Integrating Domain Knowledge and Machine Learning in Rice Cultivation: A Case Study of Algeria

Integrating Domain Knowledge and Machine Learning in Rice Cultivation: A Case Study of Algeria

Alvin Sherman Library

Research has highlighted Artificial Intelligence (AI) as a promising solution to mitigate the threat of food insecurity. Rice, a staple in the global diet, is particularly vulnerable to heat stress caused by climate change. The challenges of climate change, population growth, and increased famine risk may be alleviated through the implementation of AI models in rice cultivation. For decades, agricultural workers have faced the dilemma of needing to increase crop yields while dealing with dwindling resources and the need for more efficient practices. AI models, however, are limited by the quality and scope of the data they receive. Integrating domain knowledge with machine learning systems offers an advanced approach to predictive analysis in rice cultivation. Precision agriculture, which involves using AI software for data-driven decision-making, has the potential to significantly improve crop management practices. This study examines the role of AI in agriculture with a specific focus on rice cultivation in Algeria and provides a comprehensive overview of the intersection between domain knowledge and machine learning. Data from World Bank Group was analyzed for historical and projected temperature patterns, identifying Algeria as one of the countries most affected by climate change and its resulting impact on crop yield. This region thus, presents substantial opportunities for leveraging machine learning systems to enhance agricultural outcomes. Based on thirty years of Algerian agricultural and climate data, our study proposes a framework for synthesizing domain knowledge with machine learning algorithms to support climate-resilient rice production.