Remote sensing hail damage on maize crops in smallholder farms using data acquired by remotely piloted aircraft system

Mbulisi Sibanda ORCID logo ; Helen S Ndlovu ; Kiara Brewer ; Siphiwokuhle Buthelezi ; Trylee N Matongera ; Onisimo Mutanga ; John Odidndi ; Alistair D Clulow ; Vimbayi GP Chimonyo ; Tafadzwanashe Mabhaudhi ORCID logo ; (2023) Remote sensing hail damage on maize crops in smallholder farms using data acquired by remotely piloted aircraft system. Smart agricultural technology, 6 (100325). p. 100325. ISSN 2772-3755 DOI: 10.1016/j.atech.2023.100325
Copy

Smallholder farmers reside in marginal environments typified by dryland maize-based farming systems. Despite the significant contribution of smallholder farmers to food production, they are vulnerable to extreme weather events such as hailstorms, floods and drought. Extreme weather events are expected to increase in frequency and intensity under climate change, threatening the sustainability of smallholder farming systems. Access to climate services and information, as well as digital advisories such as Robust spatially explicit monitoring techniques from remotely piloted aircraft systems (RPAS), could be instrumental in understanding the impact and extent of crop damage. It could assist in providing adequate response mechanisms suitable for bolstering crop productivity in a spatially explicit manner. This study, therefore, sought to evaluate the utility of drone-derived multispectral data in estimating crop productivity elements (Equivalent water thickness (EWT), Chlorophyll content, and leaf area index (LAI)) in maize smallholder croplands based on the random forest regression algorithm. A hailstorm occurred in the study area during the reproductive stages 2 to 3 and 3 to 4. EWT, Chlorophyll content, and LAI were measured before and after the storm. Results of this study showed that EWT, Chlorophyll content, and LAI could be optimally estimated based on the red edge and its spectral derivatives. Specifically, EWT was estimated to a rRMEs 2.7% and 59%, RMSEs of 5.31 gm<sup>−2</sup> and 27.35 gm<sup>-2</sup>, R<sup>2</sup> of 0.88 and 0.77, while chlorophyll exhibited rRMSE of 28% and 25%, RMSEs of 87.4 µmol m<sup>−</sup><sup>2</sup> and 76.2 µmol m<sup>−</sup><sup>2</sup> and R<sup>2</sup> of 0.89 and 0.80 and LAI yielded a rRMSE of 10.9% and 15.2%, RMSEs of 0.6 m<sup>2</sup>/m<sup>2</sup> and 0.19 m<sup>2</sup>/m<sup>2</sup> before and after the hail damage, respectively. Overall, the study underscores the potential of RPAS-based remote sensing as a valuable resource for assessing crop damage and responding to the impact of hailstorms on crop productivity in smallholder croplands. This offers a means to enhance agricultural resilience and adaptability under climate change.

picture_as_pdf

picture_as_pdf
Sibanda-etal-2023-Remote-sensing-hail-damage-on-maize-crops.pdf
subject
Published Version
Available under Creative Commons: Attribution-NonCommercial-No Derivative Works 4.0

View Download

Atom BibTeX OpenURL ContextObject in Span Multiline CSV OpenURL ContextObject Dublin Core Dublin Core MPEG-21 DIDL Data Cite XML EndNote HTML Citation JSON MARC (ASCII) MARC (ISO 2709) METS MODS RDF+N3 RDF+N-Triples RDF+XML RIOXX2 XML Reference Manager Refer Simple Metadata ASCII Citation EP3 XML
Export

Downloads