Matches in SemOpenAlex for { <https://semopenalex.org/work/W3154050314> ?p ?o ?g. }
- W3154050314 endingPage "49" @default.
- W3154050314 startingPage "37" @default.
- W3154050314 abstract "• Hyperspectral remote sensing was used to estimate biomass yield of Moringa oleifera cultivars. • Random forest algorithm was used to model biomass yield of plants at two growth stages. • The M. oleifera cultivars could be spectrally discriminated. • Whole plant estimation models were more accurate than leaf and stem biomass yield models. • Data collected on two-month old plants were more accurate in estimating biomass yield. • Cultivar specific models were more accurate than models with combined data across different cultivars. Moringa oleifera Lam. is a functional plant considered to be high in nutrients as well as medicinal properties, largely utilised in most of the developing countries. Therefore, early prediction of M. oleifera biomass yield is a valuable pre- and post-harvest planning strategy for ensuring a reliable supply of the plant products and for marketing purposes. Subsequently, the objective of the current study was to explore the potential use of hyperspectral data in predicting biomass yield of different cultivars of M. oleifera . Canopy hyperspectral data were collected on five M. oleifera cultivars when they were one month and two months old using a hand-held spectroradiometer. The M. oleifera plants were harvested after two months and their leaves as well as stems were separated and immediately (i.e. within a minute) weighed (g plant −1 ). First-order derivative was used to transform the reflectance spectra and analysis of variance (ANOVA) as well as random forest (RF) regression and classification algorithm were used to analyse the data. The results showed that the first-order spectra of the five cultivars were significantly different ( p ≤ 0.05) from each other in most portions of the electromagnetic spectrum. Furthermore, the results indicated that the studied M. oleifera cultivars can be discriminated from each other using their first-order derivative of reflectance and RF classifier. RF regression models developed to predict the biomass yield of a two-month old M. oleifera crop were more accurate compared to the models developed when the plant was month old. The relative root mean square error of validation (RRMSEV) for biomass models of two-months old plants ranged between 23 and 37%, while the RRMSEV for biomass models of one-month-old plants ranged between 30 and 59%. Cultivar Tanzania obtained the most accurate whole plant biomass yield prediction model with a RRMSEV of 23.20%. When the data aggregated across the five cultivars to develop a universal model, the results showed R 2 = 0.59: RMSEV = 6.47 g plant −1 ; RRMSEV =29.42% for the whole plant biomass yield, R 2 = 0.52, RMSEV = 4.78 g plant −1 RRMSEV =29.51% for the leaves biomass yield and R 2 = 0.42; RMSEV = 2.17 g plant −1 RRMSEV = 37.35% for the stem biomass yield. Based on current results, the study infers that combined spectral data across different cultivars may not be useful in estimating M. oleifera biomass yield. The results underscore the use of hyperspectral data as a quick non-destructive means to measure the yield of M. oleifera medicinal plant. Furthermore, the present study gives an insight into the potential of hyperspectral data to be extrapolated to larger scales for prediction of biomass yield of medicinal plants using spaceborne and airborne acquired data." @default.
- W3154050314 created "2021-04-26" @default.
- W3154050314 creator A5019162875 @default.
- W3154050314 creator A5051688723 @default.
- W3154050314 creator A5059430796 @default.
- W3154050314 creator A5065191695 @default.
- W3154050314 creator A5066398391 @default.
- W3154050314 date "2021-08-01" @default.
- W3154050314 modified "2023-09-23" @default.
- W3154050314 title "Leveraging of hyperspectral remote sensing on estimating biomass yield of Moringa oleifera Lam. medicinal plant" @default.
- W3154050314 cites W1554190159 @default.
- W3154050314 cites W1685317713 @default.
- W3154050314 cites W1968894504 @default.
- W3154050314 cites W1973675439 @default.
- W3154050314 cites W1978366487 @default.
- W3154050314 cites W1992725907 @default.
- W3154050314 cites W1999606853 @default.
- W3154050314 cites W2013328968 @default.
- W3154050314 cites W2026569282 @default.
- W3154050314 cites W2029306313 @default.
- W3154050314 cites W2037957915 @default.
- W3154050314 cites W2044186731 @default.
- W3154050314 cites W2055390799 @default.
- W3154050314 cites W2085718984 @default.
- W3154050314 cites W2091493105 @default.
- W3154050314 cites W2097018019 @default.
- W3154050314 cites W2098057602 @default.
- W3154050314 cites W2101956379 @default.
- W3154050314 cites W2113249705 @default.
- W3154050314 cites W2113771104 @default.
- W3154050314 cites W2117134952 @default.
- W3154050314 cites W2124121789 @default.
- W3154050314 cites W2131822674 @default.
- W3154050314 cites W2137876738 @default.
- W3154050314 cites W2141315566 @default.
- W3154050314 cites W2148724039 @default.
- W3154050314 cites W2150924127 @default.
- W3154050314 cites W2155122816 @default.
- W3154050314 cites W2163614163 @default.
- W3154050314 cites W2188115011 @default.
- W3154050314 cites W2221311684 @default.
- W3154050314 cites W2254707079 @default.
- W3154050314 cites W2317582304 @default.
- W3154050314 cites W2598497520 @default.
- W3154050314 cites W2601985677 @default.
- W3154050314 cites W2767183862 @default.
- W3154050314 cites W2768471687 @default.
- W3154050314 cites W2792932027 @default.
- W3154050314 cites W2796569263 @default.
- W3154050314 cites W2799965583 @default.
- W3154050314 cites W2901028058 @default.
- W3154050314 cites W2901530735 @default.
- W3154050314 cites W2911964244 @default.
- W3154050314 cites W2913507636 @default.
- W3154050314 cites W2916207245 @default.
- W3154050314 cites W2950477222 @default.
- W3154050314 cites W2954885898 @default.
- W3154050314 cites W3130086166 @default.
- W3154050314 cites W4244307164 @default.
- W3154050314 doi "https://doi.org/10.1016/j.sajb.2021.03.035" @default.
- W3154050314 hasPublicationYear "2021" @default.
- W3154050314 type Work @default.
- W3154050314 sameAs 3154050314 @default.
- W3154050314 citedByCount "0" @default.
- W3154050314 crossrefType "journal-article" @default.
- W3154050314 hasAuthorship W3154050314A5019162875 @default.
- W3154050314 hasAuthorship W3154050314A5051688723 @default.
- W3154050314 hasAuthorship W3154050314A5059430796 @default.
- W3154050314 hasAuthorship W3154050314A5065191695 @default.
- W3154050314 hasAuthorship W3154050314A5066398391 @default.
- W3154050314 hasBestOaLocation W31540503141 @default.
- W3154050314 hasConcept C115540264 @default.
- W3154050314 hasConcept C134121241 @default.
- W3154050314 hasConcept C159078339 @default.
- W3154050314 hasConcept C191897082 @default.
- W3154050314 hasConcept C192562407 @default.
- W3154050314 hasConcept C205649164 @default.
- W3154050314 hasConcept C2776836740 @default.
- W3154050314 hasConcept C31903555 @default.
- W3154050314 hasConcept C39432304 @default.
- W3154050314 hasConcept C54286561 @default.
- W3154050314 hasConcept C62649853 @default.
- W3154050314 hasConcept C6557445 @default.
- W3154050314 hasConcept C86803240 @default.
- W3154050314 hasConceptScore W3154050314C115540264 @default.
- W3154050314 hasConceptScore W3154050314C134121241 @default.
- W3154050314 hasConceptScore W3154050314C159078339 @default.
- W3154050314 hasConceptScore W3154050314C191897082 @default.
- W3154050314 hasConceptScore W3154050314C192562407 @default.
- W3154050314 hasConceptScore W3154050314C205649164 @default.
- W3154050314 hasConceptScore W3154050314C2776836740 @default.
- W3154050314 hasConceptScore W3154050314C31903555 @default.
- W3154050314 hasConceptScore W3154050314C39432304 @default.
- W3154050314 hasConceptScore W3154050314C54286561 @default.
- W3154050314 hasConceptScore W3154050314C62649853 @default.
- W3154050314 hasConceptScore W3154050314C6557445 @default.
- W3154050314 hasConceptScore W3154050314C86803240 @default.
- W3154050314 hasFunder F4320320671 @default.