Integrating Vegetation Indices and Texture Features From UAS Imagery to Improve Yield Prediction and Growth Analysis of Spinach ( Spinacia oleracea L.)
Year: 2026
Type: article
Abstract: Spinach ( Spinacia oleracea L.) yield prediction using unmanned aerial systems (UAS) has shown promise, but most existing models have been trained and validated within a single trial, leaving their generalizability across growing seasons largely untested; although UAS‐based growth analysis has been applied in other crops, it remains underexplored in spinach. The objectives of this study were to assess whether the fusion of vegetation indices (VIs) and textural features (TFs) could improve prediction ability, as evaluated through a cross‐year validation, in which the model was trained on data from 1 year and tested on unseen data from a different year. In addition, the UAS feature was further leveraged to perform spinach growth analysis. A 2‐year experiment (Exp. 1 and Exp. 2) was conducted using a randomized complete block design. One UAS flight mission was carried out before harvest, and yield was manually harvested at Exp. 1, while nine flight missions were implemented in addition to four biomass subsamples for Exp. 2. The UAS data and fresh yield of spinach from Exp. 2 were used to establish machine‐learning models and perform growth analysis, while the data from Exp. 1 was used to validate model accuracy. A fusion of VIs and TFs significantly improved the prediction ability of the models validated by the cross‐year scheme. Among the four models, Lasso regression showed the highest accuracy. In addition, a significant correlation between the maximum normalized difference red edge index (NDRE) growth rate and average yield was observed, suggesting that NDRE at the early growth stages reflects the final spinach yield. Our study highlights the potential of UAS, along with machine learning and growth function, to predict yield and describe growth of spinach.
DOI: 10.1155/ioa/1411368
Language: English
Subfield: Ecology
Field: Environmental Science
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: gold
Estimated APC paid: $1,000
OpenAlex ID: W7204188076