Enhancing Meghdoot: Integrating AI for Smarter Agricultural Advisories
| cg.authorship.types | CGIAR single centre | en_US |
| cg.contributor.affiliation | International Livestock Research Institute | en_US |
| cg.contributor.crp | Climate Change, Agriculture and Food Security | en_US |
| cg.contributor.donor | CGIAR Trust Fund | en_US |
| cg.contributor.initiative | Digital Innovation | en_US |
| cg.coverage.country | India | en_US |
| cg.coverage.iso3166-alpha2 | IN | en_US |
| cg.coverage.region | Asia | en_US |
| cg.coverage.region | Southern Asia | en_US |
| cg.creator.identifier | Ram Dhulipala: 0000-0002-9720-3247 | en_US |
| cg.howPublished | Grey Literature | en_US |
| cg.place | Nairobi, Kenya | en_US |
| cg.reviewStatus | Internal Review | en_US |
| cg.subject.actionArea | Systems Transformation | en_US |
| cg.subject.impactArea | Poverty reduction, livelihoods and jobs | en_US |
| cg.subject.sdg | SDG 1 - No poverty | en_US |
| cg.subject.sdg | SDG 2 - Zero hunger | en_US |
| cg.subject.sdg | SDG 13 - Climate action | en_US |
| dc.contributor.author | Dhulipala, Ram | en_US |
| dc.contributor.author | Singh, Kanika | en_US |
| dc.date.accessioned | 2025-01-31T09:34:44Z | en_US |
| dc.date.available | 2025-01-31T09:34:44Z | en_US |
| dc.identifier.uri | https://hdl.handle.net/10568/172636 | en_US |
| dc.title | Enhancing Meghdoot: Integrating AI for Smarter Agricultural Advisories | en_US |
| dcterms.abstract | Digital Innovation Initiative at ILRI, in collaboration with partners, is integrating Artificial Intelligence (AI) into Meghdoot to enhance its efficiency and accuracy. A pilot project has tested AI models, such as Random Forest regression, Naive Bayesian, and Stacked Models, alongside OpenAI prompt engineering. Conducted at three locations in India, the pilot has demonstrated promising results. Efforts are underway to refine machine learning models, incorporate expert knowledge, and explore techniques like noisy labels to improve advisory quality. A web-based platform has also been developed to automate advisory generation, allowing users to select parameters like location, crop type, and AI model. The system generates personalized advisories using historical, observed, and forecasted weather data. It provides both AI-generated and traditional advisories, along with weather forecasts and SMS summaries for easy dissemination. Moving forward, the goal is to integrate this AI-powered advisory system into Meghdoot, scaling it nationwide to improve agricultural decision-making, enhance sustainability, and increase resilience among farmers. | en_US |
| dcterms.accessRights | Open Access | en_US |
| dcterms.audience | Academics | en_US |
| dcterms.audience | CGIAR | en_US |
| dcterms.audience | Donors | en_US |
| dcterms.audience | Scientists | en_US |
| dcterms.bibliographicCitation | Dhulipala, R. and Singh, K.2024. Enhancing Meghdoot: Integrating AI for Smarter Agricultural Advisories. Progress Report. Nairobi, Kenya: ILRI. | en_US |
| dcterms.issued | 2024-12-29 | en_US |
| dcterms.language | en | en_US |
| dcterms.license | CC-BY-4.0 | en_US |
| dcterms.publisher | International Livestock Research Institute | en_US |
| dcterms.subject | agriculture | en_US |
| dcterms.subject | climate change | en_US |
| dcterms.subject | food security | en_US |
| dcterms.type | Report | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Enhancing Meghdoot Integrating AI for Smarter Agricultural Advisories.pdf
- Size:
- 384.2 KB
- Format:
- Adobe Portable Document Format
- Description:
- Report
License bundle
1 - 1 of 1
Loading...
- Name:
- license.txt
- Size:
- 1.75 KB
- Format:
- Item-specific license agreed upon to submission
- Description: