Use of Unmanned Aerial Vehicles (UAVs) Imagery in Phenotyping of Bambara Groundnut

Abstract

In this experiment, proximal measurements and Unmanned Aerial Vehicle (UAV) imagery was used to determine growth stages for bambara groundnut (Vigna subterranea (L.) Verdc.). The crop is a high potential crop due to its ability to yield in marginal environments, but neglected and underutilised due to lack of information on its growth in different environments. This study evaluated the correlation between Normalised Difference Vegetation Index (NDVI) derived from the ground as well as airborne sensors to test the ability of remotely sensed data to identify growth stages. NDVI and chlorophyll content of bambara groundnut leaves were measured at ground level at 18, 32, 46 and 88 days after planting (DAP) comprising vegetative, flowering, pod formation and maturity growth stages. The UAV imagery for the experimental plots was acquired with 0.2m resolution at maturity. The result showed a significant (p < 0.05) linear relationship between proximal NDVI and chlorophylls content at all growth stages ofgrowth. The R2 varied from 0.57 in the vegetative stage to 0.78 in the flowering stage. Furthermore, NDVI derived from proximal measurements and UAV data showed a significant (p < 0.05) correlation. The observed high correlation between proximal sensors, UAV data and crop parameters suggest that remote sensing technologies can be used for rapid phenotyping to hasten the development of models to assess the performance of underutilised crops for food and nutrition security.

A Systematic Review of UAV Applications for Mapping Neglected and Underutilised Crop Species’ Spatial Distribution and Health

“…Based on Figure 13, the main machine learning algorithms utilised in conjunction with drone-acquired data were linear regression (39%), random forest (28%), support vector machine (SVM) (22%), and artificial neural network (ANN) (17%), in order of frequency in the literature. Linear regression techniques were the most frequent regression algorithms in assessing NUS crop health (Figure 13) [22,30]. The frequency of linear regression and machine learning-based algorithms was also detected during the bibliometric analysis, as illustrated in Figure 2b (red cluster).…”

“…Remote Sens. 2023, 15, x FOR PEER REVIEW 17 of 32 algorithms in assessing NUS crop health (Figure 13) [22,30]. The frequency of linear regression and machine learning-based algorithms was also detected during the bibliometric analysis, as illustrated in Figure 2b (red cluster).…”

“…), finger (Eleusine coracana), and proso millet (Panicum milliaceum)) (Figure 5a). UAV-based remotely sensed data was utilised in mapping the attributes of amaranth (n= 6) [17], Legume (Fabaceae) (n = 2) [18], Sweet potato (n = 2) [20], sorghum (n = 2) [21], and bambara groundnut (Vigna subterranea) (n = 2) [22] (Figure 5b). Most of the retrieved literature remotely sensed various NUS using hyperspectral data, hence the decline in the frequency of NUS studies that utilised drone and satellite-acquired remotely sensed data (Figure 5).…”

“…This approach was accurate because VIs could partially overcome the influence of shadows and other noise in the background [85]. A growing body of literature demonstrates the optimal performance of VIs [22,24,29]. Specifically, VIs are robust because they can suppress background effects compared with bands [79].…”

“…A list of the articles used in this study is provided as supplementary data, Frequences. References [6,12,14,15,17,18,[20][21][22][23][24][26][27][28]30,31,52,66,67,84,86,94,99,[105][106][107][108][109][110][111][112][113][114][115][116][117][118][119][120][121][122][123] Data Availability Statement: The data will be availed upon request from the first author. The first author's contact details are detailed in the names section of tis manuscript.…”