Thesis topics
Climate Change Adaptation Strategies in Crop and Fruit Production through Artificial Intelligence and Data-Driven Methods
title
Climate Change Adaptation Strategies in Crop and Fruit Production through Artificial Intelligence and Data-Driven Methods
institution
doctoral_school
supervisor
discipline
description
Climate change represents one of the most complex challenges of our time, fundamentally
reshaping the sustainability and resilience of agricultural production. Rising temperatures, shifts
in precipitation patterns, soil moisture decline, and the increasing frequency of extreme weather
events all exert significant pressure on crop and fruit production systems. Traditional cultivation
techniques and decision-support tools are increasingly insufficient to address these dynamic and
interrelated environmental changes.
The proposed doctoral research aims to develop a data-driven and artificial intelligence-based
methodological framework to support the adaptation of crop and fruit production systems to
climate change. The research will focus on the identification, integration, and analysis of diverse
data sources, including meteorological, soil, remote sensing, yield, and phenological data, to
enable more accurate modeling of climatic impacts on plant development and productivity.
Building on these data, machine learning and AI algorithms will be employed to uncover patterns
linking weather variability and crop growth, predict stress conditions, and optimize key
management decisions such as irrigation, fertilization, and variety selection.
A critical component of the research will be ensuring data quality and interoperability across
different information sources, which is essential for building and validating predictive models.
Furthermore, the project seeks to develop a climate-adaptive decision support system that utilizes
real-time data to assist farmers in improving production efficiency, stability, and sustainability.
The expected outcome is a scientifically grounded, AI-enhanced adaptation strategy that
strengthens the resilience of crop and fruit production under changing environmental conditions.
The research aims to contribute to the emergence of an innovative, data-driven, and climate-
smart agricultural paradigm, capable of effectively responding to climate challenges while
preserving natural resources.
reshaping the sustainability and resilience of agricultural production. Rising temperatures, shifts
in precipitation patterns, soil moisture decline, and the increasing frequency of extreme weather
events all exert significant pressure on crop and fruit production systems. Traditional cultivation
techniques and decision-support tools are increasingly insufficient to address these dynamic and
interrelated environmental changes.
The proposed doctoral research aims to develop a data-driven and artificial intelligence-based
methodological framework to support the adaptation of crop and fruit production systems to
climate change. The research will focus on the identification, integration, and analysis of diverse
data sources, including meteorological, soil, remote sensing, yield, and phenological data, to
enable more accurate modeling of climatic impacts on plant development and productivity.
Building on these data, machine learning and AI algorithms will be employed to uncover patterns
linking weather variability and crop growth, predict stress conditions, and optimize key
management decisions such as irrigation, fertilization, and variety selection.
A critical component of the research will be ensuring data quality and interoperability across
different information sources, which is essential for building and validating predictive models.
Furthermore, the project seeks to develop a climate-adaptive decision support system that utilizes
real-time data to assist farmers in improving production efficiency, stability, and sustainability.
The expected outcome is a scientifically grounded, AI-enhanced adaptation strategy that
strengthens the resilience of crop and fruit production under changing environmental conditions.
The research aims to contribute to the emergence of an innovative, data-driven, and climate-
smart agricultural paradigm, capable of effectively responding to climate challenges while
preserving natural resources.
student count limit
2
location
Szombathely, Budapest
deadline
2026-05-31