A Data-Driven Strategy for Long-Term Agrarian Sustainability using the Application of Machine Learning Algorithms to Predictive Models for Pest and Disease Management
The reactive pest and disease management strategies implemented for sustainable agriculture are delayed, pesticide use is high, and crop losses are high due to human monitoring. It is not very efficient, not free of errors prone, and not environmentally friendly. In order to address these problems,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | SHS Web of Conferences |
| Online Access: | https://www.shs-conferences.org/articles/shsconf/pdf/2025/07/shsconf_iciaites2025_01033.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The reactive pest and disease management strategies implemented for sustainable agriculture are delayed, pesticide use is high, and crop losses are high due to human monitoring. It is not very efficient, not free of errors prone, and not environmentally friendly. In order to address these problems, this study presents the Pest and Disease Management Machine Learning Algorithm (PDM MLA), a data driven pest and disease control approach. PDM-MLA based on predictive modeling predicts infestations with high accuracy by analyzing weather, parameters of soil, history of outbreaks of pests, and crop health data. Real time decisionmaking with the help of it helps in making proactive intervention which minimizes crop damage and also helps to better use pesticides. PDM-MLA is unlike conventional methods which, even when targeting specific cancers, may create chemical dependency issues and are unnecessary risks for the environment. In addition, costs and ecological balance are increased by resource efficiency insofar as pest control measures are only applied when needed. PDM-MLA results from empirical evidence show an improved predictive accuracy, and thus lower crop losses, increased yield and more sustainable farming. This framework combines IoT sensor networks and big data analytics, with AI based forecasting, to offer a scalable solution for precision agriculture. By pointing out its potential to transform modern farming in terms of food security and sustainable farming and machinery, the study helps people be aware. |
|---|---|
| ISSN: | 2261-2424 |