Copula-Based Joint Drought Index Using Precipitation, NDVI, and Runoff and Its Application in the Yangtze River Basin, China
Hongfei Wei,
Xiuguo Liu,
Weihua Hua
et al.
Abstract:Drought monitoring ensures the Yangtze River Basin’s social economy and agricultural production. Developing a comprehensive index with high monitoring precision is essential to enhance the accuracy of drought management strategies. This study proposes the standardized comprehensive drought index (SCDI) using a novel approach that utilizes the joint distribution of C-vine copula to effectively combine three critical drought factors: precipitation, NDVI, and runoff. The study analyzes the reliability and effecti… Show more
“…Furthermore, mutual feedback and time lag between vegetation and dry conditions are crucial for the construction of a drought index. Vegetation changes reflect the wet and dry conditions of the region, as well as the relationship between soil, atmosphere, and water [5,[26][27][28][29]. The Normalized Difference Vegetation Index (NDVI), land surface temperature (LST), precipitation (PRE), evapotranspiration (ET), and soil moisture (SM) were selected as independent variables to construct a remote sensing drought monitoring model.…”
Driven by continuously evolving precipitation shifts and temperature increases, the frequency and intensity of droughts have increased. There is an obvious need to accurately monitor drought. With the popularity of machine learning, many studies have attempted to use machine learning combined with multiple indicators to construct comprehensive drought monitoring models. This study tests four machine learning model frameworks, including random forest (RF), convolutional neural network (CNN), support vector regression (SVR), and BP neural network (BP), which were used to construct four comprehensive drought monitoring models. The accuracy and drought monitoring ability of the four models when simulating a well-documented Inner Mongolian grassland site were compared. The results show that the random forest model is the best among the four models. The R2 range of the test set is 0.44–0.79, the RMSE range is 0.44–0.72, and the fitting accuracy relationship could be described as RF > CNN > SVR ≈ BP. Correlation analysis between the fitting results of the four models and SPEI found that the correlation coefficient of RF from June to September was higher than that of the other three models, though we noted the correlation coefficient of CNN in May was slightly higher than that of RF (CNN = 0.79; RF = 0.78). Our results demonstrate that comprehensive drought monitoring indices developed from RF models are accurate, have high drought monitoring ability, and can achieve the same monitoring effect as SPEI. This study can provide new technical support for comprehensive regional drought monitoring.
“…Furthermore, mutual feedback and time lag between vegetation and dry conditions are crucial for the construction of a drought index. Vegetation changes reflect the wet and dry conditions of the region, as well as the relationship between soil, atmosphere, and water [5,[26][27][28][29]. The Normalized Difference Vegetation Index (NDVI), land surface temperature (LST), precipitation (PRE), evapotranspiration (ET), and soil moisture (SM) were selected as independent variables to construct a remote sensing drought monitoring model.…”
Driven by continuously evolving precipitation shifts and temperature increases, the frequency and intensity of droughts have increased. There is an obvious need to accurately monitor drought. With the popularity of machine learning, many studies have attempted to use machine learning combined with multiple indicators to construct comprehensive drought monitoring models. This study tests four machine learning model frameworks, including random forest (RF), convolutional neural network (CNN), support vector regression (SVR), and BP neural network (BP), which were used to construct four comprehensive drought monitoring models. The accuracy and drought monitoring ability of the four models when simulating a well-documented Inner Mongolian grassland site were compared. The results show that the random forest model is the best among the four models. The R2 range of the test set is 0.44–0.79, the RMSE range is 0.44–0.72, and the fitting accuracy relationship could be described as RF > CNN > SVR ≈ BP. Correlation analysis between the fitting results of the four models and SPEI found that the correlation coefficient of RF from June to September was higher than that of the other three models, though we noted the correlation coefficient of CNN in May was slightly higher than that of RF (CNN = 0.79; RF = 0.78). Our results demonstrate that comprehensive drought monitoring indices developed from RF models are accurate, have high drought monitoring ability, and can achieve the same monitoring effect as SPEI. This study can provide new technical support for comprehensive regional drought monitoring.
The rapid development of digital tools for crop management offers new opportunities to mitigate the effects of climate change on agriculture. This study examines the Normalized Difference Vegetation Index (NDVI) in coffee-growing areas of the province of Rodriguez de Mendoza, southern Peru, from 2001 to 2022. The objectives were the following: (a) to analyze NDVI trends in these areas; (b) to investigate trends in climatic variables and their correlations with altitude and NDVI; and c) to develop linear models tailored to each coffee-growing area. The study identified significant differences in NDVI trends among coffee plants, with mean NDVI values ranging from about 0.6 to 0.8. These values suggest the presence of stress conditions that should be monitored to improve crop quality, particularly in Huambo. Variability in rainfall, maximum and minimum temperatures, relative humidity, and altitude was also observed, with NDVI values showing a strong negative correlation with altitude. These results are crucial for making informed strategic decisions in integrated crop management and for monitoring crop health using vegetation indices.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.