A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems

This manuscript aims to develop a new multivariate composite index for monitoring agricultural drought. To achieve this, the AVHRR, VIIRS, CHIRPS data series over a period of 40 years, rainfall and crop yield data as references were used. Variables include parameters for vegetative stress (SVCI, PV,...

Full description

Bibliographic Details
Main Authors: Hanade Houmma, I., Gadal, S., El Mansouri, L., Garba, M., Gbetkom, P.G., Mamane Barkawi, M.B., Hadria, R.
Format: Journal Article
Language:Inglés
Published: Informa UK Limited 2023
Subjects:
Online Access:https://hdl.handle.net/10568/139779
_version_ 1855519060731625472
author Hanade Houmma, I.
Gadal, S.
El Mansouri, L.
Garba, M.
Gbetkom, P.G.
Mamane Barkawi, M.B.
Hadria, R.
author_browse El Mansouri, L.
Gadal, S.
Garba, M.
Gbetkom, P.G.
Hadria, R.
Hanade Houmma, I.
Mamane Barkawi, M.B.
author_facet Hanade Houmma, I.
Gadal, S.
El Mansouri, L.
Garba, M.
Gbetkom, P.G.
Mamane Barkawi, M.B.
Hadria, R.
author_sort Hanade Houmma, I.
collection Repository of Agricultural Research Outputs (CGSpace)
description This manuscript aims to develop a new multivariate composite index for monitoring agricultural drought. To achieve this, the AVHRR, VIIRS, CHIRPS data series over a period of 40 years, rainfall and crop yield data as references were used. Variables include parameters for vegetative stress (SVCI, PV, SMN), water stress (PCI, RDI, NRDI), and heat stress (SMT, TCI, STCI), and a new variable related to environmental conditions was calculated through a normalized rainfall efficiency index. Then, random forest algorithm was used to determine the weights of each component of the model by considering interannual fluctuations in cereal yields as an impact variable. The multivariate composite model was compared to the VHI, NVSWI and SPI-12 indices for validation. The results show a large spatiotemporal concordance between the MDCI and the validation indices with a maximum correlation of 0.95 with the VHI and a highly significant p value (< 2.2e-16). Validation of the MDCI model by SPI-12 shows a significantly higher statistically significant relationship than that observed between SPI and VHI and NVSWI. P value range from 3.531e-05 to 6.137e-06 with correlations that vary between 0.6 and 0.64 depending on the station. It is also highly correlated with the Palmer drought severity index (PDSI) and climatic water deficit index (CWDI), with R = 0.85 and p value < 5.8e-10 and R = 0.72 and p value < 1.9e-6, respectively. Finally, the study provides a new direction for multivariate modeling of agricultural drought that should be further explored under various agroclimatic conditions.
format Journal Article
id CGSpace139779
institution CGIAR Consortium
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher Informa UK Limited
publisherStr Informa UK Limited
record_format dspace
spelling CGSpace1397792025-12-08T09:54:28Z A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems Hanade Houmma, I. Gadal, S. El Mansouri, L. Garba, M. Gbetkom, P.G. Mamane Barkawi, M.B. Hadria, R. drought remote sensing forests sahel This manuscript aims to develop a new multivariate composite index for monitoring agricultural drought. To achieve this, the AVHRR, VIIRS, CHIRPS data series over a period of 40 years, rainfall and crop yield data as references were used. Variables include parameters for vegetative stress (SVCI, PV, SMN), water stress (PCI, RDI, NRDI), and heat stress (SMT, TCI, STCI), and a new variable related to environmental conditions was calculated through a normalized rainfall efficiency index. Then, random forest algorithm was used to determine the weights of each component of the model by considering interannual fluctuations in cereal yields as an impact variable. The multivariate composite model was compared to the VHI, NVSWI and SPI-12 indices for validation. The results show a large spatiotemporal concordance between the MDCI and the validation indices with a maximum correlation of 0.95 with the VHI and a highly significant p value (< 2.2e-16). Validation of the MDCI model by SPI-12 shows a significantly higher statistically significant relationship than that observed between SPI and VHI and NVSWI. P value range from 3.531e-05 to 6.137e-06 with correlations that vary between 0.6 and 0.64 depending on the station. It is also highly correlated with the Palmer drought severity index (PDSI) and climatic water deficit index (CWDI), with R = 0.85 and p value < 5.8e-10 and R = 0.72 and p value < 1.9e-6, respectively. Finally, the study provides a new direction for multivariate modeling of agricultural drought that should be further explored under various agroclimatic conditions. 2023-12-31 2024-03-01T14:53:26Z 2024-03-01T14:53:26Z Journal Article https://hdl.handle.net/10568/139779 en Open Access application/pdf Informa UK Limited Hanadé Houmma, I., Gadal, S., El Mansouri, L., Garba, M., Gbetkom, P.G., Mamane Barkawi, M.B. & Hadria, R. (2023). A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems. Geomatics, Natural Hazards and Risk, 14(1): 2223384, 1-34.
spellingShingle drought
remote sensing
forests
sahel
Hanade Houmma, I.
Gadal, S.
El Mansouri, L.
Garba, M.
Gbetkom, P.G.
Mamane Barkawi, M.B.
Hadria, R.
A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems
title A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems
title_full A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems
title_fullStr A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems
title_full_unstemmed A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems
title_short A new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for Sahelian agrosystems
title_sort new multivariate agricultural drought composite index based on random forest algorithm and remote sensing data developed for sahelian agrosystems
topic drought
remote sensing
forests
sahel
url https://hdl.handle.net/10568/139779
work_keys_str_mv AT hanadehoummai anewmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT gadals anewmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT elmansouril anewmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT garbam anewmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT gbetkompg anewmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT mamanebarkawimb anewmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT hadriar anewmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT hanadehoummai newmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT gadals newmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT elmansouril newmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT garbam newmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT gbetkompg newmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT mamanebarkawimb newmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems
AT hadriar newmultivariateagriculturaldroughtcompositeindexbasedonrandomforestalgorithmandremotesensingdatadevelopedforsahelianagrosystems