Experiment code 21.7.3.41
Experiment Title Impact of Climate Change on Paddy Crop Using Machine Learning models in Navsari
Research Type Departmental Research
Experiment Background Agricultural productivity in Navsari district is strongly influenced by climatic factors such as rainfall, temperature and other weather variables. Climate variability and changes over years impact the yield of paddy. In Navsari district, farmers face irregular rainfall and rising temperatures that directly affect crop yield. Traditional regression models provide limited predictive ability in nonlinear and complex relationships, whereas machine learning approaches might better capture interactions between climate and productivity. Analytical techniques such as classical regression models and modern machine learning (ML) models offer different advantages in prediction and understanding of these relationships. This study proposes a comparison of classical and advanced machine learning methods to assess how climate variability affects crop yields in Navsari using secondary data.
Experiment Group Social Science
Unit Type (02)EDUCATION UNIT
Unit (12)NAVINCHANDRA MAFATLAL COLLEGE OF AGRICULTURE (NAVSARI)
Department (247)Statistics Department, NMCA, Navsari
BudgetHead (303/12712/03)303/03/REG/01784
Objective
  1. To analyze the impact of climate variability on rice productivity in Navsari district using classical and machine learning techniques.
  2. To evaluate and compare the performance of different models.
PI Name (NAU-EMP-2025-001970)PRASHANTBHAI RAMESHKUMAR VEKARIYA
PI Email prashantvekariya@nau.in
PI Mobile 9737819161
Year of Approval 2026
Commencement Year 2026
Completion Year 2027
Research Methodology
  • Data Collection Tools & Techniques:

Data Sources:

Directorate of Agriculture, Gujarat (Area, Production & Yield reports)

Directorate of Economics and Statistics (DES)

India Meteorological Department (IMD) and Agricultural Meteorology Department, NAU, Navsari

Techniques:

Classical Statistical Methods

Multiple Linear Regression (Draper & Smith (1998))

Time Series Models (ARIMA/SARIMA) (Box, et al. (2015))

Machine Learning Techniques

Random Forest Regression (Breiman, L. (2001))

XGBoost (Chen & Guestrin (2016))

 Model Evaluation Criteria

Root Mean Square Error (RMSE)

Mean Absolute Error (MAE)

Coefficient of Determination (R²)

Cross-validation techniques (Hastie et al. (2017))
(NAU-EMP-2025-001970)
PRASHANTBHAI RAMESHKUMAR VEKARIYA 		prashantvekariya@nau.in 9737819161 09-02-2026
Active
Sr. No. Operation Date Nature of Data Value of Data Operation Status
Sr. No. Operation Date Operation Status
Sr. No. Operation Date Operation Status
Sr. No. Operation Date Operation Status
About Us

NAU-AEMS-ZP is an "Agricultural Experiment Monitoring System", which is developed to manage and provide information on all agricultural experiments done by Navsari Agricultural University.

Contact Us

© 2021 NAU , Navsari Agricutural University. All rights reserved. Design by IT Cell, NAU

Unique Visit Counter: 109934