What question did this study set out to answer?

This study aims to develop a machine learning framework for accurately predicting paddy yield using historical agro-meteorological data.

June 22, 2026Open Access

Machine Learning Based Paddy Yield Prediction in Haryana and Punjab Using Historical Agro-Meteorological Data from ERA5

View Full Paper

Ask AI

Bookmark

This study aims to develop a machine learning framework for accurately predicting paddy yield using historical agro-meteorological data.
Used historical data from 1981-2023 for model training.
Incorporated climatic variables like rainfall, temperature, and soil moisture.
Evaluated models including Random Forest, LSTM, and Monte Carlo dropout against 2023 yield data.
LSTM model achieved R² of 0.91 for both states and MAPE of 3.2% for Haryana, 5.28% for Punjab.
LSTM with Monte Carlo dropout had R² values of 0.96 in Haryana, 0.88 in Punjab; MAPE of 2.1% and 7.43% respectively.
Predicted intervals of ±8-12% for Haryana and ±12-18% for Punjab enhanced forecasting utility.

No takes yet. Share an insight, caveat, or question.

Randomized trial demonstrates machine learning enhances paddy yield predictions in Haryana and Punjab, indicating improved agricultural planning.

Khare et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial demonstrates machine learning enhances paddy yield predictions in Haryana and Punjab, indicating improved agricultural planning.