Exploitation of spectral indices NDVI, NDWI &amp; SAVI in Random Forest classifier model for mapping weak rosemary cover: application on Gourrama region, Morocco

Chafik, Hassan; Berrada, Mohamed; Legdou, Anass; Amine, Aouatif; Lahssini, Saïd

doi:10.1109/morgeo49228.2020.9121895

Cited by 8 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Puletti et al (2018) had also classified forest areas in the Mediterranean region by RF classifier with an overall accuracy of 86.2% and reported thereby that Sentinel-2A images are appropriate for periodic forest monitoring and mapping. Another example concerns a local scale mapping for a weak rosemary cover conducted by Chafik et al (2020) in Errachidia in the south-east of Morocco that provides a satisfying accuracy of 90%, slightly lower than our finding.…”

Section: Random Forest Classification Accuracy and The Importance Of ...contrasting

confidence: 76%

Assessment of Sentinel‐2A images for estimating rosemary land cover through an object‐based image analysis approach

et al. 2022

View full text Add to dashboard Cite

Rosemary is a medicinal plant widely used in the food and pharmaceutical industry. In Morocco, rosemary harvesting generates significant benefits for the local economy. Even though, decision makers are short of accurate information about its geographical distribution area. The aim of this study is to delineate the rosemary shrubs in the Oriental region in Morocco in order to provide guidance for the sustainable use of these natural resources. We therefore used the freely available images of Sentinel‐2A for binary classification (rosemary shrubs and the other lands) through an object‐based image‐analysis approach. The random forest classifier was deployed and trained with different object features likewise spectral values and vegetation indices. As a result, the distribution area of rosemary is 240,747 ha, which represents 18% of the studied area. Besides, an encouraging overall accuracy of 94.24% was attained; the user's accuracy for the class of “rosemary” and “Others” is 93.3% and 95.0%, respectively; meanwhile, the producer's accuracy for “rosemary” and “Others” is 93.72% and 94.65%.

show abstract

Section: Random Forest Classification Accuracy and The Importance Of ...contrasting

confidence: 76%

Assessment of Sentinel‐2A images for estimating rosemary land cover through an object‐based image analysis approach

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Along with the geology, slope, aspect, contour, and soil formation of the watershed (Meshram et al, 2019). The spectral indices, soil-adjusted vegetation index (SAVI) (Equation 2) (Chafik et al, 2020), moisture stress index (MSI) (Equation 5), normalised difference turbidity index (NDTI) (Equation 1), normalised difference moisture index (NDMI) (Equation 3), Bare soil Index (BSI) (Equation 4) were found using the formula provided in Table 2 Hembram and Saha, 2020;Sanskriti et al, 2021;Tirkey et al, 2016). The land covers land use (LULC) for the years 2010 and 2021, geology, soil type, and mean annual rainfall (2010-2021) was derived using ArcGIS software 10.8.…”

Section: Study Parametersmentioning

confidence: 99%

Water induced surface erosion risk assessment in Jumar agricultural watershed, Jharkhand, India using multivariate statistics and GIS

Pandey¹,

Kumari²

2023

Preprint

View full text Add to dashboard Cite

The state of Jharkhand suffers immensely from water-induced surface erosion causing loss of socio-economic Jumar watershed of Ranchi district, Jharkhand was selected for a study period of 2020 and 2021 to analyse climate change, seasonal change in quality of water and soil resources, hydro-geomorphometry and land cover land use (LULC) using GIS and multivariate statistics. The water quality analysis revealed the presence of higher content of presence of metals such as Ca, Mg, K, and Na, higher alkalinity, TDS, and turbidity in monsoon and post-monsoon months of 2021. The soil quality analysis showed that the region has excessive carbonate salts with dominant presence of metal such as calcium, magnesium and sodium, disturbing the soil structure and lowering its infiltration capacity, promoting nutrient deficiencies, and leading to possible metal contamination in few years. Lack of vegetation covers adds to surface erosion under high intensity rainfall (1685-2083mm). The correlation analysis was done seasonally for both soil and water quality revealing the strong influence of metal ions with pH, alkalinity, salinity, and TDS, showing a prominent silicate weathering and ion exchange process indicating prominent surface erosion in watershed. The PCA on water and soil quality data showed that salinity, TDS, Alkalinity, Hardness and EC are the principal components. The morphometric study showed that the Jumar watershed has rolling and slightly undulating terrain, with mild slope and dendritic stream pattern of 4th order stream. Low basin relief and drainage density, compactness constant (0.00192), Ruggedness number (0.0609), and basin relief ratio (0.00552) indicated the dominance of low stream orders (1st ) in the area pointing to low potential energy in surface flow. The hydrological indices indicated that the watershed is low risk of gully formation in lowlands. Through the application of other GIS based rainfall, LULC and spectral indices (NDMI, MSI, SAVI and BSI) it was found that there has been a huge increase in urbanization, barren land, sparse vegetation cover, and immense water stress especially in summer and winter season of 2020 and 2021 in the watershed. The Lack of water conservation and traditional agriculture using agrochemicals is very prominent in the watershed, hence an immediate need for water and soil quality management is required.

show abstract

Machine Learning and Remote Sensing in Mapping and Estimating Rosemary Cover Biomass

Chafik¹,

Berrada²,

Legdou³

et al. 2021

Geospatial Intelligence

View full text Add to dashboard Cite

Exploitation of spectral indices NDVI, NDWI & SAVI in Random Forest classifier model for mapping weak rosemary cover: application on Gourrama region, Morocco

Cited by 8 publications

References 9 publications

Assessment of Sentinel‐2A images for estimating rosemary land cover through an object‐based image analysis approach

Assessment of Sentinel‐2A images for estimating rosemary land cover through an object‐based image analysis approach

Water induced surface erosion risk assessment in Jumar agricultural watershed, Jharkhand, India using multivariate statistics and GIS

Machine Learning and Remote Sensing in Mapping and Estimating Rosemary Cover Biomass

Contact Info

Product

Resources

About