Efficiency of Machine Learning Techniques for Predicting Vapor Pressure Deficit in Arid and Semi-Arid Regions (Case Study: South Khorasan Province)

Climate change, as one of the global challenges of the present century, has profound impacts on water resources and agriculture. The increase in temperature and decrease in rainfall in arid and semi-arid regions have made optimal water resource management a top priority.In countries facing climate change and drought, accurate estimation of evapotranspiration plays a vital role in water resource management and ensuring food security.One of the key factors affecting evapotranspiration is the vapor pressure deficit (VPD), which significantly impacts the accuracy of related calculations. This study focuses on predicting the vapor pressure deficit using advanced machine learning techniques. The methods employed include linear regression (LR), generalized additive model (GAM), random subspace (RSS), random forest (RF), and M۵ Purned model(M۵P). In this study, monthly average data, including temperature, humidity, precipitation, and vapor pressure deficit, were extracted from the JRA-۵۵ database for the period from ۱۹۵۸ to ۲۰۲۳. The analysis of vapor pressure deficit data in the study areas of Birjand, Sarayan, Qaen, and Tabas showed that the annual average vapor pressure deficit increased by ۶ Pascals, ۱۰ Pascals, ۴ Pascals, and ۵ Pascals, respectively.In the next step, the extracted data for temperature, precipitation, and humidity were used as input variables, and vapor pressure deficit was used as the target variable in machine learning algorithms. Model performance was evaluated using root mean square error (RMSE), mean absolute error (MAE), Pearson correlation (CC), and Kling-Gupta efficiency (KGE) as evaluation indices.The results showed that the GAM model outperformed other models in all study areas. The evaluation values for each region were as follows: Birjand [ RMSE=۰.۳۰۸, MAE=۰.۲۴۷, KGE=۰.۹۱۴, CC=۰.۹۲۰], SAarayan [RMSE=۰.۴۰۱, MAE=۰.۳۰۳, KGE=۰.۹۳۷, CC=۰.۹۵۱], Qaen [RMSE=۰.۰۷۲, MAE=۰.۰۵۵, KGE=۰.۹۸۷, CC=۰.۹۹۷] and Tabas[RMSE=۰.۲۳۰, MAE=۰.۱۸۴, KGE=۰.۹۲۰, CC=۰.۹۴۲] The predictions made by the model indicated that, over the next ۱۰ years, the annual average vapor pressure deficit in the studied regions will significantly increase: Birjand: ۹ Pascals, Sarayan: ۱۰ Pascals, Qaen: ۷ Pascals and Tabas: ۵ PascalsThis increase signifies serious challenges for water resources and an increase in water consumption in the region’s hot and dry climatic conditions. Finally, this study recommends the GAM model as an effective tool for future research, especially for use in the development of smart irrigation systems, which play a crucial role in sustainable water resource management.

کلیدواژه ها:

Vapor Pressure Deficit ، GAM ، machine learning ، Drought