terclim by ICS banner
IVES 9 IVES Conference Series 9 Comparison of imputation methods in long and varied phenological series. Application to the Conegliano dataset, including observations from 1964 over 400 grape varieties

Comparison of imputation methods in long and varied phenological series. Application to the Conegliano dataset, including observations from 1964 over 400 grape varieties

Abstract

A large varietal collection including over 1700 varieties was maintained in Conegliano, ITA, since the 1950s. Phenological data on a subset of 400 grape varieties including wine grapes, table grapes, and raisins were acquired at bud break, flowering, veraison, and ripening since 1964. Despite the efforts in maintaining and acquiring data over such an extensive collection, the data set has varying degrees of missing cases depending on the variety and the year. This is ubiquitous in phenology datasets with significant size and length. In this work, we evaluated four state-of-the-art methods to estimate missing values in this phenological series: k-Nearest Neighbour (kNN), Multivariate Imputation by Chained Equations (mice), MissForest, and Bidirectional Recurrent Imputation for Time Series (BRITS). For each phenological stage, we evaluated the performance of the methods in two ways. 1) On the full dataset, we randomly hold-out 10% of the true values for use as a test set and repeated the process 1000 times (Monte Carlo cross-validation). 2) On a reduced and almost complete subset of varieties, we varied the percentage of missing values from 10% to 70% by random deletion. In all cases, we evaluated the performance on the original values using normalized root mean squared error. For the full dataset we also obtained performance statistics by variety and by year. MissForest provided average errors of 17% (3 days) at budbreak, 14% (4 days) at flowering, 14.5% (7 days) at veraison, and 17% (3 days) at maturity. We completed the imputations of the Conegliano dataset, one of the world’s most extensive and varied phenological time series and a steppingstone for future climate change studies in grapes. The dataset is now ready for further analysis, and a rigorous evaluation of imputation errors is included.

DOI:

Publication date: May 31, 2022

Issue: Terclim 2022

Type: Article

Authors

Luca Brillante1, Greg Jones2 and Diego Tomasi3

1Department of Viticulture & Enology, California State University, Fresno, USA
2Abacela Vineyard and Winery, Roseburg, OR, USA
3CREA-VE Research Centre for Viticulture and Enology, Conegliano, Italy

Contact the author

Keywords

phenology, climate change, time series, imputation methods, recurrent neural networks

Tags

IVES Conference Series | Terclim 2022

Citation

Related articles…

Oenological performances of new white grape varieties

The wine industry works to minimize pesticides and adapt to climate change. Breeding programs have developed disease-resistant grape varieties, particularly against downy and powdery mildew, to minimize pesticide applications [1]. However, their enological potential remains underexplored.

Read More

Development and validation of a free solvent UHPLC/MS-MS method to analyse melatonin and its precursors in Spanish commercial wines  

Melatonin is a bioactive compound present in foods and beverages such as wines. During alcoholic fermentation, yeast transforms tryptophan into certain indole compounds, including melatonin. This paper aims to develop and validate a free solvent analytical method by ultra-high performance liquid chromatography coupled with high resolution mass spectrometry (UHPLC/MS-MS) to determine melatonin and its precursors (L-tryptophan, tryptamine, serotonin, tryptophol, N-acetylserotonin, 5-hydroxytryptophan, and 3- indoleacetic) that appropriately prevent the matrix effect.

Read More

Beyond liking scores: the importance of the drinking experience to understand our consumers

The presentation will approach the understanding of wine consumers´ perception based on the experiential model suggested by Warell (2008). In this framework, wine consumption gives rise to a
variety of experiences related to the perception, understanding, and judgment of the product. These
multidimensional facets of the drinking experience can be explored by measuring affective, cognitive,
and sensory responses of consumers, which are shown to be stable regardless of the social context.

Read More

Projected impacts of climate change on viticulture over France wine-regions using downscalled CMIP6 multi-model data

Winegrape is a crop for which the quality and the identity of the final product depends strongly on the
climatic conditions of the year. By impacting production systems and the way in which wines are
developed, climate change represents a major challenge for the wine industry (Ollat et al., 2021).

Read More

Non Saccharomyces wine yeasts: emerging trends and challenges in winemaking

In the past, the contribution of non-Saccharomyces yeasts in winemaking has always been considered negative for their limited enological attitude if compared with Saccharomyces cerevisiae. In recent decades there has been a reevaluation of the role of non-Saccharomyces wine yeasts especially when used in combination and in support with S. cerevisiae (mixed fermentation). In this regard, selected non-Saccharomyces yeasts could be profitable used to give distinctive features, to enhance flavor and aroma complexity and to reduce the ethanol content of wines. Further emerging trends in the use of these yeasts are related to their role as bioprotectants and producers of health promoters compounds.

Read More