Drought vulnerability of central Sahel agrosystems: a modelling-approach based on magnitudes of changes and machine learning techniques

ABSTRACT

Agricultural drought is a complex phenomenon with numerous consequences and negative implications for agriculture and food systems. The Sahel is frequently affected by severe droughts, leading to significant losses in agricultural yields. Consequently, assessing vulnerability to agricultural drought is essential for strengthening early warning systems. The aim of this study is to develop a new multivariate agricultural drought vulnerability index (MADVI) that combines static and dynamic factors extracted from satellite data. First, pixel temporal regression from 1981 to 2021 was applied to climatic and biophysical covariates to determine the gradients of trend magnitudes. Second, principal component analysis was applied to groups of factors that indicate the same type of vulnerability to configure the basic equation of vulnerability to agricultural drought. Then, random forest (RF), K-nearest neighbours (KNN), support vector machine (SVM) and naïve Bayes (NB) were used to predict drought vulnerability classes using the 28 factors as inputs and 708 pts of randomly distributed class labels. The results showed statistical agreement between the predicted MADVI spatial variability and the reference model (R=0.86 for RF) and its statistical relationships with the vulnerability subcomponents, with an R=0.73 with exposure to climate risk, R=0.64 with the socioeconomic sensitivity index, R=0.6 with the biophysical sensitivity index and a relatively weak correlation (R=0.21) with the physiographic sensitivity index. The overall vulnerability situation in the watershed is 21.8% extreme, 10% very high, 16.8% high, 27.7% moderate, 22.2% low and 1.5% relatively low considering the cartographic results of the predicted vulnerability classes with SVM having the best performance (accuracy=0.96, Kappa=0.95). The study is the first approach that uses the gradients of magnitudes of satellite covariate anomaly trends in multivariate modelling of vulnerability to agricultural drought. It can be easily scaled up across the Sahel region to improve early warning measures related to the impacts of agricultural drought.

KEYWORDS:

• Vulnerability
• drought
• indices
• climate hazard
• machine learning
• Sahel region

Acknowledgements

We gratefully thank the following research structures: the laboratory (UR 18) of the Department of Geodesy and Topography (IAV Hassan II), the laboratory of UMR CNRS ESPACE 7300 (AMU France), the Regional Center for Agronomic Research of Marrakech (INRA, Morocco) and Institut National de la Recherche Agronomique du Niger (INRAN) for their contributions and collaborations in this research.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data available

All data supporting the findings of this study are available and publicly accessible on the Google Earth Engine platform via https://developers.google.com/earth-engine/datasets/. The results data is also available upon reasonable request from the corresponding author, [IHH].

Additional information

Funding

This research was supported by the Islamic Development Bank under a three-year thesis grant [grant number: ID 600040753]. The first author is very grateful for this financial support.