Scholarlink

<p>Climate change poses a critical threat to agricultural productivity, especially in climate-sensitive regions like Morocco. Understanding how shifting climatic patterns influence agriculture is vital for ensuring food security and sustainable economic growth. This study examines the impact of climate change on agricultural GDP in Morocco, a country with diverse climatic zones, ranging from semi-arid to Mediterranean. Understanding the influence of climatic variables on agricultural productivity is crucial for developing effective adaptation strategies and policy-making. Using data from 1990 to 2022, including temperature, humidity, wind speed, and precipitation from NASA’s MERRA-2, combined with economic data from the World Bank, we applied machine learning models, such as lasso regression, random forests, and neural networks, to analyze these relationships. The results indicate that temperature is the most influential climatic factor, consistently associated with reductions in agricultural productivity due to heat stress. Wind speed shows a moderate effect, supporting pollination in some regions while accelerating evaporation in others. Precipitation also plays a significant role, particularly in rain-fed agricultural areas. In contrast, relative humidity was found to have limited influence on agricultural GDP in most Moroccan regions, as demonstrated by the Lasso regression analysis. Among the models, the Random Forest approach achieved the highest predictive accuracy, with an R-squared value of 0.699, outperforming linear models and neural networks. This research highlights the sensitivity of Morocco’s agricultural sector to temperature changes and the need for region-specific strategies to improve resilience against climate variability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Impact of climate change on agricultural GDP in Morocco using machine learning techniques

  • 期刊论文

  • 发表日期：

    2025年6月16日

查看全文
  • Samir En-Nia,
  • Mariem Liouaeddine,
  • Zakaria Mansouri

摘要

Climate change poses a critical threat to agricultural productivity, especially in climate-sensitive regions like Morocco. Understanding how shifting climatic patterns influence agriculture is vital for ensuring food security and sustainable economic growth. This study examines the impact of climate change on agricultural GDP in Morocco, a country with diverse climatic zones, ranging from semi-arid to Mediterranean. Understanding the influence of climatic variables on agricultural productivity is crucial for developing effective adaptation strategies and policy-making. Using data from 1990 to 2022, including temperature, humidity, wind speed, and precipitation from NASA’s MERRA-2, combined with economic data from the World Bank, we applied machine learning models, such as lasso regression, random forests, and neural networks, to analyze these relationships. The results indicate that temperature is the most influential climatic factor, consistently associated with reductions in agricultural productivity due to heat stress. Wind speed shows a moderate effect, supporting pollination in some regions while accelerating evaporation in others. Precipitation also plays a significant role, particularly in rain-fed agricultural areas. In contrast, relative humidity was found to have limited influence on agricultural GDP in most Moroccan regions, as demonstrated by the Lasso regression analysis. Among the models, the Random Forest approach achieved the highest predictive accuracy, with an R-squared value of 0.699, outperforming linear models and neural networks. This research highlights the sensitivity of Morocco’s agricultural sector to temperature changes and the need for region-specific strategies to improve resilience against climate variability.