ARCHIVES
VOL. 10, ISSUE 2 (2025)
Adaptive ML and DL framework for climate-reseilient agriculture
Authors
Muskan, Palamakula Sowmika Reddy, Bazaru Sivanandini, Dr Meena Chaudhary, Dr Narender Gautam
Abstract
Climate change impacts have serious implications for world agriculture,
jeopardizing food supplies and farmers' livelihoods. In this research, the
Integrated Adaptive Yield Prediction Framework (IAYPF) is proposed, using
machine learning (ML) and deep learning (DL) methodologies to improve the
precision of crop yield prediction. By combining multiple data
sources—meteorological factors, soil type, and agronomic data—the framework
develops a strong and adaptive prediction model. The IAYPF focuses on
state-of-the-art feature selection, region-adapted adaptation plans, and
wide-ranging validation schemes to provide reliable and interpretable outcomes.
Cutting-edge innovations like attention mechanisms and transfer learning are
utilized to enhance the accuracy and efficiency of forecasting models.
Directions for future developments for the system involve the incorporation of
socio-economic variables, design of accessible systems for farmers, and partnership
with local agricultural academies to enhance responsiveness. Moreover, the
framework delves into real-time observation, multi-crop flexibility, and cell
guide to increase its sensible use. It additionally highlights scalable
deployment, dynamic retraining of fashions with remarks loops, and
decision-support equipment custom-made to unique agro-ecological zones. Aimed
at mitigating the exposure that is inherent in climate variability, the IAYPF
seeks to make a contribution toward sustainable agriculture, improve food
security, and increase the resilience of farming systems.
Download
Pages:65-71
How to cite this article:
Muskan, Palamakula Sowmika Reddy, Bazaru Sivanandini, Dr Meena Chaudhary, Dr Narender Gautam "Adaptive ML and DL framework for climate-reseilient agriculture". International Journal of Advanced Education and Research, Vol 10, Issue 2, 2025, Pages 65-71
Download Author Certificate
Please enter the email address corresponding to this article submission to download your certificate.