Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.17254455 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>Cassava (Manihot esculenta Crantz) is a staple food for over 500 million people in SubSaharan Africa, but its productivity is being threatened by climate-driven pest epidemics such as whiteflies (Bemisia tabaci), mealybugs (Phenacoccus manihoti), and viral pathogens such as cassava mosaic and brown streak. These insects, whose reproduction and dissemination increase with temperature rise and erratic rains, cause 20–80 % yield losses in heavy infestations and threaten domestic food security. Conventional scouting and reactive pesticides have not been effective in controlling the outbreaks in the presence of fluctuating climatic conditions. This study suggests a cloud-based predictive analytics framework that pulls in real-time meteorology data, field-level observations from farmers, remote-sensing imagery, and past pest–climate datasets into a single cloud data warehouse. Machine-learning models convert these inputs into spatial risk maps and early warning messages, which are delivered via mobile dashboards to farmers, extension agents, and policy-makers. The model concept recognizes the ways in which elastic cloud-based infrastructure is able to overcome local hardware and connectivity limitations, improving timely pest detection and enabling climate-smart and risk-informed decision-making at the farm and community levels. </p>