Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data

In arid environments of the world, particularly in sub-Saharan Africa and Asia, floodplain wetlands are a valuable agricultural resource. However, the water reticulation role by wetlands and crop production can negatively impact wetland plants. Knowledge on the foliar biochemical elements of wetland...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mandla Dlamini, George Chirima, Mbulisi Sibanda, Elhadi Adam, Timothy Dube
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/17a3cd1453d14a059b2503e40a449f9d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:17a3cd1453d14a059b2503e40a449f9d
record_format dspace
spelling oai:doaj.org-article:17a3cd1453d14a059b2503e40a449f9d2021-11-11T18:51:19ZCharacterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data10.3390/rs132142492072-4292https://doaj.org/article/17a3cd1453d14a059b2503e40a449f9d2021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4249https://doaj.org/toc/2072-4292In arid environments of the world, particularly in sub-Saharan Africa and Asia, floodplain wetlands are a valuable agricultural resource. However, the water reticulation role by wetlands and crop production can negatively impact wetland plants. Knowledge on the foliar biochemical elements of wetland plants enhances understanding of the impacts of agricultural practices in wetlands. This study thus used Sentinel-2 multispectral data to predict seasonal variations in the concentrations of nine foliar biochemical elements in plant leaves of key floodplain wetland vegetation types and crops in the uMfolozi floodplain system (UFS). Nutrient concentrations in different floodplain plant species were estimated using Sentinel-2 multispectral data derived vegetation indices in concert with the random forest regression. The results showed a mean R<sup>2</sup> of 0.87 and 0.86 for the dry winter and wet summer seasons, respectively. However, copper, sulphur, and magnesium were poorly correlated (R<sup>2</sup> ≤ 0.5) with vegetation indices during the summer season. The average % relative root mean square errors (RMSE’s) for seasonal nutrient estimation accuracies for crops and wetland vegetation were 15.2 % and 26.8%, respectively. There was a significant difference in nutrient concentrations between the two plant types, (R<sup>2</sup> = 0.94 (crops), R<sup>2</sup> = 0.84 (vegetation). The red-edge position 1 (REP1) and the normalised difference vegetation index (NDVI) were the best nutrient predictors. These results demonstrate the usefulness of Sentinel-2 imagery and random forests regression in predicting seasonal, nutrient concentrations as well as the accumulation of chemicals in wetland vegetation and crops.Mandla DlaminiGeorge ChirimaMbulisi SibandaElhadi AdamTimothy DubeMDPI AGarticlecrop productionmultispectral datarandom forestsvegetation indiceswetlands conservationScienceQENRemote Sensing, Vol 13, Iss 4249, p 4249 (2021)
institution DOAJ
collection DOAJ
language EN
topic crop production
multispectral data
random forests
vegetation indices
wetlands conservation
Science
Q
spellingShingle crop production
multispectral data
random forests
vegetation indices
wetlands conservation
Science
Q
Mandla Dlamini
George Chirima
Mbulisi Sibanda
Elhadi Adam
Timothy Dube
Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data
description In arid environments of the world, particularly in sub-Saharan Africa and Asia, floodplain wetlands are a valuable agricultural resource. However, the water reticulation role by wetlands and crop production can negatively impact wetland plants. Knowledge on the foliar biochemical elements of wetland plants enhances understanding of the impacts of agricultural practices in wetlands. This study thus used Sentinel-2 multispectral data to predict seasonal variations in the concentrations of nine foliar biochemical elements in plant leaves of key floodplain wetland vegetation types and crops in the uMfolozi floodplain system (UFS). Nutrient concentrations in different floodplain plant species were estimated using Sentinel-2 multispectral data derived vegetation indices in concert with the random forest regression. The results showed a mean R<sup>2</sup> of 0.87 and 0.86 for the dry winter and wet summer seasons, respectively. However, copper, sulphur, and magnesium were poorly correlated (R<sup>2</sup> ≤ 0.5) with vegetation indices during the summer season. The average % relative root mean square errors (RMSE’s) for seasonal nutrient estimation accuracies for crops and wetland vegetation were 15.2 % and 26.8%, respectively. There was a significant difference in nutrient concentrations between the two plant types, (R<sup>2</sup> = 0.94 (crops), R<sup>2</sup> = 0.84 (vegetation). The red-edge position 1 (REP1) and the normalised difference vegetation index (NDVI) were the best nutrient predictors. These results demonstrate the usefulness of Sentinel-2 imagery and random forests regression in predicting seasonal, nutrient concentrations as well as the accumulation of chemicals in wetland vegetation and crops.
format article
author Mandla Dlamini
George Chirima
Mbulisi Sibanda
Elhadi Adam
Timothy Dube
author_facet Mandla Dlamini
George Chirima
Mbulisi Sibanda
Elhadi Adam
Timothy Dube
author_sort Mandla Dlamini
title Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data
title_short Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data
title_full Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data
title_fullStr Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data
title_full_unstemmed Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data
title_sort characterizing leaf nutrients of wetland plants and agricultural crops with nonparametric approach using sentinel-2 imagery data
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/17a3cd1453d14a059b2503e40a449f9d
work_keys_str_mv AT mandladlamini characterizingleafnutrientsofwetlandplantsandagriculturalcropswithnonparametricapproachusingsentinel2imagerydata
AT georgechirima characterizingleafnutrientsofwetlandplantsandagriculturalcropswithnonparametricapproachusingsentinel2imagerydata
AT mbulisisibanda characterizingleafnutrientsofwetlandplantsandagriculturalcropswithnonparametricapproachusingsentinel2imagerydata
AT elhadiadam characterizingleafnutrientsofwetlandplantsandagriculturalcropswithnonparametricapproachusingsentinel2imagerydata
AT timothydube characterizingleafnutrientsofwetlandplantsandagriculturalcropswithnonparametricapproachusingsentinel2imagerydata
_version_ 1718431688549203968