmental data and scientific models into timely, actionable intelligence for growers, industry bodies and biosecurity agencies.
The four main components of the systems are surveillance, data management, modelling and analysis, and communication.
Surveillance
Knowledge of the state of the crop and pest system are usually important to provide the models with biofixes1. Biofixes give models a starting point to anchor the simulation. They are a “reality check” to save small errors from accumulating over time. A biofixes for a pest simulation could be the first adult insect trapped.
Surveillance can be automated or manual (involving trap inspections, sweep netting or plant inspections). Automated traps offer the advantage of timely notification, reduced servicing costs and persistent surveillance effort.
At Cervantes Agritech, we use a mix of in-house and third-party developed smart traps. Bring together the information needed to understand pest pressure across farms, regions and borders. Our informatics platform can ingest trap records, field observations, laboratory diagnostics, crop phenology, weather data, remote-sensing products and operational data from existing systems.
It supports both manual and automated data capture, including mobile field applications, connected traps and IoT devices, with standardised data structures that improve consistency across programs and jurisdictions.
Data Management
Reliable forecasts depend on reliable data. Built-in validation rules identify incomplete, implausible or inconsistent records before they affect analysis. Role-based access controls, audit trails and configurable data-sharing arrangements allow organisations to retain control of commercially or market-sensitive information.
This enables collaboration without requiring all participants to expose their underlying data unnecessarily. At Cervantes Agritech, we take our data custodianship responsibilities seriously. We believe that farmers are entitled to access data collected on their farms and have a default right to privacy.
Forecasting and risk modelling
Forecasting tools translate surveillance and environmental information into estimates of pest development, population pressure, likely activity periods and management risk. Depending on the pest and available evidence, models may include degree-day accumulation, phenology models, habitat suitability, spread-risk analysis, trap-catch interpretation and machine-learning approaches.
Models can be configured for local conditions and progressively improved as more field data becomes available.
CLIMEX models are intended to simulate a pests geographical dynamics in response to climate and weather, indicating its potential distribution, number of generations and seasonal dynamics. In our informatics platform the CLIMEX models are used to provide a seasonal outlook at each location as well as insights into the suitability patterns as a map.
DYMEX models capture detailed population dynamics, and are used to identify the abundance patterns of each lifestage through time. We use these models to identify management windows, when susceptible lifestages are likely to be present in the crop, and when the next trapping window is likely to occur.
There are literally 100’s of CLIMEX and DYMEX models that have been published. Here is a list of some of them that are of popular concern for agriculture and horticulture.
| Scientific name | Common names | CLIMEX | DYMEX |
| Bactrocera tryoni | Queensland fruit fly | ✓ | ✓ |
| Bactrocera dorsalis | Oriental fruit fly | ✓ | ✓ |
| Bactrocera zonata | Peach fruit fly | ✓ | |
| Ceratitis capitata | Mediterranean fruit fly, Medfly | ✓ | ✓ |
| Helicoverpa armigera | Cotton bollworm, corn earworm | ✓ | ✓ |
| Spodoptera frugiperda | Fall armyworm | ✓ | ✓ |
| Spodoptera exigua | Beet armyworm | ✓ | |
| Epiphyas postvittana | Light-brown apple moth | ✓ | |
| Bemisia tabaci MEAM1 | Silver-leaf whitefly | ✓ | |
| Cydia pomonella | Codling moth, Carpocapsa | ✓ | |
| Plutella xylostella | DIamond-back moth | ✓ | ✓ |
| Halyomorpha halys | Brown marmorated stinkbug | ✓ | Under development |
| Oryctes rhinoceros | Coconut rhinoceros beetle | ✓ | |
Maps, dashboards and alerts
Users receive information through intuitive dashboards, interactive maps and targeted notifications. Rather than requiring users to interpret raw datasets, the platform presents current pest status, forecast risk, emerging hotspots and recommended monitoring or intervention windows.
Alerts can be tailored by crop, pest, location, user role and risk threshold, helping growers and program managers focus attention where it is most needed.
- A specific event in the life cycle of a pest that serves as a reference point for starting simulation models. ↩︎
