Grapevine cultivation under tropical conditions is highly susceptible to abiotic stress, making reliable assessment of plant vigor important for precision management. This study presents an integrated multisensor Artificial Intelligence of Things (AIoT) framework combined with deep learning for estimating a relative grapevine vigor index using RGB canopy imagery. Environmental sensors provide contextual measurements of microclimatic and soil conditions, while image data are processed using a convolutional neural network–based model to estimate vigor levels derived from fractional green canopy cover. Approximately 1,600 RGB canopy images and 4,320 environmental telemetry records were used to train and evaluate the model. The results demonstrate that the proposed approach achieved a mean absolute error (MAE) of 8.73, a root mean square error (RMSE) of 11.74, and a coefficient of determination (R²) of 0.57 in predicting the relative vigor index. The integration of environmental sensing and image-based analysis provides an initial contribution to tropical grapevine vigor monitoring, although the model remains limited by single-site data and moderate predictive performance. Overall, the proposed framework provides a practical foundation for image-based vigor estimation and integrated data acquisition in tropical precision viticulture.
Collaboration network of the authors
7 authors ·
12 co-authorship links
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
Affiliation unknown
Different organisations
Same organisation
Affiliation unknown
Thicker line = more joint articles · bigger circle = more articles
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.