AI system
- System
-
YES-TECH (Yield Estimation System based on Technology): satellite remote sensing, weather data and analytical models, including an 'AI/ML model' for kharif crops and a 'semi-physical model' for rabi crops in Madhya Pradesh
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
Ministry of Agriculture and Farmers Welfare (YES-TECH manual); Madhya Pradesh implementation by the Madhya Pradesh Council of Science and Technology as Technology Implementation Partner, mentored by NRSC Hyderabad (per CSE)
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
A national YES-TECH manual and guidelines mandating technology-based yield estimates with at least 30 percent weightage. A state Technology Implementation Partner (MPCST) running satellite, weather and ground-truth data through AI/ML and semi-physical models. Ground-truthing points (130,989 in Madhya Pradesh as of August 2025, per CSE) and a YES-TECH committee reviewing periodic reports. Insurers computing claims from estimated actual yield against threshold yield.
- Human oversight
-
Not assessed
- Relation to AI
-
Official PIB documents (deployer, not the model's maker) state YES-TECH employs AI-driven analytics and that Madhya Pradesh relies fully on technology-based yield estimates. CSE's presentation says kharif yields come from an “AI/ML model” whose results are used to disburse claims. The model output thus directly determines payouts. Whether this produced a benefit is contested. PIB asserts faster, more transparent settlement without data. CSE and Down To Earth document reduced claims, protests and rollback calls among large soybean farmers in Sehore, Vidisha and Bhopal. They also record some farmers' appreciation of timeliness and insurers' claim that manual yields were under-reported. No independent quantified beneficial outcome was found.
- AI contribution
-
YES-TECH produced estimates of crop yields that Madhya Pradesh used to calculate insurance payments. The cited CSE presentation describes an AI or machine-learning model for kharif crops.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
kharif payouts in the three districts fell from Rs 217.91 crore to Rs 55.2 crore
- Category
-
Improved Organizational Efficiency
- Status
-
Not assessed
- Beneficiary groups
-
People. Organizations. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
kharif payouts in the three districts fell from Rs 217.91 crore to Rs 55.2 crore
- Comparison
-
claims paid under manual crop-cutting experiments (2018)
- Results
-
Reference: R217.91 crore. Result: R55.2 crore.
- Additional value from AI
-
Not assessed
- Limitations
-
Official accounts assert faster settlement without quantified supporting results. CSE and Down To Earth report both appreciation of prompt payments and complaints that the estimates reduced payouts. The sources do not establish an independently measured net benefit.
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: Ministry of Agriculture and Farmers Welfare (YES-TECH manual); Madhya Pradesh implementation by the Madhya Pradesh Council of Science and Technology as Technology Implementation Partner, mentored by NRSC Hyderabad (per CSE). Operator: Government of Madhya Pradesh under PMFBY with insurers (AIC, SBI General Insurance, HDFC Ergo); nine states in all as of January 2025.
- Jurisdictions
-
Benefit: Madhya Pradesh,
India (CSE field assessment in Sehore, Vidisha and Bhopal districts). Developer: India. Operator: India. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Accurate historical yield data, since threshold yields and model training depend on past CCE records (CSE). Open satellite data (Sentinel-1) and weather-station data availability. Farmer trust and transparency about input data validation, which CSE found lacking in three districts. State decision on weightage (100 percent in Madhya Pradesh, 30–50 percent elsewhere).
- Replication attempts
-
1 follow-up entries. Outcome unresolved: 1.
- Later findings
-
1 January 2025. By January 2025 nine states had adopted YES-TECH with Madhya Pradesh fully transitioned, per the PIB backgrounder of 14 February 2026; Down To Earth reports that Madhya Pradesh farmers and unions protested low payouts in 2024-25.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0355-source-0001–0008
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Developer, Independent
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Organizations. Society.
- Depth
-
Not assessed
- Reasons
-
People: No verified individual outcome. CSE reports some farmers valuing faster disbursement and others reporting lower claims than losses. Organizations: PIB claims faster settlement without figures. CSE records insurers' view that manual CCEs were manipulated and that YES-TECH removed that interface. Society: Adoption by nine states is stated, but no outcome at scale is documented. Down To Earth reports payouts in three districts fell sharply between 2018 and 2024.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently studied
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Agricultural crop insurance / yield estimation. Government crop-insurance scheme (PMFBY).
- Purpose
-
Estimate crop yields from satellite, weather and model data to replace or supplement manual crop-cutting experiments. The aim: insurance losses assessed accurately and claims paid on time. The claimed benefit (faster, more transparent settlement) is that purpose and is contested.
- Dates
-
Date basis unassessed: 2023 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 8ab6dfa1e286…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 21 October 2026.
Sources
-
Report Independent author
Mahaur, C. (2026). Implementation of Yield Estimation System Based on Technology (YES-TECH) in Madhya Pradesh. Centre for Science and Environment presentation (PDF), CSE webinar of 18 May 2026.
Data is run into the 'AI/ML model' (kharif) and 'semi-physical model' (rabi) to estimate the yield or into a set of their merged parameters, if needed
Large soybean farmers expressed dissatisfaction with shift to YES-TECH, reporting decline in claims received compared to manual CCEs
Some farmers expressed satisfaction - they appreciated the timeliness of claim disbursement compared earlier settlement time
-
News report Independent author
Mahaur, C. (2026). Can technology make India's crop insurance payouts more accurate? Down To Earth, 27 May 2026.
Starting kharif 2023, Madhya Pradesh took the lead by adopting YES-TECH for select crops such as soybean, wheat and paddy
-
News report Independent author
Mahaur, C. & Khurana, A. (2026). Beyond the Lens: Madhya Pradesh Farmers Struggle With Satellite-Based Crop Insurance Under PMFBY. Down To Earth, 20 August 2026.
In 2024-25, farmers and unions in multiple districts of Madhya Pradesh mounted protests, claiming that insurance payouts were too low to cover their losses despite high premiums being paid.
-
Press release Developer
YES-TECH Manual is a comprehensive guide developed after extensive testing and piloting in 100 districts of India.
-
Press release Developer
Press Information Bureau (2025). Pradhan Mantri Fasal Bima Yojana turns Nine. 17 February 2025 (PRID 2104175).
YES-TECH enables large scale adoption of technology-based yield estimates for yield loss and insurance claim assessments under PMFBY.
-
Press release Developer
YES-TECH, CROPIC, and the PMFBY WhatsApp Chatbot are leveraging AI-enabled tools to make crop insurance under PMFBY more innovative, faster, and more transparent for farmers.