Advancing grapevine phenology predictions: a comparison of regression-based statistical learning approach and conventional models in mediterranean environment.
6 affiliations
- 1Department of Agricultural Sciences, University of Sassari, Sassari, 07100, SS, Italy. [email protected].
- 2CMCC Foundation- Euro-Mediterranean Center on Climate Changes, Lecce, Italy. [email protected].
- 3Department of Plant and Agroecosystem Sciences, UW-Madison, Madison, WI, 53706, USA. [email protected].
- 4Department of Agricultural Sciences, University of Sassari, Sassari, 07100, SS, Italy. [email protected].
- 5Department of Agricultural Sciences, University of Sassari, Sassari, 07100, SS, Italy.
- 6CMCC Foundation- Euro-Mediterranean Center on Climate Changes, Lecce, Italy.
Abstract
Climate conditions can significantly affect plant dormancy and growing season, impacting crop development and its productivity. Temperature is considered the primary driver of grapevine phenology, with endodormancy and ecodormancy largely regulated by chilling and forcing accumulations, respectively. Nevertheless, additional climatic factors, such as precipitation, radiation and atmospheric circulation patterns, may also contribute and regulate variability of different phenological phases. As hotspot of climate change, Mediterranean regions are witnessing negative compounding effects by enhanced warming and changes in precipitation patterns on crop systems and linked agro-industry. Among these, viticulture is a particularly relevant economic crop in Mediterranean regions. This research aims to assess some conventional phenological modeling approaches to project several phenological stages of grapevine in Sardinia (Italy), comparing the results to regression-based stepwise Statistical Learning that can potentially account for effect of several climate variables. Combined models (i.e. Chilling Hours-Growing Degree Hours) improve prediction of budburst phenological timing (RMSEs: 7 days) in relation to more complex models (i.e., PhenoFlex). The Growing Degree Days model was more accurate than complex phenological models in predicting blooming and veraison (RMSEs of 6 and 4 days, respectively). The regression-based statistical learning approach achieved phenological prediction performances comparable to the best of the conventional models (RMSEs: 4-7 days). Regression-based statistical learning approach was able to infer contribution of several climate variables on grapevine phenology, at a larger seasonal scale. Implementing both modeling approaches showed similar spatial patterns, except for budburst phase which indicated earlier timings over mountainous regions through regression-based statistical learning contrary to conventional model, highlighting the influence of maximum and minimum temperatures from previous year.
Related
- Gastrointestinal parasites and molecular characterisation of Cryptosporidium spp. and Giardia sp. in ruminants and other domestic animals in Corsica (France), a Mediterranean island environment.
- Soil–Arthropod Interactions Across Forest Types in a Mediterranean Mountain Landscape
- Contrasting short‐ and long‐term direct and indirect interactions in Mediterranean oak savannah communities
- Distinct functional syndromes and responses to fire history of three Mediterranean woody resprouter species
- Litter VOC emissions inventory from deciduous urban trees in the mediterranean region
BibTeX
@article{didevarasl2026advancing,
title = {{Advancing grapevine phenology predictions: a comparison of regression-based statistical learning approach and conventional models in mediterranean environment.}},
author = {Ali Didevarasl and Pierfrancesco Deiana and Donatella Spano and Jose M Costa Saura and Luca Mercenaro and Giovanni Nieddu and Antonio Trabucco},
journal = {International journal of biometeorology},
year = {2026},
month = oct,
doi = {10.1007/s00484-026-03312-3},
url = {https://europepmc.org/article/MED/42842031},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Advancing grapevine phenology predictions: a comparison of regression-based statistical learning approach and conventional models in mediterranean environment.
AU - Ali Didevarasl
AU - Pierfrancesco Deiana
AU - Donatella Spano
AU - Jose M Costa Saura
AU - Luca Mercenaro
AU - Giovanni Nieddu
AU - Antonio Trabucco
PY - 2026
DA - 2026/10/07
JO - International journal of biometeorology
DO - 10.1007/s00484-026-03312-3
UR - https://europepmc.org/article/MED/42842031
AB - Climate conditions can significantly affect plant dormancy and growing season, impacting crop development and its productivity. Temperature is considered the primary driver of grapevine phenology, with endodormancy and ecodormancy largely regulated by chilling and forcing accumulations, respectively. Nevertheless, additional climatic factors, such as precipitation, radiation and atmospheric circulation patterns, may also contribute and regulate variability of different phenological phases. As hotspot of climate change, Mediterranean regions are witnessing negative compounding effects by enhanced warming and changes in precipitation patterns on crop systems and linked agro-industry. Among these, viticulture is a particularly relevant economic crop in Mediterranean regions. This research aims to assess some conventional phenological modeling approaches to project several phenological stages of grapevine in Sardinia (Italy), comparing the results to regression-based stepwise Statistical Learning that can potentially account for effect of several climate variables. Combined models (i.e. Chilling Hours-Growing Degree Hours) improve prediction of budburst phenological timing (RMSEs: 7 days) in relation to more complex models (i.e., PhenoFlex). The Growing Degree Days model was more accurate than complex phenological models in predicting blooming and veraison (RMSEs of 6 and 4 days, respectively). The regression-based statistical learning approach achieved phenological prediction performances comparable to the best of the conventional models (RMSEs: 4-7 days). Regression-based statistical learning approach was able to infer contribution of several climate variables on grapevine phenology, at a larger seasonal scale. Implementing both modeling approaches showed similar spatial patterns, except for budburst phase which indicated earlier timings over mountainous regions through regression-based statistical learning contrary to conventional model, highlighting the influence of maximum and minimum temperatures from previous year.
SN - 0020-7128
SN - 1432-1254
ER -