Climate Change Impact on Agricultural Land Suitability: An Interpretable Machine Learning-Based Eurasia Case Study
V. Shevchenko, Aleksandr Lukashevich, Daria Taniushkina, Alexander Bulkin, Roland Grinis, Kirill Kovalev, Veronika Narozhnaia, Nazar Sotiriadi, A. N. Krenke, Yury Maximov
Abstract
The United Nations has identified improving food security and reducing hunger as essential components of its sustainable development goals. As of 2022, approximately 735 million people worldwide are experiencing hunger and malnutrition, with numerous fatalities reported. Climate change significantly impacts agricultural land suitability, potentially leading to severe food shortages and subsequent social and political conflicts. To address this issue, we have developed a machine learning-based approach to predict the risk of substantial land suitability degradation and changes in irrigation patterns. Our study focuses on Central Eurasia, a region burdened with economic and social challenges. This study is among the first to employ interpretable machine learning methods to assess the impact of climate change on agricultural land suitability under various carbon emission scenarios. The feature importance analysis reveals specific climate and terrain characteristics that may influence land suitability. The efficacy of our model is demonstrated through its performance metrics, achieving an accuracy of 86% and a mean average precision of 72% in a multi-class land suitability classification task. Tackling the most vulnerable regions in Eastern Europe and Northern Asia offers policymakers valuable insights for making informed decisions and preventing a humanitarian crisis, such as supplying additional water and fertilizers. This study highlights the potential of machine learning in addressing global challenges, particularly in reducing hunger and malnutrition.